pandas索引操作

import pandas as pd
import numpy as np

df_1 = pd.DataFrame([[‘Jack‘,‘M‘,40],[‘Tony‘,‘M‘,20],[‘Mary‘,‘F‘,30],[‘Bob‘,‘M‘,25]], columns=[‘name‘,‘gender‘,‘age‘])  #列表创建DataFrame
print(‘------ df_1是： ------‘)
print(df_1)

# 列名索引
a = df_1[‘name‘]
print(a)

# 同时取多列
b = df_1[[‘name‘,‘age‘]]
print(b)

# 切片索引，按行索引
bb = df_1[1:3]
print(bb)

aa = df_1[df_1.age>25]
print(aa)

# isin 索引
cc = df_1[df_1.name.isin([‘Jack‘,‘Bob‘])]
print(cc)

# loc取行
dd = df_1.loc[df_1.name.isin([‘Jack‘,‘Bob‘])] #去满足条件的所有行
print(dd)

# loc取行
ee = df_1.loc[1:3]  #直接按照标签取，不是属于切片，所以会1-3行全部取出来
print(ee)

ff = df_1.loc[df_1.name.isin([‘Jack‘,‘Bob‘]) | (df_1.age>25)]  #多个条件,‘|‘条件取行
print(‘the value of ff is: ‘)
print(ff)
print(df_1.name.isin([‘Jack‘,‘Bob‘]) | (df_1.age>25))

gg = df_1.loc[df_1.name.isin([‘Jack‘,‘Bob‘]) & (df_1.age>25)]  #多个条件取行,‘&‘条件取行
print(‘the value of gg is: ‘)
print(gg)
print(df_1.name.isin([‘Jack‘,‘Bob‘]) & (df_1.age>25))

hh = df_1.loc[df_1.name.isin([‘Jack‘,‘Bob‘]) | (df_1.age>25), ‘age‘]
print(hh)

ii = df_1.loc[1:3, ‘name‘:‘gender‘]  # ‘name‘:‘gender‘顺序有前后
print(‘the value of ii is: ‘)
print(ii)

jj = df_1.iloc[1:3]  #此时按照切片规则取行
print(‘the value of jj is: ‘)
print(jj)

mm = df_1.ix[1:3]  #此时按照标签规则取行，而不是切片规则
print(‘the value of mm is: ‘)
print(mm)

nn = df_1.ix[1:3, ‘name‘:‘gender‘]  #此时按照标签规则取行，而不是切片规则
print(‘the value of nn is: ‘)
print(nn)

array_test = np.array([[1,2,3,4],[2,3,4,5],[3,4,5,6]])
df_3 = pd.DataFrame(array_test, index = [‘aa‘, ‘bb‘, ‘ff‘], columns = [‘c1‘, ‘c2‘, ‘c3‘, ‘c4‘])  #数组创建DataFrame
print(‘------ df_3是： ------‘)
print(df_3)

df_4 = df_3[df_3>3]  #取满足条件的值
print(‘the value of df_4 is :‘)
print(df_4)

df_3[df_3>3]=0  #将满足条件的值重新赋值
print(‘the value of df_3 is :‘)
print(df_3)