风控（五）——基于决策树规则挖掘油品贷案例

本数据为滴滴司机使用油品贷的数据。
油品贷的坏账率高达5%，非常高，一定是会赔钱的。并且能够通过欺诈检测。
来申请油品贷的司机本身是已经有A卡了，A卡评级为A-F。本来是只有F不放款，但是在油品贷上只有评级为A放款才能不亏钱。
滴滴是和很多加油站有合作的，加油站会给滴滴提供司机数据。
导入包

import pandas as pd
import numpy as np

#显示全部特征
pd.set_option('display.max_columns', None)

导入数据

data = pd.read_excel('oil_data_for_tree.xlsx')
data.head()

org_lst 不需要做特殊变换，直接去重
agg_lst 数值型变量做聚合
dstc_lst 文本型变量做cnt

org_lst = ['uid','create_dt','oil_actv_dt','class_new','bad_ind']
agg_lst = ['oil_amount','discount_amount','sale_amount','amount','pay_amount','coupon_amount','payment_coupon_amount']
dstc_lst = ['channel_code','oil_code','scene','source_app','call_source']

数据重组

df = data[org_lst].copy()
df[agg_lst] = data[agg_lst].copy()
df[dstc_lst] = data[dstc_lst].copy()

看一下缺失情况

df.isna().mean()

看一下基础变量的describe

df.describe()

对creat_dt做补全，用oil_actv_dt来填补，并且截取6个月的数据。
构造变量的时候不能直接对历史所有数据做累加。
否则随着时间推移，变量分布会有很大的变化。

def time_isna(x,y):
    if str(x) == 'NaT':
        x = y
    else:
        x = x
    return x
df2 = df.sort_values(['uid','create_dt'],ascending = False)
df2['create_dt'] = df2.apply(lambda x: time_isna(x.create_dt,x.oil_actv_dt),axis = 1)
df2['dtn'] = (df2.oil_actv_dt - df2.create_dt).apply(lambda x :x.days)
df = df2[df2['dtn']<180]
df.head()

对org_list变量求历史贷款天数的最大间隔，并且去重

base = df[org_lst]
base['dtn'] = df['dtn']
base = base.sort_values(['uid','create_dt'],ascending = False)
base = base.drop_duplicates(['uid'],keep = 'first')
base.shape

维度(11099, 6)
做变量衍生

gn = pd.DataFrame()
for i in agg_lst:
    tp = pd.DataFrame(df.groupby('uid').apply(lambda df:len(df[i])).reset_index())
    tp.columns = ['uid',i + '_cnt']
    if gn.empty == True:
        gn = tp
    else:
        gn = pd.merge(gn,tp,on = 'uid',how = 'left')
    tp = pd.DataFrame(df.groupby('uid').apply(lambda df:np.where(df[i]>0,1,0).sum()).reset_index())
    tp.columns = ['uid',i + '_num']
    if gn.empty == True:
        gn = tp
    else:
        gn = pd.merge(gn,tp,on = 'uid',how = 'left')
    tp = pd.DataFrame(df.groupby('uid').apply(lambda df:np.nansum(df[i])).reset_index())
    tp.columns = ['uid',i + '_tot']
    if gn.empty == True:
        gn = tp
    else:
        gn = pd.merge(gn,tp,on = 'uid',how = 'left')
    tp = pd.DataFrame(df.groupby('uid').apply(lambda df:np.nanmean(df[i])).reset_index())
    tp.columns = ['uid',i + '_avg']
    if gn.empty == True:
        gn = tp
    else:
        gn = pd.merge(gn,tp,on = 'uid',how = 'left')
    tp = pd.DataFrame(df.groupby('uid').apply(lambda df:np.nanmax(df[i])).reset_index())
    tp.columns = ['uid',i + '_max']
    if gn.empty == True:
        gn = tp
    else:
        gn = pd.merge(gn,tp,on = 'uid',how = 'left')
    tp = pd.DataFrame(df.groupby('uid').apply(lambda df:np.nanmin(df[i])).reset_index())
    tp.columns = ['uid',i + '_min']
    if gn.empty == True:
        gn = tp
    else:
        gn = pd.merge(gn,tp,on = 'uid',how = 'left')
    tp = pd.DataFrame(df.groupby('uid').apply(lambda df:np.nanvar(df[i])).reset_index())
    tp.columns = ['uid',i + '_var']
    if gn.empty == True:
        gn = tp
    else:
        gn = pd.merge(gn,tp,on = 'uid',how = 'left')
    tp = pd.DataFrame(df.groupby('uid').apply(lambda df:np.nanmax(df[i]) -np.nanmin(df[i]) ).reset_index())
    tp.columns = ['uid',i + '_var']
    if gn.empty == True:
        gn = tp
    else:
        gn = pd.merge(gn,tp,on = 'uid',how = 'left')
    tp = pd.DataFrame(df.groupby('uid').apply(lambda df:np.nanmean(df[i])/max(np.nanvar(df[i]),1)).reset_index())
    tp.columns = ['uid',i + '_var']
    if gn.empty == True:
        gn = tp
    else:
        gn = pd.merge(gn,tp,on = 'uid',how = 'left')

对dstc_lst变量求distinct个数

gc = pd.DataFrame()
for i in dstc_lst:
    tp = pd.DataFrame(df.groupby('uid').apply(lambda df: len(set(df[i]))).reset_index())
    tp.columns = ['uid',i + '_dstc']
    if gc.empty == True:
        gc = tp
    else:
        gc = pd.merge(gc,tp,on = 'uid',how = 'left')

将变量组合在一起

fn = pd.merge(base,gn,on= 'uid')
fn = pd.merge(fn,gc,on= 'uid') 
fn.shape

维度(11099, 74)

fn = fn.fillna(0)
fn.head(100)

训练决策树模型

x = fn.drop(['uid','oil_actv_dt','create_dt','bad_ind','class_new'],axis = 1)
y = fn.bad_ind.copy()
from sklearn import tree

dtree = tree.DecisionTreeRegressor(max_depth = 2,min_samples_leaf = 500,min_samples_split = 5000)
dtree = dtree.fit(x,y)

输出决策树图像，并作出决策

import pydotplus 
from IPython.display import Image
from sklearn.externals.six import StringIO
import os
os.environ["PATH"] += os.pathsep + 'C:/Program Files (x86)/Graphviz2.38/bin/'
with open(path + "dt.dot", "w") as f:
    tree.export_graphviz(dtree, out_file=f)
dot_data = StringIO()
tree.export_graphviz(dtree, out_file=dot_data,
                         feature_names=x.columns,
                         class_names=['bad_ind'],
                         filled=True, rounded=True,
                         special_characters=True)
graph = pydotplus.graph_from_dot_data(dot_data.getvalue()) 
Image(graph.create_png())

通过加入两条规则，我们最终可以将坏客户率控制在1.2%。