Series索引,创建
import pandas as pd
t1=pd.Series([1,2,3,4,2,2],index=list('abcdef'))
print(t1)
print('*'*100)
tem_dict={'name':'3','age':30,'tel':10010}
t2=pd.Series(tem_dict)
print(t2)
print(t2.astype('float'))
print(t2['age'])
print(t2[1])
print(t2[:2])
print('*'*100)
print(t2[[1,2]])
print(t2[['age','name']])
print('*'*100)
print(t1[t1>2])
print('*'*100)
print(t1.index)
print('*'*100)
print(list(t1.index))
print(list(t1.index)[:2])
for i in t1.index:
print(i)
print('*'*100)
print(len(t1.index))
print(t1.values)
DataFrame描述信息
import pandas as pd
import numpy as np
print(pd.DataFrame(np.arange(12).reshape(3,4)))
print(pd.DataFrame(np.arange(12).reshape(3,4),index=list('abc'),columns=list('wxyz')))
d1={'tel':['130','111'],'name':['lj','ljm']}
t2=pd.DataFrame(d1)
print(t2)
print(t2.index)
print(t2.columns)
print(t2.values)
print(t2.shape)
print(t2.dtypes)
print(t2.ndim)
DataFrame索引
import pandas as pd
import numpy as np
t3=pd.DataFrame(np.arange(12).reshape(3,4),index=list('abc'),columns=list('wxyz'))
print(t3)
print(t3.loc['a','z'])
print(t3.loc['a'])
print(t3.loc['a',:])
print(t3.loc[:,'y'])
print(t3.loc[['a','c'],:])
print(t3.loc[:,['y','z']])
print(t3.iloc[1])
print(t3.iloc[1,:])
print(t3.iloc[:,1])
print(t3.iloc[:,[1,2]])
print(t3.iloc[1:,:1])
布尔索引+缺失值填充
import pandas as pd
import numpy as np
t3=pd.DataFrame(np.arange(12).reshape(3,4),index=list('abc'),columns=list('wxyz'))
print(pd.notnull(t3))
t3.iloc[[1,2],[1,2]]=np.nan
print(t3)
print('*'*100)
print(t3[pd.notnull(t3['x'])])
print('*'*100)
print(t3.dropna(axis=0,how='any'))
print(t3.fillna(0))
print(t3.fillna(t3.mean()))
print('*'*100)
print(t3['x'].fillna(t3['x'].mean()))