数据分析-展示缺失值情况并提取信息

一、展示缺失值详情

#查看缺失值情况
def missing_values(alldata):
    alldata_na = pd.DataFrame(alldata.isnull().sum(), columns={'missingNum'})
    alldata_na['missingRatio'] = alldata_na['missingNum']/len(alldata)*100
    alldata_na['existNum'] = len(alldata) - alldata_na['missingNum']
    
    alldata_na['train_notna'] = len(train) - train.isnull().sum()
    alldata_na['test_notna'] = alldata_na['existNum'] - alldata_na['train_notna'] 
    alldata_na['dtype'] = alldata.dtypes
    
    alldata_na = alldata_na[alldata_na['missingNum']>0].reset_index().sort_values(by=['missingNum','index'],ascending=[False,True])
    alldata_na.set_index('index',inplace=True)
    return alldata_na
 
alldata_na = missing_values(alldata)
alldata_na

二、对特定的缺失值进行观察

#对于Name*相关空值
a = pd.Series(alldata.columns)
NameList = a[a.str.contains('Name')].values

allNameNa = alldata_na.ix[NameList ,:]
print(allNameNa )

三、对普通的DataFrame进行数据缺失检查函数

np.isnan(dataframe).any()