dhb 待调试

data/graph/matplot.py

@@ -103,14 +103,6 @@ def density_chart(dataset,title):
     plt.title(title)
     plt.show()
 
-def learning_curve():
-
-        
-    
-def pdp_chart():
-    
-    return 1
-
 
 def uniVarChart():
     return 1       

mvp/dhb.py

 import pandas as pd
-import mysqldb
-
+from data.datasource import mysqldb,mongodb
+import datetime
+import dateutil
 '''
 model instructions : established a dhb obj which cotains attrubutes of dhb model
 
@@ -176,24 +177,11 @@ class dhb():
     'dhb_overview_ntdun_call_total_duration',
     'dhb_overview_ntdun_call_total_times',
     'dhb_overview_ntdun_first_call_time']
-    
-
-    
-'''
-instructions :
-    build a constructor of dhb
-Params:
-
 
-'''
-    # ime period set as default
-    start_time_period = (datetime.date.today() - relativedelta(months=+7)).strftime("%Y-%m-%d 00:00:00")
-    end_time_period = (datetime.date.today() - relativedelta(days=+16)).strftime("%Y-%m-%d 00:00:00")
-    
     def __init__(self,overdue_days=15,features=None,sql=None,start_time_period=None,end_time_period=None):
         try:
             if features != None:
-                self.features = features   
+                self.features = features
             if sql != None:
                 self.sql = sql
             else:
@@ -207,41 +195,46 @@ Params:
 
             if start_time_period != None:
                 self.start_time_period = start_time_period
+            else:
+                self.start_time_period =(datetime.date.today() - dateutil.relativedelta(months=+7)).strftime("%Y-%m-%d 00:00:00")
             if end_time_period != None:
                 self.end_time_period = end_time_period
+            else:
+                self.end_time_period = (datetime.date.today() - dateutil.relativedelta(days=+16)).strftime("%Y-%m-%d 00:00:00")
         except Exception as e:
             print('Parameters Error:\n',e)
 
