Release 0.0.1

.gitignore

@@ -3,9 +3,8 @@ __pycache__/
 __OLD__/
 .specstory/
 .history/
-.cursorindexingignore
+.vscode/
 data
 cvttpy
-# SpecStory explanation file
-.specstory/.what-is-this.md
 results/
+tmp/

.vscode/.env

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

.vscode/launch.json

@@ -1,158 +0,0 @@
-{
-    // 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": "${workspaceFolder}/..",
-                "CONFIG_SERVICE": "cloud16.cvtt.vpn:6789",
-                "MODEL_CONFIG": "vecm",
-                "CVTT_URL": "http://cvtt-tester-01.cvtt.vpn:23456",
-                // "CVTT_URL": "http://dev-server-02.cvtt.vpn:23456",
-            },
-            "args": [
-                // "--config=${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": "-------- 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

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

.vscode/settings.json

@@ -1,19 +0,0 @@
-{
-    "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,
-}

AGENTS.md

@@ -0,0 +1,149 @@
+# Agent Instructions
+
+## Repository purpose
+
+This repository analyzes test results with Jupyter notebooks and Python or
+Bash scripts. Inputs are commonly SQLite databases containing time-series data
+and JSON columns, but analyses may use other test-result formats.
+
+Ignore `__SAV__/`. It is unrelated legacy material, is not part of the active
+project, and must not be read, edited, moved, or used as a source of conventions
+unless the user explicitly requests it.
+
+## Active layout
+
+- `notebooks/`: exploratory and report-oriented Jupyter notebooks.
+- `scripts/`: reusable Python and Bash analysis utilities.
+- `data/`: local input data. Contents are ignored except for `.gitkeep`.
+- `results/`: generated tables, figures, exports, and reports. Contents are
+  ignored except for `.gitkeep`.
+- `requirements.txt`: Python dependencies needed to reproduce repository work.
+
+Keep reusable logic in `scripts/` and use notebooks to orchestrate analysis,
+explain decisions, and present results. Do not create a separate `analysis/`
+tree.
+
+## Python environment
+
+The intended virtual environment is `~/.pyenv/python3.12-venv`.
+
+```bash
+source ~/.pyenv/python3.12-venv/bin/activate
+python -m pip install -r requirements.txt
+```
+
+Agents may install packages in this environment when needed. Whenever a package
+is installed for repository work, update `requirements.txt` in the same change
+with a suitable direct dependency declaration. Use `python -m pip`, not bare
+`pip`, in documented commands.
+
+Do not create an in-repository virtual environment unless the user asks for
+one.
+
+## Data handling
+
+- Treat files in `data/` as local, potentially large, and potentially
+  sensitive.
+- Do not commit SQLite databases, raw test results, or generated results.
+- Do not modify source data in place. Write transformed data and exports under
+  `results/`.
+- Use parameterized SQL for values. Do not construct SQL by interpolating
+  untrusted data.
+- Parse JSON columns defensively and preserve missing, malformed, and unexpected
+  values unless the analysis explicitly defines another policy.
+- State assumptions about timestamps, time zones, ordering, units, and duplicate
+  observations in the notebook or script that relies on them.
+- Avoid loading entire databases into memory when a filtered query or chunked
+  read is practical.
+
+## Notebook conventions
+
+- A notebook must run from a fresh kernel, top to bottom, without relying on
+  hidden interactive state.
+- Set random seeds where nondeterminism affects results.
+- Keep data paths relative to the repository root and avoid machine-specific
+  absolute paths.
+- Move logic that is reused or substantial enough to test into `scripts/`.
+- Clear cell outputs before committing notebooks. Never commit embedded source
+  data, credentials, or bulky generated output.
+- Keep concise Markdown context near analyses: purpose, input assumptions,
+  method, and interpretation.
+
+## Scripts
+
+- Python scripts should expose reusable functions and use a guarded CLI entry
+  point when executable.
+- Bash scripts must start with `#!/usr/bin/env bash` and use
+  `set -euo pipefail`.
+- Prefer explicit CLI arguments over hard-coded paths or parameters.
+- Fail with actionable error messages when required data, tables, columns, or
+  configuration are missing.
+
+## Verification
+
+Verification should be proportional to the change. At minimum:
+
+- Run `pytest` for Python script changes.
+- Add or update tests for reusable parsing, transformation, query, and
+  calculation logic.
+- Execute changed notebooks from a fresh kernel with `nbmake`.
+- Run changed Bash scripts against a safe fixture or exercise their
+  non-destructive validation/help path.
+- Clear notebook outputs after execution and before committing.
+
+Useful commands:
+
+```bash
+python -m pytest
+python -m pytest --nbmake notebooks
+jupyter nbconvert --ClearOutputPreprocessor.enabled=True --inplace path/to/notebook.ipynb
+```
+
+If verification cannot be run, report exactly what was skipped and why.
+
+## Release rules
+
+- Update `CHANGELOG.md` for every release with the release version, release
+  date, Git tag, and a concise summary of notable changes.
+- Use release headers in `YYYY-MM-DD vMAJOR.MINOR.PATCH` form.
+- Use version numbers in `MAJOR.MINOR.PATCH` form. Start this repository at
+  `0.0.1`.
+- Use Git tags in `vMAJOR.MINOR.PATCH` form, matching the changelog version
+  exactly. For example, version `0.0.1` must be tagged as `v0.0.1`.
+- Create the Git tag only after the changelog and any release-related version
+  changes are complete.
+- Do not push release commits or tags unless the user explicitly requests it.
+
+## Mandatory background review
+
+Changes to Python scripts, Bash scripts, or notebook code cells require approval
+from a separate background reviewer agent before the implementing agent may
+declare the work complete.
+
+The implementing agent must:
+
+1. Finish the implementation and run the relevant verification.
+2. Ask a separate background agent to review the diff for correctness,
+   reproducibility, data safety, and test coverage.
+3. Address every material finding, rerun affected checks, and request follow-up
+   review when the fix materially changes the code.
+4. Report the reviewer outcome in the final response.
+
+The reviewer must inspect the actual diff and relevant surrounding files; a
+self-review does not satisfy this requirement. Documentation-only,
+configuration-only, dependency-only, and ignore-rule-only changes do not
+require background approval unless they also alter Python, Bash, or notebook
+code cells.
+
+If no background reviewer is available, complete all other work but do not
+claim reviewer approval. End the handoff with the exact status:
+
+`review pending`
+
+## Change discipline
+
+- Preserve user changes and avoid unrelated cleanup.
+- Do not edit or commit generated files from `data/` or `results/`.
+- Do not push or commit unless the user explicitly requests it. The `master`
+  branch being unprotected does not imply permission to push directly.
+- Keep changes focused and explain any new assumptions or dependencies.

CHANGELOG.md

@@ -0,0 +1,7 @@
+# Changelog
+
+All notable changes to this project are documented in this file.
+
+## 2026-07-25 v0.0.1
+
+- Established the initial repository structure and project guidance.

LIBRARIES

@@ -1,2 +0,0 @@
-cvttpy_tools: 1.3.4
-cvttpy_trading: 2.4.1

VERSION

@@ -1 +0,0 @@
-0.0.3

__SAV__/CHANGELOG.md

@@ -0,0 +1,2 @@
+## 2026-02-09 (v0.0.9)
+- related to the changes made in *cvttpy_tools 1.4.7*

__SAV__/VERSION

@@ -0,0 +1 @@
+0.0.9

__SAV__/apps/pair_selector/pair_selector.py

@@ -0,0 +1,937 @@
+from __future__ import annotations
+
+import asyncio
+import os
+import sqlite3
+from dataclasses import dataclass
+from typing import Any, Dict, List, Optional, Sequence, Set, Tuple, Union
+
+from aiohttp import web
+import numpy as np
+import pandas as pd
+from statsmodels.tsa.stattools import adfuller, coint # type: ignore
+from statsmodels.tsa.vector_ar.vecm import coint_johansen  # type: ignore
+
+
+from cvttpy_tools.base.app import App
+from cvttpy_tools.base.base import NamedObject
+from cvttpy_tools.base.config import Config, CvttAppConfig
+from cvttpy_tools.base.logger import Log
+from cvttpy_tools.base.timeutils import NanoPerSec, SecPerHour, current_nanoseconds
+from cvttpy_tools.comm.web.rest_service import RestService
+
+from cvttpy_trading.trading.exchange_config import ExchangeAccounts
+from cvttpy_trading.trading.instrument import ExchangeInstrument
+from cvttpy_trading.trading.mkt_data.md_summary import MdTradesAggregate, MdSummary
+
+from pairs_trading.apps.pair_selector.renderer import HtmlRenderer
+from pairs_trading.lib.live.rest import RESTSender
+
+
+@dataclass
+class BacktestAggregate:
+    aggr_time_ns_: int
+    num_trades_: Optional[int]
+
+
+@dataclass
+class InstrumentQuality(NamedObject):
+    instrument_: ExchangeInstrument
+    record_count_: int
+    latest_tstamp_: Optional[pd.Timestamp]
+    status_: str
+    reason_: str
+
+
+@dataclass
+class PairStats(NamedObject):
+    pair_name_: str
+    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 {
+            "exchange_a": self.instrument_a_.exchange_id_,
+            "exchange_b": self.instrument_b_.exchange_id_,
+            "pair_name": self.pair_name_,
+            "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_,
+        }
+
+
+def _extract_price_from_fields(
+    price_field: str,
+    inst: ExchangeInstrument,
+    open: Optional[float],
+    high: Optional[float],
+    low: Optional[float],
+    close: Optional[float],
+    vwap: Optional[float],
+) -> float:
+    field_map = {
+        "open": open,
+        "high": high,
+        "low": low,
+        "close": close,
+        "vwap": vwap,
+    }
+    raw = field_map.get(price_field, close)
+    if raw is None:
+        raw = 0.0
+    return inst.get_price(raw)
+
+
+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
+        ]
+
+
+AggregateLike = Union[MdTradesAggregate, BacktestAggregate]
+
+
+class QualityChecker(NamedObject):
+    interval_sec_: int
+
+    def __init__(self, interval_sec: int) -> None:
+        self.interval_sec_ = interval_sec
+
+    def evaluate(
+        self,
+        inst: ExchangeInstrument,
+        aggr: Sequence[AggregateLike],
+        now_ts: Optional[pd.Timestamp] = None,
+    ) -> 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 = now_ts or 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: Sequence[AggregateLike]) -> 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: Optional[int], next_nt: Optional[int]) -> float:
+        if prev_nt is None and next_nt is None:
+            return 0.0
+        if prev_nt is None:
+            return float(next_nt or 0)
+        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]
+    ) -> Dict[str, PairStats]:
+        instruments = list(series.keys())
+        results: Dict[str, PairStats] = {}
+        for i in range(len(instruments)):
+            for j in range(i + 1, len(instruments)):
+                inst_a, inst_b, pair_name = self._normalized_pair(
+                    instruments[i], 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"
+                )
+                # Log.info(f"{self.fname()}: analyzing {pair_name}")
+                stats = self._compute_stats(inst_a, inst_b, pair_name, merged)
+                if stats:
+                    results[pair_name] = stats
+        return self._rank(results)
+
+    def _compute_stats(
+        self,
+        inst_a: ExchangeInstrument,
+        inst_b: ExchangeInstrument,
+        pair_name: str,
+        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(
+            pair_name_=pair_name,
+            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: Dict[str, PairStats]) -> Dict[str, PairStats]:
+        ranked = list(results.values())
+        self._assign_ranks(ranked, key=lambda r: r.pvalue_eg_, attr="rank_eg_")
+        self._assign_ranks(ranked, key=lambda r: r.pvalue_adf_, attr="rank_adf_")
+        self._assign_ranks(ranked, key=lambda r: r.pvalue_j_, attr="rank_j_")
+        for res in ranked:
+            res.composite_rank_ = res.rank_eg_ + res.rank_adf_ # + res.rank_j_
+        ranked.sort(key=lambda r: r.composite_rank_)
+        return {res.pair_name_: res for res in ranked}
+
+    @staticmethod
+    def _normalized_pair(
+        inst_a: ExchangeInstrument, inst_b: ExchangeInstrument
+    ) -> Tuple[ExchangeInstrument, ExchangeInstrument, str]:
+        inst_a_id = PairAnalyzer._pair_label(inst_a.instrument_id())
+        inst_b_id = PairAnalyzer._pair_label(inst_b.instrument_id())
+        if inst_a_id <= inst_b_id:
+            return inst_a, inst_b, f"{inst_a_id}<->{inst_b_id}"
+        return inst_b, inst_a, f"{inst_b_id}<->{inst_a_id}"
+
+    @staticmethod
+    def _pair_label(instrument_id: str) -> str:
+        if instrument_id.startswith("PAIR-"):
+            return instrument_id[len("PAIR-") :]
+        return instrument_id
+
+    @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_: Dict[str, 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:
+        return _extract_price_from_fields(
+            price_field=self.price_field_,
+            inst=inst,
+            open=aggr.open_,
+            high=aggr.high_,
+            low=aggr.low_,
+            close=aggr.close_,
+            vwap=aggr.vwap_,
+        )
+
+    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) -> Dict[str, Dict[str, Any]]:
+        return {
+            pair_name: stats.as_dict()
+            for pair_name, stats in self.pair_results_cache_.items()
+        }
+
+
+class PairSelectionBacktest(NamedObject):
+    config_: object
+    instruments_: List[ExchangeInstrument]
+    price_field_: str
+    input_db_: str
+    output_db_: str
+    interval_sec_: int
+    history_depth_hours_: int
+    quality_: QualityChecker
+    analyzer_: PairAnalyzer
+    inst_by_key_: Dict[Tuple[str, str], ExchangeInstrument]
+    inst_by_id_: Dict[str, Optional[ExchangeInstrument]]
+    ambiguous_ids_: Set[str]
+
+    def __init__(
+        self,
+        config: Config,
+        instruments: List[ExchangeInstrument],
