virgo-modules 0.0.89__tar.gz → 0.0.90__tar.gz

{virgo_modules-0.0.89 → virgo_modules-0.0.90}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo_modules
-Version: 0.0.89
+Version: 0.0.90
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire

{virgo_modules-0.0.89 → virgo_modules-0.0.90}/setup.py

@@ -5,7 +5,7 @@ with open("virgo_app/README.md", "r") as f:
 
 setup(
     name="virgo_modules",
-    version="0.0.89",
+    version="0.0.90",
     description="data processing and statistical modeling using stock market data",
     package_dir={"": "virgo_app"},
     packages=find_packages(where="virgo_app"),

{virgo_modules-0.0.89 → virgo_modules-0.0.90}/virgo_app/virgo_modules/src/edge_utils.py

@@ -10,7 +10,7 @@ from virgo_modules.src.ticketer_source import FeatureSelector
 from feature_engine.discretisation import EqualWidthDiscretiser
 from feature_engine.datetime import DatetimeFeatures
 
-from .ticketer_source import VirgoWinsorizerFeature, InverseHyperbolicSine
+from .ticketer_source import VirgoWinsorizerFeature, InverseHyperbolicSine, FeaturesEntropy
 
 class produce_model_wrapper:
     """
@@ -90,8 +90,8 @@ class produce_model_wrapper:
         self.model = model
         self.pipe_transform = pipe
         self.pipeline = Pipeline([('pipe_transform',self.pipe_transform), ('model',self.model)])
-        self.features_to_model = self.pipe_transform.fit_transform(self.X_train).columns
         self.pipeline.fit(self.X_train, self.y_train)
+        self.features_to_model = self.pipeline[:-1].transform(self.X_train).columns
 
 class register_results():
     """
@@ -217,6 +217,7 @@ def data_processing_pipeline_classifier(
         bins_discretize = 10, correlation = 0.85, fillna = True,
         invhypervolsin_features = False,
         date_features_list = False,
+        entropy_set_list = False,
         pipeline_order = 'selector//winzorizer//discretizer//median_inputer//drop//correlation'
         ):
 
@@ -233,6 +234,7 @@ def data_processing_pipeline_classifier(
                     fillna (boolean): if true to fill na features
                     invhypervolsin_features (list): list of features to apply inverse hyperbolic sine
                     date_features_list (list): list of features to compute from Date field. (list of features from feature_engine)
+                    entropy_set_list (list): list of dictionaries that contains features and targets to compute entropy
                     pipeline_order (str): custom pipeline order eg. selector//winzorizer//discretizer//median_inputer//drop//correlation
             Returns:
                     pipe (obj): pipeline object
@@ -245,7 +247,15 @@ def data_processing_pipeline_classifier(
     median_imputer_pipe = [('median_imputer', MeanMedianImputer())] if fillna else []
     invhypersin_pipe = [('invhypervolsin scaler', InverseHyperbolicSine(features = invhypervolsin_features))] if invhypervolsin_features else []
     datetimeFeatures_pipe = [('date features', DatetimeFeatures(features_to_extract = date_features_list, variables = 'Date', drop_original = False))] if date_features_list else []
-
+    
+    entropy_pipe = list()
+    if entropy_set_list:
+        for setx_ in entropy_set_list:
+            setx = setx_['set'].split('//')
+            target_ = setx_['target']
+            subpipe_name = '_'.join(setx) + 'entropy'
+            entropy_pipe.append((subpipe_name, FeaturesEntropy(features = setx, target = target_)))
+    
     pipe_dictionary = {
         'selector': select_pipe,
         'winzorizer':winzorizer_pipe,
@@ -255,6 +265,7 @@ def data_processing_pipeline_classifier(
         'median_inputer':median_imputer_pipe,
         'arcsinh_scaler': invhypersin_pipe,
         'date_features': datetimeFeatures_pipe,
+        'entropy_features' : entropy_pipe,
     }
 
     pipeline_steps = pipeline_order.split('//')

{virgo_modules-0.0.89 → virgo_modules-0.0.90}/virgo_app/virgo_modules/src/ticketer_source.py

@@ -147,7 +147,7 @@ class FeatureSelector(BaseEstimator, TransformerMixin):
     def transform(self, X, y=None):
         return X[self.columns]
 
-class features_entropy(BaseEstimator, TransformerMixin):
+class FeaturesEntropy(BaseEstimator, TransformerMixin):
     """
     Class that creates a feature that calculate entropy for a given feature classes, but it might get some leackeage in the training set.
     this class is compatible with scikitlearn pipeline
@@ -193,8 +193,8 @@ class features_entropy(BaseEstimator, TransformerMixin):
         train_dates = unique_dates[:cut]
         max_train_date = max(train_dates)
         
-        X_ = X[X['Date'] <= max_train_date]
-        df = pd.merge(X_, y, left_index=True, right_index=True, how = 'left').copy()
+        X_ = X[X['Date'] <= max_train_date].copy()
+        df = X_.join(y, how = 'left')
 
         column_list = [f'{self.feature_type}_signal_{colx}' for colx in self.features]
         
@@ -241,12 +241,12 @@ class features_entropy(BaseEstimator, TransformerMixin):
             .copy()
         )
         
-        del df, df_aggr
+        del df, df_aggr, X_
         return self
 
     def transform(self, X, y=None):
 
-        X = X.merge(self.entropy_map, on=self.column_list, how = 'left')
+        X = X.join(self.entropy_map.set_index(self.column_list), on=self.column_list, how = 'left')
         X[self.feature_name] = X[self.feature_name].fillna(self.default_null)
         return X
 
@@ -2598,9 +2598,8 @@ class produce_model:
         self.model = model
         self.pipe_transform = pipe
         self.pipeline = Pipeline([('pipe_transform',self.pipe_transform), ('model',self.model)])
-        self.features_to_model = self.pipe_transform.fit_transform(self.X_train).columns
         self.pipeline.fit(self.X_train, self.y_train)
-
+        self.features_to_model = self.pipeline[:-1].transform(self.X_train).columns
 
 class hmm_feature_selector():
     """

{virgo_modules-0.0.89 → virgo_modules-0.0.90}/virgo_app/virgo_modules.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo-modules
-Version: 0.0.89
+Version: 0.0.90
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire