crossval + hyperparam tested on DF

training_models/train_models.py → training_models/eval_models.py

@@ -79,26 +79,26 @@ if __name__ == "__main__":
     # --------------------------------------------------------------------------------------------------------
     # 1. No class weight
     models_1 = {#"DT" : DecisionTreeClassifier(), 
-            "RF" : RandomForestClassifier(), 
+            "RF" : RandomForestClassifier(n_estimators=50), 
             # "Bagging" : BaggingClassifier(),
             # "AB" : AdaBoostClassifier(), 
             # "XGB": XGBClassifier(),
-            # "LR" : LogisticRegression(), 
-            # "ElNet" : LogisticRegression(penalty='elasticnet'), 
-            # "SVM" : SVC(), 
-            # "MLP" : MLPClassifier(),
+            # "LR" : LogisticRegression(max_iter=1000), 
+            # "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'), 
+            # "SVM" : SVC(probability=True), 
+            # "MLP" : MLPClassifier(max_iter=500),
             }
     
     # 2. Class weight 
     models_2 = {#"DT" : DecisionTreeClassifier(class_weight='balanced'), 
-            "RF" : RandomForestClassifier(class_weight='balanced'), 
+            "RF" : RandomForestClassifier(n_estimators=50, class_weight='balanced'), 
             # "Bagging" : BaggingClassifier(), # <-
             # "AB" : AdaBoostClassifier(),  # <-
             # "XGB": XGBClassifier(), # <-
-            # "LR" : LogisticRegression(class_weight='balanced'), 
-            # "ElNet" : LogisticRegression(penalty='elasticnet', class_weight='balanced'), 
-            # "SVM" : SVC(class_weight='balanced'), 
-            # "MLP" : MLPClassifier(), # <-
+            # "LR" : LogisticRegression(max_iter=1000, class_weight='balanced'), 
+            # "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet', class_weight='balanced'), 
+            # "SVM" : SVC(probability=True, class_weight='balanced'), 
+            # "MLP" : MLPClassifier(max_iter=500), # <-
             }
     # --------------------------------------------------------------------------------------------------------
 

training_models/hyperparam_tuning.py

+"""
+    Selecting best models through cross validation and hyperparameter tunning 
+    for each method: 
+        1. Original training dataset
+        2. Original training dataset - Cost sensitive
+        3. Oversampling
+        4. Undersampling
+"""
+
+# Libraries
+# --------------------------------------------------------------------------------------------------------
+import pandas as pd
+import numpy as np
+from xgboost import XGBClassifier
+from sklearn.metrics import confusion_matrix
+from sklearn.metrics import f1_score, make_scorer, precision_score, recall_score
+from sklearn.model_selection import StratifiedKFold, cross_validate
+from sklearn.ensemble import RandomForestClassifier, BaggingClassifier, AdaBoostClassifier
+from sklearn.neural_network import MLPClassifier
+from sklearn.svm import SVC
+from sklearn.linear_model import  LogisticRegression
+from sklearn.tree import DecisionTreeClassifier
+from scipy.stats import randint, uniform
+from sklearn.model_selection import RandomizedSearchCV
+# --------------------------------------------------------------------------------------------------------
+
+# Function to read datasets
+# --------------------------------------------------------------------------------------------------------
+def read_data():
+    import numpy as np
+
+    # Load test data
+    X_test_pre = np.load('./gen_train_data/data/output/pre/X_test_pre.npy', allow_pickle=True)
+    y_test_pre = np.load('./gen_train_data/data/output/pre/y_test_pre.npy', allow_pickle=True)
+    X_test_post = np.load('./gen_train_data/data/output/post/X_test_post.npy', allow_pickle=True)
+    y_test_post = np.load('./gen_train_data/data/output/post/y_test_post.npy', allow_pickle=True)
+
+    # Load ORIGINAL training data
+    X_train_pre = np.load('./gen_train_data/data/output/pre/X_train_pre.npy', allow_pickle=True)
+    y_train_pre = np.load('./gen_train_data/data/output/pre/y_train_pre.npy', allow_pickle=True)
+    X_train_post = np.load('./gen_train_data/data/output/post/X_train_post.npy', allow_pickle=True)
+    y_train_post = np.load('./gen_train_data/data/output/post/y_train_post.npy', allow_pickle=True)
+
+    # Load oversampled training data
+    X_train_over_pre = np.load('./gen_train_data/data/output/pre/X_train_over_pre.npy', allow_pickle=True)
+    y_train_over_pre = np.load('./gen_train_data/data/output/pre/y_train_over_pre.npy', allow_pickle=True)
+    X_train_over_post = np.load('./gen_train_data/data/output/post/X_train_over_post.npy', allow_pickle=True)
+    y_train_over_post = np.load('./gen_train_data/data/output/post/y_train_over_post.npy', allow_pickle=True)
+
+    # Load undersampled training data
+    X_train_under_pre = np.load('./gen_train_data/data/output/pre/X_train_under_pre.npy', allow_pickle=True)
+    y_train_under_pre = np.load('./gen_train_data/data/output/pre/y_train_under_pre.npy', allow_pickle=True)
+    X_train_under_post = np.load('./gen_train_data/data/output/post/X_train_under_post.npy', allow_pickle=True)
+    y_train_under_post = np.load('./gen_train_data/data/output/post/y_train_under_post.npy', allow_pickle=True)
+
+    data_dic = {
+        "X_test_pre": X_test_pre,
+        "y_test_pre": y_test_pre,
+        "X_test_post": X_test_post,
+        "y_test_post": y_test_post,
+        "X_train_pre": X_train_pre,
+        "y_train_pre": y_train_pre,
+        "X_train_post": X_train_post,
+        "y_train_post": y_train_post,
+        "X_train_over_pre": X_train_over_pre,
+        "y_train_over_pre": y_train_over_pre,
+        "X_train_over_post": X_train_over_post,
+        "y_train_over_post": y_train_over_post,
+        "X_train_under_pre": X_train_under_pre,
+        "y_train_under_pre": y_train_under_pre,
+        "X_train_under_post": X_train_under_post,
+        "y_train_under_post": y_train_under_post,
+    }
+
+    return data_dic
+# --------------------------------------------------------------------------------------------------------
+
+if __name__ == "__main__":
+
+    # Reading training data
+    data_dic = read_data()
+
+    # Defining the models to train
+    # --------------------------------------------------------------------------------------------------------
+    # 1. No class weight
+    models_1 = {"DT" : DecisionTreeClassifier(), 
+            # "RF" : RandomForestClassifier(n_estimators=50), 
+            # "Bagging" : BaggingClassifier(),
+            # "AB" : AdaBoostClassifier(), 
+            # "XGB": XGBClassifier(),
+            # "LR" : LogisticRegression(max_iter=1000), 
+            # "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet'), 
+            # "SVM" : SVC(probability=True), 
+            # "MLP" : MLPClassifier(max_iter=500),
+            }
+    
+    # 2. Class weight 
+    models_2 = {"DT" : DecisionTreeClassifier(class_weight='balanced'), 
+            # "RF" : RandomForestClassifier(n_estimators=50, class_weight='balanced'), 
+            # "Bagging" : BaggingClassifier(), # <-
+            # "AB" : AdaBoostClassifier(),  # <-
+            # "XGB": XGBClassifier(), # <-
+            # "LR" : LogisticRegression(max_iter=1000, class_weight='balanced'), 
+            # "ElNet" : LogisticRegression(max_iter=1000, penalty='elasticnet', class_weight='balanced'), 
+            # "SVM" : SVC(probability=True, class_weight='balanced'), 
+            # "MLP" : MLPClassifier(max_iter=500), # <-
+            }
+
+    # Hyperparameter tuning setup
+    # --------------------------------------------------------------------------------------------------------
+    hyperparameters = {
+        "DT": {'splitter': ['best', 'random'], 
+            'max_features': ['sqrt', 'log2'], 
+            'criterion': ['gini', 'entropy', 'log_loss']},
+        "RF": {'n_estimators': randint(100, 250), 
+            'max_features': ['sqrt', 'log2'], 
+            'criterion': ['gini', 'entropy']},
+        "Bagging": {'n_estimators': randint(10, 100), 
+                    'max_samples': [0.8, 1.0], 
+                    'max_features': [0.8, 1.0], 
+                    'warm_start': [True, False]},
+        "AB": {'n_estimators': randint(50, 150), 
+            'learning_rate': uniform(0.8, 1.2)},
+        "XGB": {'n_estimators': randint(100, 1000), 
+                'max_depth': randint(3, 10), 
+                'learning_rate': uniform(0.01, 0.3)},
+        "LR": {'penalty': ['l1', 'l2', None], 
+            'solver': ['lbfgs', 'sag', 'saga']},
+        "EL": {'solver': ['lbfgs', 'sag', 'saga']},
+        "SVM": {'C': uniform(0.8, 1.2), 
+                'kernel': ['linear', 'poly', 'rbf', 'sigmoid']},
+        "MLP": {'activation': ['identity', 'logistic', 'tanh', 'relu'], 
+                'hidden_layer_sizes': randint(50, 150), 
+                'learning_rate': ['constant', 'invscaling', 'adaptive']}
+    }
+    # --------------------------------------------------------------------------------------------------------
+
+    # Cross-validation setup
+    # --------------------------------------------------------------------------------------------------------
+    # Defining cross-validation protocol
+    cv = StratifiedKFold(n_splits=10, shuffle=True, random_state=1)
+    method_names = {
+        0: "ORIG",
+        1: "ORIG_CW",
+        2: "OVER",
+        3: "UNDER"
+    }
+    # --------------------------------------------------------------------------------------------------------
+
+    # Hyperparameter tuning loop and exporting results
+    # --------------------------------------------------------------------------------------------------------
+    # Store each df as a sheet in an excel file
+    sheets_dict = {}
+    for i, group in enumerate(['pre', 'post']):
+        for j, method in enumerate(['', '', 'over_', 'under_']):
+            print(f"ITERATION {i+j}")
+            # Get dataset based on group and method
+            X = data_dic['X_train_' + method + group]
+            y = data_dic['y_train_' + method + group]
+            # Use group of models with class weight if needed
+            models = models_2 if j == 2 else models_1 
+            # 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():
+                # Find optimal hyperparams for curr model
+                params = hyperparameters[model_name]
+                search = RandomizedSearchCV(model, param_distributions=params, cv=cv, n_jobs=1, 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)
+            
+            # 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('./training_models/output/hyperparam.xlsx') as writer:
+        for sheet_name, data in sheets_dict.items():
+            data.to_excel(writer, sheet_name=sheet_name)
+    # --------------------------------------------------------------------------------------------------------
+    
+