+        price_field: str,
+        input_db: str,
+        output_db: str,
+    ) -> None:
+        self.config_ = config
+        self.instruments_ = instruments
+        self.price_field_ = price_field
+        self.input_db_ = input_db
+        self.output_db_ = output_db
+
+        interval_sec = int(config.get_value("interval_sec", 0))
+        if interval_sec <= 0:
+            Log.warning(
+                f"{self.fname()}: interval_sec not set; defaulting to 60 seconds"
+            )
+            interval_sec = 60
+        history_depth_hours = int(config.get_value("history_depth_hours", 0))
+        assert history_depth_hours > 0, "history_depth_hours must be > 0"
+
+        self.interval_sec_ = interval_sec
+        self.history_depth_hours_ = history_depth_hours
+        self.quality_ = QualityChecker(interval_sec=interval_sec)
+        self.analyzer_ = PairAnalyzer(
+            price_field=price_field, interval_sec=interval_sec
+        )
+
+        self.inst_by_key_ = {
+            (inst.exchange_id_, inst.instrument_id()): inst for inst in instruments
+        }
+        self.inst_by_id_ = {}
+        self.ambiguous_ids_ = set()
+        for inst in instruments:
+            inst_id = inst.instrument_id()
+            if inst_id in self.inst_by_id_:
+                existing = self.inst_by_id_[inst_id]
+                if existing is not None and existing.exchange_id_ != inst.exchange_id_:
+                    self.inst_by_id_[inst_id] = None
+                    self.ambiguous_ids_.add(inst_id)
+            elif inst_id not in self.ambiguous_ids_:
+                self.inst_by_id_[inst_id] = inst
+
+        if self.ambiguous_ids_:
+            Log.warning(
+                f"{self.fname()}: ambiguous instrument_id(s) without exchange_id: "
+                f"{sorted(self.ambiguous_ids_)}"
+            )
+
+    def run(self) -> None:
+        df = self._load_input_df()
+        if df.empty:
+            Log.warning(f"{self.fname()}: no rows in md_1min_bars")
+            return
+
+        df = self._filter_instruments(df)
+        if df.empty:
+            Log.warning(f"{self.fname()}: no rows after instrument filtering")
+            return
+
+        conn = self._init_output_db()
+        try:
+            self._run_backtest(df, conn)
+        finally:
+            conn.commit()
+            conn.close()
+
+    def _load_input_df(self) -> pd.DataFrame:
+        if not os.path.exists(self.input_db_):
+            raise FileNotFoundError(f"input_db not found: {self.input_db_}")
+        with sqlite3.connect(self.input_db_) as conn:
+            df = pd.read_sql_query(
+                """
+                SELECT
+                    tstamp,
+                    tstamp_ns,
+                    exchange_id,
+                    instrument_id,
+                    open,
+                    high,
+                    low,
+                    close,
+                    volume,
+                    vwap,
+                    num_trades
+                FROM md_1min_bars
+                """,
+                conn,
+            )
+        if df.empty:
+            return df
+
+        ts_ns = pd.to_datetime(df["tstamp_ns"], unit="ns", utc=True, errors="coerce")
+        ts_txt = pd.to_datetime(df["tstamp"], utc=True, errors="coerce")
+        df["tstamp"] = ts_ns.fillna(ts_txt)
+        df = df.dropna(subset=["tstamp", "instrument_id"]).copy()
+        df["exchange_id"] = df["exchange_id"].fillna("")
+        df["instrument_id"] = df["instrument_id"].astype(str)
+        df["tstamp_ns"] = df["tstamp"].astype("int64")
+        return df.sort_values("tstamp").reset_index(drop=True)
+
+    def _filter_instruments(self, df: pd.DataFrame) -> pd.DataFrame:
+        instrument_ids = {inst.instrument_id() for inst in self.instruments_}
+        df = df[df["instrument_id"].isin(instrument_ids)].copy()
+        if "exchange_id" in df.columns:
+            exchange_ids = {inst.exchange_id_ for inst in self.instruments_}
+            df = df[
+                (df["exchange_id"].isin(exchange_ids)) | (df["exchange_id"] == "")
+            ].copy()
+        return df
+
+    def _init_output_db(self) -> sqlite3.Connection:
+        if os.path.exists(self.output_db_):
+            os.remove(self.output_db_)
+        conn = sqlite3.connect(self.output_db_)
+        conn.execute(
+            """
+            CREATE TABLE pair_selection_history (
+                tstamp TEXT,
+                tstamp_ns INTEGER,
+                pair_name TEXT,
+                exchange_a TEXT,
+                instrument_a TEXT,
+                exchange_b TEXT,
+                instrument_b TEXT,
+                pvalue_eg REAL,
+                pvalue_adf REAL,
+                pvalue_j REAL,
+                trace_stat_j REAL,
+                rank_eg INTEGER,
+                rank_adf INTEGER,
+                rank_j INTEGER,
+                composite_rank REAL
+            )
+            """
+        )
+        conn.execute(
+            """
+            CREATE INDEX idx_pair_selection_history_pair_name
+            ON pair_selection_history (pair_name)
+            """
+        )
+        conn.execute(
+            """
+            CREATE UNIQUE INDEX idx_pair_selection_history_tstamp_pair
+            ON pair_selection_history (tstamp, pair_name)
+            """
+        )
+        conn.commit()
+        return conn
+
+    def _resolve_instrument(
+        self, exchange_id: str, instrument_id: str
+    ) -> Optional[ExchangeInstrument]:
+        if exchange_id:
+            inst = self.inst_by_key_.get((exchange_id, instrument_id))
+            if inst is not None:
+                return inst
+        inst = self.inst_by_id_.get(instrument_id)
+        if inst is None and instrument_id in self.ambiguous_ids_:
+            return None
+        return inst
+
+    def _build_day_series(
+        self, df_day: pd.DataFrame
+    ) -> Dict[ExchangeInstrument, pd.DataFrame]:
+        series: Dict[ExchangeInstrument, pd.DataFrame] = {}
+        group_cols = ["exchange_id", "instrument_id"]
+        for key, group in df_day.groupby(group_cols, dropna=False):
+            exchange_id, instrument_id = key
+            inst = self._resolve_instrument(str(exchange_id or ""), str(instrument_id))
+            if inst is None:
+                continue
+            df_inst = group.copy()
+            df_inst["price"] = [
+                _extract_price_from_fields(
+                    price_field=self.price_field_,
+                    inst=inst,
+                    open=float(row.open), #type: ignore
+                    high=float(row.high), #type: ignore
+                    low=float(row.low), #type: ignore
+                    close=float(row.close), #type: ignore
+                    vwap=float(row.vwap),#type: ignore
+                )
+                for row in df_inst.itertuples(index=False)
+            ]
+            df_inst = df_inst[["tstamp", "tstamp_ns", "price", "num_trades"]]
+            if inst in series:
+                series[inst] = pd.concat([series[inst], df_inst], ignore_index=True)
