to discard

.gitignore

@@ -1,11 +1,10 @@
 # SpecStory explanation file
 __pycache__/
 __OLD__/
-.specstory/
 .history/
 .cursorindexingignore
 data
-.vscode/
+####.vscode/
 cvttpy
 # SpecStory explanation file
 .specstory/.what-is-this.md

configuration/equity.cfg

@@ -0,0 +1,27 @@
+{
+    "security_type": "EQUITY",
+    "data_directory": "./data/equity",
+    "datafiles": [
+        "20250618.mktdata.ohlcv.db",
+    ],
+    "db_table_name": "md_1min_bars",
+    "exchange_id": "ALPACA",
+    "instrument_id_pfx": "STOCK-",
+    "trading_hours": {
+        "begin_session": "9:30:00",
+        "end_session": "16:00:00",
+        "timezone": "America/New_York"
+    },
+    "price_column": "close",
+    "min_required_points": 30,
+    "zero_threshold": 1e-10,
+    "dis-equilibrium_open_trshld": 2.0,
+    "dis-equilibrium_close_trshld": 1.0,
+    "training_minutes": 120,
+    "funding_per_pair": 2000.0,
+    # "fit_method_class": "pt_trading.sliding_fit.SlidingFit",
+    "fit_method_class": "pt_trading.static_fit.StaticFit",
+    "exclude_instruments": ["CAN"],
+    "close_outstanding_positions": false
+    
+}

configuration/equity_lg.cfg

@@ -0,0 +1,26 @@
+{
+    "security_type": "EQUITY",
+    "data_directory": "./data/equity",
+    "datafiles": [
+        "20250602.mktdata.ohlcv.db",
+    ],
+    "db_table_name": "md_1min_bars",
+    "exchange_id": "ALPACA",
+    "instrument_id_pfx": "STOCK-",
+    "trading_hours": {
+        "begin_session": "9:30:00",
+        "end_session": "16:00:00",
+        "timezone": "America/New_York"
+    },
+    "price_column": "close",
+    "min_required_points": 30,
+    "zero_threshold": 1e-10,
+    "dis-equilibrium_open_trshld": 2.0,
+    "dis-equilibrium_close_trshld": 1.0,
+    "training_minutes": 120,
+    "funding_per_pair": 2000.0,
+    "fit_method_class": "pt_trading.fit_methods.StaticFit",
+    "exclude_instruments": ["CAN"]
+}
+# "fit_method_class": "pt_trading.fit_methods.SlidingFit",
+# "fit_method_class": "pt_trading.fit_methods.StaticFit",

lg_notes.md

@@ -0,0 +1,115 @@
+07.11.2025
+pairs_trading/configuration <---- directory for config
+equity_lg.cfg <-------- copy of equity.cfg
+How to run a Program: TRIANGLEsquare ----> triangle EQUITY backtest
+Results are in  > results (timestamp table for all runs)
+table "...timestamp... .pt_backtest_results.equity.db"
+going to table  using sqlite
+> sqlite3 '/home/coder/results/20250721_175750.pt_backtest_results.equity.db'
+
+sqlite> .databases
+main: /home/coder/results/20250717_180122.pt_backtest_results.equity.db r/w
+sqlite> .tables
+config                 outstanding_positions  pt_bt_results   
+
+sqlite> PRAGMA table_info('pt_bt_results');
+0|date|DATE|0||0
+1|pair|TEXT|0||0
+2|symbol|TEXT|0||0
+3|open_time|DATETIME|0||0
+4|open_side|TEXT|0||0
+5|open_price|REAL|0||0
+6|open_quantity|INTEGER|0||0
+7|open_disequilibrium|REAL|0||0
+8|close_time|DATETIME|0||0
+9|close_side|TEXT|0||0
+10|close_price|REAL|0||0
+11|close_quantity|INTEGER|0||0
+12|close_disequilibrium|REAL|0||0
+13|symbol_return|REAL|0||0
+14|pair_return|REAL|0||0
+
+select count(*) as cnt from pt_bt_results;
+8
+
+select * from pt_bt_results;
+
+select 
+date, close_time, pair, symbol, symbol_return, pair_return
+from pt_bt_results ;
+
+select date, sum(symbol_return) as daily_return 
+from pt_bt_results where date = '2025-06-18' group by date;
+
+.quit
+
+sqlite3 '/home/coder/results/20250717_172435.pt_backtest_results.equity.db'
+
+sqlite> select date, sum(symbol_return) as daily_return 
+from pt_bt_results group by date;
+
+2025-06-02|1.29845390060828
+...
+2025-06-18|-43.5084977104115 <========== ????? ==========>
+2025-06-20|11.8605547517183
+
+
+select 
+date, close_time, pair, symbol, symbol_return, pair_return
+from pt_bt_results ;
+
+select date, close_time, pair, symbol, symbol_return, pair_return
+from pt_bt_results where date = '2025-06-18';
+
+
+./scripts/load_equity_pair_intraday.sh -A NVDA -B QQQ -d 20250701  -T ./intraday_md
+
+to inspect exactly what sources, formats, and processing steps you can open the script with:
+head -n 50 ./scripts/load_equity_pair_intraday.sh
+
+
+
+✓ Data file found: /home/coder/pairs_trading/data/crypto/20250605.mktdata.ohlcv.db
+
+sqlite3 '/home/coder/results/20250722_201930.pt_backtest_results.crypto.db'
+
+sqlite3 '/home/coder/results/xxxxxxxx_yyyyyy.pt_backtest_results.pseudo.db'
+
+11111111
+=== At your terminal, run these commands:
+sqlite3 '/home/coder/results/20250722_201930.pt_backtest_results.crypto.db'
+=== Then inside the SQLite prompt:
+.mode csv
+.headers on
+.output results_20250722.csv
+SELECT * FROM pt_bt_results;
+.output stdout
+.quit
+
+cd /home/coder/
+
+# === mode csv formats output as CSV
+# === headers on includes column names
+# === output my_table.csv directs output to that file
+# === Run your SELECT query, then revert output
+# === Open my_table.csv in Excel directly
+
+# ======== Using scp (Secure Copy)
+# === On your local machine, open a terminal and run:
+scp cvtt@953f6e8df266:/home/coder/results_20250722.csv ~/Downloads/
+
+
+# ===== convert cvs pandas dataframe ====== -->
+import pandas as pd
+# Replace with the actual path to your CSV file
+file_path = '/home/coder/results_20250722.csv'
+# Read the CSV file into a DataFrame
+df = pd.read_csv(file_path)
+# Show the first few rows
+print(df.head())
+
+
+
+
+
+

lib/pt_trading/results.py

@@ -427,14 +427,16 @@ class BacktestResult:
                         trd["open_scaled_disequilibrium"] is not None
                         and trd["open_scaled_disequilibrium"] is not None
                     ):
-                        disequil_info = f" | Open Dis-eq: {trd['open_scaled_disequilibrium']:.2f},"
+                        disequil_info = (
-                        f" Close Dis-eq: {trd['open_scaled_disequilibrium']:.2f}"
+                            f' | Open Dis-eq: {trd["open_scaled_disequilibrium"]:.2f},'
+                            f' Close Dis-eq: {trd["close_scaled_disequilibrium"]:.2f}'
+                        )
 
                     print(
-                        f" {trd['open_time'].time()}-{trd['close_time'].time()}  {trd['symbol']}: "
+                        f' {trd["open_time"].time()}-{trd["close_time"].time()}  {trd["symbol"]}: '
-                        f" {trd['open_side']} @ ${trd['open_price']:.2f},"
+                        f' {trd["open_side"]} @ ${trd["open_price"]:.2f},'
-                        f" {trd["close_side"]} @ ${trd["close_price"]:.2f},"
+                        f' {trd["close_side"]} @ ${trd["close_price"]:.2f},'
-                        f" Return: {trd['symbol_return']:.2f}%{disequil_info}"
+                        f' Return: {trd["symbol_return"]:.2f}%{disequil_info}'
                     )
                     pair_return += trd["symbol_return"]
 

lib/pt_trading/rolling_window_fit.py

@@ -188,7 +188,8 @@ class RollingFit(PairsTradingFitMethod):
         open_px_b = open_row[f"{colname_b}"]
 
         # creating the trades
-        print(f"OPEN_TRADES: {row["tstamp"]} {open_scaled_disequilibrium=}")
+        # use outer single quotes so we can reference DataFrame keys with double quotes inside
+        print(f'OPEN_TRADES: {open_tstamp} open_scaled_disequilibrium={open_scaled_disequilibrium}')
         if open_disequilibrium > 0:
             open_side_a = "SELL"
             open_side_b = "BUY"
@@ -237,10 +238,7 @@ class RollingFit(PairsTradingFitMethod):
             ),
         ]
         # Create DataFrame with explicit dtypes to avoid concatenation warnings
-        df = pd.DataFrame(
+        df = pd.DataFrame(trd_signal_tuples, columns=self.TRADES_COLUMNS)
-            trd_signal_tuples,
-            columns=self.TRADES_COLUMNS,
-        )
         # Ensure consistent dtypes
         return df.astype(
             {

lib/pt_trading/vecm_rolling_fit.py

@@ -1,14 +1,47 @@
+# original script moved to vecm_rolling_fit_01.py
+
+# 09.09.25  Added GARCH model - predicting volatility
+
+# Rule of thumb:
+# alpha + beta ≈ 1 → strong volatility clustering, persistence.
+# If much lower → volatility mean reverts quickly.
+# If > 1 → model is unstable / non-stationary (bad).
+
+# the VECM disequilibrium (mean reversion signal) and 
+# the GARCH volatility forecast (risk measure).
+# combine them → e.g., only enter trades when:
+
+# high_volatility = 1 → persistence > 0.95 or volatility > 2 (rule of thumb: unstable / risky regime).
+# high_volatility = 0 → stable regime.
+
+
+# VECM disequilibrium z-score > threshold and
+# GARCH-forecasted volatility is not too high (avoid noise-driven signals).
+# This creates a volatility-adjusted pairs trading strategy, more robust than plain VECM
+
+# now pair_predict_result_ DataFrame includes:
+# disequilibrium, scaled_disequilibrium, z-scores, garch_alpha, garch_beta, garch_persistence (α+β rule-of-thumb)
+# garch_vol_forecast (1-step volatility forecast)
+
+# Would you like me to also add a warning flag column 
+# (e.g., "high_volatility" = 1 if persistence > 0.95 or vol_forecast > threshold) 
+# so you can easily detect unstable regimes?
+
+# VECM/GARCH 
+# vecm_rolling_fit.py:
 from typing import Any, Dict, Optional, cast
 
+import numpy as np
 import pandas as pd
+from typing import Any, Dict, Optional
 from pt_trading.results import BacktestResult
 from pt_trading.rolling_window_fit import RollingFit
 from pt_trading.trading_pair import TradingPair
 from statsmodels.tsa.vector_ar.vecm import VECM, VECMResults
+from arch import arch_model
 
 NanoPerMin = 1e9
 
-
 class VECMTradingPair(TradingPair):
     vecm_fit_: Optional[VECMResults]
     pair_predict_result_: Optional[pd.DataFrame]
@@ -23,20 +56,23 @@ class VECMTradingPair(TradingPair):
         super().__init__(config, market_data, symbol_a, symbol_b)
         self.vecm_fit_ = None
         self.pair_predict_result_ = None
+        self.garch_fit_ = None
+        self.sigma_spread_forecast_ = None
+        self.garch_alpha_ = None
+        self.garch_beta_ = None
+        self.garch_persistence_ = None
+        self.high_volatility_flag_ = None
 
     def _train_pair(self) -> None:
         self._fit_VECM()
         assert self.vecm_fit_ is not None
+
         diseq_series = self.training_df_[self.colnames()] @ self.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_["disequilibrium"] = diseq_series
-            self.training_df_[self.colnames()] @ self.vecm_fit_.beta
+        self.training_df_["scaled_disequilibrium"] = (
-        )
-        # Normalize the dis-equilibrium
-        self.training_df_["scaled_dis-equilibrium"] = (
             diseq_series - self.training_mu_
         ) / self.training_std_
 
