import numpy as np
import pandas as pd
import warnings
warnings.filterwarnings('ignore')
data=pd.read_csv('/Users/chouyangyu/Downloads/cs-training.csv')
data.head(10)
data=data.iloc[:,1:]
data.columns= ['Label', 'RevolvingRatio', 'Age', '30-59D', 'DebtRatio', 'MonthlyIncome',
'OpenL', '90D', 'RealEstate', '60-89D', 'Dependents']
data.head(10)
missdf=data.isnull().sum().sort_values(ascending=False).reset_index()
missdf.columns=['feature','miss_num']
missdf['miss_percentage']=missdf['miss_num']/data.shape[0]