+            else:
+                series[inst] = df_inst
+        for inst in list(series.keys()):
+            series[inst] = series[inst].sort_values("tstamp").reset_index(drop=True)
+        return series
+
+    def _run_backtest(self, df: pd.DataFrame, conn: sqlite3.Connection) -> None:
+        window_minutes = self.history_depth_hours_ * 60
+        window_td = pd.Timedelta(minutes=window_minutes)
+        step_td = pd.Timedelta(seconds=self.interval_sec_)
+
+        df = df.copy()
+        df["day"] = df["tstamp"].dt.normalize()
+        days = sorted(df["day"].unique())
+        for day in days:
+            day_label = pd.Timestamp(day).date()
+            df_day = df[df["day"] == day]
+            t0 = df_day["tstamp"].min()
+            t_last = df_day["tstamp"].max()
+            if t_last - t0 < window_td:
+                Log.warning(
+                    f"{self.fname()}: skipping {day_label} (insufficient data)"
+                )
+                continue
+
+            day_series = self._build_day_series(df_day)
+            if len(day_series) < 2:
+                Log.warning(
+                    f"{self.fname()}: skipping {day_label} (insufficient instruments)"
+                )
+                continue
+
+            start = t0
+            expected_end = start + window_td
+            while expected_end <= t_last:
+                window_slices: Dict[ExchangeInstrument, pd.DataFrame] = {}
+                ts: Optional[pd.Timestamp] = None
+                for inst, df_inst in day_series.items():
+                    df_win = df_inst[
+                        (df_inst["tstamp"] >= start)
+                        & (df_inst["tstamp"] < expected_end)
+                    ]
+                    if df_win.empty:
+                        continue
+                    window_slices[inst] = df_win
+                    last_ts = df_win["tstamp"].iloc[-1]
+                    if ts is None or last_ts > ts:
+                        ts = last_ts
+
+                if window_slices and ts is not None:
+                    price_series: Dict[ExchangeInstrument, pd.DataFrame] = {}
+                    for inst, df_win in window_slices.items():
+                        aggr = self._to_backtest_aggregates(df_win)
+                        q = self.quality_.evaluate(
+                            inst=inst, aggr=aggr, now_ts=ts
+                        )
+                        if q.status_ != "PASS":
+                            continue
+                        price_series[inst] = df_win[["tstamp", "price"]]
+                    pair_results = self.analyzer_.analyze(price_series)
+                    Log.info(f"{self.fname()}: Saving Results for window ending {ts}")
+                    self._insert_results(conn, ts, pair_results)
+
+                start = start + step_td
+                expected_end = start + window_td
+
+    @staticmethod
+    def _to_backtest_aggregates(df_win: pd.DataFrame) -> List[BacktestAggregate]:
+        aggr: List[BacktestAggregate] = []
+        for tstamp_ns, num_trades in zip(df_win["tstamp_ns"], df_win["num_trades"]):
+            nt = None if pd.isna(num_trades) else int(num_trades)
+            aggr.append(
+                BacktestAggregate(aggr_time_ns_=int(tstamp_ns), num_trades_=nt)
+            )
+        return aggr
+
+    @staticmethod
+    def _insert_results(
+        conn: sqlite3.Connection,
+        ts: pd.Timestamp,
+        pair_results: Dict[str, PairStats],
+    ) -> None:
+        if not pair_results:
+            return
+        iso = ts.isoformat()
+        ns = int(ts.value)
+        rows = []
+        for pair_name in sorted(pair_results.keys()):
+            stats = pair_results[pair_name]
+            rows.append(
+                (
+                    iso,
+                    ns,
+                    pair_name,
+                    stats.instrument_a_.exchange_id_,
+                    stats.instrument_a_.instrument_id(),
+                    stats.instrument_b_.exchange_id_,
+                    stats.instrument_b_.instrument_id(),
+                    stats.pvalue_eg_,
+                    stats.pvalue_adf_,
+                    stats.pvalue_j_,
+                    stats.trace_stat_j_,
+                    stats.rank_eg_,
+                    stats.rank_adf_,
+                    stats.rank_j_,
+                    stats.composite_rank_,
+                )
+            )
+        conn.executemany(
+            """
+            INSERT INTO pair_selection_history (
+                tstamp,
+                tstamp_ns,
+                pair_name,
+                exchange_a,
+                instrument_a,
+                exchange_b,
+                instrument_b,
+                pvalue_eg,
+                pvalue_adf,
+                pvalue_j,
+                trace_stat_j,
+                rank_eg,
+                rank_adf,
+                rank_j,
+                composite_rank
+            ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+            """,
+            rows,
+        )
+        conn.commit()
+
+
+
+class PairSelector(NamedObject):
+    instruments_: List[ExchangeInstrument]
+    engine_: PairSelectionEngine
+    rest_service_: Optional[RestService]
+    backtest_: Optional[PairSelectionBacktest]
+
+    def __init__(self) -> None:
+        App.instance().add_cmdline_arg("--oneshot", action="store_true", default=False)
+        App.instance().add_cmdline_arg("--backtest", action="store_true", default=False)
+        App.instance().add_cmdline_arg("--input_db", default=None)
+        App.instance().add_cmdline_arg("--output_db", default=None)
+        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.backtest_ = None
+        self.rest_service_ = None
+        if App.instance().get_argument("backtest", False):
+            input_db = App.instance().get_argument("input_db", None)
+            output_db = App.instance().get_argument("output_db", None)
+            if not input_db or not output_db:
+                raise ValueError(
+                    "--input_db and --output_db are required when --backtest is set"
+                )
+            self.backtest_ = PairSelectionBacktest(
+                config=cfg,
+                instruments=self.instruments_,
+                price_field=price_field,
+                input_db=input_db,
+                output_db=output_db,
+            )
+            return
+
+        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:
+        if App.instance().get_argument("backtest", False):
+            if self.backtest_ is None:
+                raise RuntimeError("backtest runner not initialized")
+            self.backtest_.run()
+            return
+        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=HtmlRenderer.render_data_quality(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=HtmlRenderer.render_pairs(pairs), content_type="text/html"
+        )
+
+
+if __name__ == "__main__":
+    App()
+    CvttAppConfig()
+    PairSelector()
+    App.instance().run()

