class ModelDetails():
def __init__(self, intercept, coefs):
"""Because the scorecardpy package can only take a model class of
LogisticRegression from the scikit-learn package this class is needed
to hold the values from the statsmodels package.
"""
self.intercept_ = [intercept]
self.coef_ = [coefs.tolist()]
model = ModelDetails(fit.params[0], fit.params[1:])
# Create scorecard
card = sc.scorecard(bins, model, X_train.columns[1:], points0=800, pdo=50)
# Create scores
train_score = sc.scorecard_ply(train, card, print_step=0)
test_score = sc.scorecard_ply(test, card, print_step=0)
# Plot scorecard
sc.perf_psi(score={
'train': train_score,
'test': test_score
},
label={
'train': y_train,
'test': y_test
})
y_train = train_woe.loc[:,'creditability']
X_train = train_woe.loc[:,train_woe.columns != 'creditability']
y_test = test_woe.loc[:,'creditability']
X_test = test_woe.loc[:,train_woe.columns != 'creditability']
# logistic regression ------
from sklearn.linear_model import LogisticRegression
lr = LogisticRegression(penalty='l1', C=0.9, solver='saga', n_jobs=-1)
lr.fit(X_train, y_train)
# lr.coef_
# lr.intercept_
# predicted proability
train_pred = lr.predict_proba(X_train)[:,1]
test_pred = lr.predict_proba(X_test)[:,1]
# performance ks & roc ------
train_perf = sc.perf_eva(y_train, train_pred, title = "train")
test_perf = sc.perf_eva(y_test, test_pred, title = "test")
# score ------
card = sc.scorecard(bins_adj, lr, X_train.columns)
# credit score
train_score = sc.scorecard_ply(train, card, print_step=0)
test_score = sc.scorecard_ply(test, card, print_step=0)
# psi
sc.perf_psi(
score = {'train':train_score, 'test':test_score},
label = {'train':y_train, 'test':y_test}
)
def evaluate_main(self):
writer = pd.ExcelWriter("{}_report.xlsx".format(self.filename))
odds0 = float(self.df_train_woe[self.target_name].value_counts()[1]) / float(self.df_train_woe[self.target_name].value_counts()[0])
b = self.double_score / np.log(2)
a = self.base_score + b * np.log(odds0)
card = sc.scorecard(self.bins_adj, self.model, self.final_features, points0=self.base_score,
odds0=odds0,
pdo=self.double_score)
card_df = pd.DataFrame(columns=["variable", "bin", "points"])
for key, value in card.items():
card_df = pd.concat([card_df, value])
card_df.to_excel(writer, 'card_result')
self.train_pred = self.model.predict_proba(self.df_train_woe[self.final_features])[:, 1]
perf = sc.perf_eva(self.df_train_woe[self.target_name], self.train_pred, title="train")
print("On train-data, the evaluation follows:\nks={}, auc={}, gini={}".format(perf["KS"], perf["AUC"],
perf["Gini"]))
perf["pic"].savefig("{}_train.png".format(self.filename))
_score = sc.scorecard_ply(self.df_train, card, print_step=0)
_score["flag"] = self.df_train_woe[self.target_name]
_score["pred"] = self.train_pred
_rs = self._get_score_table(_score, a, b)
_rs.to_excel(writer, 'train_result')
if self.df_test.any().any():
y_test = self.df_test_woe[self.target_name]
self.test_pred = self.model.predict_proba(self.df_test_woe[self.final_features])[:, 1]
perf = sc.perf_eva(y_test, self.test_pred, title="test")
print("On test-data, the evaluation follows:\nks={}, auc={}, gini={}".format(perf["KS"],
perf["AUC"],
perf["Gini"]))
perf["pic"].savefig("{}_test.png".format(self.filename))
_score = sc.scorecard_ply(self.df_test, card, print_step=0)
_score["flag"] = self.df_test_woe[self.target_name]
_score["pred"] = self.test_pred
_rs = self._get_score_table(_score, a, b)
_rs.to_excel(writer, 'test_result')
if self.df_ott.any().any():
y_ott = self.df_ott_woe[self.target_name]
self.ott_pred = self.model.predict_proba(self.df_ott_woe[self.final_features])[:, 1]
try:
perf = sc.perf_eva(y_ott, self.ott_pred , title="ott")
print("On ott-data, the evaluation follows:\nks={}, auc={}, gini={}".format(perf["KS"],
perf["AUC"],
perf["Gini"]))
perf["pic"].savefig("{}_test.png".format(self.filename))
_score = sc.scorecard_ply(self.df_ott, card, print_step=0)
_score["flag"] = self.df_ott_woe[self.target_name]
_score["pred"] = self.ott_pred
_rs = self._get_score_table(_score,a,b)
_rs.to_excel(writer, 'ott_result')
except:
self.log.info("Cannot caculation the ott data!")
