virgo-modules 0.2.3__tar.gz → 0.2.5__tar.gz

{virgo_modules-0.2.3 → virgo_modules-0.2.5}/PKG-INFO

@@ -1,36 +1,19 @@
 Metadata-Version: 2.1
 Name: virgo_modules
-Version: 0.2.3
+Version: 0.2.5
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire
 Author-email: miguelmayhem92@gmail.com
 License: MIT
+Platform: UNKNOWN
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.9, <3.10
 Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: feature-engine==1.6.1
-Requires-Dist: matplotlib==3.6.3
-Requires-Dist: mlflow==2.1.1
-Requires-Dist: numpy==1.23.5
-Requires-Dist: optuna==3.1.0
-Requires-Dist: pandas==1.5.3
-Requires-Dist: plotly==5.15.0
-Requires-Dist: rsa==4.9
-Requires-Dist: scikit-learn==1.2.1
-Requires-Dist: scipy==1.10.0
-Requires-Dist: seaborn==0.12.2
-Requires-Dist: starlette==0.22.0
-Requires-Dist: statsmodels==0.13.5
-Requires-Dist: ta==0.10.2
-Requires-Dist: yfinance==0.2.9
-Requires-Dist: hmmlearn==0.3.0
-Requires-Dist: boto3
 Provides-Extra: dev
-Requires-Dist: pytest>=7.0; extra == "dev"
+License-File: LICENSE
 
