virgo-modules 0.4.2__tar.gz → 0.4.4__tar.gz

{virgo_modules-0.4.2 → virgo_modules-0.4.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo_modules
-Version: 0.4.2
+Version: 0.4.4
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire

{virgo_modules-0.4.2 → virgo_modules-0.4.4}/setup.py

@@ -5,7 +5,7 @@ with open("virgo_app/README.md", "r") as f:
 
 setup(
     name="virgo_modules",
-    version="0.4.2",
+    version="0.4.4",
     description="data processing and statistical modeling using stock market data",
     package_dir={"": "virgo_app"},
     packages=find_packages(where="virgo_app"),

{virgo_modules-0.4.2 → virgo_modules-0.4.4}/virgo_app/virgo_modules/src/edge_utils/edge_utils.py

@@ -9,7 +9,7 @@ from feature_engine.imputation import  MeanMedianImputer
 from feature_engine.discretisation import EqualWidthDiscretiser
 from feature_engine.datetime import DatetimeFeatures
 
-from ..transformer_utils import VirgoWinsorizerFeature, InverseHyperbolicSine, FeaturesEntropy, FeatureSelector
+from ..transformer_utils import VirgoWinsorizerFeature, InverseHyperbolicSine, FeaturesEntropy, FeatureSelector, InteractionFeatures
 
 from plotly.subplots import make_subplots
 import plotly.graph_objects as go
@@ -220,6 +220,7 @@ def data_processing_pipeline_classifier(
         invhypervolsin_features = False,
         date_features_list = False,
         entropy_set_list = False,
+        interaction_features_cont = False,
         pipeline_order = 'selector//winzorizer//discretizer//median_inputer//drop//correlation'
         ):
 
@@ -237,6 +238,7 @@ def data_processing_pipeline_classifier(
                     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
+                    interaction_features_cont (tuple): tuple of lists of interaction features
                     pipeline_order (str): custom pipeline order eg. selector//winzorizer//discretizer//median_inputer//drop//correlation
             Returns:
                     pipe (obj): pipeline object
@@ -249,6 +251,7 @@ 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 []
+    interaction_features = [("interaction features", InteractionFeatures(interaction_features_cont[0], interaction_features_cont[1]))] if interaction_features_cont else []
     
     entropy_pipe = list()
     if entropy_set_list:
@@ -267,6 +270,7 @@ def data_processing_pipeline_classifier(
         'median_inputer':median_imputer_pipe,
         'arcsinh_scaler': invhypersin_pipe,
         'date_features': datetimeFeatures_pipe,
+        'interaction_features': interaction_features,
         'entropy_features' : entropy_pipe,
     }
 

{virgo_modules-0.4.2 → virgo_modules-0.4.4}/virgo_app/virgo_modules/src/re_utils.py

@@ -792,7 +792,7 @@ def apply_KF(self, trends):
         
 stock_eda_panel.apply_KF = apply_KF
 
-def call_ml_objects(stock_code, client, call_models = False):
+def call_ml_objects(stock_code, client, call_models = False, clean_name=False):
     '''
     call artifcats from mlflow
 
@@ -805,7 +805,11 @@ def call_ml_objects(stock_code, client, call_models = False):
     '''
     objects = dict()
     
-    registered_model_name = f'{stock_code}_models'
+    if clean_name:
+        renamed_stock_code = stock_code.replace("^","__",).replace(".","__").replace("=","__").replace("-","__")
+        registered_model_name = f'{renamed_stock_code}_models'
+    else:
+        registered_model_name = f'{stock_code}_models'
     latest_version_info = client.get_latest_versions(registered_model_name, stages=["Production"])
     latest_production_version = latest_version_info[0].version
     run_id_prod_model = latest_version_info[0].run_id
@@ -816,18 +820,27 @@ def call_ml_objects(stock_code, client, call_models = False):
     )
 
      ## calling models
-    
+    if clean_name:
+        path_hmm = f"runs:/{run_id_prod_model}/{renamed_stock_code}-hmm-model"
+    else:
+        path_hmm = f"runs:/{run_id_prod_model}/{stock_code}-hmm-model"
+
     hmm_model = mlflow.pyfunc.load_model(
-            f"runs:/{run_id_prod_model}/{stock_code}-hmm-model",
-             suppress_warnings = True
+            path_hmm,
+            suppress_warnings = True
             )
     objects['called_hmm_models'] = hmm_model
     
     if call_models:
         
+        if clean_name:
+            path_model = f"runs:/{run_id_prod_model}/{renamed_stock_code}-forecasting-model"
+        else:
+            path_model = f"runs:/{run_id_prod_model}/{stock_code}-forecasting-model"
+
         forecasting_model = mlflow.pyfunc.load_model(
-            f"runs:/{run_id_prod_model}/{stock_code}-forecasting-model",
-             suppress_warnings = True
+            path_model,
+            suppress_warnings = True
             )
         objects['called_forecasting_model'] = forecasting_model
         

{virgo_modules-0.4.2 → virgo_modules-0.4.4}/virgo_app/virgo_modules/src/transformer_utils.py

@@ -248,3 +248,44 @@ class signal_combiner(BaseEstimator, TransformerMixin):
             if self.drop:
                 X = X.drop(columns = [self.prefix_up + column, self.prefix_low + column])
         return X
+    
+class InteractionFeatures(BaseEstimator, TransformerMixin):
+
+    """
+    Class that applies feature interaction.
+    this class is compatible with scikitlearn pipeline
+
+    Attributes
+    ----------
+    feature_list1 : list
+        list of features to combine
+    feature_list2 : list
+        list of features to combine
+
+    Methods
+    -------
+    fit(additional="", X=DataFrame, y=None):
+        fit transformation.
+    transform(X=DataFrame, y=None):
+        apply feature transformation
+    """
+
+    def __init__(self, feature_list1, feature_list2):
+        self.feature_list1 = feature_list1
+        self.feature_list2 = feature_list2
+
+    def fit(self, X, y=None):
+        return self
+    
+    def simple_div_interaction(self, data, feature1, feature2, feature_name):
+        data[feature_name] = data[feature1]*data[feature2]
+        data[feature_name] = data[feature_name].replace([np.inf, -np.inf], 0)
+        data[feature_name] = data[feature_name].fillna(0)
+        return data
+
+    def transform(self, X, y=None):
+        for f1 in self.feature_list1:
+            for f2 in self.feature_list2:
+                fn = 'iterm_'+f1.replace("norm_","")+"_"+f2.replace("norm_","")
+                X = self.simple_div_interaction(X, f1, f2, fn)
+        return X

{virgo_modules-0.4.2 → virgo_modules-0.4.4}/virgo_app/virgo_modules.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo-modules
-Version: 0.4.2
+Version: 0.4.4
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire