preparing for pre tuning

model_selection/hyperparam_tuning.py

@@ -20,6 +20,7 @@ from sklearn.linear_model import  LogisticRegression
 from sklearn.tree import DecisionTreeClassifier
 from scipy.stats import randint, uniform
 from sklearn.model_selection import RandomizedSearchCV
+import os 
 # --------------------------------------------------------------------------------------------------------
 
 # Function to read training datasets
@@ -77,7 +78,7 @@ if __name__ == "__main__":
             "AB" : AdaBoostClassifier(algorithm='SAMME'), 
             "XGB": XGBClassifier(),
             "LR" : LogisticRegression(max_iter=1000), 
-            "SVM" : SVC(probability=True), 
+            "SVM" : SVC(), 
             "MLP" : MLPClassifier(max_iter=500)
             # "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet')
             }
@@ -88,7 +89,7 @@ if __name__ == "__main__":
             "Bagging" : BaggingClassifier(estimator= DecisionTreeClassifier(class_weight='balanced')),
             "AB" : AdaBoostClassifier(estimator= DecisionTreeClassifier(class_weight='balanced'), algorithm='SAMME'),  
             "LR" : LogisticRegression(max_iter=1000, class_weight='balanced'), 
-            "SVM" : SVC(probability=True, class_weight='balanced'), 
+            "SVM" : SVC(class_weight='balanced'), 
             # "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet', class_weight='balanced'), 
             # "XGB": XGBClassifier(), # <-
             # "MLP" : MLPClassifier(max_iter=500) # <-
@@ -150,20 +151,21 @@ if __name__ == "__main__":
             # Save results: params and best score for each of the mdodels of this method and group
             hyperparam_df = pd.DataFrame(index=list(models.keys()), columns=['Parameters','Score'])
             for model_name, model in models.items():
-                print(f"{group}-{method}-{model_name} \n\n")
+                print(f"{group}-{method_names[j]}-{model_name}")
                 # Find optimal hyperparams for curr model
                 params = hyperparameters[model_name]
                 search = RandomizedSearchCV(model, param_distributions=params, cv=cv, n_jobs=3, scoring='precision')
                 search.fit(X,y)
                 hyperparam_df.at[model_name,'Parameters']=search.best_params_
                 hyperparam_df.at[model_name,'Score']=round(search.best_score_,4)
+                os.system('clear')
             
             # Store the DataFrame in the dictionary with a unique key for each sheet
             sheet_name = f"{group}_{method_names[j]}"
             sheets_dict[sheet_name] = hyperparam_df
 
     # Write results to Excel file
-    with pd.ExcelWriter('./output/hyperparam.xlsx') as writer:
+    with pd.ExcelWriter('./output/hyperparam_pre.xlsx') as writer:
         for sheet_name, data in sheets_dict.items():
             data.to_excel(writer, sheet_name=sheet_name)
     # --------------------------------------------------------------------------------------------------------