 # Virgo Package
 
@@ -51,3 +34,4 @@ obj = stock_eda_panel(stock_code = 'PEP', n_days = 20)
 obj.get_data()
 print(obj.df.shape)
 ```
+

{virgo_modules-0.2.3 → virgo_modules-0.2.5}/setup.py

@@ -5,7 +5,7 @@ with open("virgo_app/README.md", "r") as f:
 
 setup(
     name="virgo_modules",
-    version="0.2.3",
+    version="0.2.5",
     description="data processing and statistical modeling using stock market data",
     package_dir={"": "virgo_app"},
     packages=find_packages(where="virgo_app"),

{virgo_modules-0.2.3 → virgo_modules-0.2.5}/virgo_app/virgo_modules/src/re_utils.py

@@ -1383,6 +1383,12 @@ def extract_data_traintest(object_stock,features_to_search,configs, target_confi
         getattr(object_stock, method_to_use)(**arguments_to_use, plot = False, save_features = False)
         if method_to_use not in ['minmax_pricefeature']:
             object_stock.produce_order_features(feature_name)
+        last_signal_featlist = configs.get('custom_transformations',{}).get('compute_last_signal', False)
+        if last_signal_featlist:
+                last_signal_featlist = last_signal_featlist
+                last_signal_featlist = last_signal_featlist.split('//')
+                if feature_name in last_signal_featlist:
+                    object_stock.compute_last_signal(feature_name, False)
     # geting targets
     object_stock.get_categorical_targets(**target_params_up)
     object_stock.df = object_stock.df.drop(columns = ['target_down']).rename(columns = {'target_up':'target_up_save'})

{virgo_modules-0.2.3 → virgo_modules-0.2.5}/virgo_app/virgo_modules/src/ticketer_source.py

@@ -173,6 +173,8 @@ class stock_eda_panel(object):
         perform additional asset ROC feature, then a new feature is created in the main dataframe
     produce_order_features(feature_name=str, save_features=boolean):
         perform a feature that captures high and low values in an index. this is usefull to know duration/persistence of a signal
+    compute_last_signal (feature_name=str, save_features=boolean):
+        perform a feature that captures high and low values in an index. this is usefull to know duration/persistence of a signal
     create_hmm_derived_features():
         create features derived from hmm states features. Features are the index of the state, the duration of the state, chain raturn
     cluster_hmm_analysis(n_clusters=int,features_hmm=list, test_data_size=int, seed=int, lag_returns_state=int, plot=boolean, save_features=boolean, model=obj):
@@ -1383,6 +1385,53 @@ class stock_eda_panel(object):
             self.signals.append(signal_feature_name)
             self.signals.append(order_feature_name)
 
+    def compute_last_signal(self,feature, save_features = False):
+        """
+        perform two new features when signal is observed, one for the last duration of the previous chain, second for the last duration of the same sign signal
+
+        Parameters
+        ----------
+        feature_name (str): name of the feature
+        save_features (boolean): True to save feature configuration and feature names
+        
+        Returns
+        -------
+        None
+        """
+        def create_last_signal(df, feature, prefix, type ='0'):
+            if type == '0':
+                condition = df[f'order_signal_{feature}'] != 0
+            elif type == '+':
+                condition = df[f'order_signal_{feature}'] > 0
+            elif type == '-':
+                condition = df[f'order_signal_{feature}'] < 0
+            df[f'last_maxorder_{feature}'] = np.where(condition, df[f'order_signal_{feature}'],np.nan)
+            df['tmp_chain_index'] = df[f'last_maxorder_{feature}'].shift(-1)
+            df['last'] = np.where((df[f'last_maxorder_{feature}'] != 0) & (df['tmp_chain_index'].isna()),df[f'last_maxorder_{feature}'], np.nan )
+            df['last'] = df['last'].shift(1)
+            df[f'last_maxorder_{feature}'] = df['last'].fillna(method = 'ffill')
+            df = df.drop(columns = ['tmp_chain_index','last'])
+            df[f'last_maxorder_{feature}'] = np.where(df[f'order_signal_{feature}'] != 0,df[f'last_maxorder_{feature}'],np.nan)
+            df[f'last_maxorder_{feature}'] = df[f'last_maxorder_{feature}'].fillna(0)
+            df = df.rename(columns = {f'last_maxorder_{feature}':f'{prefix}_{feature}'})
+            return df
+        prefix0, prefix1, prefix2 = 'ldur', 'pos', 'neg'
+        self.df = create_last_signal(self.df, feature, prefix0, type ='0')
+        self.df = create_last_signal(self.df, feature, prefix1, type ='+')
+        self.df = create_last_signal(self.df, feature, prefix2, type ='-')
+
+        self.df[f'sldur_{feature}'] = np.where(
+            self.df[f'order_signal_{feature}'] > 0, self.df[f'{prefix1}_{feature}'],
+            np.where(
+                self.df[f'order_signal_{feature}'] < 0, self.df[f'{prefix2}_{feature}'],
+                0
+            )
+        )
+        self.df = self.df.drop(columns = [f'{prefix1}_{feature}',f'{prefix2}_{feature}'])
+        if save_features:
+                self.signals.append(f'sldur_{feature}')
+                self.signals.append(f'ldur_{feature}')
+
     def create_hmm_derived_features(self, lag_returns):
         """
         create features derived from hmm states features. Features are the index of the state, the duration of the state, chain raturn

{virgo_modules-0.2.3 → virgo_modules-0.2.5}/virgo_app/virgo_modules.egg-info/PKG-INFO

@@ -1,36 +1,19 @@
 Metadata-Version: 2.1
 Name: virgo-modules
-Version: 0.2.3
+Version: 0.2.5
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire
 Author-email: miguelmayhem92@gmail.com
 License: MIT
+Platform: UNKNOWN
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.9, <3.10
 Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: feature-engine==1.6.1
-Requires-Dist: matplotlib==3.6.3
-Requires-Dist: mlflow==2.1.1
-Requires-Dist: numpy==1.23.5
-Requires-Dist: optuna==3.1.0
-Requires-Dist: pandas==1.5.3
-Requires-Dist: plotly==5.15.0
-Requires-Dist: rsa==4.9
-Requires-Dist: scikit-learn==1.2.1
-Requires-Dist: scipy==1.10.0
-Requires-Dist: seaborn==0.12.2
-Requires-Dist: starlette==0.22.0
-Requires-Dist: statsmodels==0.13.5
-Requires-Dist: ta==0.10.2
-Requires-Dist: yfinance==0.2.9
-Requires-Dist: hmmlearn==0.3.0
-Requires-Dist: boto3
 Provides-Extra: dev
-Requires-Dist: pytest>=7.0; extra == "dev"
+License-File: LICENSE
 
 # Virgo Package
 
@@ -51,3 +34,4 @@ obj = stock_eda_panel(stock_code = 'PEP', n_days = 20)
 obj.get_data()
 print(obj.df.shape)
 ```
+