逻辑回归专题02
逻辑回归案例
- 1.逻辑回归制作评分卡
-
- 1.1.数据的预处理
- 1.2.分箱操作
- 1.3.计算各箱WOE值并映射到数据
- 1.4.建模及模型验证
- 1.5.制作评分卡
1.逻辑回归制作评分卡
1.1.数据的预处理
1、导入所需要的库
%matplotlib inline
import numpy as np
import pandas as pd
from sklearn.linear_model import LogisticRegression as LR
2、获取数据并对数据进行预处理
data = pd.read_csv(r'D:\python练习\python sklearn芝士/rankingcard.csv',index_col=0)
data.head()
data.info()
<class 'pandas.core.frame.DataFrame'>
Int64Index: 150000 entries, 1 to 150000
Data columns (total 11 columns):
SeriousDlqin2yrs 150000 non-null int64
RevolvingUtilizationOfUnsecuredLines 150000 non-null float64
age 150000 non-null int64
NumberOfTime30-59DaysPastDueNotWorse 150000 non-null int64
DebtRatio 150000 non-null float64
MonthlyIncome 120269 non-null float64
NumberOfOpenCreditLinesAndLoans 150000 non-null int64
NumberOfTimes90DaysLate 150000 non-null int64
NumberRealEstateLoansOrLines 150000 non-null int64
NumberOfTime60-89DaysPastDueNotWorse 150000 non-null int64
NumberOfDependents 146076 non-null float64
dtypes: float64(4), int64(7)
memory usage: 13.7 MB
##############################################
#去除重复值
##############################################
data.drop_duplicates(inplace=True)
data.index = range(data.shape[0]) #删除重复值之后恢复
data.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 149391 entries, 0 to 149390
Data columns (total 11 columns):
SeriousDlqin2yrs 149391 non-null int64
RevolvingUtilizationOfUnsecuredLines 149391 non-null float64
age 149391 non-null int64
NumberOfTime30-59DaysPastDueNotWorse 149391 non-null int64
DebtRatio 149391 non-null float64
MonthlyIncome 120170 non-null float64
NumberOfOpenCreditLinesAndLoans 149391 non-null int64
NumberOfTimes90DaysLate 149391 non-null int64
NumberRealEstateLoansOrLines 149391 non-null int64
NumberOfTime60-89DaysPastDueNotWorse 149391 non-null int64
NumberOfDependents 145563 non-null float64
dtypes: float64(4), int64(7)
memory usage: 12.5 MB
##############################################
#填补缺失值
##############################################
data.isnull().sum()/data.shape[0]
data['NumberOfDependents'].fillna(int(data['NumberOfDependents'].mean()),inplace=True) #缺失值用均值进行填充
#使用随机森林进行填充一个特征的缺失值的函数
def fill_missing_rf(x,y,to_fill):
#x:要填补的特征矩阵
#y:完整的，没有缺失值的标签
#to_fill:字符串，要填补的那一列的名称
df = x.copy()
fill = df.loc[:,to_fill]
df = pd.concat([df.loc[:,df.columns != to_fill],pd.DataFrame(y)],axis = 1) #构建新特征矩阵和新标签
Ytrain = fill[fill.notnull()]
Ytest = fill[fill.isnull()]
Xtrain = df.iloc[Ytrain.index ,:]
Xtest = df.iloc[Ytest.index , :] #构建训练集和测试集
from sklearn.ensemble import RandomForestRegressor as rfr
rfr = rfr(n_estimators= 100)
rfr = rfr.fit(Xtrain , Ytrain)
Ypredict = rfr.predict(Xtest)
return Ypredict #用随机森林回归来填补缺失值
#传参产生结果
x = data.iloc[:,1:]
y = data['SeriousDlqin2yrs']
