fix

.envrc

@@ -0,0 +1 @@
+source /home/oleg/.pyenv/python3.12-venv/bin/activate

.gitignore

@@ -5,7 +5,7 @@ __OLD__/
 .history/
 .cursorindexingignore
 data
-.vscode/
 cvttpy
 # SpecStory explanation file
 .specstory/.what-is-this.md
+results/

.vscode/.env

@@ -0,0 +1 @@
+PYTHONPATH=/home/oleg/develop

.vscode/launch.json

@@ -0,0 +1,177 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+    
+
+        {
+            "name": "Python Debugger: Current File",
+            "type": "debugpy",
+            "request": "launch",
+            "python": "/home/oleg/.pyenv/python3.12-venv/bin/python",
+            "program": "${file}",
+            "console": "integratedTerminal",
+            "env": {
+                "PYTHONPATH": "${workspaceFolder}/lib:${workspaceFolder}/.."
+            },
+        },
+        {
+            "name": "-------- Live Pair Trading --------",
+        },
+        {
+            "name": "PAIR TRADER",
+            "type": "debugpy",
+            "request": "launch",
+            "python": "/home/oleg/.pyenv/python3.12-venv/bin/python",
+            "program": "${workspaceFolder}/apps/pair_trader.py",
+            "console": "integratedTerminal",
+            "env": {
+                "PYTHONPATH": "${workspaceFolder}/..",
+                "CONFIG_SERVICE": "cloud16.cvtt.vpn:6789",
+                "CVTT_URL": "http://cvtt-tester-01.cvtt.vpn:23456",
+                "MODEL_CONFIG": "vecm",
+                "PAIR_TRADER_REST_PORT": "54320"
+            },
+            "args": [
+                // "--config=${workspaceFolder}/configuration/pair_trader.cfg",
+                "--config=http://cloud16.cvtt.vpn:6789/apps/pairs_trading/pair_trader",
+                "--book_id=TSTBOOK_PT_20260113",
+                "--instrument_A=COINBASE_AT:PAIR-ADA-USD", 
+                "--instrument_B=COINBASE_AT:PAIR-SOL-USD",
+            ],
+        },
+        {
+            "name": "PAIR SELECTOR",
+            "type": "debugpy",
+            "request": "launch",
+            "python": "/home/oleg/.pyenv/python3.12-venv/bin/python",
+            "program": "${workspaceFolder}/apps/pair_selector.py",
+            "console": "integratedTerminal",
+            "env": {
+                "PYTHONPATH": "${workspaceFolder}/..",
+                "CONFIG_SERVICE": "cloud16.cvtt.vpn:6789",
+                // "CVTT_URL": "http://cvtt-tester-01.cvtt.vpn:23456",
+                "CVTT_URL": "http://dev-server-02.cvtt.vpn:23456",
+                "PAIR_SELECTOR_REST_PORT": "44320"
+            },
+            "args": [
+                // "--config=${workspaceFolder}/configuration/pair_trader.cfg",
+                "--config=http://cloud16.cvtt.vpn:6789/apps/pairs_trading/pair_selector",
+            ],
+        },
+        {
+            "name": "-------- VECM --------",
+        },
+        {
+            "name": "CRYPTO VECM BACKTEST (optimized)",
+            "type": "debugpy",
+            "request": "launch",
+            "python": "/home/oleg/.pyenv/python3.12-venv/bin/python",
+            "program": "${workspaceFolder}/research/backtest.py",
+            "args": [
+                "--config=http://cloud16.cvtt.vpn:6789/apps/pairs_trading/backtest",
+                "--instruments=CRYPTO:BNBSPOT:PAIR-ADA-USDT,CRYPTO:BNBSPOT:PAIR-SOL-USDT",
+                "--date_pattern=20250911",
+                "--result_db=${workspaceFolder}/research/results/crypto/%T.vecm-opt.ADA-SOL.20250605.crypto_results.db",            
+            ],
+            "env": {
+                "PYTHONPATH": "${workspaceFolder}/..",
+                "CONFIG_SERVICE": "cloud16.cvtt.vpn:6789",
+                "MODEL_CONFIG": "vecm-opt"
+            },
+            "console": "integratedTerminal"
+        },
+        // {
+        //     "name": "EQUITY VECM (rolling)",
+        //     "type": "debugpy",
+        //     "request": "launch",
+        //     "python": "/home/oleg/.pyenv/python3.12-venv/bin/python",
+        //     "program": "${workspaceFolder}/research/backtest.py",
+        //     "args": [
+        //         "--config=${workspaceFolder}/configuration/vecm.cfg",
+        //         "--instruments=COIN:EQUITY:ALPACA,MSTR:EQUITY:ALPACA",
+        //         "--date_pattern=20250605",
+        //         "--result_db=${workspaceFolder}/research/results/equity/%T.vecm.COIN-MSTR.20250605.equity_results.db",            
+        //     ],
+        //     "env": {
+        //         "PYTHONPATH": "${workspaceFolder}/lib"
+        //     },
+        //     "console": "integratedTerminal"
+        // },
+        // {
+        //     "name": "EQUITY-CRYPTO VECM (rolling)",
+        //     "type": "debugpy",
+        //     "request": "launch",
+        //     "python": "/home/oleg/.pyenv/python3.12-venv/bin/python",
+        //     "program": "${workspaceFolder}/research/backtest.py",
+        //     "args": [
+        //         "--config=${workspaceFolder}/configuration/vecm.cfg",
+        //         "--instruments=COIN:EQUITY:ALPACA,BTC-USDT:CRYPTO:BNBSPOT",
+        //         "--date_pattern=20250605",
+        //         "--result_db=${workspaceFolder}/research/results/intermarket/%T.vecm.COIN-BTC.20250601.equity_results.db",            
+        //     ],
+        //     "env": {
+        //         "PYTHONPATH": "${workspaceFolder}/lib"
+        //     },
+        //     "console": "integratedTerminal"
+        // },
+        {
+            "name": "-------- B a t c h e s --------",
+        },
+        {
+            "name": "CRYPTO OLS Batch (rolling)",
+            "type": "debugpy",
+            "request": "launch",
+            "python": "/home/oleg/.pyenv/python3.12-venv/bin/python",
+            "program": "${workspaceFolder}/research/backtest.py",
+            "args": [
+                "--config=${workspaceFolder}/configuration/ols.cfg",
+                "--instruments=ADA-USDT:CRYPTO:BNBSPOT,SOL-USDT:CRYPTO:BNBSPOT",
+                "--date_pattern=2025060*",
+                "--result_db=${workspaceFolder}/research/results/crypto/%T.ols.ADA-SOL.2025060-.crypto_results.db",            
+            ],
+            "env": {
+                "PYTHONPATH": "${workspaceFolder}/lib"
+            },
+            "console": "integratedTerminal"
+        },
+        {
+            "name": "CRYPTO VECM Batch (rolling)",
+            "type": "debugpy",
+            "request": "launch",
+            "python": "/home/oleg/.pyenv/python3.12-venv/bin/python",
+            "program": "${workspaceFolder}/research/backtest.py",
+            "args": [
+                "--config=${workspaceFolder}/configuration/vecm.cfg",
+                "--instruments=ADA-USDT:CRYPTO:BNBSPOT,SOL-USDT:CRYPTO:BNBSPOT",
+                "--date_pattern=2025060*",
+                "--result_db=${workspaceFolder}/research/results/crypto/%T.vecm.ADA-SOL.2025060-.crypto_results.db",            
+            ],
+            "env": {
+                "PYTHONPATH": "${workspaceFolder}/lib"
+            },
+            "console": "integratedTerminal"
+        },
+        {
+            "name": "-------- Viz Test --------",
+        },
+        {
+            "name": "Viz Test",
+            "type": "debugpy",
+            "request": "launch",
+            "python": "/home/oleg/.pyenv/python3.12-venv/bin/python",
+            "program": "${workspaceFolder}/tests/viz_test.py",
+            "args": [
+                "--config=${workspaceFolder}/configuration/ols.cfg",
+                "--instruments=ADA-USDT:CRYPTO:BNBSPOT,SOL-USDT:CRYPTO:BNBSPOT",
+                "--date_pattern=20250605",
+            ],
+            "env": {
+                "PYTHONPATH": "${workspaceFolder}/lib"
+            },
+            "console": "integratedTerminal"
+        }
+    ]
+}

.vscode/pairs_trading.code-workspace

@@ -0,0 +1,10 @@
+{
+    "folders": [
+        {
+            "path": ".."
+        }
+    ],
+    "settings": {
+        "workbench.colorTheme": "Dracula Theme"
+    }
+}

.vscode/settings.json

@@ -0,0 +1,19 @@
+{
+    "python.testing.pytestEnabled": true,
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestArgs": [
+        "unittests"
+    ],
+    "python.testing.cwd": "${workspaceFolder}",
+    "python.testing.autoTestDiscoverOnSaveEnabled": true,
+    "python.defaultInterpreterPath": "/home/oleg/.pyenv/python3.12-venv/bin/python3",
+    "python.testing.pytestPath": "python3",
+    "python.analysis.extraPaths": [
+        "${workspaceFolder}",
+        "${workspaceFolder}/..",
+        "${workspaceFolder}/unittests"
+    ],
+    "python.envFile": "${workspaceFolder}/.env",
+    "python.testing.debugPort": 3000,
+    "python.testing.promptToConfigure": false,
+}

PAIRS_TRADING_BACKTEST_USAGE.md

@@ -0,0 +1,185 @@
+# Enhanced Pairs Trading Backtest Usage Guide
+
+## Overview
+
+The enhanced `pt_backtest.py` script now supports multi-day and multi-instrument backtesting with SQLite database output. This guide explains how to use the new features.
+
+## New Features
+
+### 1. Multi-Day Data Processing
+- Process multiple data files in a single run
+- Support for wildcard patterns in configuration files
+- CLI override for data file specification
+
+
+### 2. Dynamic Instrument Selection
+- Auto-detection of instruments from database
+- CLI override for instrument specification
+- No need to manually update configuration files
+
+### 3. SQLite Database Output
+- Automated storage of backtest results
+- Structured data format for analysis
+- Optional database output (can be disabled)
+
+## Command Line Arguments
+
+### Required Arguments
+- `--config`: Path to configuration file
+- `--result_db`: Path to SQLite database for results (use "NONE" to disable)
+
+### Optional Arguments
+- `--datafiles`: Comma-separated list of data files (overrides config)
+- `--instruments`: Comma-separated list of instruments (overrides auto-detection)
+
+## Usage Examples
+
+### Basic Usage (Auto-detect instruments, use config datafiles)
+```bash
+python src/pt_backtest.py --config configuration/crypto.cfg --result_db results.db
+```
+
+### Specify Instruments via CLI
+```bash
+python src/pt_backtest.py \
+    --config configuration/crypto.cfg \
+    --result_db results.db \
+    --instruments "BTC-USDT,ETH-USDT,ADA-USDT"
+```
+
+### Override Data Files via CLI
+```bash
+python src/pt_backtest.py \
+    --config configuration/crypto.cfg \
+    --result_db results.db \
+    --datafiles "20250528.mktdata.ohlcv.db,20250529.mktdata.ohlcv.db"
+```
+
+### Complete Override (Custom instruments and data files)
+```bash
+python src/pt_backtest.py \
+    --config configuration/crypto.cfg \
+    --result_db results.db \
+    --instruments "BTC-USDT,ETH-USDT" \
+    --datafiles "20250528.mktdata.ohlcv.db,20250529.mktdata.ohlcv.db"
+```
+
+### Disable Database Output
+```bash
+python src/pt_backtest.py \
+    --config configuration/crypto.cfg \
+    --result_db NONE
+```
+
+## Configuration File Updates
+
+### Wildcard Support in Data Files
+The configuration file now supports wildcards in the `datafiles` array:
+
+```json
+{
+    "datafiles": [
+        "2025*.mktdata.ohlcv.db",
+        "specific_file.db",
+        "202405*.mktdata.ohlcv.db"
+    ]
+}
+```
+
+### Multiple Patterns
+You can specify multiple wildcard patterns:
+
+```json
+{
+    "datafiles": [
+        "202405*.mktdata.ohlcv.db",
+        "202406*.mktdata.ohlcv.db",
+        "special_data.db"
+    ]
+}
+```
+
+## Database Schema
+
+The script creates a `pt_bt_results` table with the following schema:
+
+| Column | Type | Description |
+|--------|------|-------------|
+| date | DATE | Trading date extracted from filename |
+| pair | TEXT | Trading pair name (e.g., "BTC-USDT & ETH-USDT") |
+| symbol | TEXT | Individual symbol (e.g., "BTC-USDT") |
+| open_time | DATETIME | Trade opening time |
+| open_side | TEXT | Opening side (BUY/SELL) |
+| open_price | REAL | Opening price |
+| open_quantity | INTEGER | Opening quantity |
+| open_disequilibrium | REAL | Disequilibrium at opening |
+| close_time | DATETIME | Trade closing time |
+| close_side | TEXT | Closing side (BUY/SELL) |
+| close_price | REAL | Closing price |
+| close_quantity | INTEGER | Closing quantity |
+| close_disequilibrium | REAL | Disequilibrium at closing |
+| symbol_return | REAL | Individual symbol return (%) |
+| pair_return | REAL | Combined pair return (%) |
+
+## Auto-Detection Logic
+
+### Instrument Auto-Detection
+When `--instruments` is not specified, the script:
+1. Connects to each data file
+2. Queries distinct `instrument_id` values from the configured table
+3. Removes the configured prefix (`instrument_id_pfx`)
+4. Uses the resulting symbols for pair generation
+
+### Data File Resolution
+The script resolves data files in this order:
+1. If `--datafiles` is specified, use those files
+2. Otherwise, process each pattern in config `datafiles`:
+   - Expand wildcards using `glob.glob()`
+   - Resolve relative paths using `data_directory`
+   - Remove duplicates and sort
+
+## Output
+
+### Console Output
+- Lists all data files to be processed
+- Shows auto-detected or specified instruments
+- Displays trade signals for each file
+- Prints returns by day and pair
+- Shows grand totals and outstanding positions
+
+### Database Output
+- Creates database and table automatically
+- Stores detailed trade information
+- Includes calculated returns
+- One record per symbol per trade
+
+## Error Handling
+
+The script includes comprehensive error handling:
+- Invalid data files are skipped with warnings
+- Database connection errors are reported
+- Auto-detection failures fall back gracefully
+- Processing errors are logged with stack traces
+
+## Performance Considerations
+
+- Wildcard expansion happens once at startup
+- Database connections are opened/closed per operation
+- Large numbers of files are processed sequentially
+- Memory usage scales with the number of instruments and data points
+
+## Troubleshooting
+
+### Common Issues
+
+1. **No instruments found**: Check that the database contains data for the specified exchange_id
+2. **No data files found**: Verify wildcard patterns and data_directory path
+3. **Database errors**: Ensure write permissions for the result database path
+4. **Memory issues**: Consider processing fewer files at once or reducing instrument count
+
+### Debug Tips
+
+- Use `--result_db NONE` to disable database output during testing
+- Start with a small set of instruments using `--instruments`
+- Test with explicit file lists using `--datafiles` before using wildcards
+- Check console output for detailed processing information 

README.md

@@ -0,0 +1,132 @@
+# Pairs Trading Backtest
+
+This document provides a guide to understanding, configuring, and running the pairs trading backtest system.
+
+## Overview
+
+The system is designed to backtest pairs trading strategies on historical market data. 
+It allows users to select different strategies, configure parameters, and analyze the 
+performance of these strategies.
+
+## Core Concepts
+
+### Trading Pair
+A trading pair consists of two financial instruments (e.g., stocks or cryptocurrencies) 
+whose prices are believed to have a long-term statistical relationship (cointegration). 
+The strategy aims to profit from temporary deviations from this relationship.
+
+### Strategy
+The system supports different strategies for identifying and exploiting trading opportunities. Each strategy has its own set of configurable parameters.
+
+### Trading Signals
+Trading signals indicate when to open or close a position based on the configured strategy 
+and parameters. These signals are typically generated when the "dis-equilibrium" (the 
+deviation from the long-term relationship) crosses certain thresholds.
+
+## Running a Backtest
+
+### 1. Configuration
+
+The primary configuration for the backtest is managed in the `src/pt_backtest.py` file. Here, you will define which dataset to use (cryptocurrencies or equities) and which strategy to employ.
+
+#### Choosing a Dataset:
+You can switch between `CRYPTO_CONFIG` and `EQT_CONFIG` by uncommenting the desired configuration block:
+
+```python
+# CONFIG = CRYPTO_CONFIG  # For cryptocurrency data
+CONFIG = EQT_CONFIG      # For equity data
+```
+
+Each configuration dictionary specifies:
+- `data_directory`: Path to the data files.
+- `datafiles`: A list of database files to process. You can comment/uncomment specific files to include/exclude them from the backtest.
+- `db_table_name`: The name of the table within the SQLite database.
+- `instruments`: A list of symbols to consider for forming trading pairs.
+- `trading_hours`: Defines the session start and end times, crucial for equity markets.
+- `stat_model_price`: The column in the data to be used as the price (e.g., "close").
+- `dis-equilibrium_open_trshld`: The threshold (in standard deviations) of the dis-equilibrium for opening a trade.
+- `dis-equilibrium_close_trshld`: The threshold (in standard deviations) of the dis-equilibrium for closing an open trade.
+- `training_minutes`: The length of the rolling window (in minutes) used to train the model (e.g., calculate cointegration, mean, and standard deviation of the dis-equilibrium).
+- `funding_per_pair`: The amount of capital allocated to each trading pair.
+
+#### Choosing a Strategy:
+The system currently offers two main strategies: `StaticFitStrategy` and `SlidingFitStrategy`. You select a strategy by instantiating it:
+
+```python
+# STRATEGY = StaticFitStrategy()
+STRATEGY = SlidingFitStrategy()
+```
+
+- **`StaticFitStrategy`**: This strategy fits the cointegration model once at the beginning 
+  of each trading day (or for the entire dataset if run on a single file without a rolling 
+  window logic in the strategy itself). The parameters (mean, standard deviation of 
+  dis-equilibrium) derived from this initial fit are used for generating trading signals 
+  throughout the day.
+    - **Pros**: Simpler, computationally less intensive.
+    - **Cons**: May not adapt well to changing market conditions during the day.
+
+- **`SlidingFitStrategy`**: This strategy uses a rolling window approach. The cointegration model and its parameters are re-estimated at regular intervals (defined by `training_minutes` and how the strategy implements the sliding window). This allows the strategy to adapt to evolving market dynamics.
+    - **Pros**: More adaptive to changing market conditions.
+    - **Cons**: Computationally more intensive. The `training_minutes` parameter is crucial here as it defines the look-back period for each re-estimation.
+
+### 2. Parameters for Trading Signals
+
+The key parameters that determine trading signals are primarily found within the `CONFIG` dictionaries:
+
+- **`dis-equilibrium_open_trshld`**: This is the number of standard deviations the current dis-equilibrium must move away from its mean (calculated during the training period) to trigger an opening signal.
+    - A *higher* value means the strategy will wait for a more significant deviation before entering a trade, leading to fewer but potentially more robust signals.
+    - A *lower* value means the strategy will enter trades on smaller deviations, leading to more frequent signals but potentially more false positives.
+
+- **`dis-equilibrium_close_trshld`**: This is the number of standard deviations the current dis-equilibrium must revert towards its mean (from its peak deviation) to trigger a closing signal.
+    - A *higher* value (closer to the `dis-equilibrium_open_trshld`) means the strategy will close trades more quickly as the dis-equilibrium starts to revert.
+    - A *lower* value (closer to zero) means the strategy will hold onto trades longer, waiting for the dis-equilibrium to revert more significantly towards the mean.
+
+- **`training_minutes`**:
+    - For `StaticFitStrategy`, this determines the initial period of data used to establish the cointegration relationship and calculate the baseline dis-equilibrium statistics for the entire trading day (or dataset portion being processed).
+    - For `SlidingFitStrategy`, this defines the length of the rolling window. The model is refit using data from the most recent `training_minutes` period. A shorter window makes the strategy more responsive to recent price action but might be more prone to noise. A longer window provides a more stable model but might be slower to adapt to new trends.
+
+### 3. Running the Script
+
+Once the configuration is set, you can run the backtest from your terminal:
+
+```bash
+python src/pt_backtest.py
+```
+
+The script will process each datafile specified in the `CONFIG`, create all possible unique pairs from the `instruments` list, and apply the chosen strategy.
+
+### 4. Interpreting Results
+
+The script will output:
+- Progress messages for each datafile being processed.
+- A summary of trades taken.
+- Grand totals of performance metrics (PnL, etc.).
+- A list of any outstanding positions at the end of the backtest.
+
+The core logic for a pair involves:
+1.  **Data Preparation**: For each pair, relevant price series are extracted.
+2.  **Training Phase** (for `SlidingFitStrategy`, this happens repeatedly; for `StaticFitStrategy`, typically once per day/file):
+    *   The `get_datasets()` method in `TradingPair` splits data into training and testing sets.
+    *   `check_cointegration()` uses the Johansen test to see if the pair's price series are cointegrated within the current training window. If not, the pair is often skipped for that window.
+    *   If cointegrated, `fit_VECM()` estimates a Vector Error Correction Model (VECM). The `beta` coefficients from this model define the cointegrating relationship (the "spread" or "dis-equilibrium series").
+    *   `training_mu_` (mean) and `training_std_` (standard deviation) of this dis-equilibrium series are calculated. These are crucial for scaling the dis-equilibrium and setting trade thresholds.
+3.  **Prediction/Trading Phase**:
+    *   The strategy iterates through the "testing" data points.
+    *   For each point, the current dis-equilibrium is calculated using the `beta` from the VECM.
+    *   This dis-equilibrium is then scaled: `(current_disequilibrium - training_mu_) / training_std_`.
+    *   This scaled value is compared against `dis-equilibrium_open_trshld` and `dis-equilibrium_close_trshld` to generate buy/sell/close signals.
+
+## Customizing and Extending
+
+-   **Adding New Strategies**: Create a new class that inherits from a base strategy class (if one exists) or implements a similar interface to `StaticFitStrategy` or `SlidingFitStrategy`. The core method to implement would be `run_pair()`.
+-   **Modifying Data Loading**: The `tools/data_loader.py` can be modified to support different data formats or sources.
+-   **Changing Cointegration/Model Parameters**: The `TradingPair` class houses the VECM fitting and cointegration checks. You can adjust parameters like `k_ar_diff` in `coint_johansen` or the `VECM` model itself.
+
+## Important Considerations
+
+-   **Data Quality**: Ensure your market data is clean, accurate, and properly formatted. Gaps or errors in data can significantly impact backtest results.
+-   **Transaction Costs**: The current backtest might not explicitly model transaction costs (brokerage fees, slippage). These can have a significant impact on the profitability of high-frequency strategies. Consider adding a cost model to `BacktestResult` or within the strategy execution.
+-   **Look-ahead Bias**: Be extremely careful to avoid look-ahead bias. Ensure that decisions at any point in time are made using only information that would have been available at that time. The use of `training_df_` and `testing_df_` in `TradingPair` is designed to help prevent this.
+-   **Overfitting**: When optimizing parameters (`dis-equilibrium_open_trshld`, `training_minutes`, etc.), be mindful of overfitting to the historical data. A strategy that performs exceptionally well on past data may not perform well in the future. Use out-of-sample testing or walk-forward optimization for more robust validation.
+
+This tutorial should provide a solid foundation for working with the pairs trading backtest system. Experiment with different configurations and strategies to find what works best for your chosen markets and instruments.

VERSION

@@ -0,0 +1 @@
+0.0.6

apps/pair_selector.py

@@ -0,0 +1,223 @@
+from __future__ import annotations
+
+import asyncio
+from typing import Any, Dict, List
+
+from aiohttp import web
+
+from cvttpy_tools.app import App
+from cvttpy_tools.base import NamedObject
+from cvttpy_tools.config import CvttAppConfig
+from cvttpy_tools.logger import Log
+from cvttpy_tools.web.rest_service import RestService
+from cvttpy_trading.trading.exchange_config import ExchangeAccounts
+from cvttpy_trading.trading.instrument import ExchangeInstrument
+
+from pairs_trading.lib.pair_selector_engine import PairSelectionEngine
+
+
+class PairSelector(NamedObject):
+    instruments_: List[ExchangeInstrument]
+    engine_: PairSelectionEngine
+    rest_service_: RestService
+
+    def __init__(self) -> None:
+        App.instance().add_cmdline_arg("--oneshot", action="store_true", default=False)
+        App.instance().add_call(App.Stage.Config, self._on_config())
+        App.instance().add_call(App.Stage.Run, self.run())
+
+    async def _on_config(self) -> None:
+        cfg = CvttAppConfig.instance()
+        self.instruments_ = self._load_instruments(cfg)
+        price_field = cfg.get_value("model/stat_model_price", "close")
+
+        self.engine_ = PairSelectionEngine(
+            config=cfg,
+            instruments=self.instruments_,
+            price_field=price_field,
+        )
+
+        self.rest_service_ = RestService(config_key="/api/REST")
+        self.rest_service_.add_handler("GET", "/data_quality", self._on_data_quality)
+        self.rest_service_.add_handler("GET", "/pair_selection", self._on_pair_selection)
+
+    def _load_instruments(self, cfg: CvttAppConfig) -> List[ExchangeInstrument]:
+        instruments_cfg = cfg.get_value("instruments", [])
+        instruments: List[ExchangeInstrument] = []
+        assert len(instruments_cfg) >= 2, "at least two instruments required"
+        for item in instruments_cfg:
+            if isinstance(item, str):
+                parts = item.split(":", 1)
+                if len(parts) != 2:
+                    raise ValueError(f"invalid instrument format: {item}")
+                exch_acct, instrument_id = parts
+            elif isinstance(item, dict):
+                exch_acct = item.get("exch_acct", "")
+                instrument_id = item.get("instrument_id", "")
+                if not exch_acct or not instrument_id:
+                    raise ValueError(f"invalid instrument config: {item}")
+            else:
+                raise ValueError(f"unsupported instrument entry: {item}")
+
+            exch_inst = ExchangeAccounts.instance().get_exchange_instrument(
+                exch_acct=exch_acct, instrument_id=instrument_id
+            )
+            assert exch_inst is not None, f"no ExchangeInstrument for {exch_acct}:{instrument_id}"
+            exch_inst.user_data_["exch_acct"] = exch_acct
+            instruments.append(exch_inst)
+        return instruments
+
+    async def run(self) -> None:
+        oneshot = App.instance().get_argument("oneshot", False)
+        while True:
+            await self.engine_.run_once()
+            if oneshot:
+                break
+            sleep_for = self.engine_.sleep_seconds_until_next_cycle()
+            await asyncio.sleep(sleep_for)
+
+    async def _on_data_quality(self, request: web.Request) -> web.Response:
+        fmt = request.query.get("format", "html").lower()
+        quality = self.engine_.quality_dicts()
+        if fmt == "json":
+            return web.json_response(quality)
+        return web.Response(text=self._render_quality_html(quality), content_type="text/html")
+
+    async def _on_pair_selection(self, request: web.Request) -> web.Response:
+        fmt = request.query.get("format", "html").lower()
+        pairs = self.engine_.pair_dicts()
+        if fmt == "json":
+            return web.json_response(pairs)
+        return web.Response(text=self._render_pairs_html(pairs), content_type="text/html")
+
+    def _render_quality_html(self, quality: List[Dict[str, Any]]) -> str:
+        rows = "".join(
+            f"<tr>"
+            f"<td>{q.get('instrument','')}</td>"
+            f"<td>{q.get('record_count','')}</td>"
+            f"<td>{q.get('latest_tstamp','')}</td>"
+            f"<td>{q.get('status','')}</td>"
+            f"<td>{q.get('reason','')}</td>"
+            f"</tr>"
+            for q in sorted(quality, key=lambda x: str(x.get("instrument", "")))
+        )
+        return f"""
+<!DOCTYPE html>
+<html>
+<head>
+    <meta charset='utf-8'/>
+    <title>Data Quality</title>
+    <style>
+        body {{ font-family: Arial, sans-serif; margin: 20px; }}
+        table {{ border-collapse: collapse; width: 100%; }}
+        th, td {{ border: 1px solid #ccc; padding: 8px; text-align: left; }}
+        th {{ background: #f2f2f2; }}
+    </style>
+</head>
+<body>
+    <h2>Data Quality</h2>
+    <table>
+        <thead>
+            <tr><th>Instrument</th><th>Records</th><th>Latest</th><th>Status</th><th>Reason</th></tr>
+        </thead>
+        <tbody>{rows}</tbody>
+    </table>
+</body>
+</html>
+"""
+
+    def _render_pairs_html(self, pairs: List[Dict[str, Any]]) -> str:
+        if not pairs:
+            body = "<p>No pairs available. Check data quality and try again.</p>"
+        else:
+            body_rows = []
+            for p in pairs:
+                body_rows.append(
+                    "<tr>"
+                    f"<td>{p.get('instrument_a','')}</td>"
+                    f"<td>{p.get('instrument_b','')}</td>"
+                    f"<td data-value='{p.get('rank_eg',0)}'>{p.get('rank_eg','')}</td>"
+                    f"<td data-value='{p.get('rank_adf',0)}'>{p.get('rank_adf','')}</td>"
+                    f"<td data-value='{p.get('rank_j',0)}'>{p.get('rank_j','')}</td>"
+                    f"<td data-value='{p.get('pvalue_eg','')}'>{p.get('pvalue_eg','')}</td>"
+                    f"<td data-value='{p.get('pvalue_adf','')}'>{p.get('pvalue_adf','')}</td>"
+                    f"<td data-value='{p.get('pvalue_j','')}'>{p.get('pvalue_j','')}</td>"
+                    "</tr>"
+                )
+            body = "\n".join(body_rows)
+
+        return f"""
+<!DOCTYPE html>
+<html>
+<head>
+    <meta charset='utf-8'/>
+    <title>Pair Selection</title>
+    <style>
+        body {{ font-family: Arial, sans-serif; margin: 20px; }}
+        table {{ border-collapse: collapse; width: 100%; }}
+        th, td {{ border: 1px solid #ccc; padding: 8px; text-align: left; }}
+        th.sortable {{ cursor: pointer; background: #f2f2f2; }}
+    </style>
+</head>
+<body>
+    <h2>Pair Selection</h2>
+    <table id="pairs-table">
+        <thead>
+            <tr>
+                <th>Instrument A</th>
+                <th>Instrument B</th>
+                <th class="sortable" data-type="num">Rank-EG</th>
+                <th class="sortable" data-type="num">Rank-ADF</th>
+                <th class="sortable" data-type="num">Rank-J</th>
+                <th>EG p-value</th>
+                <th>ADF p-value</th>
+                <th>Johansen pseudo p</th>
+            </tr>
+        </thead>
+        <tbody>
+            {body}
+        </tbody>
+    </table>
+    <script>
+    (function() {{
+        const table = document.getElementById('pairs-table');
+        if (!table) return;
+        const getValue = (cell) => {{
+            const val = cell.getAttribute('data-value');
+            const num = parseFloat(val);
+            return isNaN(num) ? val : num;
+        }};
+        const toggleSort = (index, isNumeric) => {{
+            const tbody = table.querySelector('tbody');
+            const rows = Array.from(tbody.querySelectorAll('tr'));
+            const th = table.querySelectorAll('th')[index];
+            const dir = th.getAttribute('data-dir') === 'asc' ? 'desc' : 'asc';
+            th.setAttribute('data-dir', dir);
+            rows.sort((a, b) => {{
+                const va = getValue(a.children[index]);
+                const vb = getValue(b.children[index]);
+                if (isNumeric && !isNaN(va) && !isNaN(vb)) {{
+                    return dir === 'asc' ? va - vb : vb - va;
+                }}
+                return dir === 'asc'
+                    ? String(va).localeCompare(String(vb))
+                    : String(vb).localeCompare(String(va));
+            }});
+            tbody.innerHTML = '';
+            rows.forEach(r => tbody.appendChild(r));
+        }};
+        table.querySelectorAll('th.sortable').forEach((th, idx) => {{
+            th.addEventListener('click', () => toggleSort(idx, th.dataset.type === 'num'));
+        }});
+    }})();
+    </script>
+</body>
+</html>
+"""
+
+
+if __name__ == "__main__":
+    App()
+    CvttAppConfig()
+    PairSelector()
+    App.instance().run()

apps/pair_trader.py

@@ -0,0 +1,169 @@
+from __future__ import annotations
+
+import asyncio
+from typing import Callable, Coroutine, Dict, List
+import aiohttp.web as web
+
+from cvttpy_tools.app import App
+from cvttpy_tools.config import Config
+from cvttpy_tools.base import NamedObject
+from cvttpy_tools.config import CvttAppConfig
+from cvttpy_tools.logger import Log
+from cvttpy_tools.settings.cvtt_types import BookIdT
+from cvttpy_tools.web.rest_service import RestService
+
+# ---
+from cvttpy_trading.trading.instrument import ExchangeInstrument
+from cvttpy_trading.trading.mkt_data.md_summary import MdTradesAggregate
+from cvttpy_trading.trading.exchange_config import ExchangeAccounts
+# ---
+from pairs_trading.lib.live.mkt_data_client import CvttRestMktDataClient
+
+'''
+config http://cloud16.cvtt.vpn/apps/pairs_trading
+'''
+
+HistMdCbT = Callable[[List[MdTradesAggregate]], Coroutine]
+UpdateMdCbT = Callable[[MdTradesAggregate], Coroutine]
+
+class PairTrader(NamedObject):
+    config_: CvttAppConfig
+    instruments_: List[ExchangeInstrument]
+    book_id_: BookIdT
+
+    live_strategy_: "PtLiveStrategy" #type: ignore
+    ti_sender_: "TradingInstructionsSender" #type: ignore
+    pricer_client_: CvttRestMktDataClient
+    rest_service_: RestService
+    
+    latest_history_: Dict[ExchangeInstrument, List[MdTradesAggregate]]
+    
+    def __init__(self) -> None:
+        self.instruments_ = []
+        self.latest_history_ = {}
+        
+        App.instance().add_cmdline_arg(
+            "--instrument_A",
+            type=str,
+            required=True,
+            help=(
+                " Instrument A in pair (e.g., COINBASE_AT:PAIR-BTC-USD)"
+            ),
+        )
+        App.instance().add_cmdline_arg(
+            "--instrument_B",
+            type=str,
+            required=True,
+            help=(
+                " Instrument B in pair (e.g., COINBASE_AT:PAIR-ETH-USD)"
+            ),
+        )
+
+        App.instance().add_cmdline_arg(
+            "--book_id",
+            type=str,
+            required=True,
+            help="Book ID"
+        )
+        App.instance().add_call(App.Stage.Config, self._on_config())
+        App.instance().add_call(App.Stage.Run, self.run())
+        
+    async def _on_config(self) -> None:
+        self.config_ = CvttAppConfig.instance()
+        self.book_id_ = App.instance().get_argument(name="book_id")
+        
+        # ------- PARSE INSTRUMENTS -------
+        instr_list: List[str] = []
+        instr_str = App.instance().get_argument("instrument_A", "")
+        assert instr_str != "", "Missing insrument A" 
+        instr_list.append(instr_str)
+        instr_str = App.instance().get_argument("instrument_B", "")
+        assert instr_str != "", "Missing insrument B" 
+        instr_list.append(instr_str)
+ 
+        for instr in instr_list:
+            instr_parts = instr.split(":")
+            if len(instr_parts) != 2:
+                raise ValueError(f"Invalid pair format: {instr}")   
+            exch_acct = instr_parts[0]
+            instrument_id = instr_parts[1]
+            exch_inst = ExchangeAccounts.instance().get_exchange_instrument(exch_acct=exch_acct, instrument_id=instrument_id)
+            assert exch_inst is not None, f"No ExchangeInstrument for {instr}"
+            exch_inst.user_data_["exch_acct"] = exch_acct
+            self.instruments_.append(exch_inst)
+
+        Log.info(f"{self.fname()} Instruments: {self.instruments_[0].details_short()} <==> {self.instruments_[1].details_short()}")
+        
+        # ------- CREATE STRATEGY -------
+        from pairs_trading.lib.pt_strategy.live.live_strategy import PtLiveStrategy
+        strategy_config = CvttAppConfig.instance() #self.config_.get_subconfig("strategy_config", Config({}))
+        self.live_strategy_ = PtLiveStrategy(
+            config=strategy_config,
+            pairs_trader=self,
+        )
+        Log.info(f"{self.fname()} Strategy created: {self.live_strategy_}")  
+        model_name = self.config_.get_value("model/name", "?model/name?")
+        self.config_.set_value("strategy_id", f"{self.live_strategy_.__class__.__name__}:{model_name}")
+        
+        # # ------- CREATE PRICER CLIENT -------
+        self.pricer_client_ = CvttRestMktDataClient(config=self.config_)
+        Log.info(f"{self.fname()} MD client created: {self.pricer_client_}")  
+        
+        # ------- CREATE TRADER CLIENT -------
+        from pairs_trading.lib.live.ti_sender import TradingInstructionsSender
+        self.ti_sender_ = TradingInstructionsSender(config=self.config_, pairs_trader=self)
+        Log.info(f"{self.fname()} TI sender created: {self.ti_sender_}")
+
+        # # ------- CREATE REST SERVER -------
+        self.rest_service_ = RestService(
+            config_key=f"/api/REST"
+        )
+        
+        # --- Strategy Handlers
+        self.rest_service_.add_handler(
+            method="POST",
+            url="/api/strategy",
+            handler=self._on_api_request,
+        )
+        
+    async def subscribe_md(self) -> None:
+        from functools import partial
+        for exch_inst in self.instruments_:
+            exch_acct = exch_inst.user_data_.get("exch_acct", "?exch_acct?")
+            instrument_id = exch_inst.instrument_id()
+            
+            await self.pricer_client_.add_subscription(
+                exch_acct=exch_acct,
+                instrument_id=instrument_id,
+                interval_sec=self.live_strategy_.interval_sec(),
+                history_depth_sec=self.live_strategy_.history_depth_sec(),
+                callback=partial(self._on_md_summary, exch_inst=exch_inst)
+            )
+
+    async def _on_md_summary(self, history: List[MdTradesAggregate], exch_inst: ExchangeInstrument) -> None:
+        Log.info(f"{self.fname()}: got {exch_inst.details_short()} data")
+        self.latest_history_[exch_inst] = history
+        if len(self.latest_history_) == 2:
+            from itertools import chain
+            all_aggrs = sorted(list(chain.from_iterable(self.latest_history_.values())), key=lambda X: X.aggr_time_ns_)
+
+            await self.live_strategy_.on_mkt_data_hist_snapshot(hist_aggr=all_aggrs)
+            self.latest_history_ = {}
+
+    async def _on_api_request(self, request: web.Request) -> web.Response:
+        # TODO choose pair
+        # TODO confirm chosen pair (after selection is implemented)
+        return web.Response() # TODO  API request handler implementation
+    
+    
+    async def run(self) -> None:
+        Log.info(f"{self.fname()} ...")
+        while True:
+            await asyncio.sleep(0.1)
+        pass
+
+if __name__ == "__main__":
+    App()
+    CvttAppConfig()
+    PairTrader()
+    App.instance().run()

build.sh

@@ -0,0 +1,183 @@
+#!/usr/bin/env bash
+
+# ---------------- Settings
+
+repo=git@cloud21.cvtt.vpn:/works/git/cvtt2/research/pairs_trading.git
+
+dist_root=/home/cvttdist/software/cvtt2
+dist_user=cvttdist
+dist_host="cloud21.cvtt.vpn"
+dist_ssh_port="22"
+
+dist_locations="cloud21.cvtt.vpn:22 hs01.cvtt.vpn:22"
+version_file="VERSION"
+
+prj=pairs_trading
+brnch=master
+interactive=N
+
+# ---------------- Settings
+
+# ---------------- cmdline
+
+usage() {
+  echo "Usage: $0 [-b <branch (master)> -i (interactive)"
+  exit 1
+}
+
+while getopts "b:i" opt; do
+  case ${opt} in
+    b )
+      brnch=$OPTARG
+      ;;
+    i )
+      interactive=Y
+      ;;
+    \? )
+      echo "Invalid option: -$OPTARG" >&2
+      usage
+      ;;
+    : )
+      echo "Option -$OPTARG requires an argument." >&2
+      usage
+      ;;
+  esac
+done
+# ---------------- cmdline
+
+confirm() {
+    if [ "${interactive}" == "Y" ]; then
+        echo "--------------------------------"
+        echo -n "Press <Enter> to continue" && read
+    fi
+}
+
+
+if [ "${interactive}" == "Y" ]; then
+    echo -n "Enter project [${prj}]: "
+    read project
+    if [ "${project}" == "" ]
+    then
+        project=${prj}
+    fi
+else
+    project=${prj}
+fi
+
+# repo=${git_repo_arr[${project}]}
+if [ -z ${repo} ]; then
+    echo "ERROR: Project repository for ${project} not found"
+    exit -1
+fi
+echo "Project repo: ${repo}"
+
+if [ "${interactive}" == "Y" ]; then
+    echo -n "Enter branch to build release from [${brnch}]: "
+    read branch
+    if [ "${branch}" == "" ]
+    then
+        branch=${brnch}
+    fi
+else
+    branch=${brnch}
+fi
+
+tmp_dir=$(mktemp -d)
+function cleanup {
+    cd ${HOME}
+    rm -rf ${tmp_dir}
+}
+trap cleanup EXIT
+
+
+prj_dir="${tmp_dir}/${prj}"
+
+cmd_arr=()
+Cmd="git clone ${repo} ${prj_dir}"
+cmd_arr+=("${Cmd}")
+
+Cmd="cd ${prj_dir}"
+cmd_arr+=("${Cmd}")
+
+if [ "${interactive}" == "Y" ]; then
+    echo "------------------------------------"
+    echo "The following commands will execute:"
+    echo "------------------------------------"
+    for cmd in "${cmd_arr[@]}"
+    do
+        echo ${cmd}
+    done
+fi
+
+confirm
+
+for cmd in "${cmd_arr[@]}"
+do
+    echo ${cmd} && eval ${cmd}
+done
+
+Cmd="git checkout ${branch}"
+echo ${Cmd} && eval ${Cmd}
+if [ "${?}" != "0" ]; then
+    echo "ERROR: Branch ${branch} is not found"
+    cd ${HOME} && rm -rf ${tmp_dir}
+    exit -1
+fi
+
+
+release_version=$(cat ${version_file} | awk -F',' '{print $1}')
+whats_new=$(cat ${version_file} | awk -F',' '{print $2}')
+
+
+echo "--------------------------------"
+echo "Version file: ${version_file}"
+echo "Release version: ${release_version}"
+
+confirm
+
+version_tag="v${release_version}"
+version_comment="'${version_tag} ${project} ${branch} $(date +%Y-%m-%d)\n${whats_new}'"
+
+cmd_arr=()
+Cmd="git tag -a ${version_tag} -m ${version_comment}"
+cmd_arr+=("${Cmd}")
+
+Cmd="git push origin --tags"
+cmd_arr+=("${Cmd}")
+
+Cmd="rm -rf .git"
+cmd_arr+=("${Cmd}")
+
+SourceLoc=../${project}
+
+dist_path="${dist_root}/${project}/${release_version}"
+
+for dist_loc in ${dist_locations}; do
+    dhp=(${dist_loc//:/ })
+    dist_host=${dhp[0]}
+    dist_port=${dhp[1]}
+    Cmd="rsync -avzh"
+    Cmd="${Cmd} --rsync-path=\"mkdir -p ${dist_path}"
+    Cmd="${Cmd} && rsync\" -e \"ssh -p ${dist_ssh_port}\""
+    Cmd="${Cmd} $SourceLoc ${dist_user}@${dist_host}:${dist_path}/"
+    cmd_arr+=("${Cmd}")
+done
+
+if [ "${interactive}" == "Y" ]; then
+    echo "------------------------------------"
+    echo "The following commands will execute:"
+    echo "------------------------------------"
+    for cmd in "${cmd_arr[@]}"
+    do
+        echo ${cmd}
+    done
+fi
+
+confirm
+
+for cmd in "${cmd_arr[@]}"
+do
+    pwd && echo ${cmd} && eval ${cmd}
+done
+
+echo "$0 Done ${project} ${release_version}"

configuration/__DELETE__/ols-exp.cfg

@@ -0,0 +1,43 @@
+{
+    "market_data_loading": {
+        "CRYPTO": {
+            "data_directory": "./data/crypto",
+            "db_table_name": "md_1min_bars",
+            "instrument_id_pfx": "PAIR-",
+        },
+        "EQUITY": {
+            "data_directory": "./data/equity",
+            "db_table_name": "md_1min_bars",
+            "instrument_id_pfx": "STOCK-",
+        }
+    },
+
+    # ====== Funding ======
+    "funding_per_pair": 2000.0,
+    # ====== Trading Parameters ======
+    "stat_model_price": "close",
+    "execution_price": {
+        "column": "vwap",
+        "shift": 1,
+    },
+    "dis-equilibrium_open_trshld": 2.0,
+    "dis-equilibrium_close_trshld": 0.5,
+    "training_size": 120,
+    "model_class": "pairs_trading.lib.pt_strategy.models.OLSModel",
+    "model_data_policy_class": "pairs_trading.lib.pt_strategy.model_data_policy.ExpandingWindowDataPolicy",
+
+    # ====== Stop Conditions ======
+    "stop_close_conditions": {
+        "profit": 2.0,
+        "loss": -0.5
+    }
+
+    # ====== End of Session Closeout ======
+    "close_outstanding_positions": true,
+    # "close_outstanding_positions": false,
+    "trading_hours": {
+        "timezone": "America/New_York",
+        "begin_session": "7:30:00",
+        "end_session": "18:30:00",
+    }
+}

configuration/__DELETE__/ols-opt.cfg

@@ -0,0 +1,47 @@
+{
+    "market_data_loading": {
+        "CRYPTO": {
+            "data_directory": "./data/crypto",
+            "db_table_name": "md_1min_bars",
+            "instrument_id_pfx": "PAIR-",
+        },
+        "EQUITY": {
+            "data_directory": "./data/equity",
+            "db_table_name": "md_1min_bars",
+            "instrument_id_pfx": "STOCK-",
+        }
+    },
+
+    # ====== Funding ======
+    "funding_per_pair": 2000.0,
+    # ====== Trading Parameters ======
+    "stat_model_price": "close",
+    "execution_price": {
+        "column": "vwap",
+        "shift": 1,
+    },
+    "dis-equilibrium_open_trshld": 1.75,
+    "dis-equilibrium_close_trshld": 0.9,
+    "model_class": "pairs_trading.lib.pt_strategy.models.OLSModel",
+
+    # "model_data_policy_class": "pairs_trading.lib.pt_strategy.model_data_policy.EGOptimizedWndDataPolicy",
+    # "model_data_policy_class": "pairs_trading.lib.pt_strategy.model_data_policy.ADFOptimizedWndDataPolicy",
+    "model_data_policy_class": "pairs_trading.lib.pt_strategy.model_data_policy.JohansenOptdWndDataPolicy",
+    "min_training_size": 60,
+    "max_training_size": 150,
+
+    # ====== Stop Conditions ======
+    "stop_close_conditions": {
+        "profit": 2.0,
+        "loss": -0.5
+    }
+
+    # ====== End of Session Closeout ======
+    "close_outstanding_positions": true,
+    # "close_outstanding_positions": false,
+    "trading_hours": {
+        "timezone": "America/New_York",
+        "begin_session": "7:30:00",
+        "end_session": "18:30:00",
+    }
+}

configuration/__DELETE__/ols.cfg

@@ -0,0 +1,47 @@
+{
+    "market_data_loading": {
+        "CRYPTO": {
+            "data_directory": "./data/crypto",
+            "db_table_name": "md_1min_bars",
+            "instrument_id_pfx": "PAIR-",
+        },
+        "EQUITY": {
+            "data_directory": "./data/equity",
+            "db_table_name": "md_1min_bars",
+            "instrument_id_pfx": "STOCK-",
+        }
+    },
+
+    # ====== Funding ======
+    "funding_per_pair": 2000.0,
+    # ====== Trading Parameters ======
+    "stat_model_price": "close",
+    "execution_price": {
+        "column": "vwap",
+        "shift": 1,
+    },
+    "dis-equilibrium_open_trshld": 1.75,
+    "dis-equilibrium_close_trshld": 0.9,
+    "model_class": "pairs_trading.lib.pt_strategy.models.OLSModel",
+
+    "training_size": 120,
+    "model_data_policy_class": "pairs_trading.lib.pt_strategy.model_data_policy.RollingWindowDataPolicy",
+    # "model_data_policy_class": "pairs_trading.lib.pt_strategy.model_data_policy.OptimizedWindowDataPolicy",
+    # "min_training_size": 60,
+    # "max_training_size": 150,
+
+    # ====== Stop Conditions ======
+    "stop_close_conditions": {
+        "profit": 2.0,
+        "loss": -0.5
+    }
+
+    # ====== End of Session Closeout ======
+    "close_outstanding_positions": true,
+    # "close_outstanding_positions": false,
+    "trading_hours": {
+        "timezone": "America/New_York",
+        "begin_session": "7:30:00",
+        "end_session": "18:30:00",
+    }
+}

configuration/__DELETE__/vecm.cfg

@@ -0,0 +1,48 @@
+{
+    "market_data_loading": {
+        "CRYPTO": {
+    "data_directory": "./data/crypto",
+    "db_table_name": "md_1min_bars",
+    "instrument_id_pfx": "PAIR-",
+        },
+        "EQUITY": {
+            "data_directory": "./data/equity",
+            "db_table_name": "md_1min_bars",
+            "instrument_id_pfx": "STOCK-",
+        }
+    },
+
+    # ====== Funding ======
+    "funding_per_pair": 2000.0,
+  
+    # ====== Trading Parameters ======
+    "stat_model_price": "close", # "vwap"
+    "execution_price": {
+        "column": "vwap",
+        "shift": 1,
+    },
+    "dis-equilibrium_open_trshld": 1.75,
+    "dis-equilibrium_close_trshld": 1.0,
+    "model_class": "pairs_trading.lib.pt_strategy.models.VECMModel",
+
+    "training_size": 120,
+    "model_data_policy_class": "pairs_trading.lib.pt_strategy.model_data_policy.RollingWindowDataPolicy",
+    # "model_data_policy_class": "pairs_trading.lib.pt_strategy.model_data_policy.OptimizedWindowDataPolicy",
+    # "min_training_size": 60,
+    # "max_training_size": 150,
+
+    # ====== Stop Conditions ======
+    "stop_close_conditions": {
+        "profit": 2.0,
+        "loss": -0.5
+    }
+
+    # ====== End of Session Closeout ======
+    "close_outstanding_positions": true,
+    # "close_outstanding_positions": false,
+    "trading_hours": {
+        "timezone": "America/New_York",
+        "begin_session": "7:30:00",
+        "end_session": "18:30:00",
+    }
+}

configuration/backtest.cfg

@@ -0,0 +1,46 @@
+{
+    "refdata": {
+        "assets": @inc=http://@env{CONFIG_SERVICE}/refdata/assets
+        , "instruments": @inc=http://@env{CONFIG_SERVICE}/refdata/instruments
+        , "exchange_instruments": @inc=http://@env{CONFIG_SERVICE}/refdata/exchange_instruments
+        , "dynamic_instrument_exchanges": ["ALPACA"]
+        , "exchanges": @inc=http://@env{CONFIG_SERVICE}/refdata/exchanges
+    }, 
+    "market_data_loading": {
+        "CRYPTO": {
+            "data_directory": "./data/crypto",
+            "db_table_name": "md_1min_bars",
+            "instrument_id_pfx": "PAIR-",
+        },
+        "EQUITY": {
+            "data_directory": "./data/equity",
+            "db_table_name": "md_1min_bars",
+            "instrument_id_pfx": "STOCK-",
+        }
+    },
+    # ====== Funding ======
+    "funding_per_pair": 2000.0,
+
+    # ====== Model =======
+    "model": @inc=http://@env{CONFIG_SERVICE}/apps/common/models/@env{MODEL_CONFIG} 
+
+    # ====== Trading ======= 
+    "execution_price": {
+        "column": "vwap",
+        "shift": 1,
+    },
+    # ====== Stop Conditions ======
+    "stop_close_conditions": {
+        "profit": 2.0,
+        "loss": -0.5
+    }
+
+    # ====== End of Session Closeout ======
+    "close_outstanding_positions": true,
+    # "close_outstanding_positions": false,
+    "trading_hours": {
+        "timezone": "America/New_York",
+        "begin_session": "7:30:00",
+        "end_session": "18:30:00",
+    }
+}

configuration/pair_trader.cfg

@@ -0,0 +1,21 @@
+{
+    "strategy_config": @inc=file:///home/oleg/develop/pairs_trading/configuration/vecm-opt.cfg
+    "pricer_config": {
+        "pricer_url": "ws://localhost:12346/ws",
+        "history_depth_sec": 86400 #"60*60*24",  # use simpleeval
+        "interval_sec": 60
+    },
+    "ti_config": {
+        "cvtt_base_url": "http://localhost:23456"
+        "book_id": "XXXXXXXXX",
+        "strategy_id": "XXXXXXXXX",
+        "ti_endpoint": {
+            "method": "POST",
+            "url": "/trading_instructions"
+        },
+        "health_check_endpoint": {
+            "method": "GET",
+            "url": "/ping"
+        }
+    }
+}

configuration/vecm-opt.cfg

@@ -0,0 +1,56 @@
+{
+    # "refdata": {
+    #     "assets": @inc=http://@env{CONFIG_SERVICE}/refdata/assets
+    #     , "instruments": @inc=http://@env{CONFIG_SERVICE}/refdata/instruments
+    #     , "exchange_instruments": @inc=http://@env{CONFIG_SERVICE}/refdata/exchange_instruments
+    #     , "dynamic_instrument_exchanges": ["ALPACA"]
+    #     , "exchanges": @inc=http://@env{CONFIG_SERVICE}/refdata/exchanges
+    # }, 
+    # "market_data_loading": {
+    #     "CRYPTO": {
+    #         "data_directory": "./data/crypto",
+    #         "db_table_name": "md_1min_bars",
+    #         "instrument_id_pfx": "PAIR-",
+    #     },
+    #     "EQUITY": {
+    #         "data_directory": "./data/equity",
+    #         "db_table_name": "md_1min_bars",
+    #         "instrument_id_pfx": "STOCK-",
+    #     }
+    # },
+
+    # # ====== Funding ======
+    # "funding_per_pair": 2000.0,
+  
+    # ====== Trading Parameters ======
+    "stat_model_price": "close", # "vwap"
+    "execution_price": {
+        "column": "vwap",
+        "shift": 1,
+    },
+    "dis-equilibrium_open_trshld": 1.75,
+    "dis-equilibrium_close_trshld": 1.0,
+
+    "model_class": "pairs_trading.lib.pt_strategy.models.VECMModel",
+
+    # "training_size": 120,
+    # "model_data_policy_class": "pairs_trading.lib.pt_strategy.model_data_policy.RollingWindowDataPolicy",
+    "model_data_policy_class": "pairs_trading.lib.pt_strategy.model_data_policy.ADFOptimizedWndDataPolicy",
+    "min_training_size": 60,
+    "max_training_size": 150,
+
+    # # ====== Stop Conditions ======
+    # "stop_close_conditions": {
+    #     "profit": 2.0,
+    #     "loss": -0.5
+    # }
+
+    # # ====== End of Session Closeout ======
+    # "close_outstanding_positions": true,
+    # # "close_outstanding_positions": false,
+    # "trading_hours": {
+    #     "timezone": "America/New_York",
+    #     "begin_session": "7:30:00",
+    #     "end_session": "18:30:00",
+    # }
+}

lib/live/mkt_data_client.py

@@ -0,0 +1,277 @@
+from __future__ import annotations
+
+import asyncio
+from typing import Dict, Any, List, Optional, Set
+
+import requests
+
+from cvttpy_tools.base import NamedObject
+from cvttpy_tools.logger import Log
+from cvttpy_tools.config import Config
+from cvttpy_tools.timer import Timer
+from cvttpy_tools.timeutils import NanosT, current_seconds
+from cvttpy_tools.settings.cvtt_types import InstrumentIdT, IntervalSecT
+from cvttpy_tools.web.rest_client import RESTSender
+# ---
+from cvttpy_trading.trading.instrument import ExchangeInstrument
+from cvttpy_trading.trading.accounting.exch_account import ExchangeAccountNameT
+from cvttpy_trading.trading.mkt_data.md_summary import MdTradesAggregate, MdSummary, MdSummaryCallbackT
+from cvttpy_trading.trading.exchange_config import ExchangeAccounts
+# ---
+
+
+# class MdSummary(HistMdBar):
+#     def __init__(
+#         self,
+#         ts_ns: int,
+#         open: float,
+#         high: float,
+#         low: float,
+#         close: float,
+#         volume: float,
+#         vwap: float,
+#         num_trades: int,
+#     ):
+#         super().__init__(ts=ts_ns)
+#         self.open_ = open
+#         self.high_ = high
+#         self.low_ = low
+#         self.close_ = close
+#         self.volume_ = volume
+#         self.vwap_ = vwap
+#         self.num_trades_ = num_trades
+
+#     @classmethod
+#     def from_REST_response(cls, response: requests.Response) -> List[MdSummary]:
+#         res: List[MdSummary] = []
+#         jresp = response.json()
+#         hist_data = jresp.get("historical_data", [])
+#         for hd in hist_data:
+#             res.append(
+#                 MdSummary(
+#                     ts_ns=hd["time_ns"],
+#                     open=hd["open"],
+#                     high=hd["high"],
+#                     low=hd["low"],
+#                     close=hd["close"],
+#                     volume=hd["volume"],
+#                     vwap=hd["vwap"],
+#                     num_trades=hd["num_trades"],
+#                 )
+#             )
+#         return res
+
+#     def create_md_trades_aggregate(
+#         self,
+#         exch_acct: ExchangeAccountNameT,
+#         exch_inst: ExchangeInstrument,
+#         interval_sec: IntervalSecT,
+#     ) -> MdTradesAggregate:
+#         res = MdTradesAggregate(
+#             exch_acct=exch_acct,
+#             exch_inst=exch_inst,
+#             interval_ns=interval_sec * NanoPerSec,
+#         )
+#         res.set(mdbar=self)
+#         return res
+
+
+# MdSummaryCallbackT = Callable[[List[MdTradesAggregate]], Coroutine]
+
+
+class MdSummaryCollector(NamedObject):
+    sender_: RESTSender
+    exch_acct_: ExchangeAccountNameT
+    exch_inst_: ExchangeInstrument
+    interval_sec_: IntervalSecT
+    history_depth_sec_: IntervalSecT
+
+    history_: List[MdTradesAggregate]
+
+    callbacks_: List[MdSummaryCallbackT]
+    timer_: Optional[Timer]
+
+    def __init__(
+        self,
+        sender: RESTSender,
+        exch_acct: ExchangeAccountNameT,
+        instrument_id: InstrumentIdT,
+        interval_sec: IntervalSecT,
+        history_depth_sec: IntervalSecT,
+    ) -> None:
+        self.sender_ = sender
+        self.exch_acct_ = exch_acct
+
+        exch_inst = ExchangeAccounts.instance().get_exchange_instrument(
+            exch_acct=exch_acct, instrument_id=instrument_id
+        )
+        assert exch_inst is not None, f"Unable to find Exchange instrument for {exch_acct}/{instrument_id}"
+        self.exch_inst_ = exch_inst
+        self.interval_sec_ = interval_sec
+        self.history_depth_sec_ = history_depth_sec
+
+        self.history_ = []
+        self.callbacks_ = []
+        self.timer_ = None
+
+    def add_callback(self, cb: MdSummaryCallbackT) -> None:
+        self.callbacks_.append(cb)
+
+    def __hash__(self):
+        return hash(
+            (
+                self.exch_acct_,
+                self.exch_inst_.instrument_id(),
+                self.interval_sec_,
+                self.history_depth_sec_,
+            )
+        )
+
+    def rqst_data(self) -> Dict[str, Any]:
+        return {
+            "exch_acct": self.exch_acct_,
+            "instrument_id": self.exch_inst_.instrument_id(),
+            "interval_sec": self.interval_sec_,
+            "history_depth_sec": self.history_depth_sec_,
+        }
+
+    def get_history(self) -> List[MdSummary]:
+        response: requests.Response = self.sender_.send_post(
+            endpoint="md_summary", post_body=self.rqst_data()
+        )
+        if response.status_code not in (200, 201):
+            Log.error(
+                f"{self.fname()}: Received error: {response.status_code} - {response.text}"
+            )
+            return []
+        return MdSummary.from_REST_response(response=response)
+
+    def get_last(self) -> Optional[MdSummary]:
+        Log.info(f"{self.fname()}: for {self.exch_inst_.details_short()}")
+        rqst_data = self.rqst_data()
+        rqst_data["history_depth_sec"] = self.interval_sec_ * 2
+        response: requests.Response = self.sender_.send_post(
+            endpoint="md_summary", post_body=rqst_data
+        )
+        if response.status_code not in (200, 201):
+            Log.error(
+                f"{self.fname()}: Received error: {response.status_code} - {response.text}"
+            )
+            return None
+        res = MdSummary.from_REST_response(response=response)
+        Log.info(f"DEBUG *** {self.exch_inst_.base_asset_id_}: {res[-1].tstamp_}")
+        return None if len(res) == 0 else res[-1]
+
+    def is_empty(self) -> bool:
+        return len(self.history_) == 0
+
+    async def start(self) -> None:
+        if self.timer_:
+            Log.error(f"{self.fname()}: Timer is already started")
+            return
+        mdsum_hist = self.get_history()
+        self.history_ = [
+            mdsum.create_md_trades_aggregate(
+                exch_acct=self.exch_acct_,
+                exch_inst=self.exch_inst_,
+                interval_sec=self.interval_sec_,
+            )
+            for mdsum in mdsum_hist
+        ]
+        await self.run_callbacks()
+        self.set_timer()
+
+    def set_timer(self):
+        if self.timer_:
+            self.timer_.cancel()
+        start_in = self.next_load_time() - current_seconds()
+        self.timer_ = Timer(
+            start_in_sec=start_in,
+            func=self._load_new,
+        )
+        Log.info(f"{self.fname()} Timer for {self.exch_inst_.details_short()} is set to run in {start_in} sec")
+
+    def next_load_time(self) -> NanosT:
+        ALLOW_LAG_SEC = 1
+        curr_sec = int(current_seconds())
+        return (curr_sec - curr_sec % self.interval_sec_) + self.interval_sec_ + ALLOW_LAG_SEC
+
+    async def _load_new(self) -> None:
+
+        last: Optional[MdSummary] = self.get_last()
+        if not last:
+            Log.warning(f"{self.fname()}: did not get last update")
+        elif not self.is_empty() and last.ts_ns_ <= self.history_[-1].aggr_time_ns_:
+            Log.info(
+                f"{self.fname()}: Received {last}. Already Have: {self.history_[-1]}"
+            )
+        else:
+            self.history_.append(last.create_md_trades_aggregate(exch_acct=self.exch_acct_, exch_inst=self.exch_inst_, interval_sec=self.interval_sec_))
+            await self.run_callbacks()
+        self.set_timer()
+
+    async def run_callbacks(self) -> None:
+        [await cb(self.history_) for cb in self.callbacks_]
+
+    def stop(self) -> None:
+        if self.timer_:
+            self.timer_.cancel()
+            self.timer_ = None
+
+
+class CvttRestMktDataClient(NamedObject):
+    config_: Config
+    sender_: RESTSender
+    collectors_: Set[MdSummaryCollector]
+
+    def __init__(self, config: Config) -> None:
+        self.config_ = config
+        base_url = self.config_.get_value("cvtt_base_url", default="")
+        assert base_url
+        self.sender_ = RESTSender(base_url=base_url)
+        self.collectors_ = set()
+
+    async def add_subscription(
+        self,
+        exch_acct: ExchangeAccountNameT,
+        instrument_id: InstrumentIdT,
+        interval_sec: IntervalSecT,
+        history_depth_sec: IntervalSecT,
+        callback: MdSummaryCallbackT,
+    ) -> None:
+        mdsc = MdSummaryCollector(
+            sender=self.sender_,
+            exch_acct=exch_acct,
+            instrument_id=instrument_id,
+            interval_sec=interval_sec,
+            history_depth_sec=history_depth_sec,
+        )
+        mdsc.add_callback(callback)
+        self.collectors_.add(mdsc)
+        await mdsc.start()
+
+
+if __name__ == "__main__":
+    config = Config(json_src={"cvtt_base_url": "http://cvtt-tester-01.cvtt.vpn:23456"})
+    # config = Config(json_src={"cvtt_base_url": "http://dev-server-02.cvtt.vpn:23456"})
+
+    async def _calback(history: List[MdTradesAggregate]) -> None:
+        Log.info(
+            f"MdSummary Hist Length is {len(history)}. Last summary: {history[-1] if  len(history) > 0 else '[]'}"
+        )
+
+    async def __run() -> None:
+        Log.info("Starting...")
+        cvtt_client = CvttRestMktDataClient(config)
+        await cvtt_client.add_subscription(
+            exch_acct="COINBASE_AT",
+            instrument_id="PAIR-BTC-USD",
+            interval_sec=60,
+            history_depth_sec=24 * 3600,
+            callback=_calback,
+        )
+        while True:
+            await asyncio.sleep(5)
+
+    asyncio.run(__run())
+    pass

lib/live/rest_client.py.md

@@ -0,0 +1,60 @@
+```python
+from __future__ import annotations
+
+from typing import Dict
+import time
+
+import requests
+
+from cvttpy_tools.base import NamedObject
+
+class RESTSender(NamedObject):
+    session_: requests.Session
+    base_url_: str
+
+    def __init__(self, base_url: str) -> None:
+        self.base_url_ = base_url
+        self.session_ = requests.Session()
+
+    def is_ready(self) -> bool:
+        """Checks if the server is up and responding"""
+        url = f"{self.base_url_}/ping"
+        try:
+            response = self.session_.get(url)
+            response.raise_for_status()
+            return True
+        except requests.exceptions.RequestException:
+            return False
+
+    def send_post(self, endpoint: str, post_body: Dict) -> requests.Response:
+
+        while not self.is_ready():
+            print("Waiting for FrontGateway to start...")
+            time.sleep(5)
+
+        url = f"{self.base_url_}/{endpoint}"
+        try:
+            return self.session_.request(
+                method="POST",
+                url=url,
+                json=post_body,
+                headers={"Content-Type": "application/json"},
+            )
+        except requests.exceptions.RequestException as excpt:
+            raise ConnectionError(
+                f"Failed to send status={excpt.response.status_code} {excpt.response.text}"  # type: ignore
+            ) from excpt
+
+    def send_get(self, endpoint: str) -> requests.Response:
+        while not self.is_ready():
+            print("Waiting for FrontGateway to start...")
+            time.sleep(5)
+
+        url = f"{self.base_url_}/{endpoint}"
+        try:
+            return self.session_.request(method="GET", url=url)
+        except requests.exceptions.RequestException as excpt:
+            raise ConnectionError(
+                f"Failed to send status={excpt.response.status_code} {excpt.response.text}"  # type: ignore
+            ) from excpt
+```

lib/live/ti_sender.py

@@ -0,0 +1,50 @@
+from enum import Enum
+
+import requests
+
+# import aiohttp
+from cvttpy_tools.base import NamedObject
+from cvttpy_tools.config import Config
+from cvttpy_tools.logger import Log
+from cvttpy_tools.web.rest_client import RESTSender
+# ---
+from cvttpy_trading.trading.trading_instructions import TradingInstructions
+# ---
+from pairs_trading.apps.pair_trader import PairTrader
+
+
+class TradingInstructionsSender(NamedObject):
+    config_: Config
+    sender_: RESTSender
+    pairs_trader_: PairTrader
+
+    class TradingInstType(str, Enum):
+        TARGET_POSITION = "TARGET_POSITION"
+        DIRECT_ORDER = "DIRECT_ORDER"
+        MARKET_MAKING = "MARKET_MAKING"
+        NONE = "NONE"
+
+    def __init__(self, config: Config, pairs_trader: PairTrader) -> None:
+        self.config_ = config
+        base_url = self.config_.get_value("cvtt_base_url", default="")
+        assert base_url
+        self.sender_ = RESTSender(base_url=base_url)
+        self.pairs_trader_ = pairs_trader
+        
+        self.book_id_ = self.pairs_trader_.book_id_
+        assert self.book_id_, "book_id is required"
+        
+        self.strategy_id_ = config.get_value("strategy_id", "")
+        assert self.strategy_id_, "strategy_id is required"
+        
+
+    async def send_trading_instructions(self, ti: TradingInstructions) -> None:
+        Log.info(f"{self.fname()}: sending {ti=}")
+        response: requests.Response = self.sender_.send_post(
+            endpoint="trading_instructions", post_body=ti.to_dict()
+        )
+        if response.status_code not in (200, 201):
+            Log.error(
+                f"{self.fname()}: Received error: {response.status_code} - {response.text}"
+            )
+

lib/pair_selector_engine.py

@@ -0,0 +1,391 @@
+from __future__ import annotations
+from dataclasses import dataclass
+from typing import Any, Dict, List, Optional, Tuple
+
+import numpy as np
+import pandas as pd
+from statsmodels.tsa.stattools import adfuller, coint
+from statsmodels.tsa.vector_ar.vecm import coint_johansen
+# ---
+from cvttpy_tools.base import NamedObject
+from cvttpy_tools.config import Config
+from cvttpy_tools.logger import Log
+from cvttpy_tools.timeutils import NanoPerSec, SecPerHour, current_nanoseconds
+from cvttpy_tools.web.rest_client import RESTSender
+# ---
+from cvttpy_trading.trading.instrument import ExchangeInstrument
+from cvttpy_trading.trading.mkt_data.md_summary import MdTradesAggregate, MdSummary
+
+
+@dataclass
+class InstrumentQuality(NamedObject):
+    instrument_: ExchangeInstrument
+    record_count_: int
+    latest_tstamp_: Optional[pd.Timestamp]
+    status_: str
+    reason_: str
+
+
+@dataclass
+class PairStats(NamedObject):
+    instrument_a_: ExchangeInstrument
+    instrument_b_: ExchangeInstrument
+    pvalue_eg_: Optional[float]
+    pvalue_adf_: Optional[float]
+    pvalue_j_: Optional[float]
+    trace_stat_j_: Optional[float]
+    rank_eg_: int = 0
+    rank_adf_: int = 0
+    rank_j_: int = 0
+    composite_rank_: int = 0
+
+    def as_dict(self) -> Dict[str, Any]:
+        return {
+            "instrument_a": self.instrument_a_.instrument_id(),
+            "instrument_b": self.instrument_b_.instrument_id(),
+            "pvalue_eg": self.pvalue_eg_,
+            "pvalue_adf": self.pvalue_adf_,
+            "pvalue_j": self.pvalue_j_,
+            "trace_stat_j": self.trace_stat_j_,
+            "rank_eg": self.rank_eg_,
+            "rank_adf": self.rank_adf_,
+            "rank_j": self.rank_j_,
+            "composite_rank": self.composite_rank_,
+        }
+
+
+class DataFetcher(NamedObject):
+    sender_: RESTSender
+    interval_sec_: int
+    history_depth_sec_: int
+
+    def __init__(
+        self,
+        base_url: str,
+        interval_sec: int,
+        history_depth_sec: int,
+    ) -> None:
+        self.sender_ = RESTSender(base_url=base_url)
+        self.interval_sec_ = interval_sec
+        self.history_depth_sec_ = history_depth_sec
+
+    def fetch(self, exch_acct: str, inst: ExchangeInstrument) -> List[MdTradesAggregate]:
+        rqst_data = {
+            "exch_acct": exch_acct,
+            "instrument_id": inst.instrument_id(),
+            "interval_sec": self.interval_sec_,
+            "history_depth_sec": self.history_depth_sec_,
+        }
+        response = self.sender_.send_post(endpoint="md_summary", post_body=rqst_data)
+        if response.status_code not in (200, 201):
+            Log.error(
+                f"{self.fname()}: error {response.status_code} for {inst.details_short()}: {response.text}")
+            return []
+        mdsums: List[MdSummary] = MdSummary.from_REST_response(response=response)
+        return [
+            mdsum.create_md_trades_aggregate(
+                exch_acct=exch_acct, exch_inst=inst, interval_sec=self.interval_sec_
+            )
+            for mdsum in mdsums
+        ]
+
+
+class QualityChecker(NamedObject):
+    interval_sec_: int
+
+    def __init__(self, interval_sec: int) -> None:
+        self.interval_sec_ = interval_sec
+
+    def evaluate(self, inst: ExchangeInstrument, aggr: List[MdTradesAggregate]) -> InstrumentQuality:
+        if len(aggr) == 0:
+            return InstrumentQuality(
+                instrument_=inst,
+                record_count_=0,
+                latest_tstamp_=None,
+                status_="FAIL",
+                reason_="no records",
+            )
+
+        aggr_sorted = sorted(aggr, key=lambda a: a.aggr_time_ns_)
+
+        latest_ts = pd.to_datetime(aggr_sorted[-1].aggr_time_ns_, unit="ns", utc=True)
+        now_ts = pd.Timestamp.utcnow()
+        recency_cutoff = now_ts - pd.Timedelta(seconds=2 * self.interval_sec_)
+        if latest_ts <= recency_cutoff:
+            return InstrumentQuality(
+                instrument_=inst,
+                record_count_=len(aggr_sorted),
+                latest_tstamp_=latest_ts,
+                status_="FAIL",
+                reason_=f"stale: latest {latest_ts} <= cutoff {recency_cutoff}",
+            )
+
+        gaps_ok, reason = self._check_gaps(aggr_sorted)
+        status = "PASS" if gaps_ok else "FAIL"
+        return InstrumentQuality(
+            instrument_=inst,
+            record_count_=len(aggr_sorted),
+            latest_tstamp_=latest_ts,
+            status_=status,
+            reason_=reason,
+        )
+
+    def _check_gaps(self, aggr: List[MdTradesAggregate]) -> Tuple[bool, str]:
+        NUM_TRADES_THRESHOLD = 50
+        if len(aggr) < 2:
+            return True, "ok"
+
+        interval_ns = self.interval_sec_ * NanoPerSec
+        for idx in range(1, len(aggr)):
+            prev = aggr[idx - 1]
+            curr = aggr[idx]
+            delta = curr.aggr_time_ns_ - prev.aggr_time_ns_
+            missing_intervals = int(delta // interval_ns) - 1
+            if missing_intervals <= 0:
+                continue
+            
+            prev_nt = prev.num_trades_
+            next_nt = curr.num_trades_
+            estimate = self._approximate_num_trades(prev_nt, next_nt)
+            if estimate > NUM_TRADES_THRESHOLD:
+                return False, (
+                    f"gap of {missing_intervals} interval(s), est num_trades={estimate} > {NUM_TRADES_THRESHOLD}"
+                )
+        return True, "ok"
+
+    @staticmethod
+    def _approximate_num_trades(prev_nt: int, next_nt: int) -> float:
+        if prev_nt is None and next_nt is None:
+            return 0.0
+        if prev_nt is None:
+            return float(next_nt)
+        if next_nt is None:
+            return float(prev_nt)
+        return (prev_nt + next_nt) / 2.0
+
+
+class PairAnalyzer(NamedObject):
+    price_field_: str
+    interval_sec_: int
+
+    def __init__(self, price_field: str, interval_sec: int) -> None:
+        self.price_field_ = price_field
+        self.interval_sec_ = interval_sec
+
+    def analyze(self, series: Dict[ExchangeInstrument, pd.DataFrame]) -> List[PairStats]:
+        instruments = list(series.keys())
+        results: List[PairStats] = []
+        for i in range(len(instruments)):
+            for j in range(i + 1, len(instruments)):
+                inst_a = instruments[i]
+                inst_b = instruments[j]
+                df_a = series[inst_a][["tstamp", "price"]].rename(
+                    columns={"price": "price_a"}
+                )
+                df_b = series[inst_b][["tstamp", "price"]].rename(
+                    columns={"price": "price_b"}
+                )
+                merged = pd.merge(df_a, df_b, on="tstamp", how="inner").sort_values(
+                    "tstamp"
+                )
+                stats = self._compute_stats(inst_a, inst_b, merged)
+                if stats:
+                    results.append(stats)
+        self._rank(results)
+        return results
+
+    def _compute_stats(
+        self,
+        inst_a: ExchangeInstrument,
+        inst_b: ExchangeInstrument,
+        merged: pd.DataFrame,
+    ) -> Optional[PairStats]:
+        if len(merged) < 2:
+            return None
+        px_a = merged["price_a"].astype(float)
+        px_b = merged["price_b"].astype(float)
+
+        std_a = float(px_a.std())
+        std_b = float(px_b.std())
+        if std_a == 0 or std_b == 0:
+            return None
+
+        z_a = (px_a - float(px_a.mean())) / std_a
+        z_b = (px_b - float(px_b.mean())) / std_b
+
+        p_eg: Optional[float]
+        p_adf: Optional[float]
+        p_j: Optional[float]
+        trace_stat: Optional[float]
+
+        try:
+            p_eg = float(coint(z_a, z_b)[1])
+        except Exception as exc:
+            Log.warning(f"{self.fname()}: EG failed for {inst_a.details_short()}/{inst_b.details_short()}: {exc}")
+            p_eg = None
+
+        try:
+            spread = z_a - z_b
+            p_adf = float(adfuller(spread, maxlag=1, regression="c")[1])
+        except Exception as exc:
+            Log.warning(f"{self.fname()}: ADF failed for {inst_a.details_short()}/{inst_b.details_short()}: {exc}")
+            p_adf = None
+
+        try:
+            data = np.column_stack([z_a, z_b])
+            res = coint_johansen(data, det_order=0, k_ar_diff=1)
+            trace_stat = float(res.lr1[0])
+            cv10, cv5, cv1 = res.cvt[0]
+            if trace_stat > cv1:
+                p_j = 0.01
+            elif trace_stat > cv5:
+                p_j = 0.05
+            elif trace_stat > cv10:
+                p_j = 0.10
+            else:
+                p_j = 1.0
+        except Exception as exc:
+            Log.warning(f"{self.fname()}: Johansen failed for {inst_a.details_short()}/{inst_b.details_short()}: {exc}")
+            p_j = None
+            trace_stat = None
+
+        return PairStats(
+            instrument_a_=inst_a,
+            instrument_b_=inst_b,
+            pvalue_eg_=p_eg,
+            pvalue_adf_=p_adf,
+            pvalue_j_=p_j,
+            trace_stat_j_=trace_stat,
+        )
+
+    def _rank(self, results: List[PairStats]) -> None:
+        self._assign_ranks(results, key=lambda r: r.pvalue_eg_, attr="rank_eg_")
+        self._assign_ranks(results, key=lambda r: r.pvalue_adf_, attr="rank_adf_")
+        self._assign_ranks(results, key=lambda r: r.pvalue_j_, attr="rank_j_")
+        for res in results:
+            res.composite_rank_ = res.rank_eg_ + res.rank_adf_ + res.rank_j_
+        results.sort(key=lambda r: r.composite_rank_)
+
+    @staticmethod
+    def _assign_ranks(
+        results: List[PairStats], key, attr: str
+    ) -> None:
+        values = [key(r) for r in results]
+        sorted_vals = sorted([v for v in values if v is not None])
+        for res in results:
+            val = key(res)
+            if val is None:
+                setattr(res, attr, len(sorted_vals) + 1)
+                continue
+            rank = 1 + sum(1 for v in sorted_vals if v < val)
+            setattr(res, attr, rank)
+
+
+class PairSelectionEngine(NamedObject):
+    config_: object
+    instruments_: List[ExchangeInstrument]
+    price_field_: str
+    fetcher_: DataFetcher
+    quality_: QualityChecker
+    analyzer_: PairAnalyzer
+    interval_sec_: int
+    history_depth_sec_: int
+    data_quality_cache_: List[InstrumentQuality]
+    pair_results_cache_: List[PairStats]
+
+    def __init__(
+        self,
+        config: Config,
+        instruments: List[ExchangeInstrument],
+        price_field: str,
+    ) -> None:
+        self.config_ = config
+        self.instruments_ = instruments
+        self.price_field_ = price_field
+
+        interval_sec = int(config.get_value("interval_sec", 0))
+        history_depth_sec = int(config.get_value("history_depth_hours", 0)) * SecPerHour
+        base_url = config.get_value("cvtt_base_url", None)
+        assert interval_sec > 0, "interval_sec must be > 0"
+        assert history_depth_sec > 0, "history_depth_sec must be > 0"
+        assert base_url, "cvtt_base_url must be set"
+
+        self.fetcher_ = DataFetcher(
+            base_url=base_url,
+            interval_sec=interval_sec,
+            history_depth_sec=history_depth_sec,
+        )
+        self.quality_ = QualityChecker(interval_sec=interval_sec)
+        self.analyzer_ = PairAnalyzer(price_field=price_field, interval_sec=interval_sec)
+
+        self.interval_sec_ = interval_sec
+        self.history_depth_sec_ = history_depth_sec
+
+        self.data_quality_cache_ = []
+        self.pair_results_cache_ = []
+
+    async def run_once(self) -> None:
+        quality_results: List[InstrumentQuality] = []
+        price_series: Dict[ExchangeInstrument, pd.DataFrame] = {}
+
+        for inst in self.instruments_:
+            exch_acct = inst.user_data_.get("exch_acct") or inst.exchange_id_
+            aggr = self.fetcher_.fetch(exch_acct=exch_acct, inst=inst)
+            q = self.quality_.evaluate(inst, aggr)
+            quality_results.append(q)
+            if q.status_ != "PASS":
+                continue
+            df = self._to_dataframe(aggr, inst)
+            if len(df) > 0:
+                price_series[inst] = df
+        self.data_quality_cache_ = quality_results
+        self.pair_results_cache_ = self.analyzer_.analyze(price_series)
+
+    def _to_dataframe(self, aggr: List[MdTradesAggregate], inst: ExchangeInstrument) -> pd.DataFrame:
+        rows: List[Dict[str, Any]] = []
+        for item in aggr:
+            rows.append(
+                {
+                    "tstamp": pd.to_datetime(item.aggr_time_ns_, unit="ns", utc=True),
+                    "price": self._extract_price(item, inst),
+                    "num_trades": item.num_trades_,
+                }
+            )
+        df = pd.DataFrame(rows)
+        return df.sort_values("tstamp").reset_index(drop=True)
+
+    def _extract_price(self, aggr: MdTradesAggregate, inst: ExchangeInstrument) -> float:
+        price_field = self.price_field_
+        # MdTradesAggregate inherits hist bar with fields open_, high_, low_, close_, vwap_
+        field_map = {
+            "open": aggr.open_,
+            "high": aggr.high_,
+            "low": aggr.low_,
+            "close": aggr.close_,
+            "vwap": aggr.vwap_,
+        }
+        raw = field_map.get(price_field, aggr.close_)
+        return inst.get_price(raw)
+
+    def sleep_seconds_until_next_cycle(self) -> float:
+        now_ns = current_nanoseconds()
+        interval_ns = self.interval_sec_ * NanoPerSec
+        next_boundary = (now_ns // interval_ns + 1) * interval_ns
+        return max(0.0, (next_boundary - now_ns) / NanoPerSec)
+
+    def quality_dicts(self) -> List[Dict[str, Any]]:
+        res: List[Dict[str, Any]] = []
+        for q in self.data_quality_cache_:
+            res.append(
+                {
+                    "instrument": q.instrument_.instrument_id(),
+                    "record_count": q.record_count_,
+                    "latest_tstamp": q.latest_tstamp_.isoformat() if q.latest_tstamp_ else None,
+                    "status": q.status_,
+                    "reason": q.reason_,
+                }
+            )
+        return res
+
+    def pair_dicts(self) -> List[Dict[str, Any]]:
+        return [p.as_dict() for p in self.pair_results_cache_]

lib/pt_strategy/live/live_strategy.py

@@ -0,0 +1,351 @@
+from __future__ import annotations
+
+from typing import Any, Dict, List, Optional
+
+import pandas as pd
+
+# ---
+from cvttpy_tools.base import NamedObject
+from cvttpy_tools.app import App
+from cvttpy_tools.config import Config
+from cvttpy_tools.settings.cvtt_types import IntervalSecT
+from cvttpy_tools.timeutils import NanosT, SecPerHour, current_nanoseconds, NanoPerSec, format_nanos_utc
+from cvttpy_tools.logger import Log
+
+# ---
+from cvttpy_trading.trading.instrument import ExchangeInstrument
+from cvttpy_trading.trading.mkt_data.md_summary import MdTradesAggregate
+from cvttpy_trading.trading.trading_instructions import TradingInstructions
+from cvttpy_trading.trading.trading_instructions import TargetPositionSignal
+
+# ---
+from pairs_trading.lib.pt_strategy.model_data_policy import ModelDataPolicy
+from pairs_trading.lib.pt_strategy.pt_model import Prediction
+from pairs_trading.lib.pt_strategy.trading_pair import LiveTradingPair
+from pairs_trading.apps.pair_trader import PairTrader
+from pairs_trading.lib.pt_strategy.pt_market_data import LiveMarketData
+
+
+class PtLiveStrategy(NamedObject):
+    config_: Config
+    instruments_: List[ExchangeInstrument]
+
+    interval_sec_: IntervalSecT
+    history_depth_sec_: IntervalSecT
+    open_threshold_: float
+    close_threshold_: float
+
+    trading_pair_: LiveTradingPair
+    model_data_policy_: ModelDataPolicy
+    pairs_trader_: PairTrader
+
+    # for presentation: history of prediction values and trading signals
+    predictions_df_: pd.DataFrame
+    trading_signals_df_: pd.DataFrame
+    allowed_md_lag_sec_: int
+
+
+    def __init__(
+        self,
+        config: Config,
+        pairs_trader: PairTrader,
+    ):
+        self.config_ = config
+
+        self.pairs_trader_ = pairs_trader
+        self.trading_pair_ = LiveTradingPair(
+            config=config,
+            instruments=self.pairs_trader_.instruments_,
+        )
+        self.model_data_policy_ = ModelDataPolicy.create(
+            self.config_,
+            is_real_time=True,
+            pair=self.trading_pair_,
+        )
+        assert (
+            self.model_data_policy_ is not None
+        ), f"{self.fname()}: Unable to create ModelDataPolicy"
+
+        self.predictions_df_ = pd.DataFrame()
+        self.trading_signals_df_ = pd.DataFrame()
+
+        self.instruments_ = self.pairs_trader_.instruments_
+
+        App.instance().add_call(
+            stage=App.Stage.Config, func=self._on_config(), can_run_now=True
+        )
+
+    async def _on_config(self) -> None:
+        self.interval_sec_ = self.config_.get_value("interval_sec", 0)
+        assert self.interval_sec_ > 0, "interval_sec cannot be 0"
+        self.history_depth_sec_ = (
+            self.config_.get_value("history_depth_hours", 0) * SecPerHour
+        )
+        assert self.history_depth_sec_ > 0, "history_depth_hours cannot be 0"
+
+        self.allowed_md_lag_sec_ = self.config_.get_value("allowed_md_lag_sec", 3)
+
+        self.open_threshold_ = self.config_.get_value(
+            "model/disequilibrium/open_trshld", 0.0
+        )
+        self.close_threshold_ = self.config_.get_value(
+            "model/disequilibrium/close_trshld", 0.0
+        )
+
+        assert (
+            self.open_threshold_ > 0
+        ), "disequilibrium/open_trshld must be greater than 0"
+        assert (
+            self.close_threshold_ > 0
+        ), "disequilibrium/close_trshld must be greater than 0"
+
+        await self.pairs_trader_.subscribe_md()
+
+
+    def __repr__(self) -> str:
+        return f"{self.classname()}: trading_pair={self.trading_pair_}, mdp={self.model_data_policy_.__class__.__name__}, "
+
+    async def on_mkt_data_hist_snapshot(
+        self, hist_aggr: List[MdTradesAggregate]
+    ) -> None:
+        if not self._is_md_actual(hist_aggr=hist_aggr):
+            return
+
+        market_data_df: pd.DataFrame = self._create_md_df(hist_aggr=hist_aggr)
+        if len(market_data_df) == 0:
+            Log.warning(f"{self.fname()} Unable to create market data df")
+            return
+
+        self.trading_pair_.market_data_ = market_data_df
+
+        Log.info(f"{self.fname()}: Running prediction for pair: {self.trading_pair_}")
+        prediction = self.trading_pair_.run(
+            market_data_df, self.model_data_policy_.advance()
+        )
+        self.predictions_df_ = pd.concat(
+            [self.predictions_df_, prediction.to_df()], ignore_index=True
+        )
+
+        trading_instructions: List[TradingInstructions] = (
+            self._create_trading_instructions(
+                prediction=prediction, last_row=market_data_df.iloc[-1]
+            )
+        )
+        if trading_instructions is not None:
+            await self._send_trading_instructions(trading_instructions)
+
+    def _is_md_actual(self, hist_aggr: List[MdTradesAggregate]) -> bool:
+        if len(hist_aggr) == 0:
+            Log.warning(f"{self.fname()} list of aggregates IS EMPTY")
+            return False
+
+        curr_ns = current_nanoseconds()
+        
+        # MAYBE check market data length
+        
+        # at 18:05:01 we should see data for 18:04:00
+        lag_sec = (curr_ns - hist_aggr[-1].aggr_time_ns_) / NanoPerSec - self.interval_sec()
+        if lag_sec > self.allowed_md_lag_sec_:
+            Log.warning(
+                f"{self.fname()} {hist_aggr[-1].exch_inst_.details_short()}"
+                f" Lagging {int(lag_sec)} > {self.allowed_md_lag_sec_} seconds:"
+                f"\n{len(hist_aggr)} records"
+                f"\n{hist_aggr[-1].exch_inst_.base_asset_id_}: {hist_aggr[-1].tstamp()}"
+                f"\n{hist_aggr[-2].exch_inst_.base_asset_id_}: {hist_aggr[-2].tstamp()}"
+            )
+            return False
+        else:
+            Log.info(
+                f"{self.fname()} {hist_aggr[-1].exch_inst_.details_short()}"
+                f" Lag {int(lag_sec)} <= {self.allowed_md_lag_sec_} seconds"
+                f"\n{len(hist_aggr)} records"
+                f"\n{hist_aggr[-1].exch_inst_.base_asset_id_}: {hist_aggr[-1].tstamp()}"
+                f"\n{hist_aggr[-2].exch_inst_.base_asset_id_}: {hist_aggr[-2].tstamp()}"
+            )
+        return True
+
+    def _create_md_df(self, hist_aggr: List[MdTradesAggregate]) -> pd.DataFrame:
+        """
+                          tstamp              time_ns    symbol      open      high       low     close     volume  num_trades        vwap
+        0    2025-09-10 11:30:00  1757503800000000000  ADA-USDT    0.8750    0.8750    0.8743    0.8743  50710.500           0    0.874489
+        1    2025-09-10 11:30:00  1757503800000000000  SOL-USDT  219.9700  219.9800  219.6600  219.7000   2648.582           0  219.787847
+        2    2025-09-10 11:31:00  1757503860000000000  SOL-USDT  219.7000  219.7300  219.6200  219.6200   1134.886           0  219.663460
+        3    2025-09-10 11:31:00  1757503860000000000  ADA-USDT    0.8743    0.8745    0.8741    0.8741  10696.400           0    0.874234
+        4    2025-09-10 11:32:00  1757503920000000000  ADA-USDT    0.8742    0.8742    0.8739    0.8740  18546.900           0    0.874037
+        """
+
+        rows: List[Dict[str, Any]] = []
+
+        for aggr in hist_aggr:
+            exch_inst = aggr.exch_inst_
+
+            rows.append(
+                {
+                    # convert nanoseconds → tz-aware pandas timestamp
+                    "tstamp": pd.to_datetime(aggr.aggr_time_ns_, unit="ns", utc=True),
+                    "time_ns": aggr.aggr_time_ns_,
+                    "symbol": exch_inst.instrument_id().split("-", 1)[1],
+                    "exchange_id": exch_inst.exchange_id_,
+                    "instrument_id": exch_inst.instrument_id(),
+                    "open": exch_inst.get_price(aggr.open_),
+                    "high": exch_inst.get_price(aggr.high_),
+                    "low": exch_inst.get_price(aggr.low_),
+                    "close": exch_inst.get_price(aggr.close_),
+                    "volume": exch_inst.get_quantity(aggr.volume_),
+                    "num_trades": aggr.num_trades_,
+                    "vwap": exch_inst.get_price(aggr.vwap_),
+                }
+            )
+
+        source_md_df = pd.DataFrame(
+            rows,
+            columns=[
+                "tstamp",
+                "time_ns",
+                "symbol",
+                "exchange_id",
+                "instrument_id",
+                "open",
+                "high",
+                "low",
+                "close",
+                "volume",
+                "num_trades",
+                "vwap",
+            ],
+        )
+
+        # automatic sorting
+        source_md_df.sort_values(
+            by=["time_ns", "symbol"],
+            ascending=True,
+            inplace=True,
+            kind="mergesort",  # stable sort
+        )
+
+        source_md_df.reset_index(drop=True, inplace=True)
+
+        pt_mkt_data = LiveMarketData(config=self.config_, instruments=self.instruments_)
+        pt_mkt_data.origin_mkt_data_df_ = source_md_df
+        pt_mkt_data.set_market_data()
+
+        return pt_mkt_data.market_data_df_
+
+    def interval_sec(self) -> IntervalSecT:
+        return self.interval_sec_
+
+    def history_depth_sec(self) -> IntervalSecT:
+        return self.history_depth_sec_
+
+    async def _send_trading_instructions(
+        self, trading_instructions: List[TradingInstructions]
+    ) -> None:
+        for ti in trading_instructions:
+            Log.info(f"{self.fname()} Sending trading instructions {ti}")
+            await self.pairs_trader_.ti_sender_.send_trading_instructions(ti)
+
+    def _create_trading_instructions(
+        self, prediction: Prediction, last_row: pd.Series
+    ) -> List[TradingInstructions]:
+        trd_instructions: List[TradingInstructions] = []
+        pair = self.trading_pair_
+
+        scaled_disequilibrium = prediction.scaled_disequilibrium_
+        abs_scaled_disequilibrium = abs(scaled_disequilibrium)
+
+        if abs_scaled_disequilibrium >= self.open_threshold_:
+            trd_instructions = self._create_open_trade_instructions(
+                pair, row=last_row, prediction=prediction
+            )
+
+        elif abs_scaled_disequilibrium <= self.close_threshold_ or pair.to_stop_close_conditions(predicted_row=last_row):
+            trd_instructions = self._create_close_trade_instructions(
+                pair, row=last_row  # , prediction=prediction
+            )
+
+
+        return trd_instructions
+    
+    def _strength(self, scaled_disequilibrium: float) -> float:
+        # TODO PtLiveStrategy._strength()
+        return 1.0
+
+    def _create_open_trade_instructions(
+        self, pair: LiveTradingPair, row: pd.Series, prediction: Prediction
+    ) -> List[TradingInstructions]:
+        diseqlbrm = prediction.disequilibrium_
+        scaled_disequilibrium = prediction.scaled_disequilibrium_
+        if diseqlbrm > 0:
+            side_a = -1
+            side_b = 1
+        else:
+            side_a = 1
+            side_b = -1
+
+        ti_a: Optional[TradingInstructions] = TradingInstructions(
+            book=self.pairs_trader_.book_id_,
+            strategy_id=self.__class__.__name__,
+            ti_type=TradingInstructions.Type.TARGET_POSITION,
+            issued_ts_ns=current_nanoseconds(),
+            data=TargetPositionSignal(
+                strength=side_a * self._strength(scaled_disequilibrium),
+                exchange_id=pair.get_instrument_a().exchange_id_,
+                base_asset=pair.get_instrument_a().base_asset_id_,
+                quote_asset=pair.get_instrument_a().quote_asset_id_,
+                user_data={}
+            ),
+        )
+        if not ti_a:
+            return []
+        ti_b: Optional[TradingInstructions] = TradingInstructions(
+            book=self.pairs_trader_.book_id_,
+            strategy_id=self.__class__.__name__,
+            ti_type=TradingInstructions.Type.TARGET_POSITION,
+            issued_ts_ns=current_nanoseconds(),
+            data=TargetPositionSignal(
+                strength=side_b * self._strength(scaled_disequilibrium),
+                exchange_id=pair.get_instrument_b().exchange_id_,
+                base_asset=pair.get_instrument_b().base_asset_id_,
+                quote_asset=pair.get_instrument_b().quote_asset_id_,
+                user_data={}
+            ),
+        )
+        if not ti_b:
+            return []
+        return [ti_a, ti_b]
+
+
+    def _create_close_trade_instructions(
+        self, pair: LiveTradingPair, row: pd.Series
+    ) -> List[TradingInstructions]:
+        ti_a: Optional[TradingInstructions] = TradingInstructions(
+            book=self.pairs_trader_.book_id_,
+            strategy_id=self.__class__.__name__,
+            ti_type=TradingInstructions.Type.TARGET_POSITION,
+            issued_ts_ns=current_nanoseconds(),
+            data=TargetPositionSignal(
+                strength=0,
+                exchange_id=pair.get_instrument_a().exchange_id_,
+                base_asset=pair.get_instrument_a().base_asset_id_,
+                quote_asset=pair.get_instrument_a().quote_asset_id_,
+                user_data={}
+            ),
+        )
+        if not ti_a:
+            return []
+        ti_b: Optional[TradingInstructions] = TradingInstructions(
+            book=self.pairs_trader_.book_id_,
+            strategy_id=self.__class__.__name__,
+            ti_type=TradingInstructions.Type.TARGET_POSITION,
+            issued_ts_ns=current_nanoseconds(),
+            data=TargetPositionSignal(
+                strength=0,
+                exchange_id=pair.get_instrument_b().exchange_id_,
+                base_asset=pair.get_instrument_b().base_asset_id_,
+                quote_asset=pair.get_instrument_b().quote_asset_id_,
+                user_data={}
+            ),
+        )
+        if not ti_b:
+            return []
+        return [ti_a, ti_b]

