@author: 87875
"""
# Traditional Credit Scoring Using Logistic Regression
import scorecardpy as sc
import matplotlib.pyplot as plt
# data prepare ------
# load germancredit data
dat = sc.germancredit()
# filter variable via missing rate, iv, identical value rate
dt_s = sc.var_filter(dat, y="creditability")
# breaking dt into train and test
train, test = sc.split_df(dt_s, 'creditability').values()
# woe binning ------
bins = sc.woebin(dt_s, y="creditability")
print(type(bins))
for k, v in bins.items():
print(k)
print(bins["purpose"])
print(bins["purpose"].columns)
print(type(bins["purpose"]))
# sc.woebin_plot(bins["purpose"])
# plt.show()
# =============================================================================
# print("qq: 1467288927")
'BAD',
method='chimerge',
x=['JOB'],
breaks_list=break_list)
bins['JOB'] = job_bins['JOB']
# Plot WOE bins
# fig, axs = plt.subplots(ncols=2)
# sc.woebin_plot(bins, figsize=[8,5])
# Print results of binning
# for k, bin_ in bins.items():
# print(bins[k].iloc[:,0:-2].round(2).to_latex(index=False))
# split into train and test set
train, test = sc.split_df(df, 'BAD').values()
# Convert values into woe
train_woe = sc.woebin_ply(train, bins)
test_woe = sc.woebin_ply(test, bins)
# Add constant
train_woe = sm.add_constant(train_woe)
test_woe = sm.add_constant(test_woe)
y_train = train_woe.loc[:, 'BAD']
X_train = train_woe.loc[:, train_woe.columns != 'BAD']
y_test = test_woe.loc[:, 'BAD']
X_test = test_woe.loc[:, train_woe.columns != 'BAD']
# Fit logit model
def split(self):
train, test = sc.split_df(self.df,
y='DEFAULT_FLAG',
ratio=0.8,
seed=186).values()
return train, test
for e in SERVICES:
#Detecting a particular service
COEF2 = pd.DataFrame()
data = data_x.copy()
data = data.loc[data['SERVICES'] == e]
data.drop(['SERVICES'], axis=1, inplace=True)
#------------------ Grouping zone if there is not enough data------------------------
Clases_UPZ = np.unique(data['ZONE'])
Data_UPZ = data.groupby('ZONE').groups
for i in Clases_UPZ:
numero_clases = Data_UPZ[i]
if len(numero_clases) < 10:
data['ZONE'].loc[numero_clases] = 'ZONE_Other'
#-------------------- 1. OBTAINING BINS---------------------------------------
train_b, test_b = sc.split_df(data, y='OUTCOME', ratio=0.7,
seed=100).values()
bins = sc.woebin(
train_b,
y='OUTCOME',
min_perc_fine_bin=0.01, # How many bins to cut initially into
min_perc_coarse_bin=0.05, # Minimum percentage per final bin
stop_limit=0.2, # Minimum information value
max_num_bin=10, # Maximum number of bins
method='tree')
#Transforming variables to dummies
train, test, deleted_var = dummies_on(train_b, test_b, bins, continuous)
#Defining Train Data and Test Data
X_train = train[train.columns.difference(['OUTCOME'])]
Y_train = train['OUTCOME']
Y_train = Y_train.astype('int')
#默认删除信息只<0.02，缺失率>95%，单类别比例>95%的变量
dt_s = sc.var_filter(data, y='status')
print('变量预处理前后变化：', data.shape, '->', dt_s.shape)
#print(data.columns)
#print(dt_s.columns)
#分箱WOE转换
bins = sc.woebin(dt_s, y='status')
# bins
train, test = sc.split_df(dt_s, 'status').values()
print('训练集、测试集划分比例为：', train.shape[0], ':', test.shape[0])
train_woe = sc.woebin_ply(train, bins)
test_woe = sc.woebin_ply(test, bins)
#train_woe.head()
y_train = train_woe.loc[:,'status']
X_train = train_woe.loc[:, train_woe.columns != 'status']
y_test = test_woe.loc[:, 'status']
X_test = test_woe.loc[:, train_woe.columns != 'status']
lr = LogisticRegression(penalty='l1', C=0.9, solver='saga', n_jobs=-1)
lr.fit(X_train, y_train)
train_pred = lr.predict_proba(X_train)[:, 1]
df = df[cols]
df.drop(['diabetes' ], axis=1, inplace=True)
bins = sc.woebin(df, 'outcome', method='chimerge')
cols = df.iloc[:, 2:].columns
break_list = {}
for col in cols:
break_list[col] = [1.0]
bins.update(sc.woebin(df, 'outcome', method='chimerge', x=cols.tolist(),
breaks_list=break_list))
# split into train and test set
train, test = sc.split_df(df, 'outcome').values()
# Convert values into woe
train_woe = sc.woebin_ply(train, bins)
test_woe = sc.woebin_ply(test, bins)
train_woe = sm.add_constant(train_woe)
test_woe = sm.add_constant(test_woe)
y_train = train_woe.loc[:,'outcome']
X_train = train_woe.loc[:,train_woe.columns != 'outcome']
y_test = test_woe.loc[:,'outcome']
X_test = test_woe.loc[:,train_woe.columns != 'outcome']
# Fit logit model
lr = sm.GLM(y_train, X_train, family=sm.families.Binomial())