11

第五题

#encoding=utf8
#********* Begin *********#
#encoding=utf8
#********* Begin *********#
import pandas as pd
from sklearn.linear_model import LinearRegression
train_data = pd.read_csv('./step3/train_data.csv')
train_label = pd.read_csv('./step3/train_label.csv')
train_label = train_label['target']
test_data = pd.read_csv('./step3/test_data.csv')
lr = LinearRegression()
lr.fit(train_data,train_label)
predict = lr.predict(test_data)
df = pd.DataFrame({
    'result':predict})
df.to_csv('./step3/result.csv', index=False)
#********* End *********#
#********* End *********#

第一题

import numpy as np

'''
arr为一个ndarray类型的数组,line为花式索引的索引数组
'''
def advanced_index(arr,line):
    # ********** Begin *********** #
    # 利用花式索引获取 arr 数组的 line 行
    a = arr[line, :]

    # 获取数组 a 的四个角的元素
    b = np.array([a[0, 0], a[0, -1], a[-1, 0], a[-1, -1]])

    # 利用布尔索引获取 b 中大于 10 的元素
    c = b[b > 10]

    # *********** End ************ #
    return c

def main():
    line = list(map(lambda x:int(x),input().split(",")))
    arr = np.arange(24).reshape(6, 4)
    print(advanced_index(arr,line))

if __name__ == '__main__':
    main()

第四题

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')
    #********* End **********#

    train_df['weekday'] = train_df.date.apply(lambda x: datetime.strptime(x, '%Y-%m-%d').isoweekday())

    return train_df