2020c题数据预处理

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

#input excel as data
data1 = pd.read_csv(r'C:\Users\10690\Desktop\pacifier.csv')
data2 = pd.read_csv(r'C:\Users\10690\Desktop\microwave.csv')
data3 = pd.read_csv(r'C:\Users\10690\Desktop\hair_dryer.csv')

print(data1.keys())
data1.marketplace = 'US'   #replace marketplace to 'US'
row = data1.shape[0]    #shape[0]为行数  shape[1]为列数
print(row)
df = data1[data1['product_category'].isin(['Baby' , 'baby'])]  #选取data1中A列包含 的行
df.product_category = 'Baby'

df.marketplace = 'US'   #replace marketplace to 'US'

#output the data as csv
path = r'C:\Users\10690\