【机器学习基础】Python实现行转列？！超简单，赶快get起来

# 遇事不要慌，先导个包吧import pandas as pdimport numpy as np
# 造假数据data = {'name':['严小样儿','严小样儿','严小样儿','才华横竖都溢','才华横竖都溢','才华横竖都溢','幽兰幽香','幽兰幽香','幽兰幽香'],       'subject':['Python','C','SQL','Python','C','SQL','Python','C','SQL'],       'score':[95,60,95,96,95,80,99,94,88]}
# 生成dfdf = pd.DataFrame(data)df

#df.pivot(index=None, columns=None, values=None)df.pivot(index='name',columns='subject',values='score')

# 造含有重复值的假数据data1 = {'name':['严小样儿','严小样儿','严小样儿','严小样儿','才华横竖都溢','才华横竖都溢','才华横竖都溢','幽兰幽香','幽兰幽香','幽兰幽香'],       'subject':['Python','Python','C','SQL','Python','C','SQL','Python','C','SQL'],       'score':[95,95,60,95,96,95,80,99,94,88]}
df1 = pd.DataFrame(data1)df1

df1.pivot(index='name',columns='subject',values='score')
# 一旦有重复值，就会报错。ValueError: Index contains duplicate entries, cannot reshape

df1.drop_duplicates().pivot(index='name',columns='subject',values='score')

# pivot_table(data, values=None, index=None, columns=None, aggfunc='mean')pd.pivot_table(df1,index='name',columns='subject',values='score',aggfunc={'score':'max'})

# 重复数据集也可以df_pivot = pd.pivot_table(df1,index='name',columns='subject',values='score',aggfunc={'score':'max'})# 增加一个新列：Totaldf_pivot['Total'] = df_pivot.apply(lambda x:np.sum(x),axis = 1)df_pivot

# 使用去重数据集才可以pd.pivot_table(df,index='name',values='score',aggfunc='sum')

# 使用join方法把总分列加进去。total = pd.pivot_table(df,index='name',values='score',aggfunc='sum')pd.pivot_table(df,index='name',columns='subject',values='score').join(total)

total1 = pd.pivot_table(df,index='name',values='score',aggfunc='sum').rename({'score':'总分'},axis=1)pd.pivot_table(df,index='name',columns='subject',values='score').join(total1)