importance = {x: y for x, y in zip(self.final_features, self.model.coef_[0])}
iv_df = self.iv_df[self.iv_df['variable'].isin(self.final_features)]
iv_df["coef"] = iv_df.variable.map(lambda x: importance[x])
iv_df.to_excel(writer, 'feature_importance')
writer.close()
self.log.info("全部环节结束，请查看相关文件！")
'NumberRealEstateLoansOrLines_woe', 'NumberOfDependents_woe'], axis=1)
train_pred = lr.predict_proba(x_train)[:, 1]
test_pred = lr.predict_proba(x_test)[:, 1]
# # lr (statsmodels version)
# import statsmodels.api as sm
# X1 = sm.add_constant(x_train)
# logit = sm.Logit(y_train, X1)
# result = logit.fit()
# print(result.summary())
# X2 = sm.add_constant(x_test)
# predict = result.predict(X2)
# score ------
card = sc.scorecard(cutoff, lr, x_train.columns, points0=600, odds0=1 / 20, pdo=20, basepoints_eq0=False)
column = ['basepoints', 'RevolvingUtilizationOfUnsecuredLines', 'age', 'NumberOfTime30-59DaysPastDueNotWorse',
'NumberOfTimes90DaysLate', 'NumberOfTime60-89DaysPastDueNotWorse']
if not (os.path.exists('./data/card')): os.makedirs(os.path.join('./data/card'))
for i in card.keys():
card[i].to_csv('./data/card/{}.csv'.format(i), index=False)
# performance ks & roc ------
train_perf = sc.perf_eva(y_train, train_pred, title="train")
test_perf = sc.perf_eva(y_test, test_pred, title="test")
# credit score
train_score = sc.scorecard_ply(train_data, card, print_step=0, only_total_score=False)
test_score = sc.scorecard_ply(test_data, card, print_step=0, only_total_score=False)
def execute_data():
start = time.time()
try:
global modelPath, binsPath, bins, model
logger.info('入参：%s', str(request.get_data()))
request_data = request.get_json() #获取传入数据
paramsJson = request_data['paramsData']
modelFilePath = modelFilePathCheck(request_data)
if (type(paramsJson) == type({})):
#原始数据中数值型字符串转为int64
items = paramsJson.items()
for key, value in items:
if (is_number(value)):
paramsJson[key] = int(value)
logger.info("paramsJson:%s", paramsJson)
#构建dataFrame
df = pd.json_normalize(paramsJson)
if (modelPath != modelFilePath):
logger.info('调用模型路径发生变化，重新加载模型！')
logger.info('global modelFilePath:%s', modelPath)
logger.info('param modelFilePath:%s', modelFilePath)
modelPath = modelFilePath
#导入模型
model = joblib.load(modelFilePath)
else:
logger.info('调用模型路径未发生变化，使用缓存中模型。')
logger.info('global modelFilePath:%s', modelPath)
#原始数据转换为woe值
bins = model.bins
df_woe = sc.woebin_ply(df, bins)
#打标签
label = model.predict(df_woe)[0]
#构建评分卡
card = sc.scorecard(bins, model, df_woe.keys())
#评分
score = sc.scorecard_ply(df,
card,
only_total_score=False,
print_step=0)
#计算每个特征的得分
featureScore = {}
# featureScore = calculateFeatures(df, card)
if isinstance(card, dict):
card_df = pd.concat(card, ignore_index=True)
elif isinstance(card, pd.DataFrame):
card_df = card.copy(deep=True)
# x variables
xs = card_df.loc[card_df.variable != 'basepoints',
'variable'].unique()
for i in xs:
featureScore[i] = score[i + '_points'][0]
result = {}
result['code'] = '00000'
result['score'] = str(score['score'][0])
result['label'] = str(label)
result['featureScore'] = featureScore
end = time.time()
logger.info("运行结果：%s,模型执行耗时：%s", result, end - start)
return jsonify(result)
code10002['errorMsg'] = '输入值错误：请传入json格式参数'
return jsonify(code10002)
except KeyError as e:
logger.info(e)
code10001['errorMsg'] = '输入特征错误：' + str(e)
return jsonify(code10001)
except ValueError as e:
logger.info(e)
code10002['errorMsg'] = '输入值错误：' + str(e)
return jsonify(code10002)
except Exception as e:
logger.info(e)
code10003['errorMsg'] = '未知错误：' + str(e)
return jsonify(code10003)