__SAV__/apps/pair_selector/renderer.py

@@ -0,0 +1,138 @@
+from __future__ import annotations
+
+from typing import Any, Dict, List
+
+
+from cvttpy_tools.base.app import App
+from cvttpy_tools.base.base import NamedObject
+from cvttpy_tools.base.config import CvttAppConfig
+
+
+class HtmlRenderer(NamedObject):
+    def __init__(self) -> None:
+        pass
+
+    @staticmethod
+    def render_data_quality(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>
+"""
+
+    @staticmethod
+    def render_pairs(pairs: Dict[str, Dict[str, Any]]) -> str:
+        if not pairs:
+            body = "<p>No pairs available. Check data quality and try again.</p>"
+        else:
+            body_rows = []
+            for pair_name, p in pairs.items():
+                body_rows.append(
+                    "<tr>"
+                    f"<td>{pair_name}</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>Pair</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>
+"""

__SAV__/apps/pair_trader.py

@@ -4,13 +4,13 @@ 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.base.app import App
+from cvttpy_tools.base.config import Config
+from cvttpy_tools.base.base import NamedObject
+from cvttpy_tools.base.config import CvttAppConfig
+from cvttpy_tools.base.logger import Log
 from cvttpy_tools.settings.cvtt_types import BookIdT
-from cvttpy_tools.web.rest_service import RestService
+from cvttpy_tools.comm.web.rest_service import RestService
 
 # ---
 from cvttpy_trading.trading.instrument import ExchangeInstrument

__SAV__/build-dist.sh

@@ -136,6 +136,9 @@ echo "Release version: ${release_version}"
 confirm
 
 version_tag="v${release_version}"
+if [ "$(git tag -l "${version_tag}")" != "" ]; then
+    version_tag="${version_tag}.$(date +%Y%m%d_%H%M)"
+fi
 version_comment="'${version_tag} ${project} ${branch} $(date +%Y-%m-%d)\n${whats_new}'"
 
 cmd_arr=()

__SAV__/lib/live/mkt_data_client.py

@@ -1,86 +1,82 @@
 from __future__ import annotations
 
 import asyncio
-from typing import Callable, Coroutine, Dict, Any, List, Optional, Set
+from typing import Dict, Any, List, Optional, Set
 
 import requests
 
-from cvttpy_tools.base import NamedObject
-from cvttpy_tools.app import App
-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, NanoPerSec
+from cvttpy_tools.base.base import NamedObject
+from cvttpy_tools.base.logger import Log
+from cvttpy_tools.base.config import Config
+from cvttpy_tools.base.timer import Timer
+from cvttpy_tools.base.timeutils import NanosT, current_seconds
 from cvttpy_tools.settings.cvtt_types import InstrumentIdT, IntervalSecT
-
 # ---
-from cvttpy_trading.trading.mkt_data.historical_md import HistMdBar
 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
+from cvttpy_trading.trading.mkt_data.md_summary import MdTradesAggregate, MdSummary, MdSummaryCallbackT
 from cvttpy_trading.trading.exchange_config import ExchangeAccounts
-
 # ---
-from pairs_trading.lib.live.rest_client import RESTSender
+from pairs_trading.lib.live.rest import RESTSender
 
 
-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
+# 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
+#     @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
+#     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]
+# MdSummaryCallbackT = Callable[[List[MdTradesAggregate]], Coroutine]
 
 
 class MdSummaryCollector(NamedObject):
@@ -196,8 +192,9 @@ class MdSummaryCollector(NamedObject):
         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_ + 5
+        return (curr_sec - curr_sec % self.interval_sec_) + self.interval_sec_ + ALLOW_LAG_SEC
 
     async def _load_new(self) -> None:
 