-        
-    '''
-    instrucions : extract dhb features from risk_analysis
 
-    Params : nothing yet
-    returns : dhb features
-    '''   
     def dhb_features_extract(self):
-        
+        '''
+        instrucions : extract dhb features from risk_analysis
+        :param self:
+        :return: dhb features
+        '''
+
         value_map = {
-    "近3天":1,
-    "近4-5天":2,
-    "近6-7天":3,
-    "近8-15天":4,
-    "近16-30天":5,
-    "近31-60天":6,
-    "近61-90天":7,
-    "近91-120天":8,
-    "近121-150天":9,
-    "近151-180天":10,
-    "180天前":11,
-    "无":0  
-    }    
-        #print(self.sql.replace('@start_time_period',self.start_time_period).replace('@end_time_period',self.end_time_period))        
+            "近3天":1,
+            "近4-5天":2,
+            "近6-7天":3,
+            "近8-15天":4,
+            "近16-30天":5,
+            "近31-60天":6,
+            "近61-90天":7,
+            "近91-120天":8,
+            "近121-150天":9,
+            "近151-180天":10,
+            "180天前":11,
+            "无":0
+        }
+        #print(self.sql.replace('@start_time_period',self.start_time_period).replace('@end_time_period',self.end_time_period))
         # use risk_analysis to extract data
-        dhb_loan = query_sql(self.sql.replace('@start_time_period',self.start_time_period).replace('@end_time_period',self.end_time_period))
-#        dhb_loan[["dhb_overview_dun_first_call_time", "dhb_overview_dun_last_call_time","dhb_overview_ntdun_first_call_time", "dhb_overview_ntdun_last_call_time"]] = dhb_loan[["dhb_overview_dun_first_call_time", "dhb_overview_dun_last_call_time","dhb_overview_ntdun_first_call_time", "dhb_overview_ntdun_last_call_time"]].applymap(lambda x : value_map[x])      
-        
+        sql=self.sql.replace('@start_time_period',self.start_time_period).replace('@end_time_period',self.end_time_period)
+        #
+        dhb_loan = pd.read_sql(sql,mysqldb.engine_risk_analysis)
+    #        dhb_loan[["dhb_overview_dun_first_call_time", "dhb_overview_dun_last_call_time","dhb_overview_ntdun_first_call_time", "dhb_overview_ntdun_last_call_time"]] = dhb_loan[["dhb_overview_dun_first_call_time", "dhb_overview_dun_last_call_time","dhb_overview_ntdun_first_call_time", "dhb_overview_ntdun_last_call_time"]].applymap(lambda x : value_map[x])
+
         # manipul category datatype which includes sequences
-        dhb_loan[["dhb_overview_dun_first_call_time", "dhb_overview_dun_last_call_time","dhb_overview_ntdun_first_call_time", "dhb_overview_ntdun_last_call_time"]] = pd.get_dummies(df[["dhb_overview_dun_first_call_time", "dhb_overview_dun_last_call_time","dhb_overview_ntdun_first_call_time", "dhb_overview_ntdun_last_call_time"]],columns=["dhb_overview_dun_first_call_time", "dhb_overview_dun_last_call_time","dhb_overview_ntdun_first_call_time", "dhb_overview_ntdun_last_call_time"])
+        dhb_loan[["dhb_overview_dun_first_call_time", "dhb_overview_dun_last_call_time","dhb_overview_ntdun_first_call_time", "dhb_overview_ntdun_last_call_time"]] = pd.get_dummies(dhb_loan[["dhb_overview_dun_first_call_time", "dhb_overview_dun_last_call_time","dhb_overview_ntdun_first_call_time", "dhb_overview_ntdun_last_call_time"]],columns=["dhb_overview_dun_first_call_time", "dhb_overview_dun_last_call_time","dhb_overview_ntdun_first_call_time", "dhb_overview_ntdun_last_call_time"])
         # limit the upper boundary
         dhb_loan.loc[dhb_loan.dhb_last_60_and_90_days_ntdun_call_avg_duration >= 42,"dhb_last_60_and_90_days_ntdun_call_avg_duration"] = 42
         dhb_loan.loc[dhb_loan.dhb_overview_ntdun_call_duration_above60 >= 25,"dhb_overview_ntdun_call_duration_above60"] = 25
@@ -255,15 +248,15 @@ Params:
         dhb_loan.loc[dhb_loan.dhb_last_60_and_90_days_ntdun_call_in_duration>= 1000,"dhb_last_60_and_90_days_ntdun_call_in_duration"] = 1000
         dhb_loan.loc[dhb_loan.dhb_overview_dun_call_tel_total_nums>= 22,"dhb_overview_dun_call_tel_total_nums"] = 22
         dhb_loan.loc[dhb_loan.dhb_last_30_days_dun_call_total_duration>= 1100,"dhb_last_30_days_dun_call_total_duration"] = 1100
-        dhb_loan.loc[dhb_loan.dhb_last_two_weeks_ntdun_call_in_duration>= 300,"dhb_last_two_weeks_ntdun_call_in_duration"] = 300       
+        dhb_loan.loc[dhb_loan.dhb_last_two_weeks_ntdun_call_in_duration>= 300,"dhb_last_two_weeks_ntdun_call_in_duration"] = 300
         dhb_loan.to_csv("./dhb_loan_sample——"+str(datetime.date.today())+".csv")
-        print( time.strftime('%Y.%m.%d %H:%M:%S',time.localtime(time.time())) +"提取了dhb {}+ ".format(str(overdue_days)) + self.start_time_period + "to" + self.end_time_period + "时段样本")
+        print( datetime.time.strftime('%Y.%m.%d %H:%M:%S',datetime.time.localtime(datetime.time.time())) +"提取了dhb {}+ ".format(str(self.overdue_days)) + self.start_time_period + "to" + self.end_time_period + "时段样本")
         return dhb_loan
 
-    def dhb_comparasion(df=None,start_time_period = self.start_time_period, end_time_period = self.end_time_period, applied_type = None,applied_from = None):
-        df_mongo = pymongodb(start_time_period, end_time_period, limit, "{'order_id':1,'model_exec_data_source#dhb':1}")
+    def dhb_comparasion(self,limit="{'wf_created_at': {'$gte': '@start_date', '$lt': '@end_date'}}",df=None,applied_type = None,applied_from = None):
+        df_mongo = mongodb.pymongodb(self.start_time_period, self.end_time_period, limit, "{'order_id':1,'model_exec_data_source#dhb':1}")
+
 
-