@@ -45,61 +81,96 @@ class VECMTradingPair(TradingPair):
         vecm_df = self.training_df_[self.colnames()].reset_index(drop=True)
         vecm_model = VECM(vecm_df, coint_rank=1)
         vecm_fit = vecm_model.fit()
-
-        assert vecm_fit is not None
-
-        # 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
-        pass
+
+        # Error Correction Term (spread)
+        ect_series = (vecm_df @ vecm_fit.beta).iloc[:, 0]
+
+        # Difference the spread for stationarity
+        dz = ect_series.diff().dropna()
+
+        if len(dz) < 30:
+            print("Not enough data for GARCH fitting.")
+            return
+
+        # Rescale if variance too small
+        if dz.std() < 0.1:
+            dz = dz * 1000
+        # print("Scale check:", dz.std())
+
+        try:
+            garch = arch_model(dz, vol="GARCH", p=1, q=1, mean="Zero", dist="normal")
+            garch_fit = garch.fit(disp="off")
+            self.garch_fit_ = garch_fit
+
+            # Extract parameters
+            params = garch_fit.params
+            self.garch_alpha_ = params.get("alpha[1]", np.nan)
+            self.garch_beta_ = params.get("beta[1]", np.nan)
+            self.garch_persistence_ = self.garch_alpha_ + self.garch_beta_
+
+            # print (f"GARCH α: {self.garch_alpha_:.4f}, β: {self.garch_beta_:.4f}, "
+            #       f"α+β (persistence): {self.garch_persistence_:.4f}")
+
+            # One-step-ahead volatility forecast
+            forecast = garch_fit.forecast(horizon=1)
+            sigma_next = np.sqrt(forecast.variance.iloc[-1, 0])
+            self.sigma_spread_forecast_ = float(sigma_next)
+            # print("GARCH sigma forecast:", self.sigma_spread_forecast_)
+
+            # Rule of thumb: persistence close to 1 or large volatility forecast
+            self.high_volatility_flag_ = int(
+                (self.garch_persistence_ is not None and self.garch_persistence_ > 0.95)
+                or (self.sigma_spread_forecast_ is not None and self.sigma_spread_forecast_ > 2)
+            )
+
+        except Exception as e:
+            print(f"GARCH fit failed: {e}")
+            self.garch_fit_ = None
+            self.sigma_spread_forecast_ = None
+            self.high_volatility_flag_ = None
 
     def predict(self) -> pd.DataFrame:
         self._train_pair()
-
         assert self.testing_df_ is not None
         assert self.vecm_fit_ is not None
+
+        # VECM predictions
         predicted_prices = self.vecm_fit_.predict(steps=len(self.testing_df_))
-
-        # Convert prediction to a DataFrame for readability
-        predicted_df = pd.DataFrame(
-            predicted_prices, columns=pd.Index(self.colnames()), dtype=float
-        )
-
         predicted_df = pd.merge(
             self.testing_df_.reset_index(drop=True),
-            pd.DataFrame(
+            pd.DataFrame(predicted_prices, columns=pd.Index(self.colnames()), dtype=float),
-                predicted_prices, columns=pd.Index(self.colnames()), dtype=float
-            ),
             left_index=True,
             right_index=True,
             suffixes=("", "_pred"),
         ).dropna()
 
+        # Disequilibrium and z-scores
         predicted_df["disequilibrium"] = (
             predicted_df[self.colnames()] @ self.vecm_fit_.beta
         )
-
         predicted_df["signed_scaled_disequilibrium"] = (
             predicted_df["disequilibrium"] - self.training_mu_
         ) / self.training_std_
-
         predicted_df["scaled_disequilibrium"] = abs(
             predicted_df["signed_scaled_disequilibrium"]
         )
 
-        predicted_df = predicted_df.reset_index(drop=True)
+        # Add GARCH parameters + volatility forecast
+        predicted_df["garch_alpha"] = self.garch_alpha_
+        predicted_df["garch_beta"] = self.garch_beta_
+        predicted_df["garch_persistence"] = self.garch_persistence_
+        predicted_df["garch_vol_forecast"] = self.sigma_spread_forecast_
+        predicted_df["high_volatility"] = self.high_volatility_flag_
+
+        # Save results
         if self.pair_predict_result_ is None:
             self.pair_predict_result_ = predicted_df
         else:
             self.pair_predict_result_ = pd.concat(
                 [self.pair_predict_result_, predicted_df], ignore_index=True
             )
-        # Reset index to ensure proper indexing
+
-        self.pair_predict_result_ = self.pair_predict_result_.reset_index(drop=True)
         return self.pair_predict_result_
 
