对pandas的层次索引与取值的新方法详解

import numpy as np
import pandas as pd

s1 = pd.Series(data=[99, 80, 76, 80, 99],
    index=[['2017', '2017', '2018', '2018', '2018'], ['张伊曼', '张巧玲', '张诗诗', '张思思', '张可可']])
print(s1)

# DataFrame的层次索引
df1 = pd.DataFrame({
 'year': [2016, 2016, 2017, 2017, 2018],
 'fruit': ['apple', 'banana', 'apple', 'banana', 'apple'],
 'production': [10, 30, 20, 70, 100],
 'profits': [40, 30, 60, 80,10],
})
print("df1===================================")
print(df1)

df2 = df1.set_index(['year', 'fruit'])
print("df2===================================")
print(df2)

print("df2.index===================================")
print(df2.index)

print("df2.sum(level='year')===================================")
print(df2.sum(level='year'))

print("df2.mean(level='fruit')===================================")
print(df2.mean(level='fruit'))

print("df2.sum(level=['year', 'fruit'])===================================")
print(df2.sum(level=['year', 'fruit']))

# # 取值的新方法
s1 = pd.Series(data=[99, 80, 76, 80, 99],
    index=[['2017', '2017', '2018', '2018', '2018'], ['张伊曼', '张巧玲', '张诗诗', '张思思', '张可可']])

print("s1=================================")
print(s1)

print("s1.iloc[2]=================================")
print(s1.iloc[2])

print("s1.loc['2018']['张思思']=================================")
print(s1.loc['2018']['张思思'])

df1 = pd.DataFrame({
 'year': [2016, 2016, 2017, 2017, 2018],
 'fruit': ['apple', 'banana', 'apple', 'banana', 'apple'],
 'production': [10, 30, 20, 70, 100],
 'profits': [40, 30, 60, 80,10],
})
print("df1===================================")
print(df1)

print("旧方法获取值===================================")
print("df1['year'][0]===================================")
print(df1['year'][0])

print("df1.ix[0]['year']===================================")
print(df1.ix[0]['year'])

print("新方法获取值===================================")
print("df1.iloc[0][3]===================================")
print(df1.iloc[0][3])

print("df1.loc[0]['year']===================================")
print(df1.loc[0]['year'])