lib/pt_strategy/model_data_policy.py

@@ -0,0 +1,253 @@
+from __future__ import annotations
+
+import copy
+from abc import ABC, abstractmethod
+from dataclasses import dataclass
+from typing import Any, Dict, Optional, cast
+
+import numpy as np
+import pandas as pd
+
+from cvttpy_tools.config import Config
+
+@dataclass
+class DataWindowParams:
+    training_size_: int
+    training_start_index_: int
+
+
+class ModelDataPolicy(ABC):
+    config_: Config
+    current_data_params_: DataWindowParams
+    count_: int
+    is_real_time_: bool
+
+    def __init__(self, config: Config, *args: Any, **kwargs: Any):
+        self.config_ = config
+        self.current_data_params_ = DataWindowParams(
+            training_size_=config.get_value("model/training_size", 120),
+            training_start_index_=0,
+        )
+        self.count_ = 0
+        self.is_real_time_ = kwargs.get("is_real_time", False)
+
+    @abstractmethod
+    def advance(self, mkt_data_df: Optional[pd.DataFrame] = None) -> DataWindowParams:
+        self.count_ += 1
+        if not self.is_real_time_:
+            print(self.count_, end="\r")
+        return self.current_data_params_
+
+    @staticmethod
+    def create(config: Config, *args: Any, **kwargs: Any) -> ModelDataPolicy:
+        import importlib
+
+        model_data_policy_class_name = config.get_value("model/model_data_policy_class", None)
+        assert model_data_policy_class_name is not None
+        module_name, class_name = model_data_policy_class_name.rsplit(".", 1)
+        module = importlib.import_module(module_name)
+        model_training_data_policy_object = getattr(module, class_name)(
+            config=config, *args, **kwargs
+        )
+        return cast(ModelDataPolicy, model_training_data_policy_object)
+
+
+class RollingWindowDataPolicy(ModelDataPolicy):
+    def __init__(self, config: Config, *args: Any, **kwargs: Any):
+        super().__init__(config, *args, **kwargs)
+        self.count_ = 1
+
+    def advance(self, mkt_data_df: Optional[pd.DataFrame] = None) -> DataWindowParams:
+        super().advance(mkt_data_df)
+        if self.is_real_time_:
+            self.current_data_params_.training_start_index_ = 0
+            if mkt_data_df and len(mkt_data_df) > self.curren_data_params_.training_size_:
+                self.current_data_params_.training_start_index_ = -self.curren_data_params_.training_size_ 
+        else:
+            self.current_data_params_.training_start_index_ += 1
+        return self.current_data_params_
+
+
+class OptimizedWndDataPolicy(ModelDataPolicy, ABC):
+    mkt_data_df_: pd.DataFrame
+    pair_: TradingPair  # type: ignore
+    min_training_size_: int
+    max_training_size_: int
+    end_index_: int
+    prices_a_: np.ndarray
+    prices_b_: np.ndarray
+
+    def __init__(self, config: Config, *args: Any, **kwargs: Any):
+        super().__init__(config, *args, **kwargs)
+        assert (
+            kwargs.get("pair") is not None
+        ), "pair must be provided"
+        assert (config.key_exists("model/max_training_size") and config.key_exists("model/min_training_size")
+            ), "min_training_size and max_training_size must be provided"
+        self.min_training_size_ = cast(int, config.get_value("model/min_training_size"))
+        self.max_training_size_ = cast(int, config.get_value("model/max_training_size"))
+
+        from pairs_trading.lib.pt_strategy.trading_pair import TradingPair
+        self.pair_ = cast(TradingPair, kwargs.get("pair"))        
+        
+        if "mkt_data" in kwargs:
+            self.mkt_data_df_ = cast(pd.DataFrame, kwargs.get("mkt_data"))
+            col_a, col_b = self.pair_.colnames()
+            self.prices_a_ = np.array(self.mkt_data_df_[col_a])
+            self.prices_b_ = np.array(self.mkt_data_df_[col_b])
+        assert self.min_training_size_ < self.max_training_size_
+
+
+    def advance(self, mkt_data_df: Optional[pd.DataFrame] = None) -> DataWindowParams:
+        super().advance(mkt_data_df)
+        if mkt_data_df is not None:
+            self.mkt_data_df_ = mkt_data_df
+
+        if self.is_real_time_:
+            self.end_index_ = len(self.mkt_data_df_) - 1
+        else:
+            self.end_index_ = self.current_data_params_.training_start_index_ + self.max_training_size_
+            if self.end_index_ > len(self.mkt_data_df_) - 1:
+                self.end_index_ = len(self.mkt_data_df_) - 1
+                self.current_data_params_.training_start_index_ = self.end_index_ - self.max_training_size_
+                if self.current_data_params_.training_start_index_ < 0:
+                    self.current_data_params_.training_start_index_ = 0
+
+        col_a, col_b = self.pair_.colnames()
+        self.prices_a_ = np.array(self.mkt_data_df_[col_a])
+        self.prices_b_ = np.array(self.mkt_data_df_[col_b])
+
+        self.current_data_params_ = self.optimize_window_size()
+        return self.current_data_params_
+
+    @abstractmethod
+    def optimize_window_size(self) -> DataWindowParams:
+        ...
+
+class EGOptimizedWndDataPolicy(OptimizedWndDataPolicy):
+    '''
+    # Engle-Granger cointegration test
+    *** VERY SLOW ***
+    '''
+    def __init__(self, config: Config, *args: Any, **kwargs: Any):
+        super().__init__(config, *args, **kwargs)
+
+    def optimize_window_size(self) -> DataWindowParams:
+        # Run Engle-Granger cointegration test
+        last_pvalue = 1.0
+        result = copy.copy(self.current_data_params_)
+        for trn_size in range(self.min_training_size_, self.max_training_size_):
+            if self.end_index_ - trn_size < 0:
+                break
+
+            from statsmodels.tsa.stattools import coint  # type: ignore
+
+            start_index = self.end_index_ - trn_size
+            series_a = self.prices_a_[start_index : self.end_index_]
+            series_b = self.prices_b_[start_index : self.end_index_]
+            eg_pvalue = float(coint(series_a, series_b)[1])
+            if eg_pvalue < last_pvalue:
+                last_pvalue = eg_pvalue
+                result.training_size_ = trn_size
+                result.training_start_index_ = start_index
+
+        # print(
+        #     f"*** DEBUG *** end_index={self.end_index_}, best_trn_size={self.current_data_params_.training_size}, {last_pvalue=}"
+        # )
+        return result
+
+class ADFOptimizedWndDataPolicy(OptimizedWndDataPolicy):
+    # Augmented Dickey-Fuller test
+    def __init__(self, config: Config, *args: Any, **kwargs: Any):
+        super().__init__(config, *args, **kwargs)
+
+    def optimize_window_size(self) -> DataWindowParams:
+        from statsmodels.regression.linear_model import OLS
+        from statsmodels.tools.tools import add_constant
+        from statsmodels.tsa.stattools import adfuller
+
+        last_pvalue = 1.0
+        result = copy.copy(self.current_data_params_)
+        for trn_size in range(self.min_training_size_, self.max_training_size_):
+            if self.end_index_ - trn_size < 0:
+                break
+            start_index = self.end_index_ - trn_size
+            y = self.prices_a_[start_index : self.end_index_]
+            x = self.prices_b_[start_index : self.end_index_]
+
+            # Add constant to x for intercept
+            x_with_const = add_constant(x)
+
+            # OLS regression: y = a + b*x + e
+            model = OLS(y, x_with_const).fit()
+            residuals = y - model.predict(x_with_const)
+
+            # ADF test on residuals
+            try:
+                adf_result = adfuller(residuals, maxlag=1, regression="c")
+                adf_pvalue = float(adf_result[1])
+            except Exception as e:
+                # Handle edge cases with exception (e.g., constant series, etc.)
+                adf_pvalue = 1.0
+
+            if adf_pvalue < last_pvalue:
+                last_pvalue = adf_pvalue
+                result.training_size_ = trn_size
+                result.training_start_index_ = start_index
+
+        # print(
+        #     f"*** DEBUG *** end_index={self.end_index_},"
+        #     f" best_trn_size={self.current_data_params_.training_size},"
+        #     f" {last_pvalue=}"
+        # )
+        return result
+    
+class JohansenOptdWndDataPolicy(OptimizedWndDataPolicy):
+    # Johansen test
+    def __init__(self, config: Config, *args: Any, **kwargs: Any):
+        super().__init__(config, *args, **kwargs)
+
+    def optimize_window_size(self) -> DataWindowParams:
+        from statsmodels.tsa.vector_ar.vecm import coint_johansen
+        import numpy as np
+
+        best_stat = -np.inf
+        best_trn_size = 0
+        best_start_index = -1
+
+        result = copy.copy(self.current_data_params_)
+        for trn_size in range(self.min_training_size_, self.max_training_size_):
+            if self.end_index_ - trn_size < 0:
+                break
+            start_index = self.end_index_ - trn_size
+            series_a = self.prices_a_[start_index:self.end_index_]
+            series_b = self.prices_b_[start_index:self.end_index_]
+
+            # Combine into 2D matrix for Johansen test
+            try:
+                data = np.column_stack([series_a, series_b])
+
+                # Johansen test: det_order=0 (no deterministic trend), k_ar_diff=1 (lag)
+                res = coint_johansen(data, det_order=0, k_ar_diff=1)
+
+                # Trace statistic for cointegration rank 1
+                trace_stat = res.lr1[0]  # test stat for rank=0 vs >=1
+                critical_value = res.cvt[0, 1]  # 5% critical value
+
+                if trace_stat > best_stat:
+                    best_stat = trace_stat
+                    best_trn_size = trn_size
+                    best_start_index = start_index
+            except Exception:
+                continue
+
+        if best_trn_size > 0:
+            result.training_size_ = best_trn_size
+            result.training_start_index_ = best_start_index
+        else:
+            print("*** WARNING: No valid cointegration window found.")
+
+        # print(
+        #     f"*** DEBUG *** end_index={self.end_index_}, best_trn_size={best_trn_size}, trace_stat={best_stat}"
+        # )
+        return result

lib/pt_strategy/models.py

@@ -0,0 +1,104 @@
+from __future__ import annotations
+from typing import Optional
+
+import pandas as pd
+import statsmodels.api as sm
+
+
+
+from pairs_trading.lib.pt_strategy.pt_model import PairsTradingModel, Prediction
+from pairs_trading.lib.pt_strategy.trading_pair import TradingPair
+
+
+class OLSModel(PairsTradingModel):
+    model_: Optional[sm.regression.linear_model.RegressionResultsWrapper]
+    pair_predict_result_: Optional[pd.DataFrame]
+    zscore_df_: Optional[pd.DataFrame]
+
+    def predict(self, pair: TradingPair) -> Prediction:
+        self.training_df_ = pair.market_data_.copy()
+
+        zscore_df = self._fit_zscore(pair=pair)
+
+        assert zscore_df is not None
+        # zscore is both disequilibrium and scaled_disequilibrium
+        self.training_df_["dis-equilibrium"] = zscore_df[0]
+        self.training_df_["scaled_dis-equilibrium"] = zscore_df[0]
+
+        assert zscore_df is not None
+        return Prediction(
+            tstamp=pair.market_data_.iloc[-1]["tstamp"],
+            disequilibrium=self.training_df_["dis-equilibrium"].iloc[-1],
+            scaled_disequilibrium=self.training_df_["scaled_dis-equilibrium"].iloc[-1],
+        )
+
+    def _fit_zscore(self, pair: TradingPair) -> pd.DataFrame:
+        assert self.training_df_ is not None
+        symbol_a_px_series = self.training_df_[pair.colnames()].iloc[:, 0]
+        symbol_b_px_series = self.training_df_[pair.colnames()].iloc[:, 1]
+
+        symbol_a_px_series, symbol_b_px_series = symbol_a_px_series.align(
+            symbol_b_px_series, axis=0
+        )
+
+        X = sm.add_constant(symbol_b_px_series)
+        self.model_ = sm.OLS(symbol_a_px_series, X).fit()
+        assert self.model_ is not None
+
+        # alternate way would be to use models residuals (will give identical results)
+        # alpha, beta = self.model_.params
+        # spread = symbol_a_px_series - (alpha + beta * symbol_b_px_series)
+        spread = self.model_.resid
+        return pd.DataFrame((spread - spread.mean()) / spread.std())
+
+
+class VECMModel(PairsTradingModel):
+    def predict(self, pair: TradingPair) -> Prediction:
+        self.training_df_ = pair.market_data_.copy()
+        assert self.training_df_ is not None
+        vecm_fit = self._fit_VECM(pair=pair)
+
+        assert vecm_fit is not None
+        predicted_prices = vecm_fit.predict(steps=1)
+
+        # Convert prediction to a DataFrame for readability
+        predicted_df = pd.DataFrame(
+            predicted_prices, columns=pd.Index(pair.colnames()), dtype=float
+        )
+
+        disequilibrium = (predicted_df[pair.colnames()] @ vecm_fit.beta)[0][0]
+        scaled_disequilibrium = (disequilibrium - self.training_mu_) / self.training_std_
+        return Prediction(
+            tstamp=pair.market_data_.iloc[-1]["tstamp"],
+            disequilibrium=disequilibrium,
+            scaled_disequilibrium=scaled_disequilibrium,
+        )
+        
+    def _fit_VECM(self, pair: TradingPair) -> VECMResults: # type: ignore
+        from statsmodels.tsa.vector_ar.vecm import VECM, VECMResults
+
+        vecm_df = self.training_df_[pair.colnames()].reset_index(drop=True)
+        vecm_model = VECM(vecm_df, coint_rank=1)
+        vecm_fit = vecm_model.fit()
+
+        assert vecm_fit is not None
+
+        # Check if the model converged properly
+        if not hasattr(vecm_fit, "beta") or vecm_fit.beta is None:
+            print(f"{self}: VECM model failed to converge properly")
+
+        diseq_series = self.training_df_[pair.colnames()] @ vecm_fit.beta
+        # print(diseq_series.shape)
+        self.training_mu_ = float(diseq_series[0].mean())
+        self.training_std_ = float(diseq_series[0].std())
+
+        self.training_df_["dis-equilibrium"] = (
+            self.training_df_[pair.colnames()] @ vecm_fit.beta
+        )
+        # Normalize the dis-equilibrium
+        self.training_df_["scaled_dis-equilibrium"] = (
+            diseq_series - self.training_mu_
+        ) / self.training_std_
+
+        return vecm_fit
+

lib/pt_strategy/prediction.py

@@ -0,0 +1,28 @@
+from __future__ import annotations
+
+from typing import Any, Dict
+
+import pandas as pd
+
+
+class Prediction:
+    tstamp_: pd.Timestamp
+    disequilibrium_: float
+    scaled_disequilibrium_: float
+
+    def __init__(self, tstamp: pd.Timestamp, disequilibrium: float, scaled_disequilibrium: float):
+        self.tstamp_ = tstamp
+        self.disequilibrium_ = disequilibrium
+        self.scaled_disequilibrium_ = scaled_disequilibrium
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "tstamp": self.tstamp_,
+            "disequilibrium": self.disequilibrium_,
+            "signed_scaled_disequilibrium": self.scaled_disequilibrium_,
+            "scaled_disequilibrium": abs(self.scaled_disequilibrium_),
+            # "pair": self.pair_,
+        }
+    def to_df(self) -> pd.DataFrame:
+        return pd.DataFrame([self.to_dict()])
+    

lib/pt_strategy/pt_market_data.py

@@ -0,0 +1,223 @@
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import Any, Dict, List, Optional
+
+import pandas as pd
+
+# ---
+from cvttpy_tools.base import NamedObject
+from cvttpy_tools.config import Config
+from cvttpy_tools.settings.cvtt_types import JsonDictT
+
+# ---
+from cvttpy_trading.trading.mkt_data.md_summary import MdTradesAggregate
+from cvttpy_trading.trading.instrument import ExchangeInstrument
+# ---
+from pairs_trading.lib.tools.data_loader import load_market_data
+
+
+class PtMarketData(NamedObject, ABC):
+    config_: Config
+    origin_mkt_data_df_: pd.DataFrame
+    market_data_df_: pd.DataFrame
+    stat_model_price_: str
+    instruments_: List[ExchangeInstrument]
+    symbol_a_: str
+    symbol_b_: str
+
+    def __init__(self, config: Config, instruments: List[ExchangeInstrument]):
+        self.config_ = config
+        self.origin_mkt_data_df_ = pd.DataFrame()
+        self.market_data_df_ = pd.DataFrame()
+        self.stat_model_price_ = self.config_.get_value("model/stat_model_price")
+
+        self.instruments_ = instruments
+        assert len(self.instruments_) > 0, "No instruments found in config"
+        self.symbol_a_ = self.instruments_[0].instrument_id().split("-", 1)[1]
+        self.symbol_b_ = self.instruments_[1].instrument_id().split("-", 1)[1]
+
+    @abstractmethod
+    def md_columns(self) -> List[str]: ...
+
+    @abstractmethod
+    def rename_columns(self, symbol_df: pd.DataFrame) -> pd.DataFrame: ...
+    
+    @abstractmethod
+    def tranform_df_target_colnames(self) -> List[str]: ...
+        
+    def set_market_data(self) -> None:
+        self.market_data_df_ = pd.DataFrame(
+            self._transform_dataframe(self.origin_mkt_data_df_)[
+                ["tstamp"] + self.tranform_df_target_colnames()
+            ]
+        )
+
+        self.market_data_df_ = self.market_data_df_.dropna().reset_index(drop=True)
+        self.market_data_df_["tstamp"] = pd.to_datetime(self.market_data_df_["tstamp"])
+        self.market_data_df_ = self.market_data_df_.sort_values("tstamp")
+
+    def colnames(self) -> List[str]:
+        return [
+            f"{self.stat_model_price_}_{self.symbol_a_}",
+            f"{self.stat_model_price_}_{self.symbol_b_}",
+        ]
+
+    def _transform_dataframe(self, df: pd.DataFrame) -> pd.DataFrame:
+        df_selected: pd.DataFrame = pd.DataFrame(df[self.md_columns()])
+        result_df = (
+            pd.DataFrame(df_selected["tstamp"]).drop_duplicates().reset_index(drop=True)
+        )
+
+        # For each unique symbol, add a corresponding stat_model_price column
+        symbols = df_selected["symbol"].unique()
+
+        for symbol in symbols:
+            # Filter rows for this symbol
+            df_symbol = df_selected[df_selected["symbol"] == symbol].reset_index(
+                drop=True
+            )
+            # Create column name like "close-COIN"
+            temp_df: pd.DataFrame = self.rename_columns(df_symbol)
+            # Join with our result dataframe
+            result_df = pd.merge(result_df, temp_df, on="tstamp", how="left")
+            result_df = result_df.reset_index(
+                drop=True
+            )  # do not dropna() since irrelevant symbol would affect dataset
+
+        return result_df.dropna()
+    
+class ResearchMarketData(PtMarketData):
+    current_index_: int
+    is_execution_price_: bool
+
+    def __init__(self, config: Config, instruments: List[ExchangeInstrument]):
+        super().__init__(config, instruments)
+        self.current_index_ = 0
+        self.is_execution_price_ = self.config_.key_exists("execution_price")
+        if self.is_execution_price_:
+            self.execution_price_column_ = self.config_.get_value("execution_price")["column"]
+            self.execution_price_shift_ = self.config_.get_value("execution_price")["shift"]
+        else:
+            self.execution_price_column_ = None
+            self.execution_price_shift_ = 0
+
+    def has_next(self) -> bool:
+        return self.current_index_ < len(self.market_data_df_)
+
+    def get_next(self) -> pd.Series:
+        result = self.market_data_df_.iloc[self.current_index_]
+        self.current_index_ += 1
+        return result
+
+    def load(self) -> None:
+        datafiles: List[str] = self.config_.get_value("datafiles", [])
+        assert len(datafiles) > 0, "No datafiles found in config"
+
+        extra_minutes: int = self.execution_price_shift_
+
+        for datafile in datafiles:
+            md_df = load_market_data(
+                datafile=datafile,
+                instruments=self.instruments_,
+                db_table_name=self.config_.get_value("market_data_loading")[
+                    self.instruments_[0].user_data_.get("instrument_type", "?instrument_type?")
+                ]["db_table_name"],
+                trading_hours=self.config_.get_value("trading_hours"),
+                extra_minutes=extra_minutes,
+            )
+            self.origin_mkt_data_df_ = pd.concat([self.origin_mkt_data_df_, md_df])
+
+        self.origin_mkt_data_df_ = self.origin_mkt_data_df_.sort_values(by="tstamp")
+        self.origin_mkt_data_df_ = self.origin_mkt_data_df_.dropna().reset_index(
+            drop=True
+        )
+        self.set_market_data()
+        self._set_execution_price_data()
+
+    def _set_execution_price_data(self) -> None:
+        if not self.is_execution_price_:
+            return
+        if not self.config_.key_exists("execution_price"):
+            self.market_data_df_[f"exec_price_{self.symbol_a_}"] = self.market_data_df_[
+                f"{self.stat_model_price_}_{self.symbol_a_}"
+            ]
+            self.market_data_df_[f"exec_price_{self.symbol_b_}"] = self.market_data_df_[
+                f"{self.stat_model_price_}_{self.symbol_b_}"
+            ]
+            return
+        execution_price_column = self.config_.get_value("execution_price")["column"]
+        execution_price_shift = self.config_.get_value("execution_price")["shift"]
+        self.market_data_df_[f"exec_price_{self.symbol_a_}"] = self.market_data_df_[
+            f"{execution_price_column}_{self.symbol_a_}"
+        ].shift(-execution_price_shift)
+        self.market_data_df_[f"exec_price_{self.symbol_b_}"] = self.market_data_df_[
+            f"{execution_price_column}_{self.symbol_b_}"
+        ].shift(-execution_price_shift)
+        self.market_data_df_ = self.market_data_df_.dropna().reset_index(drop=True)
+
+    def md_columns(self) -> List[str]: 
+        # @abstractmethod
+        if self.is_execution_price_:
+            return ["tstamp", "symbol", self.stat_model_price_, self.execution_price_column_]
+        else:
+            return ["tstamp", "symbol", self.stat_model_price_]
+
+    def rename_columns(self, selected_symbol_df: pd.DataFrame) -> pd.DataFrame:  
+        # @abstractmethod
+        symbol = selected_symbol_df.iloc[0]["symbol"]
+        new_price_column = f"{self.stat_model_price_}_{symbol}"
+        if self.is_execution_price_:
+            new_execution_price_column = f"{self.execution_price_column_}_{symbol}"
+
+            # Create temporary dataframe with timestamp and price
+            temp_df = pd.DataFrame(
+                {
+                    "tstamp": selected_symbol_df["tstamp"],
+                    new_price_column: selected_symbol_df[self.stat_model_price_],
+                    new_execution_price_column: selected_symbol_df[self.execution_price_column_],
+                }
+            )
+        else:
+            temp_df = pd.DataFrame(
+                {
+                    "tstamp": selected_symbol_df["tstamp"],
+                    new_price_column: selected_symbol_df[self.stat_model_price_],
+                }
+            )
+        return temp_df
+
+    def tranform_df_target_colnames(self):
+        # @abstractmethod
+        return self.colnames() + self.orig_exec_prices_colnames()
+    
+    def orig_exec_prices_colnames(self) -> List[str]:
+        return [
+            f"{self.execution_price_column_}_{self.symbol_a_}",
+            f"{self.execution_price_column_}_{self.symbol_b_}",
+        ] if self.is_execution_price_ else []
+
+class LiveMarketData(PtMarketData):
+
+    def __init__(self, config: Config, instruments: List[ExchangeInstrument]):
+        super().__init__(config, instruments)
+
+    def md_columns(self) -> List[str]: 
+        # @abstractmethod
+        return ["tstamp", "symbol", self.stat_model_price_]
+
+    def rename_columns(self, selected_symbol_df: pd.DataFrame) -> pd.DataFrame:  
+        # @abstractmethod
+        symbol = selected_symbol_df.iloc[0]["symbol"]
+        new_price_column = f"{self.stat_model_price_}_{symbol}"
+        temp_df = pd.DataFrame(
+            {
+                "tstamp": selected_symbol_df["tstamp"],
+                new_price_column: selected_symbol_df[self.stat_model_price_],
+            }
+        )
+        return temp_df
+
+    def tranform_df_target_colnames(self):
+        # @abstractmethod
+        return self.colnames()