 
@@ -117,6 +188,6 @@ class VECMRollingFit(RollingFit):
         return VECMTradingPair(
             config=config,
             market_data=market_data,
-            symbol_a=symbol_a,
+            symbol_a = symbol_a,
-            symbol_b=symbol_b,
+            symbol_b = symbol_b,
         )

lib/pt_trading/z-score_rolling_fit.py

@@ -1,18 +1,28 @@
-from typing import Any, Dict, Optional, cast
+from typing import Any, Dict, Optional
 
 import pandas as pd
-from pt_trading.results import BacktestResult
+import statsmodels.api as sm
+
 from pt_trading.rolling_window_fit import RollingFit
 from pt_trading.trading_pair import TradingPair
-import statsmodels.api as sm
 
 NanoPerMin = 1e9
 
 
 class ZScoreTradingPair(TradingPair):
+    """TradingPair implementation that fits a hedge ratio with OLS and
+    computes a standardized spread (z-score).
+
+    The class stores training spread mean/std and hedge ratio so the model
+    can be applied to testing data consistently.
+    """
+
     zscore_model_: Optional[sm.regression.linear_model.RegressionResultsWrapper]
     pair_predict_result_: Optional[pd.DataFrame]
-    zscore_df_: Optional[pd.DataFrame]
+    zscore_df_: Optional[pd.Series]
+    hedge_ratio_: Optional[float]
+    spread_mean_: Optional[float]
+    spread_std_: Optional[float]
 
     def __init__(
         self,
@@ -25,47 +35,79 @@ class ZScoreTradingPair(TradingPair):
         self.zscore_model_ = None
         self.pair_predict_result_ = None
         self.zscore_df_ = None
+        self.hedge_ratio_ = None
+        self.spread_mean_ = None
+        self.spread_std_ = None
 
     def _fit_zscore(self) -> None:
+        """Fit OLS on the training window and compute training z-score."""
         assert self.training_df_ is not None
-        symbol_a_px_series = self.training_df_[self.colnames()].iloc[:, 0]
-        symbol_b_px_series = self.training_df_[self.colnames()].iloc[:, 1]
 
-        symbol_a_px_series, symbol_b_px_series = symbol_a_px_series.align(
+        # Extract price series for the two symbols from the training frame.
-            symbol_b_px_series, axis=0
+        px_df = self.training_df_[self.colnames()]
-        )
+        symbol_a_px = px_df.iloc[:, 0]
+        symbol_b_px = px_df.iloc[:, 1]
 
-        X = sm.add_constant(symbol_b_px_series)
+        # Align indexes and fit OLS: symbol_a ~ const + symbol_b
-        self.zscore_model_ = sm.OLS(symbol_a_px_series, X).fit()
+        symbol_a_px, symbol_b_px = symbol_a_px.align(symbol_b_px, join="inner")
-        assert self.zscore_model_ is not None
+        X = sm.add_constant(symbol_b_px)
-        hedge_ratio = self.zscore_model_.params.iloc[1]
+        self.zscore_model_ = sm.OLS(symbol_a_px, X).fit()
 
-        # Calculate spread and Z-score
+        # Hedge ratio is the slope on symbol_b
-        spread = symbol_a_px_series - hedge_ratio * symbol_b_px_series
+        params = self.zscore_model_.params
-        self.zscore_df_ = (spread - spread.mean()) / spread.std()
+        self.hedge_ratio_ = float(params.iloc[1]) if len(params) > 1 else 0.0
+
+        # Training spread and its standardized z-score
+        spread = symbol_a_px - self.hedge_ratio_ * symbol_b_px
+        self.spread_mean_ = float(spread.mean())
+        self.spread_std_ = float(spread.std(ddof=0)) if spread.std(ddof=0) != 0 else 1.0
+        self.zscore_df_ = (spread - self.spread_mean_) / self.spread_std_
 
     def predict(self) -> pd.DataFrame:
+        """Apply fitted hedge ratio to the testing frame and return a
+        dataframe with canonical columns:
+          - disequilibrium: signed z-score
+          - scaled_disequilibrium: absolute z-score
+          - signed_scaled_disequilibrium: same as disequilibrium (keeps sign)
+        """
+        # Fit on training window
         self._fit_zscore()
         assert self.zscore_df_ is not None
-        self.training_df_["dis-equilibrium"] = self.zscore_df_
+        assert self.hedge_ratio_ is not None
-        self.training_df_["scaled_dis-equilibrium"] = abs(self.zscore_df_)
+        assert self.spread_mean_ is not None and self.spread_std_ is not None
 
