我的目标是把csv文件中的某一列按类别同时自动拆分文件,按照一个特定类别输出文件。
废话不多说上代码
import pandas as pd
#read data from csv
df=pd.read_csv('bilibili(2).csv',sep=',',engine='python',header=[1,2],encoding="UTF-8")
# get the columns of df
df.columns = ['title', 'type']
c = list(df.columns)
print(c[1:2])
grouped=df.groupby(c[1:2]) #according different categories to group by the df
#delete duplicated data
ind_frame=df.drop_duplicates(subset=['type'], keep='first')
print(ind_frame.type)
print(range(len(ind_frame)))
for name in ind_frame.type:
print(name)
df[df.type==name].to_csv("rawdata\\_"+u"%s" %name+".csv")