lib/pt_strategy/pt_model.py

@@ -0,0 +1,30 @@
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import Any, Dict, cast
+
+# ---
+from cvttpy_tools.config import Config
+# ---
+from pairs_trading.lib.pt_strategy.prediction import Prediction
+from pairs_trading.lib.pt_strategy.trading_pair import TradingPair
+    
+class PairsTradingModel(ABC):
+
+    @abstractmethod
+    def predict(self, pair: TradingPair) -> Prediction: # type: ignore[assignment]
+        ...
+    
+    @staticmethod
+    def create(config: Config) -> PairsTradingModel:
+        import importlib
+        
+        model_class_name = config.get_value("model/model_class", None)
+        assert model_class_name is not None
+        module_name, class_name = model_class_name.rsplit(".", 1)
+        module = importlib.import_module(module_name)
+        model_object = getattr(module, class_name)()
+        return cast(PairsTradingModel, model_object)
+
+        
+

lib/pt_strategy/research_strategy.py

@@ -0,0 +1,305 @@
+from __future__ import annotations
+
+from typing import Any, Dict, List, Optional, Tuple
+
+import pandas as pd
+# ---
+from cvttpy_tools.config import Config
+# ---
+from cvttpy_trading.trading.instrument import ExchangeInstrument
+# ---
+from pairs_trading.lib.pt_strategy.model_data_policy import ModelDataPolicy
+from pairs_trading.lib.pt_strategy.pt_market_data import ResearchMarketData
+from pairs_trading.lib.pt_strategy.pt_model import Prediction
+from pairs_trading.lib.pt_strategy.trading_pair import PairState, TradingPair, ResearchTradingPair
+
+class PtResearchStrategy:
+    config_: Config
+    trading_pair_: ResearchTradingPair
+    model_data_policy_: ModelDataPolicy
+    pt_mkt_data_: ResearchMarketData 
+
+    trades_: List[pd.DataFrame]
+    predictions_df_: pd.DataFrame
+
+    def __init__(
+        self,
+        config: Config,
+        instruments: List[ExchangeInstrument]
+    ):
+        from pairs_trading.lib.pt_strategy.model_data_policy import ModelDataPolicy
+        from pairs_trading.lib.pt_strategy.trading_pair import TradingPair
+
+        self.config_ = config
+        self.trades_ = []
+        self.trading_pair_ = ResearchTradingPair(config=config, instruments=instruments)
+        self.predictions_df_ = pd.DataFrame()
+
+        import copy
+
+        # modified config must be passed to PtMarketData
+        config_copy = copy.deepcopy(config)
+        config_copy.set_value("instruments", instruments)
+        self.pt_mkt_data_ = ResearchMarketData(config=config_copy, instruments=instruments)
+        self.pt_mkt_data_.load()
+        self.model_data_policy_ = ModelDataPolicy.create(
+            config_copy, mkt_data=self.pt_mkt_data_.market_data_df_, pair=self.trading_pair_
+        )
+
+    def outstanding_positions(self) -> List[Dict[str, Any]]:
+        return list(self.trading_pair_.user_data_.get("outstanding_positions", []))
+
+    def run(self) -> None:
+        training_minutes = self.config_.get_value("training_minutes", 120)
+        market_data_series: pd.Series
+        market_data_df = pd.DataFrame()
+
+        idx = 0
+        while self.pt_mkt_data_.has_next():
+            market_data_series = self.pt_mkt_data_.get_next()
+            new_row = pd.DataFrame([market_data_series])
+            market_data_df = pd.concat([market_data_df, new_row], ignore_index=True)
+            if idx >= training_minutes:
+                break
+            idx += 1
+
+        assert idx >= training_minutes, "Not enough training data"
+
+        while self.pt_mkt_data_.has_next():
+
+            market_data_series = self.pt_mkt_data_.get_next()
+            new_row = pd.DataFrame([market_data_series])
+            market_data_df = pd.concat([market_data_df, new_row], ignore_index=True)
+
+            prediction = self.trading_pair_.run(
+                market_data_df, self.model_data_policy_.advance(mkt_data_df=market_data_df)
+            )
+            self.predictions_df_ = pd.concat(
+                [self.predictions_df_, prediction.to_df()], ignore_index=True
+            )
+            assert prediction is not None
+
+            trades = self._create_trades(
+                prediction=prediction, last_row=market_data_df.iloc[-1]
+            )
+            if trades is not None:
+                self.trades_.append(trades)
+
+        trades = self._handle_outstanding_positions()
+        if trades is not None:
+            self.trades_.append(trades)
+
+    def _create_trades(
+        self, prediction: Prediction, last_row: pd.Series
+    ) -> Optional[pd.DataFrame]:
+        pair = self.trading_pair_
+        trades = None
+
+        open_threshold = self.config_.get_value("model/disequilibrium/open_trshld")
+        close_threshold = self.config_.get_value("model/disequilibrium/close_trshld")
+        scaled_disequilibrium = prediction.scaled_disequilibrium_
+        abs_scaled_disequilibrium = abs(scaled_disequilibrium)
+
+        if pair.user_data_["state"] in [
+            PairState.INITIAL,
+            PairState.CLOSE,
+            PairState.CLOSE_POSITION,
+            PairState.CLOSE_STOP_LOSS,
+            PairState.CLOSE_STOP_PROFIT,
+        ]:
+            if abs_scaled_disequilibrium >= open_threshold:
+                trades = self._create_open_trades(
+                    pair, row=last_row, prediction=prediction
+                )
+                if trades is not None:
+                    trades["status"] = PairState.OPEN.name
+                    print(f"OPEN TRADES:\n{trades}")
+                    pair.user_data_["state"] = PairState.OPEN
+                    pair.on_open_trades(trades)
+
+        elif pair.user_data_["state"] == PairState.OPEN:
+            if abs_scaled_disequilibrium <= close_threshold:
+                trades = self._create_close_trades(
+                    pair, row=last_row, prediction=prediction
+                )
+                if trades is not None:
+                    trades["status"] = PairState.CLOSE.name
+                    print(f"CLOSE TRADES:\n{trades}")
+                    pair.user_data_["state"] = PairState.CLOSE
+                    pair.on_close_trades(trades)
+            elif pair.to_stop_close_conditions(predicted_row=last_row):
+                trades = self._create_close_trades(pair, row=last_row)
+                if trades is not None:
+                    trades["status"] = pair.user_data_["stop_close_state"].name
+                    print(f"STOP CLOSE TRADES:\n{trades}")
+                    pair.user_data_["state"] = pair.user_data_["stop_close_state"]
+                    pair.on_close_trades(trades)
+
+        return trades
+
+    def _handle_outstanding_positions(self) -> Optional[pd.DataFrame]:
+        trades = None
+        pair = self.trading_pair_
+
+        # Outstanding positions
+        if pair.user_data_["state"] == PairState.OPEN:
+            print(f"{pair}:  *** Position is NOT CLOSED. ***")
+            # outstanding positions
+            if self.config_.get_value("close_outstanding_positions", False):
+                close_position_row = pd.Series(pair.market_data_.iloc[-2])
+                # close_position_row["disequilibrium"] = 0.0
+                # close_position_row["scaled_disequilibrium"] = 0.0
+                # close_position_row["signed_scaled_disequilibrium"] = 0.0
+
+                trades = self._create_close_trades(
+                    pair=pair, row=close_position_row, prediction=None
+                )
+                if trades is not None:
+                    trades["status"] = PairState.CLOSE_POSITION.name
+                    print(f"CLOSE_POSITION TRADES:\n{trades}")
+                    pair.user_data_["state"] = PairState.CLOSE_POSITION
+                    pair.on_close_trades(trades)
+            else:
+                pair.add_outstanding_position(
+                    symbol=pair.symbol_a(),
+                    open_side=pair.user_data_["open_side_a"],
+                    open_px=pair.user_data_["open_px_a"],
+                    open_tstamp=pair.user_data_["open_tstamp"],
+                    last_mkt_data_row=pair.market_data_.iloc[-1],
+                )
+                pair.add_outstanding_position(
+                    symbol=pair.symbol_b(),
+                    open_side=pair.user_data_["open_side_b"],
+                    open_px=pair.user_data_["open_px_b"],
+                    open_tstamp=pair.user_data_["open_tstamp"],
+                    last_mkt_data_row=pair.market_data_.iloc[-1],
+                )
+        return trades
+
+    def _trades_df(self) -> pd.DataFrame:
+        types = {
+            "time": "datetime64[ns]",
+            "action": "string",
+            "symbol": "string",
+            "side": "string",
+            "price": "float64",
+            "disequilibrium": "float64",
+            "scaled_disequilibrium": "float64",
+            "signed_scaled_disequilibrium": "float64",
+            # "pair": "object",
+        }
+        columns = list(types.keys())
+        return pd.DataFrame(columns=columns).astype(types)
+
+    def _create_open_trades(
+        self, pair: ResearchTradingPair, row: pd.Series, prediction: Prediction
+    ) -> Optional[pd.DataFrame]:
+        colname_a, colname_b = pair.exec_prices_colnames()
+
+        tstamp = row["tstamp"]
+        diseqlbrm = prediction.disequilibrium_
+        scaled_disequilibrium = prediction.scaled_disequilibrium_
+        px_a = row[f"{colname_a}"]
+        px_b = row[f"{colname_b}"]
+
+        # creating the trades
+        df = self._trades_df()
+
+        print(f"OPEN_TRADES: {row["tstamp"]} {scaled_disequilibrium=}")
+        if diseqlbrm > 0:
+            side_a = "SELL"
+            side_b = "BUY"
+        else:
+            side_a = "BUY"
+            side_b = "SELL"
+
+        # save closing sides
+        pair.user_data_["open_side_a"] = side_a  # used in oustanding positions
+        pair.user_data_["open_side_b"] = side_b
+        pair.user_data_["open_px_a"] = px_a
+        pair.user_data_["open_px_b"] = px_b
+        pair.user_data_["open_tstamp"] = tstamp
+
+        pair.user_data_["close_side_a"] = side_b  # used for closing trades
+        pair.user_data_["close_side_b"] = side_a
+
+        # create opening trades
+        df.loc[len(df)] = {
+            "time": tstamp,
+            "symbol": pair.symbol_a(),
+            "side": side_a,
+            "action": "OPEN",
+            "price": px_a,
+            "disequilibrium": diseqlbrm,
+            "signed_scaled_disequilibrium": scaled_disequilibrium,
+            "scaled_disequilibrium": abs(scaled_disequilibrium),
+            # "pair": pair,
+        }
+        df.loc[len(df)] = {
+            "time": tstamp,
+            "symbol": pair.symbol_b(),
+            "side": side_b,
+            "action": "OPEN",
+            "price": px_b,
+            "disequilibrium": diseqlbrm,
+            "scaled_disequilibrium": abs(scaled_disequilibrium),
+            "signed_scaled_disequilibrium": scaled_disequilibrium,
+            # "pair": pair,
+        }
+        return df
+
+    def _create_close_trades(
+        self, pair: ResearchTradingPair, row: pd.Series, prediction: Optional[Prediction] = None
+    ) -> Optional[pd.DataFrame]:
+        colname_a, colname_b = pair.exec_prices_colnames()
+
+        tstamp = row["tstamp"]
+        if prediction is not None:
+            diseqlbrm = prediction.disequilibrium_
+            signed_scaled_disequilibrium = prediction.scaled_disequilibrium_
+            scaled_disequilibrium = abs(prediction.scaled_disequilibrium_)
+        else:
+            diseqlbrm = 0.0
+            signed_scaled_disequilibrium = 0.0
+            scaled_disequilibrium = 0.0
+        px_a = row[f"{colname_a}"]
+        px_b = row[f"{colname_b}"]
+
+        # creating the trades
+        df = self._trades_df()
+
+        # create opening trades
+        df.loc[len(df)] = {
+            "time": tstamp,
+            "symbol": pair.symbol_a(),
+            "side": pair.user_data_["close_side_a"],
+            "action": "CLOSE",
+            "price": px_a,
+            "disequilibrium": diseqlbrm,
+            "scaled_disequilibrium": scaled_disequilibrium,
+            "signed_scaled_disequilibrium": signed_scaled_disequilibrium,
+            # "pair": pair,
+        }
+        df.loc[len(df)] = {
+            "time": tstamp,
+            "symbol": pair.symbol_b(),
+            "side": pair.user_data_["close_side_b"],
+            "action": "CLOSE",
+            "price": px_b,
+            "disequilibrium": diseqlbrm,
+            "scaled_disequilibrium": scaled_disequilibrium,
+            "signed_scaled_disequilibrium": signed_scaled_disequilibrium,
+            # "pair": pair,
+        }
+        del pair.user_data_["close_side_a"]
+        del pair.user_data_["close_side_b"]
+
+        del pair.user_data_["open_tstamp"]
+        del pair.user_data_["open_px_a"]
+        del pair.user_data_["open_px_b"]
+        del pair.user_data_["open_side_a"]
+        del pair.user_data_["open_side_b"]
+        return df
+
+    def day_trades(self) -> pd.DataFrame:
+        return pd.concat(self.trades_, ignore_index=True)

lib/pt_strategy/results.py

@@ -0,0 +1,527 @@
+import os
+import sqlite3
+from datetime import date, datetime
+from typing import Any, Dict, List, Optional, Tuple
+
+import pandas as pd
+# ---
+from cvttpy_tools.config import Config
+# ---
+from cvttpy_trading.trading.instrument import ExchangeInstrument
+# ---
+from pairs_trading.lib.pt_strategy.trading_pair import TradingPair
+
+# Recommended replacement adapters and converters for Python 3.12+
+# From: https://docs.python.org/3/library/sqlite3.html#sqlite3-adapter-converter-recipes
+def adapt_date_iso(val: date) -> str:
+    """Adapt datetime.date to ISO 8601 date."""
+    return val.isoformat()
+
+
+def adapt_datetime_iso(val: datetime) -> str:
+    """Adapt datetime.datetime to timezone-naive ISO 8601 date."""
+    return val.isoformat()
+
+def convert_date(val: bytes) -> date:
+    """Convert ISO 8601 date to datetime.date object."""
+    return datetime.fromisoformat(val.decode()).date()
+
+def convert_datetime(val: bytes) -> datetime:
+    """Convert ISO 8601 datetime to datetime.datetime object."""
+    return datetime.fromisoformat(val.decode())
+
+
+# Register the adapters and converters
+sqlite3.register_adapter(date, adapt_date_iso)
+sqlite3.register_adapter(datetime, adapt_datetime_iso)
+sqlite3.register_converter("date", convert_date)
+sqlite3.register_converter("datetime", convert_datetime)
+
+
+def create_result_database(db_path: str) -> None:
+    """
+    Create the SQLite database and required tables if they don't exist.
+    """
+    try:
+        # Create directory if it doesn't exist
+        db_dir = os.path.dirname(db_path)
+        if db_dir and not os.path.exists(db_dir):
+            os.makedirs(db_dir, exist_ok=True)
+            print(f"Created directory: {db_dir}")
+
+        conn = sqlite3.connect(db_path)
+        cursor = conn.cursor()
+
+        # Create the pt_bt_results table for completed trades
+        cursor.execute(
+            """
+            CREATE TABLE IF NOT EXISTS pt_bt_results (
+                date DATE,
+                pair TEXT,
+                symbol TEXT,
+                open_time DATETIME,
+                open_side TEXT,
+                open_price REAL,
+                open_quantity INTEGER,
+                open_disequilibrium REAL,
+                close_time DATETIME,
+                close_side TEXT,
+                close_price REAL,
+                close_quantity INTEGER,
+                close_disequilibrium REAL,
+                symbol_return REAL,
+                pair_return REAL,
+                close_condition TEXT
+            )
+        """
+        )
+        cursor.execute("DELETE FROM pt_bt_results;")
+
+        # Create the outstanding_positions table for open positions
+        cursor.execute(
+            """
+            CREATE TABLE IF NOT EXISTS outstanding_positions (
+                date DATE,
+                pair TEXT,
+                symbol TEXT,
+                position_quantity REAL,
+                last_price REAL,
+                unrealized_return REAL,
+                open_price REAL,
+                open_side TEXT
+            )
+        """
+        )
+        cursor.execute("DELETE FROM outstanding_positions;")
+
+        # Create the config table for storing configuration JSON for reference
+        cursor.execute(
+            """
+            CREATE TABLE IF NOT EXISTS config (
+                id INTEGER PRIMARY KEY AUTOINCREMENT,
+                run_timestamp DATETIME,
+                config_file_path TEXT,
+                config_json TEXT,
+                datafiles TEXT,
+                instruments TEXT
+            )
+        """
+        )
+        cursor.execute("DELETE FROM config;")
+
+        conn.commit()
+        conn.close()
+
+    except Exception as e:
+        print(f"Error creating result database: {str(e)}")
+        raise
+
+
+def store_config_in_database(
+    db_path: str,
+    config_file_path: str,
+    config: Config,
+    datafiles: List[Tuple[str, str]],
+    instruments: List[ExchangeInstrument],
+) -> None:
+    """
+    Store configuration information in the database for reference.
+    """
+    import json
+
+    if db_path.upper() == "NONE":
+        return
+
+    try:
+        conn = sqlite3.connect(db_path)
+        cursor = conn.cursor()
+
+        # Convert config to JSON string
+        config_json = json.dumps(config.data(), indent=2, default=str)
+
+        # Convert lists to comma-separated strings for storage
+        datafiles_str = ", ".join([f"{datafile}" for _, datafile in datafiles])
+        instruments_str = ", ".join(
+            [
+                inst.details_short()
+                for inst in instruments
+            ]
+        )
+
+        # Insert configuration record
+        cursor.execute(
+            """
+            INSERT INTO config (
+                run_timestamp, config_file_path, config_json, datafiles, instruments
+            ) VALUES (?, ?, ?, ?, ?)
+        """,
+            (
+                datetime.now(),
+                config_file_path,
+                config_json,
+                datafiles_str,
+                instruments_str,
+            ),
+        )
+
+        conn.commit()
+        conn.close()
+
+        print(f"Configuration stored in database")
+
+    except Exception as e:
+        print(f"Error storing configuration in database: {str(e)}")
+        import traceback
+
+        traceback.print_exc()
+
+
+def convert_timestamp(timestamp: Any) -> Optional[datetime]:
+    """Convert pandas Timestamp to Python datetime object for SQLite compatibility."""
+    if timestamp is None:
+        return None
+    if isinstance(timestamp, pd.Timestamp):
+        return timestamp.to_pydatetime()
+    elif isinstance(timestamp, datetime):
+        return timestamp
+    elif isinstance(timestamp, date):
+        return datetime.combine(timestamp, datetime.min.time())
+    elif isinstance(timestamp, str):
+        return datetime.strptime(timestamp, "%Y-%m-%d %H:%M:%S")
+    elif isinstance(timestamp, int):
+        return datetime.fromtimestamp(timestamp)
+    else:
+        raise ValueError(f"Unsupported timestamp type: {type(timestamp)}")
+
+
+
+DayT = str
+TradeT = Dict[str, Any]
+OutstandingPositionT = Dict[str, Any]
+class PairResearchResult:
+    """
+    Class to handle pair research results for a single pair across multiple days.
+    Simplified version of BacktestResult focused on single pair analysis.
+    """
+    trades_: Dict[DayT, pd.DataFrame]
+    outstanding_positions_: Dict[DayT, List[OutstandingPositionT]]
+    symbol_roundtrip_trades_: Dict[str, List[Dict[str, Any]]]
+    config_: Config
+
+    def __init__(self, config: Config) -> None:
+        self.config_ = config
+        self.trades_ = {}
+        self.outstanding_positions_ = {}
+        self.total_realized_pnl = 0.0
+        self.symbol_roundtrip_trades_ = {}
+
+    def add_day_results(self, day: DayT, trades: pd.DataFrame, outstanding_positions: List[Dict[str, Any]]) -> None:
+        assert isinstance(trades, pd.DataFrame)
+        self.trades_[day] = trades
+        self.outstanding_positions_[day] = outstanding_positions
+
+    def outstanding_positions(self) -> List[OutstandingPositionT]:
+        """Get all outstanding positions across all days as a flat list."""
+        res: List[Dict[str, Any]] = []
+        for day in self.outstanding_positions_.keys():
+            res.extend(self.outstanding_positions_[day])
+        return res
+    
+    def calculate_returns(self) -> None:
+        """Calculate and store total returns for the single pair across all days."""
+        self.extract_roundtrip_trades()
+        
+        self.total_realized_pnl = 0.0
+        
+        for day, day_trades in self.symbol_roundtrip_trades_.items():
+            for trade in day_trades:
+                self.total_realized_pnl += trade['symbol_return']
+    
+    def extract_roundtrip_trades(self) -> None: 
+        """
+        Extract round-trip trades by day, grouping open/close pairs for each symbol.
+        Returns a dictionary with day as key and list of completed round-trip trades.
+        """
+        def _symbol_return(trade1_side: str, trade1_px: float, trade2_side: str, trade2_px: float) -> float:
+            if trade1_side == "BUY" and trade2_side == "SELL":
+                return (trade2_px - trade1_px) / trade1_px * 100
+            elif trade1_side == "SELL" and trade2_side == "BUY":
+                return (trade1_px - trade2_px) / trade1_px * 100
+            else:
+                return 0
+        
+        # Process each day separately
+        for day, day_trades in self.trades_.items():
+
+            # Sort trades by timestamp for the day
+            sorted_trades = day_trades #sorted(day_trades, key=lambda x: x["timestamp"] if x["timestamp"] else pd.Timestamp.min)
+            
+            day_roundtrips = []
+            
+            # Process trades in groups of 4 (open A, open B, close A, close B)
+            for idx in range(0, len(sorted_trades), 4):
+                if idx + 3 >= len(sorted_trades):
+                    break
+                    
+                trade_a_1 = sorted_trades.iloc[idx]      # Open A
+                trade_b_1 = sorted_trades.iloc[idx + 1]  # Open B  
+                trade_a_2 = sorted_trades.iloc[idx + 2]  # Close A
+                trade_b_2 = sorted_trades.iloc[idx + 3]  # Close B
+                
+                # Validate trade sequence
+                if not (trade_a_1["action"] == "OPEN" and trade_a_2["action"] == "CLOSE"):
+                    continue
+                if not (trade_b_1["action"] == "OPEN" and trade_b_2["action"] == "CLOSE"):
+                    continue
+                    
+                # Calculate individual symbol returns
+                symbol_a_return = _symbol_return(
+                    trade_a_1["side"], trade_a_1["price"], 
+                    trade_a_2["side"], trade_a_2["price"]
+                )
+                symbol_b_return = _symbol_return(
+                    trade_b_1["side"], trade_b_1["price"], 
+                    trade_b_2["side"], trade_b_2["price"]
+                )
+                
+                pair_return = symbol_a_return + symbol_b_return
+                
+                # Create round-trip records for both symbols
+                funding_per_position = self.config_.get_value("funding_per_pair", 10000) / 2
+                
+                # Symbol A round-trip
+                day_roundtrips.append({
+                    "symbol": trade_a_1["symbol"],
+                    "open_side": trade_a_1["side"],
+                    "open_price": trade_a_1["price"],
+                    "open_time": trade_a_1["time"],
+                    "close_side": trade_a_2["side"],
+                    "close_price": trade_a_2["price"],
+                    "close_time": trade_a_2["time"],
+                    "symbol_return": symbol_a_return,
+                    "pair_return": pair_return,
+                    "shares": funding_per_position / trade_a_1["price"],
+                    "close_condition": trade_a_2.get("status", "UNKNOWN"),
+                    "open_disequilibrium": trade_a_1.get("disequilibrium"),
+                    "close_disequilibrium": trade_a_2.get("disequilibrium"),
+                })
+                
+                # Symbol B round-trip
+                day_roundtrips.append({
+                    "symbol": trade_b_1["symbol"],
+                    "open_side": trade_b_1["side"],
+                    "open_price": trade_b_1["price"],
+                    "open_time": trade_b_1["time"],
+                    "close_side": trade_b_2["side"],
+                    "close_price": trade_b_2["price"],
+                    "close_time": trade_b_2["time"],
+                    "symbol_return": symbol_b_return,
+                    "pair_return": pair_return,
+                    "shares": funding_per_position / trade_b_1["price"],
+                    "close_condition": trade_b_2.get("status", "UNKNOWN"),
+                    "open_disequilibrium": trade_b_1.get("disequilibrium"),
+                    "close_disequilibrium": trade_b_2.get("disequilibrium"),
+                })
+            
+            if day_roundtrips:
+                self.symbol_roundtrip_trades_[day] = day_roundtrips
+                
+    
+    def print_returns_by_day(self) -> None:
+        """
+        Print detailed return information for each day, grouped by day.
+        Shows individual symbol round-trips and daily totals.
+        """
+        
+        print("\n====== PAIR RESEARCH RETURNS BY DAY ======")
+        
+        total_return_all_days = 0.0
+        
+        for day, day_trades in sorted(self.symbol_roundtrip_trades_.items()):
+            
+            print(f"\n--- {day} ---")
+            
+            day_total_return = 0.0
+            pair_returns = []
+            
+            # Group trades by pair (every 2 trades form a pair)
+            for idx in range(0, len(day_trades), 2):
+                if idx + 1 < len(day_trades):
+                    trade_a = day_trades[idx]
+                    trade_b = day_trades[idx + 1]
+                    
+                    # Print individual symbol results
+                    print(f"  {trade_a['open_time'].time()}-{trade_a['close_time'].time()}")
+                    print(f"    {trade_a['symbol']}: {trade_a['open_side']} @ ${trade_a['open_price']:.2f} → "
+                          f"{trade_a['close_side']} @ ${trade_a['close_price']:.2f} | "
+                          f"Return: {trade_a['symbol_return']:+.2f}% | Shares: {trade_a['shares']:.2f}")
+                    
+                    print(f"    {trade_b['symbol']}: {trade_b['open_side']} @ ${trade_b['open_price']:.2f} → "
+                          f"{trade_b['close_side']} @ ${trade_b['close_price']:.2f} | "
+                          f"Return: {trade_b['symbol_return']:+.2f}% | Shares: {trade_b['shares']:.2f}")
+                    
+                    # Show disequilibrium info if available
+                    if trade_a.get('open_disequilibrium') is not None:
+                        print(f"    Disequilibrium: Open: {trade_a['open_disequilibrium']:.4f}, "
+                              f"Close: {trade_a['close_disequilibrium']:.4f}")
+                    
+                    pair_return = trade_a['pair_return']
+                    print(f"    Pair Return: {pair_return:+.2f}% | Close Condition: {trade_a['close_condition']}")
+                    print()
+                    
+                    pair_returns.append(pair_return)
+                    day_total_return += pair_return
+            
+            print(f"  Day Total Return: {day_total_return:+.2f}% ({len(pair_returns)} pairs)")
+            total_return_all_days += day_total_return
+        
+        print(f"\n====== TOTAL RETURN ACROSS ALL DAYS ======")
+        print(f"Total Return: {total_return_all_days:+.2f}%")
+        print(f"Total Days: {len(self.symbol_roundtrip_trades_)}")
+        if len(self.symbol_roundtrip_trades_) > 0:
+            print(f"Average Daily Return: {total_return_all_days / len(self.symbol_roundtrip_trades_):+.2f}%")
+    
+    def get_return_summary(self) -> Dict[str, Any]:
+        """
+        Get a summary of returns across all days.
+        Returns a dictionary with key metrics.
+        """
+        if len(self.symbol_roundtrip_trades_) == 0:
+            return {
+                "total_return": 0.0,
+                "total_days": 0,
+                "total_pairs": 0,
+                "average_daily_return": 0.0,
+                "best_day": None,
+                "worst_day": None,
+                "daily_returns": {}
+            }
+        
+        daily_returns = {}
+        total_return = 0.0
+        total_pairs = 0
+        
+        for day, day_trades in self.symbol_roundtrip_trades_.items():
+            day_return = 0.0
+            day_pairs = len(day_trades) // 2  # Each pair has 2 symbol trades
+            
+            for trade in day_trades:
+                day_return += trade['symbol_return']
+            
+            daily_returns[day] = {
+                "return": day_return,
+                "pairs": day_pairs
+            }
+            total_return += day_return
+            total_pairs += day_pairs
+        
+        best_day = max(daily_returns.items(), key=lambda x: x[1]["return"]) if daily_returns else None
+        worst_day = min(daily_returns.items(), key=lambda x: x[1]["return"]) if daily_returns else None
+        
+        return {
+            "total_return": total_return,
+            "total_days": len(self.symbol_roundtrip_trades_),
+            "total_pairs": total_pairs,
+            "average_daily_return": total_return / len(self.symbol_roundtrip_trades_) if self.symbol_roundtrip_trades_ else 0.0,
+            "best_day": best_day,
+            "worst_day": worst_day,
+            "daily_returns": daily_returns
+        }
+    
+    
+    def print_grand_totals(self) -> None:
+        """Print grand totals for the single pair analysis."""
+        summary = self.get_return_summary()
+        
+        print(f"\n====== PAIR RESEARCH GRAND TOTALS ======")
+        print('---')
+        print(f"Total Return: {summary['total_return']:+.2f}%")
+        print('---')
+        print(f"Total Days Traded: {summary['total_days']}")
+        print(f"Total Open-Close Actions: {summary['total_pairs']}")
+        print(f"Total Trades:  4 * {summary['total_pairs']} = {4 * summary['total_pairs']}")
+        
+        if summary['total_days'] > 0:
+            print(f"Average Daily Return: {summary['average_daily_return']:+.2f}%")
+        
+        if summary['best_day']:
+            best_day, best_data = summary['best_day']
+            print(f"Best Day: {best_day} ({best_data['return']:+.2f}%)")
+        
+        if summary['worst_day']:
+            worst_day, worst_data = summary['worst_day']
+            print(f"Worst Day: {worst_day} ({worst_data['return']:+.2f}%)")
+        
+        # Update the total_realized_pnl for backward compatibility
+        self.total_realized_pnl = summary['total_return']
+    
+    def analyze_pair_performance(self) -> None:
+        """
+        Main method to perform comprehensive pair research analysis.
+        Extracts round-trip trades, calculates returns, groups by day, and prints results.
+        """
+        print(f"\n{'='*60}")
+        print(f"PAIR RESEARCH PERFORMANCE ANALYSIS")
+        print(f"{'='*60}")
+        
+        self.calculate_returns()
+        self.print_returns_by_day()
+        self.print_outstanding_positions()
+        self._print_additional_metrics()
+        self.print_grand_totals()
+    
+    def _print_additional_metrics(self) -> None:
+        """Print additional performance metrics."""
+        summary = self.get_return_summary()
+        
+        if summary['total_days'] == 0:
+            return
+        
+        print(f"\n====== ADDITIONAL METRICS ======")
+        
+        # Calculate win rate
+        winning_days = sum(1 for day_data in summary['daily_returns'].values() if day_data['return'] > 0)
+        win_rate = (winning_days / summary['total_days']) * 100
+        print(f"Winning Days: {winning_days}/{summary['total_days']} ({win_rate:.1f}%)")
+        
+        # Calculate average trade return
+        if summary['total_pairs'] > 0:
+            # Each pair has 2 symbol trades, so total symbol trades = total_pairs * 2
+            total_symbol_trades = summary['total_pairs'] * 2
+            avg_symbol_return = summary['total_return'] / total_symbol_trades
+            print(f"Average Symbol Return: {avg_symbol_return:+.2f}%")
+            
+            avg_pair_return = summary['total_return'] / summary['total_pairs'] / 2  # Divide by 2 since we sum both symbols
+            print(f"Average Pair Return: {avg_pair_return:+.2f}%")
+        
+        # Show daily return distribution
+        daily_returns_list = [data['return'] for data in summary['daily_returns'].values()]
+        if daily_returns_list:
+            print(f"Daily Return Range: {min(daily_returns_list):+.2f}% to {max(daily_returns_list):+.2f}%")
+        
+    
+    def print_outstanding_positions(self) -> None:
+        """Print outstanding positions for the single pair."""
+        all_positions: List[OutstandingPositionT] = self.outstanding_positions()
+        if not all_positions:
+            print("\n====== NO OUTSTANDING POSITIONS ======")
+            return
+            
+        print(f"\n====== OUTSTANDING POSITIONS ======")
+        print(f"{'Symbol':<10} {'Side':<4} {'Shares':<10} {'Open $':<8} {'Current $':<10} {'Value $':<12}")
+        print("-" * 70)
+        
+        total_value = 0.0
+        for pos in all_positions:
+            current_value = pos.get("last_value", 0.0)
+            print(f"{pos['symbol']:<10} {pos['open_side']:<4} {pos['shares']:<10.2f} "
+                  f"{pos['open_px']:<8.2f} {pos['last_px']:<10.2f} {current_value:<12.2f}")
+            total_value += current_value
+        
+        print("-" * 70)
+        print(f"{'TOTAL VALUE':<60} ${total_value:<12.2f}")
+    
+    def get_total_realized_pnl(self) -> float:
+        """Get total realized PnL."""
+        return self.total_realized_pnl
+    