+        # Keep training columns for inspection
+        self.training_df_["disequilibrium"] = self.zscore_df_
+        self.training_df_["scaled_disequilibrium"] = self.zscore_df_.abs()
+
+        # Apply model to testing frame
         assert self.testing_df_ is not None
-        assert self.zscore_df_ is not None
+        test_df = self.testing_df_.copy()
-        predicted_df = self.testing_df_
+        px_test = test_df[self.colnames()]
+        a_test = px_test.iloc[:, 0]
+        b_test = px_test.iloc[:, 1]
+        a_test, b_test = a_test.align(b_test, join="inner")
 
-        predicted_df["disequilibrium"] = self.zscore_df_
+        # Compute test spread and standardize using training mean/std
-        predicted_df["signed_scaled_disequilibrium"] = self.zscore_df_
+        test_spread = a_test - self.hedge_ratio_ * b_test
-        predicted_df["scaled_disequilibrium"] = abs(self.zscore_df_)
+        test_zscore = (test_spread - self.spread_mean_) / self.spread_std_
 
-        predicted_df = predicted_df.reset_index(drop=True)
+        # Attach canonical columns
+        # Align back to test_df index if needed
+        test_zscore = test_zscore.reindex(test_df.index)
+        test_df["disequilibrium"] = test_zscore
+        test_df["signed_scaled_disequilibrium"] = test_zscore
+        test_df["scaled_disequilibrium"] = test_zscore.abs()
+
+        # Reset index and accumulate results across windows
+        test_df = test_df.reset_index(drop=True)
         if self.pair_predict_result_ is None:
-            self.pair_predict_result_ = predicted_df
+            self.pair_predict_result_ = test_df
         else:
             self.pair_predict_result_ = pd.concat(
-                [self.pair_predict_result_, predicted_df], ignore_index=True
+                [self.pair_predict_result_, test_df], ignore_index=True
             )
-        # Reset index to ensure proper indexing
+
         self.pair_predict_result_ = self.pair_predict_result_.reset_index(drop=True)
         return self.pair_predict_result_.dropna()
 
@@ -78,8 +120,5 @@ class ZScoreRollingFit(RollingFit):
         self, config: Dict, market_data: pd.DataFrame, symbol_a: str, symbol_b: str
     ) -> TradingPair:
         return ZScoreTradingPair(
-            config=config,
+            config=config, market_data=market_data, symbol_a=symbol_a, symbol_b=symbol_b
-            market_data=market_data,
-            symbol_a=symbol_a,
-            symbol_b=symbol_b,
         )

