virgo-modules 0.4.1__tar.gz → 0.4.3__tar.gz

{virgo_modules-0.4.1 → virgo_modules-0.4.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo_modules
-Version: 0.4.1
+Version: 0.4.3
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire

{virgo_modules-0.4.1 → virgo_modules-0.4.3}/setup.py

@@ -5,7 +5,7 @@ with open("virgo_app/README.md", "r") as f:
 
 setup(
     name="virgo_modules",
-    version="0.4.1",
+    version="0.4.3",
     description="data processing and statistical modeling using stock market data",
     package_dir={"": "virgo_app"},
     packages=find_packages(where="virgo_app"),

{virgo_modules-0.4.1 → virgo_modules-0.4.3}/virgo_app/virgo_modules/src/hmm_utils.py

@@ -153,19 +153,21 @@ class trainer_hmm():
             ('drop_correlated', DropCorrelatedFeatures(method='spearman',threshold=self.__corr_thrshold)),
         ])
 
-        # features_hmm = list(transform_pipe.fit_transform(self.__data_train).columns)
-        # n_features = len(features_hmm)
-        # startprob_prior =  np.array([1/self.__n_clusters]*self.__n_clusters)
-        transmat_prior = np.diag([0.70]*self.__n_clusters)
-        # means_prior = np.array([1/n_features]*n_features)
+        features_hmm_ = list(transform_pipe.fit_transform(self.__data_train).columns)
+        n_features = len(features_hmm_)
+        start_prob = 0.60
+        startprob_prior =  np.array([1/self.__n_clusters]*self.__n_clusters)
+        transmat_prior = np.diag([start_prob]*self.__n_clusters)
+        transmat_prior[transmat_prior==0] = (1-start_prob)/(1-self.__n_clusters)
+        means_prior = np.array([1/n_features]*n_features)
         pipeline_hmm = Pipeline([
             ('transfrom_pipe', transform_pipe),
             ('scaler', RobustScaler()),
             ('hmm', GaussianHMM(
                 n_components =  self.__n_clusters, covariance_type = 'spherical', 
-                # startprob_prior = startprob_prior, 
+                startprob_prior = startprob_prior, 
                 transmat_prior = transmat_prior, 
-                # means_prior = means_prior,
+                means_prior = means_prior,
                 random_state = self.__seed,)
             )
         ])

{virgo_modules-0.4.1 → virgo_modules-0.4.3}/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-0.4.1 → virgo_modules-0.4.3}/virgo_app/virgo_modules.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: virgo-modules
-Version: 0.4.1
+Version: 0.4.3
 Summary: data processing and statistical modeling using stock market data
 Home-page: https://github.com/miguelmayhem92/virgo_module
 Author: Miguel Mayhuire