import numpy as np
import pandas as pd

def load_data():
    df_train = pd.read_csv('train.csv')
    df_test = pd.read_csv('test.csv')
    return df_train, df_test


def preprocess_data(df_train, df_test):
    # V4
    df_train['V4'].fillna(0, inplace=True)
    df_test['V4'].fillna(0, inplace=True)
    # V22 
    df_train['V22'].fillna(df_train['V22'].mean(), inplace=True)
    df_test['V22'].fillna(df_test['V22'].mean(), inplace=True)
    # V27
    df_train['V27'].fillna(df_train['V27'].mean(), inplace=True)
    df_test['V27'].fillna(df_test['V27'].mean(), inplace=True)
    # V29
    df_train['V29'].fillna(0, inplace=True)
    df_test['V29'].fillna(0, inplace=True)
    # V37
    df_train['V37'].fillna(df_train['V37'].mean(), inplace=True)
    df_test['V37'].fillna(df_test['V37'].mean(), inplace=True)

    X_train = df_train.drop('Class', axis=1).reset_index(drop=True)
    y_train = df_train['Class'].reset_index(drop=True)
    X_test = df_test.drop('Class', axis=1).reset_index(drop=True)
    y_test = df_test['Class'].reset_index(drop=True)

    return X_train, y_train, X_test, y_test


def predict():
    hyper_params = {
            "n_estimators": [50, 100, 200, 300, 400, 500, 600, 700],
            "learning_rate": [0.01, 0.05, 0.1, 0.2, 0.3, 0.4, 0.5],
            "max_depth": [1, 3, 4, 5, 6, 7, 8, 9, 10],
            "min_samples_split": [2, 5, 10, 15, 100],
            "tol": [1e-4, 1e-3, 1e-2, 1e-1, 1e-0],
            "validation_fraction": [0.1, 0.2, 0.3, 0.4, 0.5],
            "min_samples_leaf": [1, 2, 5, 10],
            "subsample": [0.6, 0.7, 0.8, 0.9, 1.0],
            "max_features": ["auto", "sqrt", "log2"],
    }

    df_train, df_test = load_data()

    X_train, y_train, X_test, y_test = preprocess_data(df_train, df_test)

    # Model 
    from sklearn.ensemble import GradientBoostingClassifier
    from sklearn.model_selection import RandomizedSearchCV

    model = RandomizedSearchCV(
        GradientBoostingClassifier(),
        hyper_params,
        n_iter=100000,
        scoring="roc_auc",
        n_jobs=-1,
        cv=5,
        verbose=1,
    )

    model.fit(X_train, y_train)
    print(model.score(X_test, y_test))

    print('Best parameters:', model.best_params_)



if __name__ == "__main__":
    predict()

#### Logistic Regression
# Best parameters: {'C': 20.0, 'class_weight': None, 'max_iter': 50, 'penalty': 'l2', 'solver': 'lbfgs', 'tol': 0.0001}
# Accuracy: 0.8660287081339713
# Hyperparams tuned:
#    hyper_params = {
#            'C': np.logspace(-3, 3, 7, 10, 20),
#            'penalty': ['l1', 'l2', 'elasticnet'],
#            'solver': ['liblinear', 'saga', 'lbfgs', 'newton-cg'],
#            'max_iter': [50, 100, 1000, 2500, 5000],
#            'class_weight': ['balanced', None],
#            'tol': [1e-4, 1e-3, 1e-2, 1e-1, 1],
#    }
######################