__SAV__/lib/live/rest.py

@@ -1,15 +1,14 @@
 from __future__ import annotations
 
-from typing import Dict
+from typing import Dict, Optional
 import time
 
 import requests
 
-from cvttpy_tools.base import NamedObject
-
-
+from cvttpy_tools.base.base import NamedObject
 
 class RESTSender(NamedObject):
+    # Synchronous request sernder
     session_: requests.Session
     base_url_: str
 
@@ -27,33 +26,33 @@ class RESTSender(NamedObject):
         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)
+    def send_post(
+        self, endpoint: str, post_body: Dict, headers: Optional[Dict[str, str]] = None
+    ) -> requests.Response:
 
+        if not headers:
+            headers = {"Content-Type": "application/json"}
         url = f"{self.base_url_}/{endpoint}"
         try:
             return self.session_.request(
                 method="POST",
                 url=url,
                 json=post_body,
-                headers={"Content-Type": "application/json"},
+                headers=headers,
             )
         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)
-
+    def send_get(
+        self, endpoint: str, headers: Optional[Dict[str, str]] = None
+    ) -> requests.Response:
+        if not headers:
+            headers = {}
         url = f"{self.base_url_}/{endpoint}"
         try:
-            return self.session_.request(method="GET", url=url)
+            return self.session_.request(method="GET", url=url, headers=headers)
         except requests.exceptions.RequestException as excpt:
             raise ConnectionError(
                 f"Failed to send status={excpt.response.status_code} {excpt.response.text}"  # type: ignore

__SAV__/lib/live/ti_sender.py

@@ -3,14 +3,14 @@ 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.base.base import NamedObject
+from cvttpy_tools.base.config import Config
+from cvttpy_tools.base.logger import Log
 # ---
 from cvttpy_trading.trading.trading_instructions import TradingInstructions
 # ---
-from pairs_trading.lib.live.rest_client import RESTSender
 from pairs_trading.apps.pair_trader import PairTrader
+from pairs_trading.lib.live.rest import RESTSender
 
 
 class TradingInstructionsSender(NamedObject):

__SAV__/lib/pt_strategy/live/live_strategy.py

@@ -5,12 +5,12 @@ 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.base.base import NamedObject
+from cvttpy_tools.base.app import App
+from cvttpy_tools.base.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_tools.base.timeutils import NanosT, SecPerHour, current_nanoseconds, NanoPerSec, format_nanos_utc
+from cvttpy_tools.base.logger import Log
 
 # ---
 from cvttpy_trading.trading.instrument import ExchangeInstrument
@@ -42,14 +42,14 @@ class PtLiveStrategy(NamedObject):
     # 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,
     ):
-        # import copy
-        # self.config_ = Config(json_src=copy.deepcopy(config.data()))
         self.config_ = config
 
         self.pairs_trader_ = pairs_trader
@@ -83,7 +83,7 @@ class PtLiveStrategy(NamedObject):
         )
         assert self.history_depth_sec_ > 0, "history_depth_hours cannot be 0"
 
-        await self.pairs_trader_.subscribe_md()
+        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
@@ -99,6 +99,9 @@ class PtLiveStrategy(NamedObject):
             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__}, "
 
@@ -136,23 +139,29 @@ class PtLiveStrategy(NamedObject):
             Log.warning(f"{self.fname()} list of aggregates IS EMPTY")
             return False
 
-        ALLOWED_LAG_SEC = 5.0
         curr_ns = current_nanoseconds()
-        LAG_THRESHOLD = NanosT((self.interval_sec() + ALLOWED_LAG_SEC) * NanoPerSec)
         
         # MAYBE check market data length
-        lag_ns = curr_ns - hist_aggr[-1].aggr_time_ns_
-        if lag_ns > LAG_THRESHOLD:
+        
+        # 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_ns/NanoPerSec)} seconds:"
+                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()}"
-                # f" {hist_aggr[-1].exch_inst_.base_asset_id_}: {format_nanos_utc(hist_aggr[-1].aggr_time_ns_)}"
-                # f" {hist_aggr[-2].exch_inst_.base_asset_id_}: {format_nanos_utc(hist_aggr[-2].aggr_time_ns_)}"
             )
             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:

__SAV__/lib/pt_strategy/model_data_policy.py

@@ -8,7 +8,7 @@ from typing import Any, Dict, Optional, cast
 import numpy as np
 import pandas as pd
 
-from cvttpy_tools.config import Config
+from cvttpy_tools.base.config import Config
 
 @dataclass
 class DataWindowParams:

__SAV__/lib/pt_strategy/pt_market_data.py

@@ -6,8 +6,8 @@ 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.base.base import NamedObject
+from cvttpy_tools.base.config import Config
 from cvttpy_tools.settings.cvtt_types import JsonDictT
 
 # ---

__SAV__/lib/pt_strategy/pt_model.py

@@ -4,7 +4,7 @@ from abc import ABC, abstractmethod
 from typing import Any, Dict, cast
 
 # ---
-from cvttpy_tools.config import Config
+from cvttpy_tools.base.config import Config
 # ---
 from pairs_trading.lib.pt_strategy.prediction import Prediction
 from pairs_trading.lib.pt_strategy.trading_pair import TradingPair

__SAV__/lib/pt_strategy/research_strategy.py

@@ -4,7 +4,7 @@ from typing import Any, Dict, List, Optional, Tuple
 
 import pandas as pd
 # ---
-from cvttpy_tools.config import Config
+from cvttpy_tools.base.config import Config
 # ---
 from cvttpy_trading.trading.instrument import ExchangeInstrument
 # ---

__SAV__/lib/pt_strategy/results.py

@@ -5,7 +5,7 @@ from typing import Any, Dict, List, Optional, Tuple
 
 import pandas as pd
 # ---
-from cvttpy_tools.config import Config
+from cvttpy_tools.base.config import Config
 # ---
 from cvttpy_trading.trading.instrument import ExchangeInstrument
 # ---

__SAV__/lib/pt_strategy/trading_pair.py

@@ -8,8 +8,8 @@ from typing import Any, Dict, List
 import pandas as pd
 
 # ---
-from cvttpy_tools.base import NamedObject
-from cvttpy_tools.config import Config
+from cvttpy_tools.base.base import NamedObject
+from cvttpy_tools.base.config import Config
 # ---
 from cvttpy_trading.trading.instrument import ExchangeInstrument
 # ---