x.shape
y_pred = fill_missing_rf(x,y,'MonthlyIncome')
data.loc[data.loc[:,'MonthlyIncome'].isnull(),'MonthlyIncome'] = y_pred
##############################################
#处理异常值
##############################################
data.describe([0.01,0.1,0.25,0.5,0.75,0.9,0.99]).T #描述性统计
#观察统计数据中存在age为0的异常值，于是打算直接删除该样本
(data['age'] == 0).sum() #1
data =data[data['age'] != 0]
#观察统计数据中存在逾期异常，于是打算直接删除该样本
data[data.loc[:,'NumberOfTimes90DaysLate']>90].count()
data = data[data.loc[:,'NumberOfTimes90DaysLate']<90]
#恢复索引
data.index = range(data.shape[0])
data.info()
##############################################
#样本不均衡
##############################################
x = data.iloc[:,1:]
y = data.iloc[:,0]
y.value_counts()
0 139293
1 9873
n_sample = x.shape[0]
n_1_sample = y.value_counts()[1]
n_2_sample = y.value_counts()[0]
print('样本个数:{};1占{:.2%};0占{:.2%}'.format(n_sample ,n_1_sample/n_sample ,n_2_sample/n_sample))
样本个数:149166;1占6.62%;0占93.38%
#使用上采样的方法来平衡样本
import imblearn
from imblearn.over_sampling import SMOTE
sm = SMOTE(random_state= 0)
x,y = sm.fit_sample(x,y)
n_sample = x.shape[0]
n_1_sample = y.value_counts()[1]
n_2_sample = y.value_counts()[0]
print('样本个数:{};1占{:.2%};0占{:.2%}'.format(n_sample ,n_1_sample/n_sample ,n_2_sample/n_sample))
样本个数:278584;1占50.00%;0占50.00%
##############################################
#分训练集和测试集
##############################################
from sklearn.model_selection import train_test_split
x = pd.DataFrame(x)
y = pd.DataFrame(y)
x_train , x_vali , y_train , y_vali = train_test_split(x,y,test_size = 0.3 , random_state = 0)
model_data = pd.concat([y_train , x_train],axis = 1)
model_data.index = range(model_data.shape[0])
model_data.columns = data.columns
model_data.to_csv(r'D:\python练习\python sklearn芝士\model_data.csv')
vali_data = pd.concat([y_vali , x_vali],axis = 1)
vali_data.index = range(vali_data.shape[0])
vali_data.columns = data.columns
vali_data.to_csv(r'D:\python练习\python sklearn芝士\vali_data.csv')
1.2.分箱操作
##############################################
#将选取最佳
##############################################
def graphforbestbin(DF, X, Y, n=5,q=20,graph=True):
'''
自动最优分箱函数，基于卡方检验的分箱
参数：
DF: 需要输入的数据
X: 需要分箱的列名
Y: 分箱数据对应的标签 Y 列名
n: 保留分箱个数
q: 初始分箱的个数
graph: 是否要画出IV图像
区间为前开后闭 (]
'''
DF = DF[[X,Y]].copy()
DF["qcut"],bins = pd.qcut(DF[X], retbins=True, q=q,duplicates="drop")
coount_y0 = DF.loc[DF[Y]==0].groupby(by="qcut").count()[Y]
coount_y1 = DF.loc[DF[Y]==1].groupby(by="qcut").count()[Y]
num_bins = [*zip(bins,bins[1:],coount_y0,coount_y1)]
for i in range(q):
if 0 in num_bins[0][2:]:
num_bins[0:2] = [(
num_bins[0][0],
num_bins[1][1],
num_bins[0][2]+num_bins[1][2],
num_bins[0][3]+num_bins[1][3])]
continue
for i in range(len(num_bins)):
if 0 in num_bins[i][2:]:
num_bins[i-1:i+1] = [(