requirements.txt

@@ -61,7 +61,7 @@ protobuf>=3.12.4
 psutil>=5.9.0
 ptyprocess>=0.7.0
 pycurl>=7.44.1
-pyelftools>=0.27
+# pyelftools>=0.27
 Pygments>=2.11.2
 pyparsing>=2.4.7
 pyrsistent>=0.18.1
@@ -69,7 +69,7 @@ python-debian>=0.1.43 #+ubuntu1.1
 python-dotenv>=0.19.2
 python-magic>=0.4.24
 python-xlib>=0.29
-pyxdg>=0.27
+# pyxdg>=0.27
 PyYAML>=6.0
 reportlab>=3.6.8
 requests>=2.25.1
@@ -82,113 +82,113 @@ six>=1.16.0
 soupsieve>=2.3.1
 ssh-import-id>=5.11
 statsmodels>=0.14.4
-texttable>=1.6.4
+# texttable>=1.6.4
 tldextract>=3.1.2
 tomli>=1.2.2
 ######## typed-ast>=1.4.3
-types-aiofiles>=0.1
+# types-aiofiles>=0.1
-types-annoy>=1.17
+# types-annoy>=1.17
-types-appdirs>=1.4
+# types-appdirs>=1.4
-types-atomicwrites>=1.4
+# types-atomicwrites>=1.4
-types-aws-xray-sdk>=2.8
+# types-aws-xray-sdk>=2.8
-types-babel>=2.9
+# types-babel>=2.9
-types-backports-abc>=0.5
+# types-backports-abc>=0.5
-types-backports.ssl-match-hostname>=3.7
+# types-backports.ssl-match-hostname>=3.7
-types-beautifulsoup4>=4.10
+# types-beautifulsoup4>=4.10
-types-bleach>=4.1
+# types-bleach>=4.1
-types-boto>=2.49
+# types-boto>=2.49
-types-braintree>=4.11
+# types-braintree>=4.11
-types-cachetools>=4.2
+# types-cachetools>=4.2
-types-caldav>=0.8
+# types-caldav>=0.8
-types-certifi>=2020.4
+# types-certifi>=2020.4
-types-characteristic>=14.3
+# types-characteristic>=14.3
-types-chardet>=4.0
+# types-chardet>=4.0
-types-click>=7.1
+# types-click>=7.1
-types-click-spinner>=0.1
+# types-click-spinner>=0.1
-types-colorama>=0.4
+# types-colorama>=0.4
-types-commonmark>=0.9
+# types-commonmark>=0.9
-types-contextvars>=0.1
+# types-contextvars>=0.1
-types-croniter>=1.0
+# types-croniter>=1.0
-types-cryptography>=3.3
+# types-cryptography>=3.3
-types-dataclasses>=0.1
+# types-dataclasses>=0.1
-types-dateparser>=1.0
+# types-dateparser>=1.0
-types-DateTimeRange>=0.1
+# types-DateTimeRange>=0.1
-types-decorator>=0.1
+# types-decorator>=0.1
-types-Deprecated>=1.2
+# types-Deprecated>=1.2
-types-docopt>=0.6
+# types-docopt>=0.6
-types-docutils>=0.17
+# types-docutils>=0.17
-types-editdistance>=0.5
+# types-editdistance>=0.5
-types-emoji>=1.2
+# types-emoji>=1.2
-types-entrypoints>=0.3
+# types-entrypoints>=0.3
-types-enum34>=1.1
+# types-enum34>=1.1
-types-filelock>=3.2
+# types-filelock>=3.2
-types-first>=2.0
+# types-first>=2.0
-types-Flask>=1.1
+# types-Flask>=1.1
-types-freezegun>=1.1
+# types-freezegun>=1.1
-types-frozendict>=0.1
+# types-frozendict>=0.1
-types-futures>=3.3
+# types-futures>=3.3
-types-html5lib>=1.1
+# types-html5lib>=1.1
-types-httplib2>=0.19
+# types-httplib2>=0.19
-types-humanfriendly>=9.2
+# types-humanfriendly>=9.2
-types-ipaddress>=1.0
+# types-ipaddress>=1.0
-types-itsdangerous>=1.1
+# types-itsdangerous>=1.1
-types-JACK-Client>=0.1
+# types-JACK-Client>=0.1
-types-Jinja2>=2.11
+# types-Jinja2>=2.11
-types-jmespath>=0.10
+# types-jmespath>=0.10
-types-jsonschema>=3.2
+# types-jsonschema>=3.2
-types-Markdown>=3.3
+# types-Markdown>=3.3
-types-MarkupSafe>=1.1
+# types-MarkupSafe>=1.1
-types-mock>=4.0
+# types-mock>=4.0
-types-mypy-extensions>=0.4
+# types-mypy-extensions>=0.4
-types-mysqlclient>=2.0
+# types-mysqlclient>=2.0
-types-oauthlib>=3.1
+# types-oauthlib>=3.1
-types-orjson>=3.6
+# types-orjson>=3.6
-types-paramiko>=2.7
+# types-paramiko>=2.7
-types-Pillow>=8.3
+# types-Pillow>=8.3
-types-polib>=1.1
+# types-polib>=1.1
-types-prettytable>=2.1
+# types-prettytable>=2.1
-types-protobuf>=3.17
+# types-protobuf>=3.17
-types-psutil>=5.8
+# types-psutil>=5.8
-types-psycopg2>=2.9
+# types-psycopg2>=2.9
-types-pyaudio>=0.2
+# types-pyaudio>=0.2
-types-pycurl>=0.1
+# types-pycurl>=0.1
-types-pyfarmhash>=0.2
+# types-pyfarmhash>=0.2
-types-Pygments>=2.9
+# types-Pygments>=2.9
-types-PyMySQL>=1.0
+# types-PyMySQL>=1.0
-types-pyOpenSSL>=20.0
+# types-pyOpenSSL>=20.0
-types-pyRFC3339>=0.1
+# types-pyRFC3339>=0.1
-types-pysftp>=0.2
+# types-pysftp>=0.2
-types-pytest-lazy-fixture>=0.6
+# types-pytest-lazy-fixture>=0.6
-types-python-dateutil>=2.8
+# types-python-dateutil>=2.8
-types-python-gflags>=3.1
+# types-python-gflags>=3.1
-types-python-nmap>=0.6
+# types-python-nmap>=0.6
-types-python-slugify>=5.0
+# types-python-slugify>=5.0
-types-pytz>=2021.1
+# types-pytz>=2021.1
-types-pyvmomi>=7.0
+# types-pyvmomi>=7.0
-types-PyYAML>=5.4
+# types-PyYAML>=5.4
-types-redis>=3.5
+# types-redis>=3.5
-types-requests>=2.25
+# types-requests>=2.25
-types-retry>=0.9
+# types-retry>=0.9
-types-selenium>=3.141
+# types-selenium>=3.141
-types-Send2Trash>=1.8
+# types-Send2Trash>=1.8
-types-setuptools>=57.4
+# types-setuptools>=57.4
-types-simplejson>=3.17
+# types-simplejson>=3.17
-types-singledispatch>=3.7
+# types-singledispatch>=3.7
-types-six>=1.16
+# types-six>=1.16
-types-slumber>=0.7
+# types-slumber>=0.7
-types-stripe>=2.59
+# types-stripe>=2.59
-types-tabulate>=0.8
+# types-tabulate>=0.8
-types-termcolor>=1.1
+# types-termcolor>=1.1
-types-toml>=0.10
+# types-toml>=0.10
-types-toposort>=1.6
+# types-toposort>=1.6
-types-ttkthemes>=3.2
+# types-ttkthemes>=3.2
-types-typed-ast>=1.4
+# types-typed-ast>=1.4
-types-tzlocal>=0.1
+# types-tzlocal>=0.1
-types-ujson>=0.1
+# types-ujson>=0.1
-types-vobject>=0.9
+# types-vobject>=0.9
-types-waitress>=0.1
+# types-waitress>=0.1
-types-Werkzeug>=1.0
+#types-Werkzeug>=1.0
-types-xxhash>=2.0
+#types-xxhash>=2.0
 typing-extensions>=3.10.0.2
 Unidecode>=1.3.3
 urllib3>=1.26.5