lib/pt_strategy/trading_pair.py

@@ -0,0 +1,226 @@
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from datetime import datetime
+from enum import Enum
+from typing import Any, Dict, List
+
+import pandas as pd
+
+# ---
+from cvttpy_tools.base import NamedObject
+from cvttpy_tools.config import Config
+# ---
+from cvttpy_trading.trading.instrument import ExchangeInstrument
+# ---
+from pairs_trading.lib.pt_strategy.model_data_policy import DataWindowParams
+from pairs_trading.lib.pt_strategy.prediction import Prediction
+
+
+
+class PairState(Enum):
+    INITIAL = 1
+    OPEN = 2
+    CLOSE = 3
+    CLOSE_POSITION = 4
+    CLOSE_STOP_LOSS = 5
+    CLOSE_STOP_PROFIT = 6
+
+
+class TradingPair(NamedObject, ABC):
+    config_: Config
+    model_: Any # "PairsTradingModel"
+    market_data_: pd.DataFrame
+
+    user_data_: Dict[str, Any]
+    stat_model_price_: str
+
+    instruments_: List[ExchangeInstrument]
+
+    def __init__(
+        self,
+        config: Config,
+        instruments: List[ExchangeInstrument],
+    ):
+        from pairs_trading.lib.pt_strategy.pt_model import PairsTradingModel
+
+        self.config_ = config
+        self.model_ = PairsTradingModel.create(config)
+        self.user_data_ = {}
+        self.instruments_ = instruments
+        self.instruments_[0].user_data_["symbol"] = instruments[0].instrument_id().split("-", 1)[1]
+        self.instruments_[1].user_data_["symbol"] = instruments[1].instrument_id().split("-", 1)[1]        
+        self.stat_model_price_ = config.get_value("model/stat_model_price")
+        
+    def run(self, market_data: pd.DataFrame, data_params: DataWindowParams) -> Prediction:  # type: ignore[assignment]
+        self.market_data_ = market_data[
+            data_params.training_start_index_ : data_params.training_start_index_ + data_params.training_size_
+        ]
+        return self.model_.predict(pair=self)
+
+    def colnames(self) -> List[str]:
+        return [
+            f"{self.stat_model_price_}_{self.symbol_a()}",
+            f"{self.stat_model_price_}_{self.symbol_b()}",
+        ]
+    def symbol_a(self) -> str:
+        return self.get_instrument_a().user_data_["symbol"]
+    
+    def symbol_b(self) -> str:
+        return self.get_instrument_b().user_data_["symbol"]
+
+    def get_instrument_a(self) -> ExchangeInstrument:
+        return self.instruments_[0]
+
+    def get_instrument_b(self) -> ExchangeInstrument:
+        return self.instruments_[1]
+
+    def __repr__(self) -> str:
+        return (
+            f"{self.__class__.__name__}:"
+            f" symbol_a={self.symbol_a()},"
+            f" symbol_b={self.symbol_b()},"
+            f" model={self.model_.__class__.__name__}"
+        )
+    
+class ResearchTradingPair(TradingPair):
+
+    def __init__(
+        self,
+        config: Config,
+        instruments: List[ExchangeInstrument],
+    ):
+        assert len(instruments) == 2, "Trading pair must have exactly 2 instruments"
+        super().__init__(config=config, instruments=instruments)
+
+        self.user_data_ = {
+            "state": PairState.INITIAL,
+        }
+        
+    def is_closed(self) -> bool:
+        return self.user_data_["state"] in [
+            PairState.CLOSE,
+            PairState.CLOSE_POSITION,
+            PairState.CLOSE_STOP_LOSS,
+            PairState.CLOSE_STOP_PROFIT,
+        ]
+
+    def is_open(self) -> bool:
+        return not self.is_closed()
+
+    def exec_prices_colnames(self) -> List[str]:
+        return [
+            f"exec_price_{self.symbol_a()}",
+            f"exec_price_{self.symbol_b()}",
+        ]
+
+    def to_stop_close_conditions(self, predicted_row: pd.Series) -> bool:
+        config = self.config_
+        if (
+            not config.key_exists("stop_close_conditions")
+            or config.get_value("stop_close_conditions") is None
+        ):
+            return False
+        if "profit" in config.get_value("stop_close_conditions"):
+            current_return = self._current_return(predicted_row)
+            #
+            # print(f"time={predicted_row['tstamp']} current_return={current_return}")
+            #
+            if current_return >= config.get_value("stop_close_conditions")["profit"]:
+                print(f"STOP PROFIT: {current_return}")
+                self.user_data_["stop_close_state"] = PairState.CLOSE_STOP_PROFIT
+                return True
+        if "loss" in config.get_value("stop_close_conditions"):
+            if current_return <= config.get_value("stop_close_conditions")["loss"]:
+                print(f"STOP LOSS: {current_return}")
+                self.user_data_["stop_close_state"] = PairState.CLOSE_STOP_LOSS
+                return True
+        return False
+
+    def _current_return(self, predicted_row: pd.Series) -> float:
+        if "open_trades" in self.user_data_:
+            open_trades = self.user_data_["open_trades"]
+            if len(open_trades) == 0:
+                return 0.0
+
+            def _single_instrument_return(symbol: str) -> float:
+                instrument_open_trades = open_trades[open_trades["symbol"] == symbol]
+                instrument_open_price = instrument_open_trades["price"].iloc[0]
+
+                sign = -1 if instrument_open_trades["side"].iloc[0] == "SELL" else 1
+                instrument_price = predicted_row[f"{self.stat_model_price_}_{symbol}"]
+                instrument_return = (
+                    sign
+                    * (instrument_price - instrument_open_price)
+                    / instrument_open_price
+                )
+                return float(instrument_return) * 100.0
+
+            instrument_a_return = _single_instrument_return(self.symbol_a())
+            instrument_b_return = _single_instrument_return(self.symbol_b())
+            return instrument_a_return + instrument_b_return
+        return 0.0
+
+    def on_open_trades(self, trades: pd.DataFrame) -> None:
+        if "close_trades" in self.user_data_:
+            del self.user_data_["close_trades"]
+        self.user_data_["open_trades"] = trades
+
+    def on_close_trades(self, trades: pd.DataFrame) -> None:
+        del self.user_data_["open_trades"]
+        self.user_data_["close_trades"] = trades
+
+    def add_outstanding_position(
+        self,
+        symbol: str,
+        open_side: str,
+        open_px: float,
+        open_tstamp: datetime,
+        last_mkt_data_row: pd.Series,
+    ) -> None:
+        assert symbol in [
+            self.symbol_a(),
+            self.symbol_b(),
+        ], "Symbol must be one of the pair's symbols"
+        assert open_side in ["BUY", "SELL"], "Open side must be either BUY or SELL"
+        assert open_px > 0, "Open price must be greater than 0"
+        assert open_tstamp is not None, "Open timestamp must be provided"
+        assert last_mkt_data_row is not None, "Last market data row must be provided"
+
+        exec_prices_col_a, exec_prices_col_b = self.exec_prices_colnames()
+        if symbol == self.symbol_a():
+            last_px = last_mkt_data_row[exec_prices_col_a]
+        else:
+            last_px = last_mkt_data_row[exec_prices_col_b]
+
+        funding_per_position = self.config_.get_value("funding_per_pair") / 2
+        shares = funding_per_position / open_px
+        if open_side == "SELL":
+            shares = -shares
+
+        if "outstanding_positions" not in self.user_data_:
+            self.user_data_["outstanding_positions"] = []
+
+        self.user_data_["outstanding_positions"].append(
+            {
+                "symbol": symbol,
+                "open_side": open_side,
+                "open_px": open_px,
+                "shares": shares,
+                "open_tstamp": open_tstamp,
+                "last_px": last_px,
+                "last_tstamp": last_mkt_data_row["tstamp"],
+                "last_value": last_px * shares,
+            }
+        )
+
+class LiveTradingPair(TradingPair):
+
+    def __init__(self, config: Config, instruments: List[ExchangeInstrument]):
+        super().__init__(config, instruments)
+
+    def to_stop_close_conditions(self, predicted_row: pd.Series) -> bool:
+        # TODO LiveTradingPair.to_stop_close_conditions()
+        return False
+        
+

lib/tools/config.py

@@ -0,0 +1,17 @@
+import hjson
+from typing import Dict
+from datetime import datetime
+# ---
+from cvttpy_tools.config import Config
+
+
+def load_config(config_path: str) -> Config:
+    return Config(json_src=f"file://{config_path}")
+
+
+def expand_filename(filename: str) -> str:
+    # expand %T
+    res = filename.replace("%T", datetime.now().strftime("%Y%m%d_%H%M%S"))
+    # expand %D
+    return res.replace("%D", datetime.now().strftime("%Y%m%d"))
+

lib/tools/data_loader.py

@@ -0,0 +1,150 @@
+from __future__ import annotations
+
+import sqlite3
+from typing import Any, Dict, List, Tuple, cast
+import pandas as pd
+
+from cvttpy_trading.trading.instrument import ExchangeInstrument
+
+def load_sqlite_to_dataframe(db_path:str, query:str) -> pd.DataFrame:
+    df: pd.DataFrame = pd.DataFrame()
+    import os
+    if not os.path.exists(db_path):
+        print(f"WARNING: database file {db_path} does not exist")
+        return df
+
+    try:
+        conn = sqlite3.connect(db_path)
+
+        df = pd.read_sql_query(query, conn)
+        return df
+    except sqlite3.Error as excpt:
+        print(f"SQLite error: {excpt}")
+        raise
+    except Exception as excpt:
+        print(f"Error: {excpt}")
+        raise Exception() from excpt
+    finally:
+        if "conn" in locals():
+            conn.close()
+
+
+def convert_time_to_UTC(value: str, timezone: str, extra_minutes: int = 0) -> str:
+
+    from zoneinfo import ZoneInfo
+    from datetime import datetime, timedelta
+
+    # Parse it to naive datetime object
+    local_dt = datetime.strptime(value, "%Y-%m-%d %H:%M:%S")
+    local_dt = local_dt + timedelta(minutes=extra_minutes)
+
+    zinfo = ZoneInfo(timezone)
+    result: datetime = local_dt.replace(tzinfo=zinfo).astimezone(ZoneInfo("UTC"))
+
+    return result.strftime("%Y-%m-%d %H:%M:%S")
+
+
+def load_market_data(
+    datafile: str,
+    instruments: List[ExchangeInstrument],
+    db_table_name: str,
+    trading_hours: Dict = {},
+    extra_minutes: int = 0,
+) -> pd.DataFrame:
+
+
+    inst_ids = ['"' + exch_inst.instrument_id() + '"' for exch_inst in instruments]
+    instrument_ids = list(set(inst_ids))
+    exchange_ids = list(
+        set(['"' + instrument.exchange_id() + '"' for instrument in instruments])
+    )
+
+    query = "select"
+    query += " tstamp"
+    query += ", tstamp_ns as time_ns"
+
+    query += f", substr(instrument_id, instr(instrument_id, '-') + 1) as symbol"
+    query += ", open"
+    query += ", high"
+    query += ", low"
+    query += ", close"
+    query += ", volume"
+    query += ", num_trades"
+    query += ", vwap"
+
+    query += f" from {db_table_name}"
+    query += f" where exchange_id in ({','.join(exchange_ids)})"
+    query += f" and instrument_id in ({','.join(instrument_ids)})"
+
+    df = load_sqlite_to_dataframe(db_path=datafile, query=query)
+
+    # Trading Hours
+    if len(df) > 0 and len(trading_hours) > 0:
+        date_str = df["tstamp"][0][0:10]
+
+        start_time = convert_time_to_UTC(
+            f"{date_str} {trading_hours['begin_session']}", trading_hours["timezone"]
+        )
+        end_time = convert_time_to_UTC(
+            f"{date_str} {trading_hours['end_session']}", trading_hours["timezone"], extra_minutes=extra_minutes # to get execution price
+        )
+
+        # Perform boolean selection
+        df = df[(df["tstamp"] >= start_time) & (df["tstamp"] <= end_time)]
+        df["tstamp"] = pd.to_datetime(df["tstamp"])
+
+    return cast(pd.DataFrame, df)
+
+
+# def get_available_instruments_from_db(datafile: str, config: Dict) -> List[str]:
+#     """
+#     Auto-detect available instruments from the database by querying distinct instrument_id values.
+#     Returns instruments without the configured prefix.
+#     """
+#     try:
+#         conn = sqlite3.connect(datafile)
+
+#         # Build exclusion list with full instrument_ids
+#         exclude_instruments = config.get("exclude_instruments", [])
+#         prefix = config.get("instrument_id_pfx", "")
+#         exclude_instrument_ids = [f"{prefix}{inst}" for inst in exclude_instruments]
+
+#         # Query to get distinct instrument_ids
+#         query = f"""
+#         SELECT DISTINCT instrument_id
+#         FROM {config['db_table_name']}
+#         WHERE exchange_id = ?
+#         """
+
+#         # Add exclusion clause if there are instruments to exclude
+#         if exclude_instrument_ids:
+#             placeholders = ",".join(["?" for _ in exclude_instrument_ids])
+#             query += f" AND instrument_id NOT IN ({placeholders})"
+#             cursor = conn.execute(
+#                 query, (config["exchange_id"],) + tuple(exclude_instrument_ids)
+#             )
+#         else:
+#             cursor = conn.execute(query, (config["exchange_id"],))
+#         instrument_ids = [row[0] for row in cursor.fetchall()]
+#         conn.close()
+
+#         # Remove the configured prefix to get instrument symbols
+#         instruments = []
+#         for instrument_id in instrument_ids:
+#             if instrument_id.startswith(prefix):
+#                 symbol = instrument_id[len(prefix) :]
+#                 instruments.append(symbol)
+#             else:
+#                 instruments.append(instrument_id)
+
+#         return sorted(instruments)
+
+#     except Exception as e:
+#         print(f"Error auto-detecting instruments from {datafile}: {str(e)}")
+#         return []
+
+
+# if __name__ == "__main__":
+#     df1 = load_sqlite_to_dataframe(sys.argv[1], table_name="md_1min_bars")
+
+#     print(df1)

lib/tools/filetools.py

@@ -0,0 +1,37 @@
+import os
+import glob
+from typing import Dict, List, Tuple
+# ---
+from cvttpy_tools.config import Config
+# ---
+from cvttpy_trading.trading.instrument import ExchangeInstrument
+
+DayT = str
+DataFileNameT = str
+
+def resolve_datafiles(
+    config: Config, date_pattern: str, instruments: List[ExchangeInstrument]
+) -> List[Tuple[DayT, DataFileNameT]]:
+    resolved_files: List[Tuple[DayT, DataFileNameT]] = []
+    for exch_inst in instruments:
+        pattern = date_pattern
+        inst_type = exch_inst.user_data_.get("instrument_type", "?instrument_type?")
+        data_dir = config.get_value(f"market_data_loading/{inst_type}/data_directory")
+        if "*" in pattern or "?" in pattern:
+            # Handle wildcards
+            if not os.path.isabs(pattern):
+                pattern = os.path.join(data_dir, f"{pattern}.mktdata.ohlcv.db")
+            matched_files = glob.glob(pattern)
+            for matched_file in matched_files:
+                import re
+                match = re.search(r"(\d{8})\.mktdata\.ohlcv\.db$", matched_file)
+                assert match is not None
+                day = match.group(1)
+                resolved_files.append((day, matched_file))
+        else:
+            # Handle explicit file path
+            if not os.path.isabs(pattern):
+                pattern = os.path.join(data_dir, f"{pattern}.mktdata.ohlcv.db")
+            resolved_files.append((date_pattern, pattern))
+    return sorted(list(set(resolved_files)))  # Remove duplicates and sort
+

lib/tools/viz/viz_prices.py

@@ -0,0 +1,79 @@
+from pairs_trading.lib.pt_strategy.research_strategy import PtResearchStrategy
+
+
+def visualize_prices(strategy: PtResearchStrategy, trading_date: str) -> None: 
+    # Plot raw price data
+    import matplotlib.pyplot as plt
+    # Set plotting style
+    import seaborn as sns
+
+    pair = strategy.trading_pair_
+    SYMBOL_A = pair.symbol_a()
+    SYMBOL_B = pair.symbol_b()
+    TRD_DATE = f"{trading_date[0:4]}-{trading_date[4:6]}-{trading_date[6:8]}"
+
+    plt.style.use('seaborn-v0_8')
+    sns.set_palette("husl")
+    plt.rcParams['figure.figsize'] = (15, 10)
+
+    # Get column names for the trading pair
+    colname_a, colname_b = pair.colnames()
+    price_data = strategy.pt_mkt_data_.market_data_df_.copy()
+
+    # Create separate subplots for better visibility
+    fig_price, price_axes = plt.subplots(2, 1, figsize=(18, 10))
+
+    # Plot SYMBOL_A
+    price_axes[0].plot(price_data['tstamp'], price_data[colname_a], alpha=0.7, 
+                        label=f'{SYMBOL_A}', linewidth=1, color='blue')
+    price_axes[0].set_title(f'{SYMBOL_A} Price Data ({TRD_DATE})')
+    price_axes[0].set_ylabel(f'{SYMBOL_A} Price')
+    price_axes[0].legend()
+    price_axes[0].grid(True)
+
+    # Plot SYMBOL_B
+    price_axes[1].plot(price_data['tstamp'], price_data[colname_b], alpha=0.7, 
+                        label=f'{SYMBOL_B}', linewidth=1, color='red')
+    price_axes[1].set_title(f'{SYMBOL_B} Price Data ({TRD_DATE})')
+    price_axes[1].set_ylabel(f'{SYMBOL_B} Price')
+    price_axes[1].set_xlabel('Time')
+    price_axes[1].legend()
+    price_axes[1].grid(True)
+
+    plt.tight_layout()
+    plt.show()
+        
+
+    # Plot individual prices
+    fig, axes = plt.subplots(2, 1, figsize=(18, 12))
+
+    # Normalized prices for comparison
+    norm_a = price_data[colname_a] / price_data[colname_a].iloc[0]
+    norm_b = price_data[colname_b] / price_data[colname_b].iloc[0]
+
+    axes[0].plot(price_data['tstamp'], norm_a, label=f'{SYMBOL_A} (normalized)', alpha=0.8, linewidth=1)
+    axes[0].plot(price_data['tstamp'], norm_b, label=f'{SYMBOL_B} (normalized)', alpha=0.8, linewidth=1)
+    axes[0].set_title(f'Normalized Price Comparison (Base = 1.0)  ({TRD_DATE})')
+    axes[0].set_ylabel('Normalized Price')
+    axes[0].legend()
+    axes[0].grid(True)
+
+    # Price ratio
+    price_ratio = price_data[colname_a] / price_data[colname_b]
+    axes[1].plot(price_data['tstamp'], price_ratio, label=f'{SYMBOL_A}/{SYMBOL_B} Ratio', color='green', alpha=0.8, linewidth=1)
+    axes[1].set_title(f'Price Ratio Px({SYMBOL_A})/Px({SYMBOL_B}) ({TRD_DATE})')
+    axes[1].set_ylabel('Ratio')
+    axes[1].set_xlabel('Time')
+    axes[1].legend()
+    axes[1].grid(True)
+
+    plt.tight_layout()
+    plt.show()
+
+    # Print basic statistics
+    print(f"\nPrice Statistics:")
+    print(f"  {SYMBOL_A}: Mean=${price_data[colname_a].mean():.2f}, Std=${price_data[colname_a].std():.2f}")
+    print(f"  {SYMBOL_B}: Mean=${price_data[colname_b].mean():.2f}, Std=${price_data[colname_b].std():.2f}")
+    print(f"  Price Ratio: Mean={price_ratio.mean():.2f}, Std={price_ratio.std():.2f}")
+    print(f"  Correlation: {price_data[colname_a].corr(price_data[colname_b]):.4f}")
+

