progress, sliding model - buggy

configuration/equity.cfg

@@ -20,6 +20,7 @@
     "training_minutes": 120,
     "funding_per_pair": 2000.0,
     "fit_method_class": "pt_trading.fit_methods.SlidingFit",
+    # "fit_method_class": "pt_trading.fit_methods.StaticFit",
     "exclude_instruments": ["CAN"]
     
 }

lib/pt_trading/trading_pair.py

@@ -31,6 +31,7 @@ class TradingPair:
 
  
         self.user_data_ = {}
+        self.predicted_df_ = pd.DataFrame()
 
     def _transform_dataframe(self, df: pd.DataFrame) -> pd.DataFrame:
         # Select only the columns we need
@@ -80,7 +81,7 @@ class TradingPair:
 
         testing_start_index = training_start_index + training_minutes
         self.training_df_ = self.market_data_.iloc[
-            training_start_index:testing_start_index, :
+            training_start_index:testing_start_index, : training_minutes
         ].copy()
         assert self.training_df_ is not None
         self.training_df_ = self.training_df_.dropna().reset_index(drop=True)
@@ -101,7 +102,7 @@ class TradingPair:
             f"{self.price_column_}_{self.symbol_b_}",
         ]
 
-    def fit_VECM(self):
+    def fit_VECM(self) -> None:
         assert self.training_df_ is not None
         vecm_df = self.training_df_[self.colnames()].reset_index(drop=True)
         vecm_model = VECM(vecm_df, coint_rank=1)
@@ -120,7 +121,7 @@ class TradingPair:
         # print(f"{self}: {self.vecm_fit_.summary()}")
         pass
 
-    def check_cointegration_johansen(self):
+    def check_cointegration_johansen(self) -> bool:
         assert self.training_df_ is not None
         from statsmodels.tsa.vector_ar.vecm import coint_johansen
 
@@ -129,11 +130,11 @@ class TradingPair:
         print(
             f"{self}: lr1={result.lr1[0]} > cvt={result.cvt[0, 1]}? {result.lr1[0] > result.cvt[0, 1]}"
         )
-        is_cointegrated = result.lr1[0] > result.cvt[0, 1]
+        is_cointegrated: bool = bool(result.lr1[0] > result.cvt[0, 1])
 
         return is_cointegrated
 
-    def check_cointegration_engle_granger(self):
+    def check_cointegration_engle_granger(self) -> bool:
         from statsmodels.tsa.stattools import coint
 
         col1, col2 = self.colnames()
@@ -144,7 +145,7 @@ class TradingPair:
         # Run Engle-Granger cointegration test
         pvalue = coint(series1, series2)[1]
         # Define cointegration if p-value < 0.05 (i.e., reject null of no cointegration)
-        is_cointegrated = pvalue < 0.05
+        is_cointegrated: bool = bool(pvalue < 0.05)
         print(f"{self}: is_cointegrated={is_cointegrated} pvalue={pvalue}")
         return is_cointegrated
 
@@ -179,9 +180,30 @@ class TradingPair:
         predicted_prices = self.vecm_fit_.predict(steps=len(self.testing_df_))
 
         # Convert prediction to a DataFrame for readability
-        # predicted_df =
+        predicted_df = pd.DataFrame(
+            predicted_prices, columns=pd.Index(self.colnames()), dtype=float
+        )
 
-        self.predicted_df_ = pd.merge(
+        # self.predicted_df_ = pd.merge(
+        #     self.testing_df_.reset_index(drop=True),
+        #     pd.DataFrame(
+        #         predicted_prices, columns=pd.Index(self.colnames()), dtype=float
+        #     ),
+        #     left_index=True,
+        #     right_index=True,
+        #     suffixes=("", "_pred"),
+        # ).dropna()
+
+        # self.predicted_df_["disequilibrium"] = (
+        #     self.predicted_df_[self.colnames()] @ self.vecm_fit_.beta
+        # )
+
+        # self.predicted_df_["scaled_disequilibrium"] = (
+        #     abs(self.predicted_df_["disequilibrium"] - self.training_mu_)
+        #     / self.training_std_
+        # )
+
+        predicted_df = pd.merge(
             self.testing_df_.reset_index(drop=True),
             pd.DataFrame(
                 predicted_prices, columns=pd.Index(self.colnames()), dtype=float
@@ -191,16 +213,25 @@ class TradingPair:
             suffixes=("", "_pred"),
         ).dropna()
 
-        self.predicted_df_["disequilibrium"] = (
-            self.predicted_df_[self.colnames()] @ self.vecm_fit_.beta
+        predicted_df["disequilibrium"] = (
+            predicted_df[self.colnames()] @ self.vecm_fit_.beta
         )
 
-        self.predicted_df_["scaled_disequilibrium"] = (
-            abs(self.predicted_df_["disequilibrium"] - self.training_mu_)
+        predicted_df["scaled_disequilibrium"] = (
+            abs(predicted_df["disequilibrium"] - self.training_mu_)
             / self.training_std_
         )
+        
+        print("*** PREDICTED DF")
+        print(predicted_df)
+        print("*" * 80) 
+        print("*** SELF.PREDICTED_DF")
+        print(self.predicted_df_)
+        print("*" * 80) 
 
-        # Reset index to ensure proper indexing
+        predicted_df = predicted_df.reset_index(drop=True)
+        self.predicted_df_ = pd.concat([self.predicted_df_, predicted_df], ignore_index=True)
+        # Reset index to ensure proper indexing 
         self.predicted_df_ = self.predicted_df_.reset_index()
         return self.predicted_df_
 

requirements.txt

@@ -44,6 +44,7 @@ mypy>=0.942
 mypy-extensions>=0.4.3
 netaddr>=0.8.0
 ######### netifaces>=0.11.0
+numpy>=1.26.4,<2.3.0
 oauthlib>=3.2.0
 packaging>=23.1
 pathspec>=0.11.1