Pandas

import pandas as pd
import numpy as np
s = pd.Series([1,3,6,np.nan,4,1])
print(s)

dates = pd.date_range('20191009',periods=6)
print(dates)

df = pd.DataFrame(np.random.randn(6,4),index=dates,columns=['a','b','c','d'])#行是index  列columns
print(df)

#直接用默认形式
df1 = pd.DataFrame(np.arange(12).reshape((3,4)))
print(df1)

#利用字典形式
df2 = pd.DataFrame({'A':1.,
                   'B':pd.Timestamp('20191009'),
                   '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'})
print(df2)
print(df2.index)#列的名字
print(df2.columns)#行的名字
print(df2.values)#值
print(df2.describe())
print(df2.T)#转置
df2.sort_index(axis=1,ascending=False)#按列排序  倒的序列排序
df2.sort_index(axis=0,ascending=False)#按行排序  倒的序列排序
df2.sort_values(by='E')#按某一列数值排序 

#选择数据
dates = pd.date_range('20191009',periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)),index=dates,columns=['A','B','C','D'])
# print(df['A'],df.A)
# print(df[0:3],df['20191009':'20191011'])
#select by label:loc
# print(df.loc['20191010'])
# print(df.loc[:,['A','B']])
print(df.loc['20191009',['A','B']])
#select by position:iloc
print(df.iloc[1:2,1:3])#筛选
print(df.iloc[[1,3,5],1:3])#逐个筛选
#mixed selection:ix
print(df.ix[:3,['A','C']])#第0行到第3行，A  C 两列
print(df[df.A>8])#在A那行大于8的数字显示出来

#设置值
dates = pd.date_range('20191009',periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)),index=dates,columns=['A','B','C','D'])
# df.iloc[2,2] = 1111
# df.loc['20191009','B'] = 222
# df[df.A>4] = 0
df.A[df.A>4] = 0
df['F']=np.nan#定义新的行
df['E'] = pd.Series([1,2,3,4,5,6],index=pd.date_range('20191009',periods=6))#赋值，需要匹配行的名字
print(df)

#处理丢失掉的数据
dates = pd.date_range('20191009',periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)),index=dates,columns=['A','B','C','D'])
df.iloc[0,1] = np.nan
df.iloc[1,2] = np.nan
print(df)
# print(df.fillna(value=0))
# print(df.isnull())
print(np.any(df.isnull()==True))#表格比较大，用这个看是否有丢失的数据