1.将DataFrame里面的数值提取成list
userList=list()
userList= userList + df1['userID'].values.tolist()
2 . 构造含有index的dataFrame
actData = pd.DataFrame(index=userList)
actData = actData.sort_index()
3 . 通过一个DataFrame构造一个新的DataFrame
dfNew = pd.DataFrame(df1, columns=['userID', 'blogID', 'month'])
4 . 重新命名dataFrame的column的名字
df1 = df1.rename(columns={'date':'month'})
5 . 将全部项都是nan的row删除
df.dropna(how='ALL')
6 . dataFrame 展开成二维矩阵
import pandas as pd
a={'A':[1,2,3],'B':[4,5,6],'C':[7,8,9],'D':[10,11,12]}
df1=pd.DataFrame(a)
print(df1)
df2=df1.groupby(['A' ,'B']).size().unstack()
df2.fillna(0)
print(df2)
输出:
A B C D
0 1 4 7 10
1 2 5 8 11
2 3 6 9 12
B 4 5 6
A
1 1.0 NaN NaN
2 NaN 1.0 NaN
3 NaN NaN 1.0
7 .
commented_data = pd.merge(comment_data.rename(columns={'blogID':'blogComment' ,'userID':'userID1'}).
drop(['category'] ,axis=1) ,
post_data.rename(columns={'blogID':'userPost' ,'userID':'userID2'}).
drop(['month' ,'category'] ,axis=1) ,
left_on='blogComment' ,right_on='userPost' ,how='left').drop(['userPost'] ,axis=1)
8 . dataFrame 转换成Array
x = np.array(df1.drop(['userID' ,'growthValue'] ,axis=1))
y = np.array(df1['growthValue'])