__SAV__/lib/tools/config.py

@@ -2,7 +2,7 @@ import hjson
 from typing import Dict
 from datetime import datetime
 # ---
-from cvttpy_tools.config import Config
+from cvttpy_tools.base.config import Config
 
 
 def load_config(config_path: str) -> Config:

__SAV__/lib/tools/filetools.py

@@ -2,7 +2,7 @@ import os
 import glob
 from typing import Dict, List, Tuple
 # ---
-from cvttpy_tools.config import Config
+from cvttpy_tools.base.config import Config
 # ---
 from cvttpy_trading.trading.instrument import ExchangeInstrument
 

__SAV__/research/backtest.py

@@ -4,9 +4,9 @@ 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_tools.base.app import App
+from cvttpy_tools.base.base import NamedObject
+from cvttpy_tools.base.config import CvttAppConfig
 
 # ---
 from cvttpy_trading.trading.instrument import ExchangeInstrument

__SAV__/research/notebooks/pair_select_hist.ipynb

@@ -0,0 +1,311 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Pair Selection History\n",
+        "\n",
+        "Interactive notebook for exploring pair selection history from a SQLite database.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "**Usage**\n",
+        "- Enter the SQLite `db_path` (file path).\n",
+        "- Click `Load pairs` to populate the dropdown.\n",
+        "- Select a `pair_name`, then click `Plot`.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "668ebf19",
+      "metadata": {},
+      "source": [
+        "# Settings"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "id": "c78db847",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import sqlite3\n",
+        "from pathlib import Path\n",
+        "\n",
+        "import pandas as pd\n",
+        "import plotly.express as px\n",
+        "import ipywidgets as widgets\n",
+        "from IPython.display import display\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "e7ac6adc",
+      "metadata": {},
+      "source": [
+        "# Data Loading"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "766bcf9f",
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "e0b30b1abd1b440b832fdaaa6cce8f76",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "VBox(children=(Text(value='', description='pair_db', layout=Layout(width='80%'), placeholder='/path/to/pairs.d…"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "15679f9015854d5fa7119210094fbbc8",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "Output()"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "db_path = widgets.Text(\n",
+        "    value='',\n",
+        "    placeholder='/path/to/pairs.db',\n",
+        "    description='pair_db',\n",
+        "    layout=widgets.Layout(width='80%')\n",
+        ")\n",
+        "\n",
+        "md_db_path = widgets.Text(\n",
+        "    value='',\n",
+        "    placeholder='/path/to/market_data.db',\n",
+        "    description='md_db',\n",
+        "    layout=widgets.Layout(width='80%')\n",
+        ")\n",
+        "\n",
+        "load_button = widgets.Button(description='Load pairs', button_style='info')\n",
+        "plot_button = widgets.Button(description='Plot', button_style='primary')\n",
+        "\n",
+        "pair_name = widgets.Dropdown(\n",
+        "    options=[],\n",
+        "    value=None,\n",
+        "    description='pair_name',\n",
+        "    layout=widgets.Layout(width='80%')\n",
+        ")\n",
+        "\n",
+        "status = widgets.HTML(value='')\n",
+        "output = widgets.Output()\n",
+        "\n",
+        "controls = widgets.VBox([\n",
+        "    db_path,\n",
+        "    md_db_path,\n",
+        "    widgets.HBox([load_button, plot_button]),\n",
+        "    pair_name,\n",
+        "    status,\n",
+        "])\n",
+        "\n",
+        "display(controls, output)\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "a4d47855",
+      "metadata": {},
+      "source": [
+        "# Processing"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "2c710f51",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "PLOT_WIDTH = 1100\n",
+        "PLOT_HEIGHT = 320\n",
+        "\n",
+        "def _connect(path: str):\n",
+        "    if not path:\n",
+        "        raise ValueError('Please provide db_path.')\n",
+        "    p = Path(path).expanduser().resolve()\n",
+        "    if not p.exists():\n",
+        "        raise FileNotFoundError(f'Database not found: {p}')\n",
+        "    return sqlite3.connect(p)\n",
+        "\n",
+        "\n",
+        "def _parse_tstamp(series: pd.Series) -> pd.Series:\n",
+        "    return pd.to_datetime(series, utc=True, errors='coerce').dt.tz_convert(None)\n",
+        "\n",
+        "\n",
+        "def _style_fig(fig, tmin, tmax):\n",
+        "    fig.update_layout(\n",
+        "        legend=dict(orientation='h', yanchor='bottom', y=1.02, xanchor='left', x=0),\n",
+        "        margin=dict(l=50, r=20, t=60, b=40),\n",
+        "        height=PLOT_HEIGHT,\n",
+        "        width=PLOT_WIDTH,\n",
+        "    )\n",
+        "    fig.update_xaxes(range=[tmin, tmax])\n",
+        "\n",
+        "\n",
+        "def _load_pairs(_=None):\n",
+        "    status.value = ''\n",
+        "    with output:\n",
+        "        output.clear_output()\n",
+        "    try:\n",
+        "        with _connect(db_path.value) as conn:\n",
+        "            rows = conn.execute(\n",
+        "                \"SELECT pair_name \"\n",
+        "                \"FROM pair_selection_history \"\n",
+        "                \"GROUP BY pair_name \"\n",
+        "                \"ORDER BY SUM(composite_rank), pair_name\"\n",
+        "            ).fetchall()\n",
+        "        options = [r[0] for r in rows]\n",
+        "        pair_name.options = options\n",
+        "        pair_name.value = options[0] if options else None\n",
+        "        status.value = f'Loaded {len(options)} pairs.'\n",
+        "    except Exception as exc:\n",
+        "        status.value = f\"<span style='color:#b00'>Error: {exc}</span>\"\n",
+        "\n",
+        "\n",
+        "def _plot(_=None):\n",
+        "    status.value = ''\n",
+        "    with output:\n",
