import numpy as np
import pandas as pd
from sklearn.impute import SimpleImputer
from sklearn.model_selection import train_test_split


def missing_rate(data):
    total = data.isnull().sum().sort_values(ascending=False)
    percent = (data.isnull().sum() / data.isnull().count()).sort_values(ascending=False)
    missing_data = pd.concat([total, percent], axis=1, keys=['Total', 'Percent'])
    return missing_data


def impute_missing_values(data):
    imp = SimpleImputer(missing_values=np.nan, strategy='mean')
    data_reshape = data.values.reshape(-1, 1)
    return imp.fit_transform(data_reshape)


def conv_dict(train):
    dic = {}
    for x in train:
        if train[x].dtype != 'int64':
            tmp = train[[x, "Is_Lead"]].groupby(x, as_index=False).mean().sort_values(by='Is_Lead')
            dic[x] = {x: i for i, x in enumerate(list(np.array(tmp)[:, 0]))}
    return dic


def conv_data(train, dic):
    for x in train:
        if train[x].dtype != 'int64':
            train[x] = train[x].replace(dic[x])
    return train


if __name__ == '__main__':
    train = pd.read_csv('train.csv')
    test = pd.read_csv('test.csv')
    train = train.drop(['ID'], axis=1)
    train = train.drop('Product')
    y = np.array(train['Is_Lead'])
    x = np.array(train.drop('Is_Lead', 1))

    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.8, random_state=18)