共享单车之租赁需求预估第2关：特征工程

import pandas as pd
import numpy as np
from datetime import datetime

def transform_data(train_df):
    '''
    将train_df中的datetime划分成year、month、date、weekday、hour
    :param train_df:从bike_train.csv中读取的DataFrame
    :return:无
    '''

    #********* Begin *********#
    train_df['date'] = train_df.datetime.apply(lambda x:x.split()[0])
    train_df['hour'] = train_df.datetime.apply(lambda x:x.split()[1].split(':')[0]).astype('int')
    train_df['year'] = train_df.datetime.apply(lambda x:x.split()[0].split('-')[0]).astype('int')
    train_df['month'] = train_df.datetime.apply(lambda x: x.split()[0].split('-')[1]).astype('int')
    train_df['weekday'] = train_df.date.apply(lambda x: datetime.strptime(x, '%Y-%m-%d').isoweekday())
    return train_df

    #********* End **********#