lib/tools/viz/viz_trades.py

@@ -0,0 +1,502 @@
+from __future__ import annotations
+
+
+from pairs_trading.lib.pt_strategy.results import (PairResearchResult)
+from pairs_trading.lib.pt_strategy.research_strategy import PtResearchStrategy
+
+
+def visualize_trades(strategy: PtResearchStrategy, results: PairResearchResult, trading_date: str) -> None: 
+
+    import pandas as pd
+    import plotly.express as px
+    import plotly.graph_objects as go
+    import plotly.offline as pyo
+    from IPython.display import HTML
+    from plotly.subplots import make_subplots
+
+
+    pair = strategy.trading_pair_
+    trades = results.trades_[trading_date].copy()
+    origin_mkt_data_df = strategy.pt_mkt_data_.origin_mkt_data_df_
+    mkt_data_df = strategy.pt_mkt_data_.market_data_df_
+    TRD_DATE = f"{trading_date[0:4]}-{trading_date[4:6]}-{trading_date[6:8]}"
+    SYMBOL_A = pair.symbol_a()
+    SYMBOL_B = pair.symbol_b()
+
+    
+    print(f"\nCreated trading pair: {pair}")
+    print(f"Market data shape: {pair.market_data_.shape}")
+    print(f"Column names: {pair.colnames()}")
+
+    # Configure plotly for offline mode
+    pyo.init_notebook_mode(connected=True)
+
+    # Strategy-specific interactive visualization
+    assert strategy.config_ is not None
+
+    print("=== SLIDING FIT INTERACTIVE VISUALIZATION ===")
+    print("Note: Rolling Fit strategy visualization with interactive plotly charts")
+    
+
+    # Create consistent timeline - superset of timestamps from both dataframes
+    all_timestamps = sorted(set(mkt_data_df['tstamp']))
+
+
+    # Create a unified timeline dataframe for consistent plotting
+    timeline_df = pd.DataFrame({'tstamp': all_timestamps})
+
+    # Merge with predicted data to get dis-equilibrium values
+    timeline_df = timeline_df.merge(strategy.predictions_df_[['tstamp', 'disequilibrium', 'scaled_disequilibrium', 'signed_scaled_disequilibrium']], 
+                                    on='tstamp', how='left')
+
+    # Get Symbol_A and Symbol_B market data
+    colname_a, colname_b = pair.colnames()
+    symbol_a_data = mkt_data_df[['tstamp', colname_a]].copy()
+    symbol_b_data = mkt_data_df[['tstamp', colname_b]].copy()
+
+    norm_a = symbol_a_data[colname_a] / symbol_a_data[colname_a].iloc[0]
+    norm_b = symbol_b_data[colname_b] / symbol_b_data[colname_b].iloc[0]
+
+    print(f"Using consistent timeline with {len(timeline_df)} timestamps")
+    print(f"Timeline range: {timeline_df['tstamp'].min()} to {timeline_df['tstamp'].max()}")
+
+    # Create subplots with price charts at bottom
+    fig = make_subplots(
+        rows=4, cols=1,
+        row_heights=[0.3, 0.4, 0.15, 0.15],
+        subplot_titles=[
+            f'Dis-equilibrium with Trading Thresholds ({TRD_DATE})',
+            f'Normalized Price Comparison with BUY/SELL Signals - {SYMBOL_A}&{SYMBOL_B} ({TRD_DATE})',
+            f'{SYMBOL_A} Market Data with Trading Signals ({TRD_DATE})',
+            f'{SYMBOL_B} Market Data with Trading Signals ({TRD_DATE})',
+        ],
+        vertical_spacing=0.06,
+        specs=[[{"secondary_y": False}],
+                [{"secondary_y": False}],
+                [{"secondary_y": False}],
+                [{"secondary_y": False}]]
+    )
+
+    # 1. Scaled dis-equilibrium with thresholds - using consistent timeline
+    fig.add_trace(
+        go.Scatter(
+            x=timeline_df['tstamp'],
+            y=timeline_df['scaled_disequilibrium'],
+            name='Absolute Scaled Dis-equilibrium',
+            line=dict(color='green', width=2),
+            opacity=0.8
+        ),
+        row=1, col=1
+    )
+
+    fig.add_trace(
+        go.Scatter(
+            x=timeline_df['tstamp'],
+            y=timeline_df['signed_scaled_disequilibrium'],
+            name='Scaled Dis-equilibrium',
+            line=dict(color='darkmagenta', width=2),
+            opacity=0.8
+        ),
+        row=1, col=1
+    )
+
+    # Add threshold lines to first subplot
+    fig.add_shape(
+        type="line",
+        x0=timeline_df['tstamp'].min(),
+        x1=timeline_df['tstamp'].max(),
+        y0=strategy.config_.get_value('model/disequilibrium/open_trshld'),
+        y1=strategy.config_.get_value('model/disequilibrium/open_trshld'),
+        line=dict(color="purple", width=2, dash="dot"),
+        opacity=0.7,
+        row=1, col=1
+    )
+
+    fig.add_shape(
+        type="line",
+        x0=timeline_df['tstamp'].min(),
+        x1=timeline_df['tstamp'].max(),
+        y0=-strategy.config_.get_value('model/disequilibrium/open_trshld'),
+        y1=-strategy.config_.get_value('model/disequilibrium/open_trshld'),
+        line=dict(color="purple", width=2, dash="dot"),
+        opacity=0.7,
+        row=1, col=1
+    )
+
+    fig.add_shape(
+        type="line",
+        x0=timeline_df['tstamp'].min(),
+        x1=timeline_df['tstamp'].max(),
+        y0=strategy.config_.get_value('model/disequilibrium/close_trshld'),
+        y1=strategy.config_.get_value('model/disequilibrium/close_trshld'),
+        line=dict(color="brown", width=2, dash="dot"),
+        opacity=0.7,
+        row=1, col=1
+    )
+
+    fig.add_shape(
+        type="line",
+        x0=timeline_df['tstamp'].min(),
+        x1=timeline_df['tstamp'].max(),
+        y0=-strategy.config_.get_value('model/disequilibrium/close_trshld'),
+        y1=-strategy.config_.get_value('model/disequilibrium/close_trshld'),
+        line=dict(color="brown", width=2, dash="dot"),
+        opacity=0.7,
+        row=1, col=1
+    )
+
+    fig.add_shape(
+        type="line",
+        x0=timeline_df['tstamp'].min(),
+        x1=timeline_df['tstamp'].max(),
+        y0=0,
+        y1=0,
+        line=dict(color="black", width=1, dash="solid"),
+        opacity=0.5,
+        row=1, col=1
+    )
+
+    # Add normalized price lines
+    fig.add_trace(
+        go.Scatter(
+            x=mkt_data_df['tstamp'],
+            y=norm_a,
+            name=f'{SYMBOL_A} (Normalized)',
+            line=dict(color='blue', width=2),
+            opacity=0.8
+        ),
+        row=2, col=1
+    )
+
+    fig.add_trace(
+        go.Scatter(
+            x=mkt_data_df['tstamp'],
+            y=norm_b,
+            name=f'{SYMBOL_B} (Normalized)',
+            line=dict(color='orange', width=2),
+            opacity=0.8,
+        ),
+        row=2, col=1
+    )
+
+    # Add BUY and SELL signals if available
+    if trades is not None and len(trades) > 0:
+        # Define signal groups to avoid legend repetition
+        signal_groups = {}
+        
+        # Process all trades and group by signal type (ignore OPEN/CLOSE status)
+        for _, trade in trades.iterrows():
+            symbol = trade['symbol']
+            side = trade['side']
+            # status = trade['status']
+            action = trade['action']
+            
+            # Create signal group key (without status to combine OPEN/CLOSE)
+            signal_key = f"{symbol} {side} {action}"
+            
+            # Find normalized price for this trade
+            trade_time = trade['time']
+            if symbol == SYMBOL_A:
+                closest_idx = mkt_data_df['tstamp'].searchsorted(trade_time)
+                if closest_idx < len(norm_a):
+                    norm_price = norm_a.iloc[closest_idx]
+                else:
+                    norm_price = norm_a.iloc[-1]
+            else:  # SYMBOL_B
+                closest_idx = mkt_data_df['tstamp'].searchsorted(trade_time)
+                if closest_idx < len(norm_b):
+                    norm_price = norm_b.iloc[closest_idx]
+                else:
+                    norm_price = norm_b.iloc[-1]
+            
+            # Initialize group if not exists
+            if signal_key not in signal_groups:
+                signal_groups[signal_key] = {
+                    'times': [],
+                    'prices': [],
+                    'actual_prices': [],
+                    'symbol': symbol,
+                    'side': side,
+                    # 'status': status,
+                    'action': trade['action']
+                }
+            
+            # Add to group
+            signal_groups[signal_key]['times'].append(trade_time)
+            signal_groups[signal_key]['prices'].append(norm_price)
+            signal_groups[signal_key]['actual_prices'].append(trade['price'])
+        
+        # Add each signal group as a single trace
+        for signal_key, group_data in signal_groups.items():
+            symbol = group_data['symbol']
+            side = group_data['side']
+            # status = group_data['status']
+            
+            # Determine marker properties (same for all OPEN/CLOSE of same side)
+            is_close: bool = (group_data['action'] == "CLOSE")
+            
+            if 'BUY' in side:
+                marker_color = 'green'
+                marker_symbol = 'triangle-up'
+                marker_size = 14
+            else:  # SELL
+                marker_color = 'red'
+                marker_symbol = 'triangle-down'
+                marker_size = 14
+            
+            # Create hover text for each point in the group
+            hover_texts = []
+            for i, (time, norm_price, actual_price) in enumerate(zip(group_data['times'], 
+                                                                    group_data['prices'], 
+                                                                    group_data['actual_prices'])):
+                # Find the corresponding trade to get the status for hover text
+                trade_info = trades[(trades['time'] == time) & 
+                                    (trades['symbol'] == symbol) & 
+                                    (trades['side'] == side)]
+                if len(trade_info) > 0:
+                    action = trade_info.iloc[0]['action']
+                    hover_texts.append(f'<b>{signal_key} {action}</b><br>' +
+                                    f'Time: {time}<br>' +
+                                    f'Normalized Price: {norm_price:.4f}<br>' +
+                                    f'Actual Price: ${actual_price:.2f}')
+                else:
+                    hover_texts.append(f'<b>{signal_key}</b><br>' +
+                                    f'Time: {time}<br>' +
+                                    f'Normalized Price: {norm_price:.4f}<br>' +
+                                    f'Actual Price: ${actual_price:.2f}')
+            
+            fig.add_trace(
+                go.Scatter(
+                    x=group_data['times'],
+                    y=group_data['prices'],
+                    mode='markers',
+                    name=signal_key,
+                    marker=dict(
+                        color=marker_color,
+                        size=marker_size,
+                        symbol=marker_symbol,
+                        line=dict(width=2, color='black') if is_close else None
+                    ),
+                    showlegend=True,
+                    hovertemplate='%{text}<extra></extra>',
+                    text=hover_texts
+                ),
+                row=2, col=1
+            )
+
+    # -----------------------------                
+        
+        fig.add_trace(
+            go.Scatter(
+                x=symbol_a_data['tstamp'],
+                y=symbol_a_data[colname_a],
+                name=f'{SYMBOL_A} Price',
+                line=dict(color='blue', width=2),
+                opacity=0.8
+            ),
+            row=3, col=1
+        )
+
+        # Filter trades for Symbol_A
+        symbol_a_trades = trades[trades['symbol'] == SYMBOL_A]
+        print(f"\nSymbol_A trades:\n{symbol_a_trades}")
+        
+        if len(symbol_a_trades) > 0:
+            # Separate trades by action and status for different colors
+            buy_open_trades = symbol_a_trades[(symbol_a_trades['side'].str.contains('BUY', na=False)) & 
+                                                (symbol_a_trades['action'].str.contains('OPEN', na=False))]
+            buy_close_trades = symbol_a_trades[(symbol_a_trades['side'].str.contains('BUY', na=False)) & 
+                                                (symbol_a_trades['action'].str.contains('CLOSE', na=False))]
+            
+            sell_open_trades = symbol_a_trades[(symbol_a_trades['side'].str.contains('SELL', na=False)) & 
+                                                (symbol_a_trades['action'].str.contains('OPEN', na=False))]
+            sell_close_trades = symbol_a_trades[(symbol_a_trades['side'].str.contains('SELL', na=False)) & 
+                                                (symbol_a_trades['action'].str.contains('CLOSE', na=False))]
+            
+            # Add BUY OPEN signals
+            if len(buy_open_trades) > 0:
+                fig.add_trace(
+                    go.Scatter(
+                        x=buy_open_trades['time'],
+                        y=buy_open_trades['price'],
+                        mode='markers',
+                        name=f'{SYMBOL_A} BUY OPEN',
+                        marker=dict(color='green', size=12, symbol='triangle-up'),
+                        showlegend=True
+                    ),
+                    row=3, col=1
+                )
+            
+            # Add BUY CLOSE signals
+            if len(buy_close_trades) > 0:
+                fig.add_trace(
+                    go.Scatter(
+                        x=buy_close_trades['time'],
+                        y=buy_close_trades['price'],
+                        mode='markers',
+                        name=f'{SYMBOL_A} BUY CLOSE',
+                        marker=dict(color='green', size=12, symbol='triangle-up'),
+                        line=dict(width=2, color='black'),
+                        showlegend=True
+                    ),
+                    row=3, col=1
+                )
+            
+            # Add SELL OPEN signals
+            if len(sell_open_trades) > 0:
+                fig.add_trace(
+                    go.Scatter(
+                        x=sell_open_trades['time'],
+                        y=sell_open_trades['price'],
+                        mode='markers',
+                        name=f'{SYMBOL_A} SELL OPEN',
+                        marker=dict(color='red', size=12, symbol='triangle-down'),
+                        showlegend=True
+                    ),
+                    row=3, col=1
+                )
+            
+            # Add SELL CLOSE signals
+            if len(sell_close_trades) > 0:
+                fig.add_trace(
+                    go.Scatter(
+                        x=sell_close_trades['time'],
+                        y=sell_close_trades['price'],
+                        mode='markers',
+                        name=f'{SYMBOL_A} SELL CLOSE',
+                        marker=dict(color='red', size=12, symbol='triangle-down'),
+                        line=dict(width=2, color='black'),
+                        showlegend=True
+                    ),
+                    row=3, col=1
+                )
+                    
+            # 4. Symbol_B Market Data with Trading Signals
+        fig.add_trace(
+            go.Scatter(
+                x=symbol_b_data['tstamp'],
+                y=symbol_b_data[colname_b],
+                name=f'{SYMBOL_B} Price',
+                line=dict(color='orange', width=2),
+                opacity=0.8
+            ),
+            row=4, col=1
+        )
+        
+        # Add trading signals for Symbol_B if available
+        symbol_b_trades = trades[trades['symbol'] == SYMBOL_B]
+        print(f"\nSymbol_B trades:\n{symbol_b_trades}")
+        
+        if len(symbol_b_trades) > 0:
+            # Separate trades by action and status for different colors
+            buy_open_trades = symbol_b_trades[(symbol_b_trades['side'].str.contains('BUY', na=False)) & 
+                                                (symbol_b_trades['action'].str.startswith('OPEN', na=False))]
+            buy_close_trades = symbol_b_trades[(symbol_b_trades['side'].str.contains('BUY', na=False)) & 
+                                                (symbol_b_trades['action'].str.startswith('CLOSE', na=False))]
+            
+            sell_open_trades = symbol_b_trades[(symbol_b_trades['side'].str.contains('SELL', na=False)) & 
+                                                (symbol_b_trades['action'].str.contains('OPEN', na=False))]
+            sell_close_trades = symbol_b_trades[(symbol_b_trades['side'].str.contains('SELL', na=False)) & 
+                                                (symbol_b_trades['action'].str.contains('CLOSE', na=False))]
+            
+            # Add BUY OPEN signals
+            if len(buy_open_trades) > 0:
+                fig.add_trace(
+                    go.Scatter(
+                        x=buy_open_trades['time'],
+                        y=buy_open_trades['price'],
+                        mode='markers',
+                        name=f'{SYMBOL_B} BUY OPEN',
+                        marker=dict(color='darkgreen', size=12, symbol='triangle-up'),
+                        showlegend=True
+                    ),
+                    row=4, col=1
+                )
+            
+            # Add BUY CLOSE signals
+            if len(buy_close_trades) > 0:
+                fig.add_trace(
+                    go.Scatter(
+                        x=buy_close_trades['time'],
+                        y=buy_close_trades['price'],
+                        mode='markers',
+                        name=f'{SYMBOL_B} BUY CLOSE',
+                        marker=dict(color='green', size=12, symbol='triangle-up'),
+                        line=dict(width=2, color='black'),
+                        showlegend=True
+                    ),
+                    row=4, col=1
+                )
+            
+            # Add SELL OPEN signals
+            if len(sell_open_trades) > 0:
+                fig.add_trace(
+                    go.Scatter(
+                        x=sell_open_trades['time'],
+                        y=sell_open_trades['price'],
+                        mode='markers',
+                        name=f'{SYMBOL_B} SELL OPEN',
+                        marker=dict(color='red', size=12, symbol='triangle-down'),
+                        showlegend=True
+                    ),
+                    row=4, col=1
+                )
+            
+            # Add SELL CLOSE signals
+            if len(sell_close_trades) > 0:
+                fig.add_trace(
+                    go.Scatter(
+                        x=sell_close_trades['time'],
+                        y=sell_close_trades['price'],
+                        mode='markers',
+                        name=f'{SYMBOL_B} SELL CLOSE',
+                        marker=dict(color='red', size=12, symbol='triangle-down'),
+                        line=dict(width=2, color='black'),
+                        showlegend=True
+                    ),
+                    row=4, col=1
+                )
+    
+        # Update layout
+        fig.update_layout(
+            height=1600,
+            title_text=f"Strategy Analysis - {SYMBOL_A} & {SYMBOL_B} ({TRD_DATE})",
+            showlegend=True,
+            template="plotly_white",
+            plot_bgcolor='lightgray',
+        )
+        
+        # Update y-axis labels
+        fig.update_yaxes(title_text="Scaled Dis-equilibrium", row=1, col=1)
+        fig.update_yaxes(title_text=f"{SYMBOL_A} Price ($)", row=2, col=1)
+        fig.update_yaxes(title_text=f"{SYMBOL_B} Price ($)", row=3, col=1)
+        fig.update_yaxes(title_text="Normalized Price (Base = 1.0)", row=4, col=1)
+        
+        # Update x-axis labels and ensure consistent time range
+        time_range = [timeline_df['tstamp'].min(), timeline_df['tstamp'].max()]
+        fig.update_xaxes(range=time_range, row=1, col=1)
+        fig.update_xaxes(range=time_range, row=2, col=1)
+        fig.update_xaxes(range=time_range, row=3, col=1)
+        fig.update_xaxes(title_text="Time", range=time_range, row=4, col=1)
+        
+        # Display using plotly offline mode
+        # pyo.iplot(fig)
+        fig.show()
+        
+    else:
+        print("No interactive visualization data available - strategy may not have run successfully")
+
+    print(f"\nChart shows:")
+    print(f"- {SYMBOL_A} and {SYMBOL_B} prices normalized to start at 1.0")
+    print(f"- BUY signals shown as green triangles pointing up")
+    print(f"- SELL signals shown as orange triangles pointing down")
+    print(f"- All BUY signals per symbol grouped together, all SELL signals per symbol grouped together")
+    print(f"- Hover over markers to see individual trade details (OPEN/CLOSE status)")
+
+    if trades is not None and len(trades) > 0:
+        print(f"- Total signals displayed: {len(trades)}")
+        print(f"- {SYMBOL_A} signals: {len(trades[trades['symbol'] == SYMBOL_A])}")
+        print(f"- {SYMBOL_B} signals: {len(trades[trades['symbol'] == SYMBOL_B])}")
+    else:
+        print("- No trading signals to display")
+

requirements.txt

@@ -0,0 +1,201 @@
+aiohttp>=3.8.4
+aiosignal>=1.3.1
+async-timeout>=4.0.2
+attrs>=21.2.0
+beautifulsoup4>=4.10.0
+black>=23.3.0
+flake8>=6.0.0
+certifi>=2020.6.20
+chardet>=4.0.0
+charset-normalizer>=3.1.0
+click>=8.0.3
+colorama>=0.4.4
+configobj>=5.0.6
+cryptography>=3.4.8
+distro>=1.7.0
+docker>=5.0.3
+dockerpty>=0.4.1
+docopt>=0.6.2
+eyeD3>=0.8.10
+filelock>=3.6.0
+frozenlist>=1.3.3
+grpcio>=1.30.2
+hjson>=3.0.2
+html5lib>=1.1
+httplib2>=0.20.2
+idna>=3.3
+ipython>=8.18.1
+ipywidgets>=8.1.1
+ifaddr>=0.1.7
+IMDbPY>=2021.4.18
+ipykernel>=6.29.5
+jeepney>=0.7.1
+jsonschema>=3.2.0
+jupyter>=1.0.0
+keyring>=23.5.0
+launchpadlib>=1.10.16
+lazr.restfulclient>=0.14.4
+lazr.uri>=1.0.6
+lxml>=4.8.0
+Mako>=1.1.3
+Markdown>=3.3.6
+MarkupSafe>=2.0.1
+matplotlib>=3.10.3
+more-itertools>=8.10.0
+multidict>=6.0.4
+mypy>=0.942
+mypy-extensions>=0.4.3
+nbformat>=5.10.2
+netaddr>=0.8.0
+######### netifaces>=0.11.0
+numpy>=1.26.4,<2.3.0
+oauthlib>=3.2.0
+packaging>=23.1
+pandas>=2.2.3
+pathspec>=0.11.1
+pexpect>=4.8.0
+Pillow>=9.0.1
+platformdirs>=3.2.0
+plotly>=5.19.0
+protobuf>=3.12.4
+psutil>=5.9.0
+ptyprocess>=0.7.0
+pycurl>=7.44.1
+pyelftools>=0.27
+Pygments>=2.11.2
+pyparsing>=2.4.7
+pyrsistent>=0.18.1
+python-debian>=0.1.43 #+ubuntu1.1
+python-dotenv>=0.19.2
+python-magic>=0.4.24
+python-xlib>=0.29
+pyxdg>=0.27
+PyYAML>=6.0
+reportlab>=3.6.8
+requests>=2.25.1
+requests-file>=1.5.1
+scipy<1.13.0
+seaborn>=0.13.2
+SecretStorage>=3.3.1
+setproctitle>=1.2.2
+simpleeval>=1.0.3
+six>=1.16.0
+soupsieve>=2.3.1
+ssh-import-id>=5.11
+statsmodels>=0.14.4
+texttable>=1.6.4
+tldextract>=3.1.2
+tomli>=1.2.2
+######## typed-ast>=1.4.3
+types-aiofiles>=0.1
+types-annoy>=1.17
+types-appdirs>=1.4
+types-atomicwrites>=1.4
+types-aws-xray-sdk>=2.8
+types-babel>=2.9
+types-backports-abc>=0.5
+types-backports.ssl-match-hostname>=3.7
+types-beautifulsoup4>=4.10
+types-bleach>=4.1
+types-boto>=2.49
+types-braintree>=4.11
+types-cachetools>=4.2
+types-caldav>=0.8
+types-certifi>=2020.4
+types-characteristic>=14.3
+types-chardet>=4.0
+types-click>=7.1
+types-click-spinner>=0.1
+types-colorama>=0.4
+types-commonmark>=0.9
+types-contextvars>=0.1
+types-croniter>=1.0
+types-cryptography>=3.3
+types-dataclasses>=0.1
+types-dateparser>=1.0
+types-DateTimeRange>=0.1
+types-decorator>=0.1
+types-Deprecated>=1.2
+types-docopt>=0.6
+types-docutils>=0.17
+types-editdistance>=0.5
+types-emoji>=1.2
+types-entrypoints>=0.3
+types-enum34>=1.1
+types-filelock>=3.2
+types-first>=2.0
+types-Flask>=1.1
+types-freezegun>=1.1
+types-frozendict>=0.1
+types-futures>=3.3
+types-html5lib>=1.1
+types-httplib2>=0.19
+types-humanfriendly>=9.2
+types-ipaddress>=1.0
+types-itsdangerous>=1.1
+types-JACK-Client>=0.1
+types-Jinja2>=2.11
+types-jmespath>=0.10
+types-jsonschema>=3.2
+types-Markdown>=3.3
+types-MarkupSafe>=1.1
+types-mock>=4.0
+types-mypy-extensions>=0.4
+types-mysqlclient>=2.0
+types-oauthlib>=3.1
+types-orjson>=3.6
+types-paramiko>=2.7
+types-Pillow>=8.3
+types-polib>=1.1
+types-prettytable>=2.1
+types-protobuf>=3.17
+types-psutil>=5.8
+types-psycopg2>=2.9
+types-pyaudio>=0.2
+types-pycurl>=0.1
+types-pyfarmhash>=0.2
+types-Pygments>=2.9
+types-PyMySQL>=1.0
+types-pyOpenSSL>=20.0
+types-pyRFC3339>=0.1
+types-pysftp>=0.2
+types-pytest-lazy-fixture>=0.6
+types-python-dateutil>=2.8
+types-python-gflags>=3.1
+types-python-nmap>=0.6
+types-python-slugify>=5.0
+types-pytz>=2021.1
+types-pyvmomi>=7.0
+types-PyYAML>=5.4
+types-redis>=3.5
+types-requests>=2.25
+types-retry>=0.9
+types-seaborn>0.13.2
+types-selenium>=3.141
+types-Send2Trash>=1.8
+types-setuptools>=57.4
+types-simplejson>=3.17
+types-singledispatch>=3.7
+types-six>=1.16
+types-slumber>=0.7
+types-stripe>=2.59
+types-tabulate>=0.8
+types-termcolor>=1.1
+types-toml>=0.10
+types-toposort>=1.6
+types-ttkthemes>=3.2
+types-typed-ast>=1.4
+types-tzlocal>=0.1
+types-ujson>=0.1
+types-vobject>=0.9
+types-waitress>=0.1
+types-Werkzeug>=1.0
+types-xxhash>=2.0
+typing-extensions>=3.10.0.2
+Unidecode>=1.3.3
+urllib3>=1.26.5
+wadllib>=1.3.6
+webencodings>=0.5.1
+websocket-client>=1.2.3
+yarl>=1.9.1
+zipp>=1.0.0

research/backtest.py

@@ -0,0 +1,139 @@
+from __future__ import annotations
+
+import os
+from typing import Any, Dict, List, Tuple
+
+# ---
+from cvttpy_tools.app import App
+from cvttpy_tools.base import NamedObject
+from cvttpy_tools.config import CvttAppConfig
+
+# ---
+from cvttpy_trading.trading.instrument import ExchangeInstrument
+from cvttpy_trading.settings.instruments import Instruments
+
+# ---
+from pairs_trading.lib.pt_strategy.results import (
+    PairResearchResult,
+    create_result_database,
+    store_config_in_database,
+)
+from pairs_trading.lib.pt_strategy.research_strategy import PtResearchStrategy
+from pairs_trading.lib.tools.filetools import resolve_datafiles
+
+InstrumentTypeT = str
+
+
+class Runner(NamedObject):
+    def __init__(self):
+        App()
+        CvttAppConfig()
+
+        # App.instance().add_cmdline_arg(
+        #     "--config", type=str, required=True, help="Path to the configuration file."
+        # )
+        App.instance().add_cmdline_arg(
+            "--date_pattern",
+            type=str,
+            required=True,
+            help="Date YYYYMMDD, allows * and ? wildcards",
+        )
+        App.instance().add_cmdline_arg(
+            "--instruments",
+            type=str,
+            required=True,
+            help="Comma-separated list of instrument symbols (e.g., COIN:EQUITY,GBTC:CRYPTO)",
+        )
+        App.instance().add_cmdline_arg(
+            "--result_db",
+            type=str,
+            required=True,
+            help="Path to SQLite database for storing results. Use 'NONE' to disable database output.",
+        )
+
+        App.instance().add_call(stage=App.Stage.Config, func=self._on_config())
+        App.instance().add_call(stage=App.Stage.Run, func=self.run())
+
+    async def _on_config(self) -> None:
+        # Resolve data files (CLI takes priority over config)
+        instruments: List[ExchangeInstrument] = self._get_instruments()
+        datafiles = resolve_datafiles(
+            config=CvttAppConfig.instance(),
+            date_pattern=App.instance().get_argument("date_pattern"),
+            instruments=instruments,
+        )
+
+        days = list(set([day for day, _ in datafiles]))
+        print(f"Found {len(datafiles)} data files to process:")
+        for df in datafiles:
+            print(f"  - {df}")
+
+        # Create result database if needed
+        if App.instance().get_argument("result_db").upper() != "NONE":
+            create_result_database(App.instance().get_argument("result_db"))
+
+        # Initialize a dictionary to store all trade results
+        all_results: Dict[str, Dict[str, Any]] = {}
+        is_config_stored = False
+        # Process each data file
+
+        results = PairResearchResult(config=CvttAppConfig.instance())
+        for day in sorted(days):
+            md_datafiles = [datafile for md_day, datafile in datafiles if md_day == day]
+            if not all([os.path.exists(datafile) for datafile in md_datafiles]):
+                print(f"WARNING: insufficient data files: {md_datafiles}")
+                exit(1)
+            print(f"\n====== Processing {day} ======")
+
+            if not is_config_stored:
+                store_config_in_database(
+                    db_path=App.instance().get_argument("result_db"),
+                    config_file_path=App.instance().get_argument("config"),
+                    config=CvttAppConfig.instance(),
+                    datafiles=datafiles,
+                    instruments=instruments,
+                )
+                is_config_stored = True
+
+            CvttAppConfig.instance().set_value("datafiles", md_datafiles)
+            pt_strategy = PtResearchStrategy(
+                config=CvttAppConfig.instance(),
+                instruments=instruments,
+            )
+            pt_strategy.run()
+            results.add_day_results(
+                day=day,
+                trades=pt_strategy.day_trades(),
+                outstanding_positions=pt_strategy.outstanding_positions(),
+            )
+
+        results.analyze_pair_performance()
+
+    def _get_instruments(self) -> List[ExchangeInstrument]:
+        res: List[ExchangeInstrument] = []
+
+        for inst in App.instance().get_argument("instruments").split(","):
+            instrument_type = inst.split(":")[0]
+            exchange_id = inst.split(":")[1]
+            instrument_id = inst.split(":")[2]
+            exch_inst: ExchangeInstrument = Instruments.instance().get_exch_inst(
+                exch_id=exchange_id, inst_id=instrument_id, src=f"{self.fname()}"
+            )
+            exch_inst.user_data_["instrument_type"] = instrument_type
+            res.append(exch_inst)
+
+        return res
+
+    async def run(self) -> None:
+
+        if App.instance().get_argument("result_db").upper() != "NONE":
+            print(
+                f'\nResults stored in database: {App.instance().get_argument("result_db")}'
+            )
+        else:
+            print("No results to display.")
+
+
+if __name__ == "__main__":
+    Runner()
+    App.instance().run()

scripts/load_crypto_1min.sh

@@ -0,0 +1,42 @@
+#!/usr/bin/env bash
+
+# -------------------------------------
+# --- Given month, specific dates
+# -------------------------------------
+
+# for dt in 20250528 20250529 20250530 20250531; do
+# 	rsync -ahvv cvtt@hs01.cvtt.vpn:/works/cvtt/md_archive/crypto/sim/2025/2025-05/${dt}.*.gz ./
+# done
+# -------------------------------------
+
+# -------------------------------------
+# --- Current month - all files
+# -------------------------------------
+cd $(realpath $(dirname $0))/..
+mkdir -p ./data/crypto
+pushd ./data/crypto
+
+Files=$1
+if [ -z "$Files" ]; then
+    Files="*.gz"
+fi
+
+Cmd="rsync -ahvv cvtt@hs01.cvtt.vpn:/works/cvtt/md_archive/crypto/sim/${Files} ./"
+echo $Cmd
+eval $Cmd
+# -------------------------------------
+
+for srcfname in $(ls *.db.gz); do
+    dt="${srcfname:0:8}"
+    tgtfile=${dt}.mktdata.ohlcv.db
+    echo "${srcfname} -> ${tgtfile}"
+
+    Cmd="gunzip -c $srcfname > temp.db"
+    echo $Cmd
+    eval $Cmd
+    Cmd="rm -f ${tgtfile} && sqlite3 temp.db \".dump md_1min_bars\" | sqlite3  ${tgtfile} && rm ${srcfname}"
+    echo $Cmd
+    eval $Cmd
+done
+rm temp.db
+popd

scripts/load_equity_1min.sh

@@ -0,0 +1,37 @@
+#!/usr/bin/env bash
+
+usage() {
+    echo "Usage: $0 [DatePattern]"
+    echo "DatePattern: YYYYMM or YYYYM or YYYYMMD"
+    exit 1
+}
+
+DatePattern="${1}"
+if [ -z "${DatePattern}" ]; then
+    usage
+fi
+FilePattern="${DatePattern}*.alpaca_sim_md.db.gz"
+
+cd $(realpath $(dirname $0))/..
+mkdir -p ./data/equity
+pushd ./data/equity
+
+Cmd="rsync -ahvv cvtt@hs01.cvtt.vpn:/works/cvtt/md_archive/equity/alpaca_md/sim/${FilePattern} ./"
+echo ${Cmd}
+eval ${Cmd}
+# -------------------------------------
+
+for srcfname in $(ls *.db.gz); do
+    dt="${srcfname:0:8}"
+    tgtfile=${dt}.mktdata.ohlcv.db
+    echo "${srcfname} -> ${tgtfile}"
+
+    Cmd="gunzip -c $srcfname > temp.db && rm $srcfname"
+    echo ${Cmd}
+    eval ${Cmd}
+    Cmd="rm -f ${tgtfile} && sqlite3 temp.db '.dump md_1min_bars' | sqlite3  ${tgtfile}"
+    echo ${Cmd}
+    eval ${Cmd}
+done
+rm temp.db
+popd

src/backtest_configs.py

@@ -1,95 +0,0 @@
-from typing import Any, Dict, List, Optional
-
-
-# ------------------------ Configuration ------------------------
-# Default configuration
-CRYPTO_CONFIG: Dict = {
-    "security_type": "CRYPTO",
-    # --- Data retrieval
-    "data_directory": "./data/crypto",
-    "datafiles": [
-        # "20250519.mktdata.ohlcv.db",
-        # "20250520.mktdata.ohlcv.db",
-        # "20250521.mktdata.ohlcv.db",
-        # "20250522.mktdata.ohlcv.db",
-        # "20250523.mktdata.ohlcv.db",
-        # "20250524.mktdata.ohlcv.db",
-        "20250525.mktdata.ohlcv.db",
-    ],
-    "db_table_name": "bnbspot_ohlcv_1min",
-    # ----- Instruments
-    "exchange_id": "BNBSPOT",
-    "instrument_id_pfx": "PAIR-",
-    "instruments": [
-        "BTC-USDT",
-        "BCH-USDT",
-        "ETH-USDT",
-        "LTC-USDT",
-        "XRP-USDT",
-        "ADA-USDT",
-        "SOL-USDT",
-        "DOT-USDT",
-    ],
-    "trading_hours": {
-        "begin_session": "00:00:00",
-        "end_session": "23:59:00",
-        "timezone": "UTC",
-    },
-    # ----- Model Settings
-    "price_column": "close",
-    "min_required_points": 30,
-    "zero_threshold": 1e-10,
-
-    "dis-equilibrium_open_trshld": 2.0,
-    "dis-equilibrium_close_trshld": 0.5,
-
-    # "training_minutes": 120,
-    "training_minutes": 60,
-    # ----- Validation
-    "funding_per_pair": 2000.0,  # USD
-}
-
-# ========================== EQUITIES
-EQT_CONFIG: Dict = {
-    # --- Data retrieval
-    "security_type": "EQUITY",
-    "data_directory": "./data/equity",
-    "datafiles": [
-        # "20250508.alpaca_sim_md.db",
-        # "20250509.alpaca_sim_md.db",
-        "20250512.alpaca_sim_md.db",
-        # "20250513.alpaca_sim_md.db",
-        # "20250514.alpaca_sim_md.db",
-        # "20250515.alpaca_sim_md.db",
-        # "20250516.alpaca_sim_md.db",
-        # "20250519.alpaca_sim_md.db",
-        # "20250520.alpaca_sim_md.db"
-    ],
-    "db_table_name": "md_1min_bars",
-    # ----- Instruments
-    "exchange_id": "ALPACA",
-    "instrument_id_pfx": "STOCK-",
-    "instruments": [
-        "COIN",
-        "GBTC",
-        "HOOD",
-        "MSTR",
-        "PYPL",
-    ],
-    "trading_hours": {
-        "begin_session": "9:30:00",
-        "end_session": "16:00:00",
-        "timezone": "America/New_York",
-    },
-    # ----- Model Settings
-    "price_column": "close",
-    "min_required_points": 30,
-    "zero_threshold": 1e-10,
-    "dis-equilibrium_open_trshld": 2.0,
-    "dis-equilibrium_close_trshld": 0.5,
-    "training_minutes": 120,
-    # ----- Validation
-    "funding_per_pair": 2000.0,
-}
-
-

