基于python 信用卡评分系统 的数据分析

import pandas as pd
import matplotlib.pyplot as plt #导入图像库
from sklearn.ensemble import RandomForestRegressor

# 用随机森林对缺失值预测填充函数
def set_missing(df):
    # 把已有的数值型特征取出来
    process_df = df.ix[:,[5,0,1,2,3,4,6,7,8,9]]
    # 分成已知该特征和未知该特征两部分
    known = process_df[process_df.MonthlyIncome.notnull()].as_matrix()
    unknown = process_df[process_df.MonthlyIncome.isnull()].as_matrix()
    # X为特征属性值
    X = known[:, 1:]
    # y为结果标签值
    y = known[:, 0]
    # fit到RandomForestRegressor之中
    rfr = RandomForestRegressor(random_state=0, n_estimators=200,max_depth=3,n_jobs=-1)
    rfr.fit(X,y)
    # 用得到的模型进行未知特征值预测
    predicted = rfr.predict(unknown[:, 1:]).round(0)
    print(predicted)
    # 用得到的预测结果填补原缺失数据
    df.loc[(df.MonthlyIncome.isnull()), 'MonthlyIncome'] = predicted
    return df

data = pd.read_csv(r'E:\Python\Source\CreditScore\cs-training.csv')
process_df = data.iloc[:,[5,0,1,2,3,4,6,7,8,9]]
known = process_df[process_df.MonthlyIncome.notnull()].as_matrix()
unknown = process_df[process_df.MonthlyIncome.isnull()].as_matrix()
X = known[:, 1:]
y = known[:, 0]
# fit到RandomForestRegressor之中
rfr = RandomForestRegressor(random_state=0, n_estimators=200,max_depth=3,n_jobs=-1)
rfr.fit(X,y)
# 用得到的模型进行未知特征值预测
predicted = rfr.predict(unknown[:, 1:]).round(0)
print(predicted)
data.loc[(data.MonthlyIncome.isnull()), 'MonthlyIncome'] = predicted

[8311. 1159. 8311. ... 1159. 2554. 2554.]

data=data.dropna()#删除比较少的缺失值
data = data.drop_duplicates()#删除重复项

#异常值处理
#x1 = data["age"]
x2 = data["RevolvingUtilizationOfUnsecuredLines"]
x3 = data["DebtRatio"]
fig = plt.figure(1)
ax = fig.add_subplot(111)
ax.boxplot([x2,x3])
ax.set_xticklabels(["RevolvingUtilizationOfUnsecuredLines","DebtRatio"])

[Text(0,0,'RevolvingUtilizationOfUnsecuredLines'), Text(0,0,'DebtRatio')]

output_5_1.png

#异常值处理
data = data[data["age"] > 0]
data = data[data['NumberOfTime30-59DaysPastDueNotWorse'] < 90]#剔除异常值

# 好坏客户的整体分析
data['SeriousDlqin2yrs']=1-data['SeriousDlqin2yrs']
grouped = data["SeriousDlqin2yrs"].groupby(data["SeriousDlqin2yrs"]).count()
print("坏客户占比：{:.2%}".format(grouped[0]/grouped[1]))
print(grouped)
grouped.plot(kind="bar")

output_7_2.png

坏客户占比：7.16%
SeriousDlqin2yrs
0      9706
1    135648
Name: SeriousDlqin2yrs, dtype: int64





<matplotlib.axes._subplots.AxesSubplot at 0x126eecc0>

 Y = data['SeriousDlqin2yrs']