virgo-modules 0.0.76__tar.gz → 0.0.78__tar.gz

{virgo_modules-0.0.76 → virgo_modules-0.0.78}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo_modules
-Version: 0.0.76
+Version: 0.0.78
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire

{virgo_modules-0.0.76 → virgo_modules-0.0.78}/setup.py

@@ -5,7 +5,7 @@ with open("virgo_app/README.md", "r") as f:
 
 setup(
     name="virgo_modules",
-    version="0.0.76",
+    version="0.0.78",
     description="data processing and statistical modeling using stock market data",
     package_dir={"": "virgo_app"},
     packages=find_packages(where="virgo_app"),

{virgo_modules-0.0.76 → virgo_modules-0.0.78}/virgo_app/virgo_modules/src/re_utils.py

@@ -1389,6 +1389,7 @@ def save_edge_model(data, save_path = False, save_aws = False, show_result = Fal
     if show_result:
         print(curent_edge)
 
+## this function is going to be split and deprecated
 def create_feature_edge(model, data,feature_name, threshold, target_variables):
     '''
     get latest edge execution and edge probability
@@ -1417,4 +1418,74 @@ def create_feature_edge(model, data,feature_name, threshold, target_variables):
         result_df[f'signal_{type_use}_{feature_name}'] = np.where(result_df[pred_col] >= threshold,1,0)
         result_df[f'acc_{type_use}_{feature_name}'] = np.where(result_df[f'signal_{type_use}_{feature_name}'] == result_df[pred_col.replace('proba_','')],1,0)
     
-    return result_df
+    return result_df
+
+def produce_probas(model,data, target_variables):
+    """
+    produce probabilities given a model
+
+            Parameters:
+                    model (obj): edge model artifact
+                    data (pd.DataFrame): asset data
+                    target_variables (list): names of the target columns
+
+            Returns:
+                    result_df (pd.DataFrame): result dataframe with edges
+                    label_prediction (list): list of resulting label columns
+    """
+    label_prediction = ['proba_'+x for x in target_variables]
+    predictions = model.predict_proba(data)
+    predictions = pd.DataFrame(predictions, columns = label_prediction, index = data.index)
+    
+    result_df = pd.concat([data, predictions], axis=1)
+    result_df = result_df[['Date'] + target_variables + label_prediction]
+
+    return result_df, label_prediction
+
+def produce_signals(result_df, feature_name, threshold, label_prediction):
+    """
+    produce signals from probabilities
+
+            Parameters:
+                    result_df (pd.DataFrame): asset data with probabilities
+                    feature_name (str): edge feature name
+                    threshold (float): edge threshold
+                    label_prediction (list): list of resulting label columns
+
+            Returns:
+                    result_df (pd.DataFrame): result dataframe with edges and signals
+    """
+    for pred_col in label_prediction:
+        type_use = 'low'
+        if 'down' in pred_col:
+            type_use = 'up' 
+            
+        result_df[f'signal_{type_use}_{feature_name}'] = np.where(result_df[pred_col] >= threshold,1,0)
+        result_df[f'acc_{type_use}_{feature_name}'] = np.where(result_df[f'signal_{type_use}_{feature_name}'] == result_df[pred_col.replace('proba_','')],1,0)
+
+    return result_df
+
+def edge_probas_lines(data, threshold, plot = False, look_back = 750):
+    """
+    produce a plotly plot of edges and closing prices
+
+            Parameters:
+                    data (pd.DataFrame): asset data with edge probabilities
+                    plot (boolean): if true, display plot
+                    threshold (float): edge threshold
+                    look_back (int): number of rows back to display
+
+            Returns:
+                    fig (obj): plotly go object
+    """
+    df = data[['Date','Close','proba_target_down','proba_target_up']].iloc[-look_back:]
+    
+    fig = make_subplots(specs=[[{"secondary_y": True}]])
+    fig.add_trace(go.Scatter(x=df.Date, y=df.Close,mode='lines+markers',name='Close price'))
+    fig.add_trace(go.Scatter(x=df.Date, y=df.proba_target_down,mode='lines',marker = dict(color = 'coral'),name='go down'),secondary_y=True)
+    fig.add_trace(go.Scatter(x=df.Date, y=df.proba_target_up,mode='lines',marker = dict(opacity=0.1,size=80), name='go up'),secondary_y=True)
+    fig.add_shape(type="line", xref="paper", yref="y2",x0=0.02, y0=threshold, x1=0.9, y1=threshold,line=dict(color="red",dash="dash"),)
+    fig.update_layout(title_text="sirius - edge probabilities",width=1200,height = 500)
+    if plot:
+        fig.show()
+    return fig

{virgo_modules-0.0.76 → virgo_modules-0.0.78}/virgo_app/virgo_modules/src/ticketer_source.py

@@ -2734,11 +2734,11 @@ class signal_analyser_object:
             )
         )
         df = df[~df.signal_type.isna()]
-        # df['Date'] = df.index
         df['lag_Date'] = df['Date'].shift(1)
+        df['lag_signal_type'] = df['signal_type'].shift(1)
         df['span'] = (pd.to_datetime(df['Date']) - pd.to_datetime(df['lag_Date'])).dt.days - 1
-        df['break'] = np.where(df['span'] > 3, 1, 0)
-        df['break'] = np.where(df['span'].isna(), 1, df['break'])
+        df['break'] = np.where((df['span'] > 3) & (df['lag_signal_type'] == df['signal_type']), 1, 0)
+        df['break'] = np.where((df['lag_signal_type'] != df['signal_type']), 1, df['break'])
 
         df['chain_id'] = df.sort_values(['Date']).groupby(['break']).cumcount() + 1
         df['chain_id'] = np.where(df['break'] == 1, df['chain_id'], np.nan )
@@ -2861,11 +2861,11 @@ class signal_analyser_object:
                     )
                 )
         df2 = df2[~df2.signal_type.isna()]
-        # df2['Date_'] = df2.index
         df2['lag_Date'] = df2['Date'].shift(1)
+        df2['lag_signal_type'] = df2['signal_type'].shift(1)
         df2['span'] = (pd.to_datetime(df2['Date']) - pd.to_datetime(df2['lag_Date'])).dt.days - 1
-        df2['break'] = np.where(df2['span'] > 3, 1, 0)
-        df2['break'] = np.where(df2['span'].isna(), 1, df2['break'])
+        df2['break'] = np.where((df2['span'] > 3) & (df2['lag_signal_type'] == df2['signal_type']), 1, 0)
+        df2['break'] = np.where((df2['lag_signal_type'] != df2['signal_type']), 1, df2['break'])
 
         df2['chain_id'] = df2.sort_values(['Date']).groupby(['break']).cumcount() + 1
         df2['chain_id'] = np.where(df2['break'] == 1, df2['chain_id'], np.nan )

{virgo_modules-0.0.76 → virgo_modules-0.0.78}/virgo_app/virgo_modules.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo-modules
-Version: 0.0.76
+Version: 0.0.78
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire