from normal_use import *

sumRegressors = [LGBMRegressor, RandomForestRegressor, XGBRegressor, CatBoostRegressor]
sumRegressor = Union[type(sumRegressors)]
sumParams = [{},{},{},{"silent": True}]
weight = [0.1, 0.2, 0.3, 0.4]
Sums = {}
train_test_data = None
out_weights = []

def get_random_small_train(X, y, Percentage = 0.8):
    # return X_train & y_train
    data_keys = ['X_train', 'X_test', 'y_train', 'y_test']
    data_vals = train_test_split(X, y, test_size=(1-Percentage))
    train_test_data = dict(zip(data_keys, data_vals))
    return train_test_data['X_train'], train_test_data['y_train']


def train_linear(id, regType: sumRegressor, use_RFsample = False):
    X, ys = train_test_data['X_train'], train_test_data['y_train']
    if use_RFsample:
        # X, ys = get_random_small_train(X, ys)
        # make_moons(n_samples=100, shuffle=True, noise=None, random_state=None)
        pass
    check_X_y(X, ys, multi_output=True)
    models = {}
    for target_col in ys.columns:
        y = ys[target_col]
        reg = regType(**sumParams[id])
        reg.fit(X, y)
        models[target_col] = reg
    joblib.dump(models, f"linear/{regType.__name__}_{id}.model")


def eval_linear(id, regType: sumRegressor):
    models = joblib.load(f"linear/{regType.__name__}_{id}.model")
    X, ys = train_test_data['X_test'], train_test_data['y_test']
    evals = []
    out_w_dict = {'Regressor': regType.__name__, 'Weight': weight[id]}
    out_weights.append(out_w_dict)
    for target_col, reg in models.items():
        y_hat = reg.predict(X)  # fake
        y = ys[target_col]  # real
        rmse = metrics.mean_squared_error(y, y_hat, squared=False)
        r2 = metrics.r2_score(y, y_hat)
        eval_dict = {'Error': target_col, 'RMSE': rmse, 'R^2': r2}
        evals.append(eval_dict)
        if Sums.get(target_col) is None:
            Sums[target_col] = weight[id] * y_hat
        else:
            Sums[target_col] += weight[id] * y_hat
    print(f"{regType.__name__}_{id}")
    print(pd.DataFrame(evals))


def only_linear(trainset):
    """
    Description
    -----------
    create a linear combination, weight and regressors here to change
    
    Parameters
    ----------
    trainset : dict
        train_data_set
    
    Returns
    -------
    print result on screen
    """
    global train_test_data
    train_test_data = trainset

    for i, reg in enumerate(sumRegressors):
        train_linear(i, reg)
    for i, reg in enumerate(sumRegressors):
        eval_linear(i, reg)
    ys = train_test_data['y_test']
    evals = []
    for target_col in Sums:
        y_hat = Sums[target_col] # fake
        y = ys[target_col]  # real
        rmse = metrics.mean_squared_error(y, y_hat, squared=False)
        r2 = metrics.r2_score(y, y_hat)
        eval_dict = {'Error': target_col, 'RMSE': rmse, 'R^2': r2}
        evals.append(eval_dict)
    print("linear sum for {} regressors!".format(len(sumRegressors)))
    print(pd.DataFrame(out_weights))
    print(pd.DataFrame(evals))
    print("Average R2:  ", average_R2(evals))