virgo-modules 0.3.7__tar.gz → 0.4.1__tar.gz

{virgo_modules-0.3.7 → virgo_modules-0.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo_modules
-Version: 0.3.7
+Version: 0.4.1
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire
@@ -9,7 +9,7 @@ License: MIT
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.9, <3.10
+Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Provides-Extra: dev

{virgo_modules-0.3.7 → virgo_modules-0.4.1}/setup.py

@@ -5,7 +5,7 @@ with open("virgo_app/README.md", "r") as f:
 
 setup(
     name="virgo_modules",
-    version="0.3.7",
+    version="0.4.1",
     description="data processing and statistical modeling using stock market data",
     package_dir={"": "virgo_app"},
     packages=find_packages(where="virgo_app"),
@@ -20,11 +20,8 @@ setup(
         "Programming Language :: Python :: 3.9",
         "Operating System :: OS Independent",
     ],
-    # install_requires=["feature-engine==1.6.1","matplotlib==3.6.3","mlflow==2.1.1","numpy==1.23.5","optuna==3.1.0","pandas==1.5.3",
-    #             "plotly==5.15.0","rsa==4.9","scikit-learn==1.2.1","scipy==1.10.0","seaborn==0.12.2","starlette==0.22.0","statsmodels==0.13.5",
-    #             "ta==0.10.2","yfinance==0.2.9","hmmlearn==0.3.0","boto3"],
     extras_require={
         "dev": ["pytest>=7.0"],
     },
-    python_requires=">=3.9, <3.10",
+    python_requires=">=3.9",
 )

{virgo_modules-0.3.7 → virgo_modules-0.4.1}/virgo_app/virgo_modules/src/edge_utils/edge_utils.py

@@ -414,4 +414,52 @@ def edge_probas_lines(data, threshold, plot = False, look_back = 750):
     fig.update_layout(title_text="sirius - edge probabilities",width=1200,height = 500)
     if plot:
         fig.show()
+    return fig
+
+def get_rolling_probs(data, window = 3,plot = False, look_back = 750):
+    """
+    produce a plotly plot of smoothed edges and closing prices
+
+            Parameters:
+                    data (pd.DataFrame): asset data with edge probabilities
+                    window (int): window size
+                    plot (boolean): if true, display plot
+                    look_back (int): number of rows back to display
+
+            Returns:
+                    fig (obj): plotly go object
+    """
+    prob_cols = ['proba_target_down','proba_target_up']
+    df = data[prob_cols+['Date','log_return','Close']].iloc[-look_back:]
+    for colx in prob_cols:
+        df[f'roll_{colx}'] = df.sort_values('Date')[colx].rolling(window, min_periods=1).mean()
+    df['roll_edge'] = np.where(df['roll_proba_target_up'] > df['roll_proba_target_down'],'up','down')
+    #order chaining
+    df['lag'] = df['roll_edge'].shift(1)
+    df['change'] = np.where(df['roll_edge']!=df['lag'],1,np.nan)
+    df['rn'] = df.sort_values('Date').groupby('change').cumcount() + 1
+    df['rn'] = np.where(df['change']==1,df['rn'],np.nan)
+    df['chain'] = df.sort_values('Date')['rn'].fillna(method='ffill')
+    df['chain_id'] = df.sort_values(['Date']).groupby(['chain','chain']).cumcount() + 1
+    
+    colors = {'up':'blue','down':'red'}
+    fig = make_subplots(
+        rows=2, cols=2,shared_xaxes=False,vertical_spacing=0.08,
+        specs=[[{"colspan": 2, "secondary_y":True}, None],[{}, {}]],
+            subplot_titles=("Smooth edge probabilities", "expected log return", "Duration"))
+    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.roll_proba_target_down,mode='lines',marker = dict(color = 'coral'),name='go down'),secondary_y=True,col=1,row=1)
+    fig.add_trace(go.Scatter(x=df.Date, y=df.roll_proba_target_up,mode='lines',marker = dict(opacity=0.1,size=80), name='go up'),secondary_y=True,col=1,row=1)
+
+    for re in df['roll_edge'].unique():
+         fig.add_trace(go.Box(x=df[df['roll_edge']==re]["log_return"],name=re,marker_color=colors.get(re),showlegend=False),col=1,row=2)
+
+    df_ = df.groupby(['roll_edge','chain'],as_index=False).agg(max_duration = ('chain_id','max'))
+    for re in df_['roll_edge'].unique():
+        fig.add_trace(go.Box(x=df_[df_['roll_edge']==re]["max_duration"],name=re,marker_color=colors.get(re),showlegend=False),col=2,row=2)
+        
+    fig.update_layout(title_text="sirius - smooth edge probabilities",width=1200,height = 1000)
+    if plot:
+        fig.show()
+    
     return fig

{virgo_modules-0.3.7 → virgo_modules-0.4.1}/virgo_app/virgo_modules/src/re_utils.py

@@ -749,6 +749,7 @@ def get_data(ticker_name:str, ticket_settings:dict, n_days:int = False, hmm_avai
     if len(discrete_features) > 0:
         for feature_name in discrete_features:
             object_stock.produce_order_features(feature_name)
+            object_stock.get_order_feature_nosignal(feature_name)
 
     if hmm_available:
         object_stock.cluster_hmm_analysis( n_clusters = None, 

{virgo_modules-0.3.7 → virgo_modules-0.4.1}/virgo_app/virgo_modules.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo-modules
-Version: 0.3.7
+Version: 0.4.1
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire
@@ -9,7 +9,7 @@ License: MIT
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.9, <3.10
+Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Provides-Extra: dev