python数据分析库pandas使用之二

Day 2

Pandas基本操作

titanic数据集： 密码:pje4

groupby操作

• 小示例

  A 0
  B 15
  C 5
  A 10
  B 15
  C 20
  groupby三步走：
  1、split：分块。A分到一起，B分到一起，C分到一起。
  2、apply:计和
  3、combine：汇总–>A:10 B:30 C:25

import pandas as pd
df = pd.DataFrame({'key':['A','B','C','A','B','C','A','B','C'],
                  'data':[0,5,10,5,10,15,10,5,15]})
df

#普通汇总方式
for key in['A','B','C']:
    print(key,df[df['key'] == key].sum())
'''
A key     AAA
data     15
dtype: object
B key     BBB
data     20
dtype: object
C key     CCC
data     40
dtype: object

'''
#使用groupby
df.groupby('key').sum()
#或者整合numpy中的方法
import numpy as np
df.groupby('key').aggregate(np.sum)

• 使用titanic数据集示例

import pandas as pd
df = pd.read_csv('data/titanic.csv')
#计算不同性别人群的平均生存概率
df.groupby('Sex')['Survived'].mean()
'''
Sex
female    0.742038
male      0.188908
Name: Survived, dtype: float64
'''
#计算不同性别人群的年龄情况
df.groupby('Sex')['Age'].describe() 

数值计算

import pandas as pd
#index代表索引，column代表属性
df = pd.DataFrame([[1,2,3],[4,5,6]],index=['a','b'],columns=['A','B','C'])
df

df.sum() #默认按列求和
#df.sum(axis='index')
'''
A    5
B    7
C    9
dtype: int64
'''
df.sum(axis=1)#按行求和
#df.sum(axis='columns')
'''
a     6
b    15
dtype: int64
'''
df.mean(axis=1)#min() max() median()

# 二元统计
df =  pd.read_csv('data/titanic.csv')
#统计数据之间的协方差
df.cov()

#相关系数
df.corr()

#特征计数
#年龄一般计数
df['Age'].count()
#714
#各个值计数
df['Age'].value_counts() #降序排列
'''
24.00    30
22.00    27
18.00    26
19.00    25
30.00    25
         ..
55.50     1
70.50     1
66.00     1
23.50     1
0.42      1
Name: Age, Length: 88, dtype: int64
'''
df['Age'].value_counts(ascending = True) #升序排列
'''
0.42      1
23.50     1
66.00     1
70.50     1
55.50     1
         ..
30.00    25
19.00    25
18.00    26
22.00    27
24.00    30
Name: Age, Length: 88, dtype: int64
'''
#年龄分组
df['Age'].value_counts(ascending = True,bins=5)
'''
(64.084, 80.0]       11
(48.168, 64.084]     69
(0.339, 16.336]     100
(32.252, 48.168]    188
(16.336, 32.252]    346
Name: Age, dtype: int64
'''
#各个舱位的数量
df['Pclass'].value_counts(ascending=True)
'''
2    184
1    216
3    491
Name: Pclass, dtype: int64
'''

对象操作

• Seires结构的增删改查

import pandas as pd
data = [10,11,12]
index = ['a','b','c']
s = pd.Series(data=data,index=index)
s
'''
a    10
b    11
c    12
dtype: int64
'''
#查操作
s[0:2]
'''
a    10
b    11
dtype: int64
'''
s[[True,False,True]] #bool查询
'''
a    10
c    12
dtype: int64
'''
s.loc['b']
#11
s.iloc[2]
#12
#改操作
s1 = s.copy()
s1['a'] = 100
s1
'''
a    100
b     11
c     12
dtype: int64
'''
s1.replace(to_replace=100,value=101,inplace=False)#inplace=False,原始series不变，仅是执行此操作
s1
'''
a    100
b     11
c     12
dtype: int64
'''
s1.replace(to_replace=100,value=101,inplace=True)#inplace=True,原始series改变
s1
'''
a    101
b     11
c     12
dtype: int64
'''
s1.index=['a','b','d']
s1
'''
a    101
b     11
d     12
dtype: int64
'''
s1.rename(index={'a':'A'},inplace=True)
s1
'''
A    101
b     11
d     12
dtype: int64
'''
#增操作
s2 = pd.Series([100,500],index=['g','h'])
s2
'''
g    100
h    500
dtype: int64
'''
s1.append(s2)
'''
A    101
b     11
d     12
g    100
h    500
dtype: int64
'''
s1['j'] = 500
s1
'''
A    101
b     11
d     12
j    500
dtype: int64
'''
s1.append(s2,ignore_index=False)
'''
A    101
b     11
d     12
j    500
g    100
h    500
dtype: int64
'''
s1.append(s2,ignore_index=True)
'''
0    101
1     11
2     12
3    500
4    100
5    500
dtype: int64
'''
#删操作
del s1['b']
s1
'''
d     12
j    500
dtype: int64
'''
s1.drop('d',inplace=False)
'''
j    500
dtype: int64
'''

• Pandas结构的增删改查

data = [[1,2,3],[4,5,6]]
index = ['a','b']
columns = ['A','B','C']
df = pd.DataFrame(data=data,index= index, columns=columns)
df

#查操作
df.iloc[0]
'''
A    1
B    2
C    3
Name: a, dtype: int64
'''
df.loc['a']
'''
A    1
B    2
C    3
Name: a, dtype: int64
'''
#改操作
df.loc['a']['A'] = 150
df

df.index = ['f','g']
df

#增操作
df.loc['c'] = [1,2,3]
df

data = [[1,2,3],[4,5,6]]
index = ['a','b']
columns = ['A','B','C']
df2 = pd.DataFrame(data=data,index= index, columns=columns)
df3 = pd.concat([df,df2])
df3

df3 = pd.concat([df,df2],axis=1)
df3

df2['yu'] = [10,11]
df2

df4 = pd.DataFrame([[10,11],[12,13]],index=['a','b'],columns=['D','E'])
df4

df5 = pd.concat((df2,df4),axis=1)
df5

#删操作
df5.drop(['a'],axis=0,inplace=True)
df5

df5.drop(['A'],axis=1,inplace=True)
df5

df5.drop(['yu','D','E'],axis =1,inplace=True)
df5