num_bins[i-1][0],
num_bins[i][1],
num_bins[i-1][2]+num_bins[i][2],
num_bins[i-1][3]+num_bins[i][3])]
break
else:
break
def get_woe(num_bins):
columns = ["min","max","count_0","count_1"]
df = pd.DataFrame(num_bins,columns=columns)
df["total"] = df.count_0 + df.count_1
df["percentage"] = df.total / df.total.sum()
df["bad_rate"] = df.count_1 / df.total
df["good%"] = df.count_0/df.count_0.sum()
df["bad%"] = df.count_1/df.count_1.sum()
df["woe"] = np.log(df["good%"] / df["bad%"])
return df
def get_iv(df):
rate = df["good%"] - df["bad%"]
iv = np.sum(rate * df.woe)
return iv
IV = []
axisx = []
while len(num_bins) > n:
pvs = []
for i in range(len(num_bins)-1):
x1 = num_bins[i][2:]
x2 = num_bins[i+1][2:]
pv = scipy.stats.chi2_contingency([x1,x2])[1]
pvs.append(pv)
i = pvs.index(max(pvs))
num_bins[i:i+2] = [(
num_bins[i][0],
num_bins[i+1][1],
num_bins[i][2]+num_bins[i+1][2],
num_bins[i][3]+num_bins[i+1][3])]
bins_df = pd.DataFrame(get_woe(num_bins))
axisx.append(len(num_bins))
IV.append(get_iv(bins_df))
if graph:
plt.figure()
plt.plot(axisx,IV)
plt.xticks(axisx)
plt.xlabel("number of box")
plt.ylabel("IV")
plt.show()
return bins_df
for i in model_data.columns[1:-1]:
print(i)
graphforbestbin(model_data,i,"SeriousDlqin2yrs",n=2,q=20)
类似于上面的关于 RevolvingUtilizationOfUnsecuredLines的学习曲线
auto_col_bins = {
"RevolvingUtilizationOfUnsecuredLines":6,
"age":5,
"DebtRatio":4,
"MonthlyIncome":3,
"NumberOfOpenCreditLinesAndLoans":5}
#不能使用自动分箱的变量
hand_bins = {
"NumberOfTime30-59DaysPastDueNotWorse":[0,1,2,13]
,"NumberOfTimes90DaysLate":[0,1,2,17]
,"NumberRealEstateLoansOrLines":[0,1,2,4,54]
,"NumberOfTime60-89DaysPastDueNotWorse":[0,1,2,8]
,"NumberOfDependents":[0,1,2,3]}
#保证区间覆盖使用 np.inf替换最大值，用-np.inf替换最小值
#原因：比如一些新的值出现，例如家庭人数为30，以前没出现过，改成范围为极大值之后，这些新值就都能分到箱里边了
hand_bins = {
k:[-np.inf,*v[:-1],np.inf] for k,v in hand_bins.items()}
bins_of_col = {
}
# 生成自动分箱的分箱区间和分箱后的 IV 值
for col in auto_col_bins:
bins_df = graphforbestbin(model_data,col
,"SeriousDlqin2yrs"
,n=auto_col_bins[col]
#使用字典的性质来取出每个特征所对应的箱的数量
,q=20
,graph=False)
bins_list = sorted(set(bins_df["min"]).union(bins_df["max"]))
#保证区间覆盖使用 np.inf 替换最大值 -np.inf 替换最小值
bins_list[0],bins_list[-1] = -np.inf,np.inf
bins_of_col[col] = bins_list
#合并手动分箱数据
bins_of_col.update(hand_bins)
bins_of_col
1.3.计算各箱WOE值并映射到数据
data = model_data.copy()
#函数pd.cut，可以根据已知的分箱间隔把数据分箱
#参数为 pd.cut(数据，以列表表示的分箱间隔)
data = data[["age","SeriousDlqin2yrs"]].copy()
data["cut"] = pd.cut(data["age"],[-np.inf, 48.49986200790144, 58.757170160044694, 64.0, 74.0, np.inf])
data.head()
#将数据按分箱结果聚合，并取出其中的标签值
data.groupby("cut")["SeriousDlqin2yrs"].value_counts()
#使用unstack()来将树状结构变成表状结构
data.groupby("cut")["SeriousDlqin2yrs"].value_counts().unstack()
bins_df = data.groupby("cut")["SeriousDlqin2yrs"].value_counts().unstack()
