""" 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 # -------------------------------------------------------------------------------------------------------- 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(), # "Bagging" : BaggingClassifier(), # "AB" : AdaBoostClassifier(), # "XGB": XGBClassifier(), # "LR" : LogisticRegression(), # "ElNet" : LogisticRegression(penalty='elasticnet'), # "SVM" : SVC(), # "MLP" : MLPClassifier(), } # 2. Class weight models_2 = {#"DT" : DecisionTreeClassifier(class_weight='balanced'), "RF" : RandomForestClassifier(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(), # <- } # -------------------------------------------------------------------------------------------------------- # Setup # -------------------------------------------------------------------------------------------------------- # Scorings to use for model evaluation scorings = {'recall':make_scorer(recall_score), 'precision':make_scorer(precision_score)} # Defining cross-validation protocol cv = StratifiedKFold(n_splits=10, shuffle=True, random_state=1) result_cols = [f"{model}_{metric}" for model in models_1.keys() for metric in ['PREC', 'REC']] method_names = { 0: "ORIG", 1: "ORIG_CW", 2: "OVER", 3: "UNDER" } # -------------------------------------------------------------------------------------------------------- # Evaluating performance through cross validation 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_']): # 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 in dataframe (10 columns since 10-fold cv) res_df = pd.DataFrame(columns=range(1,11), index=result_cols) for model_name, model in models.items(): cv_scores = cross_validate(model, X, y, scoring=scorings, cv=cv, return_train_score=True, n_jobs=1) res_df.loc[model_name + '_PREC'] = list(np.around(np.array(cv_scores["test_precision"]),4)) res_df.loc[model_name + '_REC'] = list(np.around(np.array(cv_scores["test_recall"]),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] = res_df # Write results to Excel file with pd.ExcelWriter('./training_models/output/cross_val_res.xlsx') as writer: for sheet_name, data in sheets_dict.items(): data.to_excel(writer, sheet_name=sheet_name) # --------------------------------------------------------------------------------------------------------