add

make_data.py

@@ -10,11 +10,10 @@ def doctor():
     # date_tmp = (datetime.datetime.now() - datetime.timedelta(days=1)).strftime("%Y-%m-%d")
 
     sql = "select d.doctor_id,d.service_exposure_pv_30,d.service_ctr_30,d.expert_exposure_pv_30,d.expert_pv_30," \
-    "b.merchant_id,budan.budan_payment_30_days " \
+    "b.merchant_id " \
           "from statistic_doctor_rank_factor d " \
     "left join hippo_merchantrelevance b on d.doctor_id = b.doctor_id " \
-    "left join al_meigou_service_smart_rank_budan_payment budan on b.merchant_id = budan.merchant_id " \
-    "where d.partition_date = '{}' and budan.stat_date = '{}';".format(date_str, date_tmp)
+    "where d.partition_date = '{}';".format(date_str)
 
     db = pymysql.connect(host='172.16.30.143', port=3306, user='work', passwd='BJQaT9VzDcuPBqkd', db='zhengxing')
     cursor = db.cursor()
@@ -22,7 +21,7 @@ def doctor():
     result = cursor.fetchall()
     df = pd.DataFrame(list(result))
     name = ["doctor_id", "service_exposure_pv_30", "service_ctr_30", "expert_exposure_pv_30", "expert_pv_30",
-            "merchant_id","budan_payment_30_days"]
+            "merchant_id"]
 
     df = df.rename(columns=dict(zip(list(range(len(name))), name)))
 
@@ -45,7 +44,7 @@ def doctor():
 
     for i in ["service_exposure_pv_30", "service_ctr_30", "expert_exposure_pv_30", "expert_pv_30",
       "doctor_discount_30_days", "expand_rechange_amount_30", "service_pv_30",
-     "mexpert_pv_30", "organization_pv_30", "budan_payment_30_days"]:
+     "mexpert_pv_30", "organization_pv_30"]:
         df[i] = df[i].astype("float")
 
     df["all_exposure"] = df["service_exposure_pv_30"] + df["expert_exposure_pv_30"]
@@ -77,7 +76,7 @@ def doctor():
     columns = ["doctor_id","score","ctr","commission","pv_ad","service_exposure_pv_30",
                "service_ctr_30","expert_exposure_pv_30","expert_pv_30",
             "merchant_id","doctor_discount_30_days","expand_rechange_amount_30","service_pv_30",
-            "mexpert_pv_30","organization_pv_30","budan_payment_30_days"]
+            "mexpert_pv_30","organization_pv_30"]
     data = df.loc[:, columns]
 
     data = data.drop_duplicates()