bins_df["woe"] = np.log((bins_df[0]/bins_df[0].sum())/(bins_df[1]/bins_df[1].sum()))
bins_df
def get_woe(df,col,y,bins):
df = df[[col,y]].copy()
df["cut"] = pd.cut(df[col],bins)
bins_df = df.groupby("cut")[y].value_counts().unstack()
woe = bins_df["woe"] = np.log((bins_df[0]/bins_df[0].sum())/(bins_df[1]/bins_df[1].sum()))
return woe
#将所有特征的WOE存储到字典当中
woeall = {
}
for col in bins_of_col:
woeall[col] = get_woe(model_data,col,"SeriousDlqin2yrs",bins_of_col[col])
woeall
#不希望覆盖掉原本的数据，创建一个新的DataFrame，索引和原始数据model_data一模一样
model_woe = pd.DataFrame(index=model_data.index)
#将原数据分箱后，按箱的结果把WOE结构用map函数映射到数据中
model_woe["age"] = pd.cut(model_data["age"],bins_of_col["age"]).map(woeall["age"])
#对所有特征操作可以写成：
for col in bins_of_col:
model_woe[col] = pd.cut(model_data[col],bins_of_col[col]).map(woeall[col])
#将标签补充到数据中
model_woe["SeriousDlqin2yrs"] = model_data["SeriousDlqin2yrs"]
#这就是我们的建模数据了
model_woe.head()
1.4.建模及模型验证
vali_woe = pd.DataFrame(index=vali_data.index)
for col in bins_of_col:
vali_woe[col] = pd.cut(vali_data[col],bins_of_col[col]).map(woeall[col])
vali_woe["SeriousDlqin2yrs"] = vali_data["SeriousDlqin2yrs"]
vali_X = vali_woe.iloc[:,:-1]
vali_y = vali_woe.iloc[:,-1]
X = model_woe.iloc[:,:-1]
y = model_woe.iloc[:,-1]
from sklearn.linear_model import LogisticRegression as LR
lr = LR().fit(X,y)
lr.score(vali_X,vali_y)#0.8641356370249832
c_1 = np.linspace(0.01,1,20)
c_2 = np.linspace(0.01,0.2,20)
score = []
for i in c_1:
lr = LR(solver='liblinear',C=i).fit(X,y)
score.append(lr.score(vali_X,vali_y))
plt.figure()
plt.plot(c_1,score)
plt.show()
lr.n_iter_#array([7], dtype=int32)
score = []
for i in [1,2,3,4,5,6]:
lr = LR(solver='liblinear',C=0.025,max_iter=i).fit(X,y)
score.append(lr.score(vali_X,vali_y))
plt.figure()
plt.plot([1,2,3,4,5,6],score)
plt.show()
import scikitplot as skplt
#%%cmd
#pip install scikit-plot
vali_proba_df = pd.DataFrame(lr.predict_proba(vali_X))
skplt.metrics.plot_roc(vali_y, vali_proba_df,
plot_micro=False,figsize=(6,6),
plot_macro=False)
1.5.制作评分卡
B = 20/np.log(2)
A = 600 + B*np.log(1/60)
B,A
base_score = A - B*lr.intercept_#lr.intercept_：截距
base_score#array([481.56390143])
score_age = woeall["age"] * (-B*lr.coef_[0][1])#lr.coef_：每一个特征建模之后得出的系数
score_age#"age"特征中每个箱对应的分数
file = "./ScoreData.csv"
#open是用来打开文件的python命令，第一个参数是文件的路径+文件名，如果你的文件是放在根目录下，则你只需要文件名就好
#第二个参数是打开文件后的用途，"w"表示用于写入，通常使用的是"r"，表示打开来阅读
#首先写入基准分数
#之后使用循环，每次生成一组score_age类似的分档和分数，不断写入文件之中
with open(file,"w") as fdata:
fdata.write("base_score,{}\n".format(base_score))
for i,col in enumerate(X.columns):#[*enumerate(X.columns)]
score = woeall[col] * (-B*lr.coef_[0][i])
score.name = "Score"
score.index.name = col
score.to_csv(file,header=True,mode="a")
参考：CDA课堂，直播课后的个人笔记总结，仅供参考，有不一样的想法的大佬们，请辩证地观看，如果有问题可以在评论区指出我再订正。