add comments

main.py

 from service.loan_dao import LoanDao
-from service.rule_regression import rule_regression
+from service.rule_regression import rule_regression, get_reapply_loan
 import pandas as pd
 
 if __name__ == '__main__':
-    regression_results_df = rule_regression(reapply_count=2)
+
+    # 复借大于n次贷款。 如需其他数据源，可自行获取
+    # 需要字段： loan_app_id,loan_status,imei,prereview_time(机审时间),customer_id,mobile,is_overdue(标签，是否逾期)
+    data = get_reapply_loan(reapply_count=2)
+
+    # 跑机审规则
+    regression_results_df = rule_regression(data)
+
+    # 结果存储
     regression_results_df.to_csv("results/%s_rule_regression_re2.csv" % 'hs')

service/rule_regression.py

@@ -9,6 +9,7 @@ logger = logger.get_logger(__name__)
 
 
 def call_risk_api(loan_app_id):
+    """调取sulu机审服务"""
     params = {'loanAppId': loan_app_id}
 
     try:
@@ -23,10 +24,26 @@ def call_risk_api(loan_app_id):
     return None
 
 
-def rule_regression(reapply_count=2):
+def get_reapply_loan(reapply_count=2):
+    """获取复借客户
+    Args:
+        reapply_count (int): 复借次数
+    Returns:
+        list: list of row, row is dictionary"""
+
+    return LoanDao.get_reapply_loan(reapply_count=reapply_count)
+
+
+def rule_regression(data):
+    """rule regression
+    Args:
+        data (list): 数据
+    Returns:
+        pandas.DataFrame: 每笔申请对应的机审情况"""
     regression_results = []
     count = 0
-    for row in LoanDao.get_reapply_loan(reapply_count=reapply_count):
+
+    for row in data:
 
         try:
             loan_app_id = row.get('loan_app_id')