+        "        output.clear_output()\n",
+        "    try:\n",
+        "        if not pair_name.value:\n",
+        "            raise ValueError('Please select a pair_name.')\n",
+        "        if not md_db_path.value:\n",
+        "            raise ValueError('Please provide md_db path.')\n",
+        "        query = (\n",
+        "            'SELECT tstamp, pvalue_eg, pvalue_adf, rank_eg, rank_adf, '\n",
+        "            'exchange_a, instrument_a, exchange_b, instrument_b '\n",
+        "            'FROM pair_selection_history '\n",
+        "            'WHERE pair_name = ? '\n",
+        "            'ORDER BY tstamp'\n",
+        "        )\n",
+        "        with _connect(db_path.value) as conn:\n",
+        "            df = pd.read_sql_query(query, conn, params=(pair_name.value,))\n",
+        "        if df.empty:\n",
+        "            raise ValueError('No data for selected pair_name.')\n",
+        "        df['tstamp'] = _parse_tstamp(df['tstamp'])\n",
+        "        df = df.dropna(subset=['tstamp'])\n",
+        "        if df.empty:\n",
+        "            raise ValueError('No valid timestamps in pair selection data.')\n",
+        "        tmin = df['tstamp'].min()\n",
+        "        tmax = df['tstamp'].max()\n",
+        "\n",
+        "        first_row = df.dropna(subset=['exchange_a', 'instrument_a', 'exchange_b', 'instrument_b']).iloc[0]\n",
+        "        ex_a = first_row['exchange_a']\n",
+        "        id_a = first_row['instrument_a']\n",
+        "        ex_b = first_row['exchange_b']\n",
+        "        id_b = first_row['instrument_b']\n",
+        "\n",
+        "        fig_p = px.line(\n",
+        "            df,\n",
+        "            x='tstamp',\n",
+        "            y=['pvalue_eg', 'pvalue_adf'],\n",
+        "            title=f'P-Values Over Time: {pair_name.value}',\n",
+        "            labels={'value': 'p-value', 'variable': 'metric', 'tstamp': 'timestamp'}\n",
+        "        )\n",
+        "        fig_p.update_layout(legend_title_text='metric')\n",
+        "        _style_fig(fig_p, tmin, tmax)\n",
+        "\n",
+        "                md_query = (\n",
+        "            'SELECT tstamp, close FROM md_1min_bars '\n",
+        "            'WHERE exchange_id = ? AND instrument_id = ? '\n",
+        "            'ORDER BY tstamp'\n",
+        "        )\n",
+        "        with _connect(md_db_path.value) as md_conn:\n",
+        "            md_a = pd.read_sql_query(md_query, md_conn, params=(ex_a, id_a))\n",
+        "            md_b = pd.read_sql_query(md_query, md_conn, params=(ex_b, id_b))\n",
+        "        if md_a.empty or md_b.empty:\n",
+        "            raise ValueError('Market data not found for selected instruments.')\n",
+        "        md_a['tstamp'] = _parse_tstamp(md_a['tstamp'])\n",
+        "        md_b['tstamp'] = _parse_tstamp(md_b['tstamp'])\n",
+        "        md_a = md_a.dropna(subset=['tstamp', 'close'])\n",
+        "        md_b = md_b.dropna(subset=['tstamp', 'close'])\n",
+        "        md_a = md_a[(md_a['tstamp'] >= tmin) & (md_a['tstamp'] <= tmax)]\n",
+        "        md_b = md_b[(md_b['tstamp'] >= tmin) & (md_b['tstamp'] <= tmax)]\n",
+        "        if md_a.empty or md_b.empty:\n",
+        "            raise ValueError('Market data is outside the pair selection time range.')\n",
+        "        md_a = md_a.sort_values('tstamp')\n",
+        "        md_b = md_b.sort_values('tstamp')\n",
+        "        md_a['scaled_close'] = (md_a['close'] - md_a['close'].iloc[0]) / md_a['close'].iloc[0] * 100\n",
+        "        md_b['scaled_close'] = (md_b['close'] - md_b['close'].iloc[0]) / md_b['close'].iloc[0] * 100\n",
+        "\n",
+        "        md_plot = pd.DataFrame({\n",
+        "            'tstamp': md_a['tstamp'],\n",
+        "            f'{ex_a}:{id_a}': md_a['scaled_close'],\n",
+        "        })\n",
+        "        md_plot = md_plot.merge(\n",
+        "            pd.DataFrame({\n",
+        "                'tstamp': md_b['tstamp'],\n",
+        "                f'{ex_b}:{id_b}': md_b['scaled_close'],\n",
+        "            }),\n",
+        "            on='tstamp',\n",
+        "            how='outer'\n",
+        "        ).sort_values('tstamp')\n",
+        "\n",
+        "        fig_m = px.line(\n",
+        "            md_plot,\n",
+        "            x='tstamp',\n",
+        "            y=[f'{ex_a}:{id_a}', f'{ex_b}:{id_b}'],\n",
+        "            title='Scaled Close Price Change (%)',\n",
+        "            labels={'value': 'scaled % change', 'variable': 'instrument', 'tstamp': 'timestamp'}\n",
+        "        )\n",
+        "        fig_m.update_layout(legend_title_text='instrument')\n",
+        "        _style_fig(fig_m, tmin, tmax)\n",
+        "\n",
+        "        with output:\n",
+        "            display(fig_p)\n",
+        "            display(fig_m)\n",
+        "    except Exception as exc:\n",
+        "        status.value = f\"<span style='color:#b00'>Error: {exc}</span>\"\n",
+        "\n",
+        "\n",
+        "load_button.on_click(_load_pairs)\n",
+        "plot_button.on_click(_plot)\n"
+      ]
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "python3.12-venv",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.12.9"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}

__SAV__/research/notebooks/pair_trading_test.ipynb

@@ -182,7 +182,7 @@
         "import os\n",
         "import importlib\n",
         "\n",
-        "from cvttpy_tools.config import Config\n",
+        "from cvttpy_tools.base.config import Config\n",
         "\n",
         "def load_config_from_file() -> Optional[Dict]:\n",
         "    global DB_TABLE_NAME\n",

configuration/__DELETE__/ols-exp.cfg

@@ -1,43 +0,0 @@
-{
-    "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

@@ -1,47 +0,0 @@
-{
-    "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

@@ -1,47 +0,0 @@
-{
-    "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

@@ -1,48 +0,0 @@
-{
-    "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",
-    }
-}