目录

2.1

---

numpy

import numpy as np
array = np.array([[1,2,3],[2,3,4]])
print(array)
print('number of dim:',array.ndim)
print('shape:',array.shape)
print('size:',array.size)

 

pandas 

1,pandas 基本介绍

 

 

 

 

df2 = pd.DataFrame({'A':1.,
                   'B':pd.Timestamp('20130102'),
                   'C':pd.Series(1,index = list(range(4)),dtype = 'float32'),
                   'D':np.array([3]*4,dtype = 'int32'),
                   'E':pd.Categorical(["test","train","test","train"]),
                   'F':'foo'})
df2

 

 

 

 

 

2,pandas 选择数据 

 

3,pandas 设置数值

import pandas as pd
import numpy as np
dates =pd.date_range('20130101',periods=6)
df= pd.DataFrame(np.arange(24).reshape((6,4)),index = dates,columns = ['A','B','C','D'])

 

 

df['E'] = pd.Series([1,2,3,4,5,6],index = pd.date_range('20130101',periods = 6))

 4,pandas 处理丢失数据

print(df.iloc[[1,2,3],1:3])

df.iloc[0,1] = np.nan

df.iloc[1,2] = np.nan

print(df.fillna(value = 0)

pd.dropna(axis = 0,how ='any') #how ={'any','all'}

pd.dropna(axis = 1)