hyperparam pre orig

model_selection/hyperparam_tuning.py

@@ -11,6 +11,7 @@
 # --------------------------------------------------------------------------------------------------------
 import pandas as pd
 import numpy as np
+
 from xgboost import XGBClassifier
 from sklearn.model_selection import StratifiedKFold
 from sklearn.ensemble import RandomForestClassifier, BaggingClassifier, AdaBoostClassifier
@@ -78,7 +79,7 @@ if __name__ == "__main__":
             "AB" : AdaBoostClassifier(algorithm='SAMME'), 
             "XGB": XGBClassifier(),
             "LR" : LogisticRegression(max_iter=1000), 
-            "SVM" : SVC(), 
+            "SVM" : SVC(max_iter=1000), 
             "MLP" : MLPClassifier(max_iter=500)
             # "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet')
             }
@@ -89,7 +90,7 @@ 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(class_weight='balanced'), 
+            "SVM" : SVC(max_iter = 1000, class_weight='balanced'), 
             # "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet', class_weight='balanced'), 
             # "XGB": XGBClassifier(), # <-
             # "MLP" : MLPClassifier(max_iter=500) # <-
@@ -142,7 +143,7 @@ if __name__ == "__main__":
     # Store each df as a sheet in an excel file
     sheets_dict = {}
     for i, group in enumerate(['pre']):
-        for j, method in enumerate(['', '', 'over_', 'under_']):
+        for j, method in enumerate(['']): #['', '', 'over_', 'under_']
             # Get dataset based on group and method
             X = data_dic['X_train_' + method + group]
             y = data_dic['y_train_' + method + group]
@@ -154,18 +155,17 @@ if __name__ == "__main__":
                 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 = RandomizedSearchCV(model, param_distributions=params, cv=cv, n_jobs=8, 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_pre.xlsx') as writer:
+    with pd.ExcelWriter('./output/hyperparam_pre_ORIG.xlsx') as writer:
         for sheet_name, data in sheets_dict.items():
             data.to_excel(writer, sheet_name=sheet_name)
     # --------------------------------------------------------------------------------------------------------