src/pt_backtest.py

@@ -1,107 +0,0 @@
-from abc import ABC, abstractmethod
-import sys
-
-from typing import Any, Dict, List, Optional
-
-import pandas as pd
-import numpy as np
-
-# ============= statsmodels ===================
-from statsmodels.tsa.vector_ar.vecm import VECM
-
-from backtest_configs import CRYPTO_CONFIG
-from strategies import StaticFitStrategy
-from tools.data_loader import load_market_data
-from tools.trading_pair import TradingPair
-from results import BacktestResult
-
-NanoPerMin = 1e9
-UNSET_FLOAT: float = sys.float_info.max
-UNSET_INT: int = sys.maxsize
-
-
-CONFIG = CRYPTO_CONFIG
-# CONFIG = EQT_CONFIG
-
-
-def run_all_pairs(config: Dict, datafile: str, price_column: str, bt_result: BacktestResult) -> None:
-
-    def _create_pairs(config: Dict) -> List[TradingPair]:
-        nonlocal datafile
-        instruments = config["instruments"]
-        all_indexes = range(len(instruments))
-        unique_index_pairs = [(i, j) for i in all_indexes for j in all_indexes if i < j]
-        pairs = []
-        market_data_df = load_market_data(
-            f'{config["data_directory"]}/{datafile}', config=CONFIG
-        )
-        for a_index, b_index in unique_index_pairs:
-            pair = TradingPair(
-                market_data=market_data_df,
-                symbol_a=instruments[a_index],
-                symbol_b=instruments[b_index],
-                price_column=price_column,
-            )
-            pairs.append(pair)
-        return pairs
- 
-
-    pairs_trades = []
-    strategy = StaticFitStrategy()
-    for pair in _create_pairs(config):
-        single_pair_trades = strategy.run_pair(pair=pair, config=CONFIG, bt_result=bt_result)
-        if single_pair_trades is not None and len(single_pair_trades) > 0:
-            pairs_trades.append(single_pair_trades)
-    # Check if result_list has any data before concatenating
-    if len(pairs_trades) == 0:
-        print("No trading signals found for any pairs")
-        return None
-
-    result = pd.concat(pairs_trades, ignore_index=True)
-    result["time"] = pd.to_datetime(result["time"])
-    result = result.set_index("time").sort_index()
-
-    bt_result.collect_single_day_results(result)
-    # BacktestResults.print_single_day_results()
-
-
-def main() -> None:
-    # Initialize a dictionary to store all trade results
-    all_results: Dict[str, Dict[str, Any]] = {}
-    bt_results = BacktestResult(config=CONFIG)
-
-    # Initialize global PnL tracking variables
-
-    # Process each data file
-    price_column = CONFIG["price_column"]
-    for datafile in CONFIG["datafiles"]:
-        print(f"\n====== Processing {datafile} ======")
-
-        # Clear the TRADES global dictionary and reset unrealized PnL for the new file
-        bt_results.clear_trades()
-
-        # Process data for this file
-        try:
-            run_all_pairs(
-                config=CONFIG, datafile=datafile, price_column=price_column, bt_result=bt_results
-            )
-
-            # Store results with file name as key
-            filename = datafile.split("/")[-1]
-            all_results[filename] = {"trades": bt_results.trades.copy()}
-
-            print(f"Successfully processed {filename}")
-
-            # No longer printing unrealized PnL since we removed that functionality
-
-        except Exception as e:
-            print(f"Error processing {datafile}: {str(e)}")
-
-    # BacktestResults.print_results_summary(all_results)
-    bt_results.calculate_returns(all_results)
-    # Print grand totals
-    bt_results.print_grand_totals()
-    bt_results.print_outstanding_positions()
-    
-if __name__ == "__main__":
-    main()

src/results.py

@@ -1,295 +0,0 @@
-from typing import Any, Dict, List
-import pandas as pd
-
-
-class BacktestResult:
-    """
-    Class to handle backtest results, trades tracking, PnL calculations, and reporting.
-    """
-
-    def __init__(self, config: Dict[str, Any]):
-        self.config = config
-        self.trades: Dict[str, Dict[str, Any]] = {}
-        self.total_realized_pnl = 0.0
-        self.outstanding_positions: List[Dict[str, Any]] = []
-
-    def add_trade(self, pair_nm, symbol, action, price):
-        """Add a trade to the results tracking."""
-        pair_nm = str(pair_nm)
-
-        if pair_nm not in self.trades:
-            self.trades[pair_nm] = {symbol: []}
-        if symbol not in self.trades[pair_nm]:
-            self.trades[pair_nm][symbol] = []
-        self.trades[pair_nm][symbol].append((action, price))
-
-    def add_outstanding_position(self, position: Dict[str, Any]):
-        """Add an outstanding position to tracking."""
-        self.outstanding_positions.append(position)
-
-    def add_realized_pnl(self, realized_pnl: float):
-        """Add realized PnL to the total."""
-        self.total_realized_pnl += realized_pnl
-
-    def get_total_realized_pnl(self) -> float:
-        """Get total realized PnL."""
-        return self.total_realized_pnl
-
-    def get_outstanding_positions(self) -> List[Dict[str, Any]]:
-        """Get all outstanding positions."""
-        return self.outstanding_positions
-
-    def get_trades(self) -> Dict[str, Dict[str, Any]]:
-        """Get all trades."""
-        return self.trades
-
-    def clear_trades(self):
-        """Clear all trades (used when processing new files)."""
-        self.trades.clear()
-
-    def collect_single_day_results(self, result):
-        """Collect and process single day trading results."""
-        if result is None:
-            return
-
-        print("\n --------------  Suggested Trades ")
-        print(result)
-
-        for row in result.itertuples():
-            action = row.action
-            symbol = row.symbol
-            price = row.price
-            self.add_trade(
-                pair_nm=row.pair, action=action, symbol=symbol, price=price
-            )
-
-    def print_single_day_results(self):
-        """Print single day results summary."""
-        for pair, symbols in self.trades.items():
-            print(f"\n--- {pair} ---")
-            for symbol, trades in symbols.items():
-                for side, price in trades:
-                    print(f"{symbol} {side} at ${price}")
-
-    def print_results_summary(self, all_results):
-        """Print summary of all processed files."""
-        print("\n====== Summary of All Processed Files ======")
-        for filename, data in all_results.items():
-            trade_count = sum(
-                len(trades)
-                for symbol_trades in data["trades"].values()
-                for trades in symbol_trades.values()
-            )
-            print(f"{filename}: {trade_count} trades")
-
-    def calculate_returns(self, all_results: Dict):
-        """Calculate and print returns by day and pair."""
-        print("\n====== Returns By Day and Pair ======")
-
-        for filename, data in all_results.items():
-            day_return = 0
-            print(f"\n--- {filename} ---")
-
-            # Process each pair
-            for pair, symbols in data["trades"].items():
-                pair_return = 0
-                pair_trades = []
-
-                # Calculate individual symbol returns in the pair
-                for symbol, trades in symbols.items():
-                    if len(trades) >= 2:  # Need at least entry and exit
-                        # Get entry and exit trades
-                        entry_action, entry_price = trades[0]
-                        exit_action, exit_price = trades[1]
-
-                        # Calculate return based on action
-                        symbol_return = 0
-                        if entry_action == "BUY" and exit_action == "SELL":
-                            # Long position
-                            symbol_return = (exit_price - entry_price) / entry_price * 100
-                        elif entry_action == "SELL" and exit_action == "BUY":
-                            # Short position
-                            symbol_return = (entry_price - exit_price) / entry_price * 100
-
-                        pair_trades.append(
-                            (
-                                symbol,
-                                entry_action,
-                                entry_price,
-                                exit_action,
-                                exit_price,
-                                symbol_return,
-                            )
-                        )
-                        pair_return += symbol_return
-
-                # Print pair returns
-                if pair_trades:
-                    print(f"  {pair}:")
-                    for (
-                        symbol,
-                        entry_action,
-                        entry_price,
-                        exit_action,
-                        exit_price,
-                        symbol_return,
-                    ) in pair_trades:
-                        print(
-                            f"    {symbol}: {entry_action} @ ${entry_price:.2f}, {exit_action} @ ${exit_price:.2f}, Return: {symbol_return:.2f}%"
-                        )
-                    print(f"    Pair Total Return: {pair_return:.2f}%")
-                    day_return += pair_return
-
-            # Print day total return and add to global realized PnL
-            if day_return != 0:
-                print(f"  Day Total Return: {day_return:.2f}%")
-                self.add_realized_pnl(day_return)
-
-    def print_outstanding_positions(self):
-        """Print all outstanding positions with share quantities and current values."""
-        if not self.get_outstanding_positions():
-            print("\n====== NO OUTSTANDING POSITIONS ======")
-            return
-
-        print(f"\n====== OUTSTANDING POSITIONS ======")
-        print(
-            f"{'Pair':<15}"
-            f" {'Symbol':<10}"
-            f" {'Side':<4}"
-            f" {'Shares':<10}"
-            f" {'Open $':<8}"
-            f" {'Current $':<10}"
-            f" {'Value $':<12}"
-            f" {'Disequilibrium':<15}"
-        )
-        print("-" * 100)
-
-        total_value = 0.0
-
-        for pos in self.get_outstanding_positions():
-            # Print position A
-            print(
-                f"{pos['pair']:<15}"
-                f" {pos['symbol_a']:<10}"
-                f" {pos['side_a']:<4}"
-                f" {pos['shares_a']:<10.2f}"
-                f" {pos['open_px_a']:<8.2f}"
-                f" {pos['current_px_a']:<10.2f}"
-                f" {pos['current_value_a']:<12.2f}"
-                f" {'':<15}"
-            )
-
-            # Print position B
-            print(
-                f"{'':<15}"
-                f" {pos['symbol_b']:<10}"
-                f" {pos['side_b']:<4}"
-                f" {pos['shares_b']:<10.2f}"
-                f" {pos['open_px_b']:<8.2f}"
-                f" {pos['current_px_b']:<10.2f}"
-                f" {pos['current_value_b']:<12.2f}"
-            )
-
-            # Print pair totals with disequilibrium info
-            print(
-                f"{'':<15}"
-                f" {'PAIR TOTAL':<10}"
-                f" {'':<4}"
-                f" {'':<10}"
-                f" {'':<8}"
-                f" {'':<10}"
-                f" {pos['total_current_value']:<12.2f}"
-            )
-
-            # Print disequilibrium details
-            print(
-                f"{'':<15}"
-                f" {'DISEQUIL':<10}"
-                f" {'':<4}"
-                f" {'':<10}"
-                f" {'':<8}"
-                f" {'':<10}"
-                f" Raw: {pos['current_disequilibrium']:<6.4f}"
-                f" Scaled: {pos['current_scaled_disequilibrium']:<6.4f}"
-            )
-
-            print("-" * 100)
-
-            total_value += pos["total_current_value"]
-
-        print(f"{'TOTAL OUTSTANDING VALUE':<80} ${total_value:<12.2f}")
-
-    def print_grand_totals(self):
-        """Print grand totals across all pairs."""
-        print(f"\n====== GRAND TOTALS ACROSS ALL PAIRS ======")
-        print(f"Total Realized PnL: {self.get_total_realized_pnl():.2f}%")
-
-    def handle_outstanding_position(self, pair, pair_result_df, last_row_index,
-                                  open_side_a, open_side_b, open_px_a, open_px_b,
-                                  open_tstamp):
-        """
-        Handle calculation and tracking of outstanding positions when no close signal is found.
-
-        Args:
-            pair: TradingPair object
-            pair_result_df: DataFrame with pair results
-            last_row_index: Index of the last row in the data
-            open_side_a, open_side_b: Trading sides for symbols A and B
-            open_px_a, open_px_b: Opening prices for symbols A and B
-            open_tstamp: Opening timestamp
-        """
-        last_row = pair_result_df.loc[last_row_index]
-        last_tstamp = last_row["tstamp"]
-        colname_a, colname_b = pair.colnames()
-        last_px_a = last_row[colname_a]
-        last_px_b = last_row[colname_b]
-
-        # Calculate share quantities based on funding per pair
-        # Split funding equally between the two positions
-        funding_per_position = self.config["funding_per_pair"] / 2
-        shares_a = funding_per_position / open_px_a
-        shares_b = funding_per_position / open_px_b
-
-        # Calculate current position values (shares * current price)
-        current_value_a = shares_a * last_px_a
-        current_value_b = shares_b * last_px_b
-        total_current_value = current_value_a + current_value_b
-
-        # Get disequilibrium information
-        current_disequilibrium = last_row["disequilibrium"]
-        current_scaled_disequilibrium = last_row["scaled_disequilibrium"]
-
-        # Store outstanding positions
-        self.add_outstanding_position(
-            {
-                "pair": str(pair),
-                "symbol_a": pair.symbol_a_,
-                "symbol_b": pair.symbol_b_,
-                "side_a": open_side_a,
-                "side_b": open_side_b,
-                "shares_a": shares_a,
-                "shares_b": shares_b,
-                "open_px_a": open_px_a,
-                "open_px_b": open_px_b,
-                "current_px_a": last_px_a,
-                "current_px_b": last_px_b,
-                "current_value_a": current_value_a,
-                "current_value_b": current_value_b,
-                "total_current_value": total_current_value,
-                "open_time": open_tstamp,
-                "last_time": last_tstamp,
-                "current_abs_term": current_scaled_disequilibrium,
-                "current_disequilibrium": current_disequilibrium,
-                "current_scaled_disequilibrium": current_scaled_disequilibrium,
-            }
-        )
-
-        # Print position details
-        print(f"{pair}: NO CLOSE SIGNAL FOUND - Position held until end of session")
-        print(f"  Open: {open_tstamp} | Last: {last_tstamp}")
-        print(f"  {pair.symbol_a_}: {open_side_a} {shares_a:.2f} shares @ ${open_px_a:.2f} -> ${last_px_a:.2f} | Value: ${current_value_a:.2f}")
-        print(f"  {pair.symbol_b_}: {open_side_b} {shares_b:.2f} shares @ ${open_px_b:.2f} -> ${last_px_b:.2f} | Value: ${current_value_b:.2f}")
-        print(f"  Total Value: ${total_current_value:.2f}")
-        print(f"  Disequilibrium: {current_disequilibrium:.4f} | Scaled: {current_scaled_disequilibrium:.4f}")
-
-        return current_value_a, current_value_b, total_current_value

src/strategies.py

@@ -1,240 +0,0 @@
-from abc import ABC, abstractmethod
-import sys
-
-from typing import Dict, Optional
-
-import pandas as pd
-
-from tools.trading_pair import TradingPair
-from results import BacktestResult
-
-NanoPerMin = 1e9
-
-class PairsTradingStrategy(ABC):
-    TRADES_COLUMNS = [
-        "time",
-        "action",
-        "symbol",
-        "price",
-        "disequilibrium",
-        "scaled_disequilibrium",
-        "pair",
-    ]
-    @abstractmethod
-    def run_pair(self, pair: TradingPair, bt_result: BacktestResult) -> Optional[pd.DataFrame]:
-        ... 
-
-class StaticFitStrategy(PairsTradingStrategy):
-    
-    def run_pair(self, config: Dict, pair: TradingPair, bt_result: BacktestResult) -> Optional[pd.DataFrame]: # abstractmethod
-        pair.get_datasets(training_minutes=config["training_minutes"])
-        try:
-            is_cointegrated = pair.train_pair()
-            if not is_cointegrated:
-                print(f"{pair} IS NOT COINTEGRATED")
-                return None
-        except Exception as e:
-            print(f"{pair}: Training failed: {str(e)}")
-            return None
-
-        try:
-            pair.predict()
-        except Exception as e:
-            print(f"{pair}: Prediction failed: {str(e)}")
-            return None
-            
-        pair_trades = self.create_trading_signals(pair=pair, config=config, result=bt_result)
-
-        return pair_trades
-
-    def create_trading_signals(self, pair: TradingPair, config: Dict, result: BacktestResult) -> pd.DataFrame:
-        beta = pair.vecm_fit_.beta
-        colname_a, colname_b = pair.colnames()
-
-        predicted_df = pair.predicted_df_
-
-        open_threshold = config["dis-equilibrium_open_trshld"]
-        close_threshold = config["dis-equilibrium_close_trshld"]
-
-        # Iterate through the testing dataset to find the first trading opportunity
-        open_row_index = None
-        for row_idx in range(len(predicted_df)):
-            curr_disequilibrium = predicted_df["scaled_disequilibrium"][row_idx]
-
-            # Check if current row has sufficient disequilibrium (not near-zero)
-            if curr_disequilibrium >= open_threshold:
-                open_row_index = row_idx
-                break
-
-        # If no row with sufficient disequilibrium found, skip this pair
-        if open_row_index is None:
-            print(f"{pair}: Insufficient disequilibrium in testing dataset. Skipping.")
-            return pd.DataFrame()
-
-        # Look for close signal starting from the open position
-        trading_signals_df = (
-            predicted_df["scaled_disequilibrium"][open_row_index:] < close_threshold
-        )
-
-        # Adjust indices to account for the offset from open_row_index
-        close_row_index = None
-        for idx, value in trading_signals_df.items():
-            if value:
-                close_row_index = idx
-                break
-
-        open_row = predicted_df.loc[open_row_index]
-        open_tstamp = open_row["tstamp"]
-        open_disequilibrium = open_row["disequilibrium"]
-        open_scaled_disequilibrium = open_row["scaled_disequilibrium"]
-        open_px_a = open_row[f"{colname_a}"]
-        open_px_b = open_row[f"{colname_b}"]
-
-        abs_beta = abs(beta[1])
-        pred_px_b = predicted_df.loc[open_row_index][f"{colname_b}_pred"]
-        pred_px_a = predicted_df.loc[open_row_index][f"{colname_a}_pred"]
-
-        if pred_px_b * abs_beta - pred_px_a > 0:
-            open_side_a = "BUY"
-            open_side_b = "SELL"
-            close_side_a = "SELL"
-            close_side_b = "BUY"
-        else:
-            open_side_b = "BUY"
-            open_side_a = "SELL"
-            close_side_b = "SELL"
-            close_side_a = "BUY"
-
-        # If no close signal found, print position and unrealized PnL
-        if close_row_index is None:
-
-            last_row_index = len(predicted_df) - 1
-
-            # Use the new method from BacktestResult to handle outstanding positions
-            result.handle_outstanding_position(
-                pair=pair,
-                pair_result_df=predicted_df,
-                last_row_index=last_row_index,
-                open_side_a=open_side_a,
-                open_side_b=open_side_b,
-                open_px_a=open_px_a,
-                open_px_b=open_px_b,
-                open_tstamp=open_tstamp,
-            )
-
-            # Return only open trades (no close trades)
-            trd_signal_tuples = [
-                (
-                    open_tstamp,
-                    open_side_a,
-                    pair.symbol_a_,
-                    open_px_a,
-                    open_disequilibrium,
-                    open_scaled_disequilibrium,
-                    pair,
-                ),
-                (
-                    open_tstamp,
-                    open_side_b,
-                    pair.symbol_b_,
-                    open_px_b,
-                    open_disequilibrium,
-                    open_scaled_disequilibrium,
-                    pair,
-                ),
-            ]
-        else:
-            # Close signal found - create complete trade
-            close_row = predicted_df.loc[close_row_index]
-            close_tstamp = close_row["tstamp"]
-            close_disequilibrium = close_row["disequilibrium"]
-            close_scaled_disequilibrium = close_row["scaled_disequilibrium"]
-            close_px_a = close_row[f"{colname_a}"]
-            close_px_b = close_row[f"{colname_b}"]
-
-            print(f"{pair}: Close signal found at index {close_row_index}")
-
-            trd_signal_tuples = [
-                (
-                    open_tstamp,
-                    open_side_a,
-                    pair.symbol_a_,
-                    open_px_a,
-                    open_disequilibrium,
-                    open_scaled_disequilibrium,
-                    pair,
-                ),
-                (
-                    open_tstamp,
-                    open_side_b,
-                    pair.symbol_b_,
-                    open_px_b,
-                    open_disequilibrium,
-                    open_scaled_disequilibrium,
-                    pair,
-                ),
-                (
-                    close_tstamp,
-                    close_side_a,
-                    pair.symbol_a_,
-                    close_px_a,
-                    close_disequilibrium,
-                    close_scaled_disequilibrium,
-                    pair,
-                ),
-                (
-                    close_tstamp,
-                    close_side_b,
-                    pair.symbol_b_,
-                    close_px_b,
-                    close_disequilibrium,
-                    close_scaled_disequilibrium,
-                    pair,
-                ),
-            ]
-
-        # Add tuples to data frame
-        return pd.DataFrame(
-            trd_signal_tuples,
-            columns=self.TRADES_COLUMNS,
-        )
-
-class SlidingFitStrategy(PairsTradingStrategy):
-    def __init__(self):
-        super().__init__()
-        self.curr_training_start_idx_ = 0 
-           
-    def run_pair(self, config: Dict, pair: TradingPair, bt_result: BacktestResult) -> Optional[pd.DataFrame]: 
-        pair.user_data_['is_position_open'] = False
-        training_minutes = config["training_minutes"]
-        while True:
-            pair.get_datasets(
-                training_minutes=training_minutes, 
-                training_start_index=self.curr_training_start_idx_, 
-                testing_size=1
-            )
-            
-            if len(pair.training_df_) < training_minutes:
-                print(f"{pair}: Not enough training data. Completing the job.")
-                break
-            
-            try:
-                is_cointegrated = pair.train_pair()
-                if not is_cointegrated:
-                    print(f"{pair} IS NOT COINTEGRATED")
-                    return None
-            except Exception as e:
-                print(f"{pair}: Training failed: {str(e)}")
-                return None
-
-            try:
-                pair.predict()
-            except Exception as e:
-                print(f"{pair}: Prediction failed: {str(e)}")
-                return None
-        
-
-            pair_trades = self.create_trading_signals(pair=pair, config=config, result=bt_result)
-
-        return pair_trades
-

src/tools/data_loader.py

@@ -1,99 +0,0 @@
-import sys
-import sqlite3
-from typing import Dict, Tuple
-import pandas as pd
-
-from tools.trading_pair import TradingPair
-
-
-def load_sqlite_to_dataframe(db_path, query):
-    try:
-        conn = sqlite3.connect(db_path)
-
-        df = pd.read_sql_query(query, conn)
-        return df
-    except sqlite3.Error as excpt:
-        print(f"SQLite error: {excpt}")
-        raise
-    except Exception as e:
-        print(f"Error: {excpt}")
-        raise
-    finally:
-        if "conn" in locals():
-            conn.close()
-
-
-def convert_time_to_UTC(value: str, timezone: str):
-
-    from zoneinfo import ZoneInfo
-    from datetime import datetime
-
-    # Parse it to naive datetime object
-    local_dt = datetime.strptime(value, "%Y-%m-%d %H:%M:%S")
-
-    zinfo = ZoneInfo(timezone)
-    result = local_dt.replace(tzinfo=zinfo)
-
-    result = result.astimezone(ZoneInfo("UTC"))
-    result = result.strftime("%Y-%m-%d %H:%M:%S")
-
-    return result
-
-
-def load_market_data(datafile: str, config: Dict) -> pd.DataFrame:
-    from tools.data_loader import load_sqlite_to_dataframe
-
-    instrument_ids = [
-        '"' + config["instrument_id_pfx"] + instrument + '"'
-        for instrument in config["instruments"]
-    ]
-    security_type = config["security_type"]
-    exchange_id = config["exchange_id"]
-
-    query = "select"
-    if security_type == "CRYPTO":
-        query += " strftime('%Y-%m-%d %H:%M:%S', tstamp/1000000000, 'unixepoch') as tstamp"
-        query += ", tstamp as time_ns"
-    else:
-        query += " tstamp"
-        query += ", tstamp_ns as time_ns"
-
-    query += f", substr(instrument_id, {len(config['instrument_id_pfx']) + 1}) as symbol"
-    query += ", open"
-    query += ", high"
-    query += ", low"
-    query += ", close"
-    query += ", volume"
-    query += ", num_trades"
-    query += ", vwap"
-
-    query += f" from {config['db_table_name']}"
-    query += f" where exchange_id ='{exchange_id}'"
-    query += f" and instrument_id in ({','.join(instrument_ids)})"
-
-    df = load_sqlite_to_dataframe(db_path=datafile, query=query)
-
-    # Trading Hours
-    date_str = df["tstamp"][0][0:10]
-    trading_hours = config["trading_hours"]
-
-    start_time = convert_time_to_UTC(
-        f"{date_str} {trading_hours['begin_session']}", trading_hours["timezone"]
-    )
-    end_time = convert_time_to_UTC(
-        f"{date_str} {trading_hours['end_session']}", trading_hours["timezone"]
-    )
-
-    # Perform boolean selection
-    df = df[(df["tstamp"] >= start_time) & (df["tstamp"] <= end_time)]
-    df["tstamp"] = pd.to_datetime(df["tstamp"])
-
-    return df
-
-
-
-
-# if __name__ == "__main__":
-#     df1 = load_sqlite_to_dataframe(sys.argv[1], table_name="md_1min_bars")
-
-#     print(df1)

src/tools/trading_pair.py

@@ -1,145 +0,0 @@
-
-from typing import List, Optional
-import pandas as pd
-from statsmodels.tsa.vector_ar.vecm import VECM
-
-class TradingPair:
-    market_data_: pd.DataFrame
-    symbol_a_: str
-    symbol_b_: str
-    price_column_: str
-
-    training_mu_: Optional[float]
-    training_std_: Optional[float]
-
-    training_df_: Optional[pd.DataFrame]
-    testing_df_: Optional[pd.DataFrame]
-
-    vecm_fit_: Optional[VECM]
-
-    def __init__(self, market_data: pd.DataFrame, symbol_a: str, symbol_b: str, price_column: str):
-        self.symbol_a_ = symbol_a
-        self.symbol_b_ = symbol_b
-        self.price_column_ = price_column
-        self.market_data_ = self._transform_dataframe(market_data)[["tstamp"] + self.colnames()]
-        
-        
-        self.training_mu_ = None
-        self.training_std_ = None
-        self.training_df_ = None
-        self.testing_df_ = None
-        self.vecm_fit_ = None
-
-    def _transform_dataframe(self, df: pd.DataFrame):
-        # Select only the columns we need
-        df_selected = df[["tstamp", "symbol", self.price_column_]]
-
-        # Start with unique timestamps
-        result_df: pd.DataFrame = pd.DataFrame(df_selected["tstamp"]).drop_duplicates().reset_index(drop=True)
-
-        # For each unique symbol, add a corresponding close price column
-        for symbol in df_selected["symbol"].unique():
-            # Filter rows for this symbol
-            df_symbol = df_selected[df_selected["symbol"] == symbol].reset_index(drop=True)
-
-            # Create column name like "close-COIN"
-            new_price_column = f"{self.price_column_}_{symbol}"
-
-            # Create temporary dataframe with timestamp and price
-            temp_df = pd.DataFrame({
-                "tstamp": df_symbol["tstamp"],
-                new_price_column: df_symbol[self.price_column_]
-            })
-
-            # Join with our result dataframe
-            result_df = pd.merge(result_df, temp_df, on="tstamp", how="left")
-            result_df = result_df.reset_index(drop=True) # do not dropna() since irrelevant symbol would affect dataset
-
-        return result_df
-    def get_datasets(self, training_minutes: int, training_start_index: int = 0, testing_size: Optional[int] = None) -> None:
-        self.training_df_ = self.market_data_.iloc[training_start_index:training_minutes - 1, :].copy()
-        self.training_df_ = self.training_df_.dropna().reset_index(drop=True)
-
-        testing_start_index = training_start_index + training_minutes
-        if testing_size is None:
-            self.testing_df_ = self.market_data_.iloc[testing_start_index:, :].copy()
-        else:
-            self.testing_df_ = self.market_data_.iloc[testing_start_index:testing_start_index + testing_size, :].copy()
-        self.testing_df_ = self.testing_df_.dropna().reset_index(drop=True)
-
-    def colnames(self) -> List[str]:
-        return [f"{self.price_column_}_{self.symbol_a_}", f"{self.price_column_}_{self.symbol_b_}"]
-
-    def fit_VECM(self):
-        vecm_df = self.training_df_[self.colnames()].reset_index(drop=True)
-        vecm_model = VECM(vecm_df, coint_rank=1)
-        vecm_fit = vecm_model.fit()
-
-        # URGENT check beta and alpha
-
-        # Check if the model converged properly
-        if not hasattr(vecm_fit, "beta") or vecm_fit.beta is None:
-            print(f"{self}: VECM model failed to converge properly")
-
-        self.vecm_fit_ = vecm_fit
-        # print(f"{self}: beta={self.vecm_fit_.beta} alpha={self.vecm_fit_.alpha}"  )
-        # print(f"{self}: {self.vecm_fit_.summary()}")
-        pass
-
-    def check_cointegration(self):
-        from statsmodels.tsa.vector_ar.vecm import coint_johansen
-        df = self.training_df_[self.colnames()].reset_index(drop=True)
-        result = coint_johansen(df, det_order=0, k_ar_diff=1)
-        # print(f"{self}: lr1={result.lr1[0]} cvt={result.cvt[0, 1]}.")
-        is_cointegrated = result.lr1[0] > result.cvt[0, 1]
-
-        return is_cointegrated
-
-    def train_pair(self) -> bool:
-        is_cointegrated = self.check_cointegration()
-        if not is_cointegrated:
-            return False
-            pass
-
-        print('*' * 80 + '\n' + f"**************** {self} IS COINTEGRATED ****************\n" + '*' * 80)
-        self.fit_VECM()
-        diseq_series = self.training_df_[self.colnames()] @ self.vecm_fit_.beta
-        self.training_mu_ = diseq_series.mean().iloc[0]
-        self.training_std_ = diseq_series.std().iloc[0]
-
-        self.training_df_["dis-equilibrium"] = self.training_df_[self.colnames()] @ self.vecm_fit_.beta
-        # Normalize the dis-equilibrium
-        self.training_df_["scaled_dis-equilibrium"] = (
-            diseq_series - self.training_mu_
-        ) / self.training_std_
-
-        return True
-
-    def predict(self) -> None:
-        predicted_prices = self.vecm_fit_.predict(steps=len(self.testing_df_))
-
-        # Convert prediction to a DataFrame for readability
-        # predicted_df = 
-
-        self.predicted_df_ = pd.merge(
-            self.testing_df_.reset_index(drop=True),
-            pd.DataFrame(predicted_prices, columns=self.colnames()),
-            left_index=True,
-            right_index=True,
-            suffixes=("", "_pred"),
-        ).dropna()
-
-        self.predicted_df_["disequilibrium"] = self.predicted_df_[self.colnames()] @ self.vecm_fit_.beta
-
-        self.predicted_df_["scaled_disequilibrium"] = (
-            abs(self.predicted_df_["disequilibrium"] - self.training_mu_) / self.training_std_
-        )
-
-        # Reset index to ensure proper indexing
-        self.predicted_df_ = self.predicted_df_.reset_index()
-        return self.predicted_df_
-
-        
-    def __repr__(self) ->str:
-        return f"{self.symbol_a_} & {self.symbol_b_}"
-