research/cointegration_test.py

@@ -9,18 +9,19 @@ import pandas as pd
 
 from tools.config import expand_filename, load_config
 from tools.data_loader import get_available_instruments_from_db
+
 from pt_trading.results import (
     BacktestResult,
     create_result_database,
     store_config_in_database,
     store_results_in_database,
 )
+
 from pt_trading.fit_method import PairsTradingFitMethod
 from pt_trading.trading_pair import TradingPair
 
 from research.research_tools import create_pairs, resolve_datafiles
 
-
 def main() -> None:
     parser = argparse.ArgumentParser(description="Run pairs trading backtest.")
     parser.add_argument(
@@ -36,7 +37,7 @@ def main() -> None:
         "--instruments",
         type=str,
         required=False,
-        help="Comma-separated list of instrument symbols (e.g., COIN,GBTC). If not provided, auto-detects from database.",
+        help = "Comma-separated list of instrument symbols (e.g., COIN,GBTC). If not provided, auto-detects from database.",
     )
     args = parser.parse_args()
 

research/notebooks/pt_pair_backtest.ipynb

@@ -0,0 +1,16 @@
+{
+ "cells": [],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.12.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

research/research_tools.py

@@ -5,7 +5,6 @@ from typing import Dict, List, Optional
 import pandas as pd
 from pt_trading.fit_method import PairsTradingFitMethod
 
-
 def resolve_datafiles(config: Dict, cli_datafiles: Optional[str] = None) -> List[str]:
     """
     Resolve the list of data files to process.
@@ -69,9 +68,9 @@ def create_pairs(
 
     for datafile in datafiles:
         md_df = load_market_data(
-            datafile=datafile,
+            datafile = datafile,
-            instruments=instruments,
+            instruments = instruments,
-            db_table_name=config_copy["market_data_loading"][instruments[0]["instrument_type"]]["db_table_name"],
+            db_table_name = config_copy["market_data_loading"][instruments[0]["instrument_type"]]["db_table_name"],
             trading_hours=config_copy["trading_hours"],
             extra_minutes=extra_minutes,
         )