virgo-modules 0.0.85__tar.gz → 0.0.87__tar.gz

{virgo_modules-0.0.85 → virgo_modules-0.0.87}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo_modules
-Version: 0.0.85
+Version: 0.0.87
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire

{virgo_modules-0.0.85 → virgo_modules-0.0.87}/setup.py

@@ -5,7 +5,7 @@ with open("virgo_app/README.md", "r") as f:
 
 setup(
     name="virgo_modules",
-    version="0.0.85",
+    version="0.0.87",
     description="data processing and statistical modeling using stock market data",
     package_dir={"": "virgo_app"},
     packages=find_packages(where="virgo_app"),

{virgo_modules-0.0.85 → virgo_modules-0.0.87}/virgo_app/virgo_modules/src/edge_utils.py

@@ -8,6 +8,7 @@ from feature_engine.selection import DropFeatures, DropCorrelatedFeatures
 from feature_engine.imputation import  MeanMedianImputer
 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
 
@@ -215,7 +216,9 @@ def data_processing_pipeline_classifier(
         features_base,features_to_drop = False, winsorizer_conf = False, discretize_columns = False,
         bins_discretize = 10, correlation = 0.85, fillna = True,
         invhypervolsin_features = False,
-        pipeline_order = 'selector//winzorizer//discretizer//median_inputer//drop//correlation'):
+        date_features_list = False,
+        pipeline_order = 'selector//winzorizer//discretizer//median_inputer//drop//correlation'
+        ):
 
     '''
     pipeline builder
@@ -229,6 +232,7 @@ def data_processing_pipeline_classifier(
                     correlation (float): correlation threshold to discard correlated features
                     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)
                     pipeline_order (str): custom pipeline order eg. selector//winzorizer//discretizer//median_inputer//drop//correlation
             Returns:
                     pipe (obj): pipeline object
@@ -240,6 +244,7 @@ def data_processing_pipeline_classifier(
     drop_corr = [('drop_corr', DropCorrelatedFeatures(threshold=correlation, method = 'spearman'))] if correlation else []
     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 []
 
     pipe_dictionary = {
         'selector': select_pipe,
@@ -249,6 +254,7 @@ def data_processing_pipeline_classifier(
         'correlation': drop_corr,
         'median_inputer':median_imputer_pipe,
         'arcsinh_scaler': invhypersin_pipe,
+        'date_features': datetimeFeatures_pipe,
     }
 
     pipeline_steps = pipeline_order.split('//')

{virgo_modules-0.0.85 → virgo_modules-0.0.87}/virgo_app/virgo_modules/src/re_utils.py

@@ -1028,7 +1028,6 @@ class produce_plotly_plots:
         if len(states_subtitles)%2 == 1:
             states_subtitles = states_subtitles + [None]
 
-
         fig = make_subplots(
             rows= rows_subplot, cols=2,
             specs = [[{"type": "scatter"},{"type": "scatter"}]]*state_rows,
@@ -1107,6 +1106,11 @@ class produce_plotly_plots:
         df_ = df[['Date','hmm_feature','Close',"chain_return"]].sort_values('Date')
         df_['Daily_Returns'] = df['Close'].pct_change(7)
 
+        df_agg_returns = df_.groupby('hmm_feature', as_index = False).agg(median =('Daily_Returns','median')).copy()
+        current_state = df_.iloc[-1,:].hmm_feature
+        medain_state_return = df_agg_returns[ df_agg_returns.hmm_feature == current_state]['median'].values[0]
+        type_state = 'low state' if medain_state_return < 0 else 'high state'
+
         for state in states:
             dfi = df_[df_.hmm_feature == state]
             fig.add_trace(go.Box(y = dfi.chain_return, name=str(state),showlegend=False, marker_color = color_map[state] ),row=1, col=1)
@@ -1151,7 +1155,6 @@ class produce_plotly_plots:
                 fig.add_trace(go.Box(x = dfi.importance, name=str(feature),showlegend=False ),row=2, col=2)
             fig.update_yaxes(visible=False, title="feature",row=2, col=2)
 
-        
         fig.update_layout(height=height_plot, width=1600, title_text = f'State model analysis: {self.ticket_name}', coloraxis=dict(colorbar_len=0.50))
 
         date_execution = datetime.datetime.today().strftime('%Y-%m-%d')
@@ -1165,6 +1168,7 @@ class produce_plotly_plots:
             'current state':message1,
             'current step in state': message2,
             'execution date':message3,
+            'type state':type_state,
         }
         
         if self.show_plot:
@@ -1196,6 +1200,7 @@ class produce_plotly_plots:
         
         if self.return_figs:
             return fig, messages
+        
     def produce_forecasting_plot(self,predictions):
         """
         display forecasting plots

{virgo_modules-0.0.85 → virgo_modules-0.0.87}/virgo_app/virgo_modules.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo-modules
-Version: 0.0.85
+Version: 0.0.87
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire