add

make_data.py

@@ -24,7 +24,7 @@ def doctor():
 
     df = df.rename(columns=dict(zip(list(range(len(name))), name)))
 
-    sql = "select merchant_id,doctor_ad_money_30_days,expand_rechange_amount_30," \
+    sql = "select merchant_id,doctor_discount_30_days,expand_rechange_amount_30," \
           "service_pv_30,expert_pv_30,organization_pv_30 from statistic_merchant_rank_factor " \
           "where partition_date = '{}';".format(date_str)
 
@@ -33,7 +33,7 @@ def doctor():
     result = cursor.fetchall()
     db.close()
     tmp = pd.DataFrame(list(result))
-    name = ["merchant_id", "doctor_ad_money_30_days", "expand_rechange_amount_30", "service_pv_30",
+    name = ["merchant_id", "doctor_discount_30_days", "expand_rechange_amount_30", "service_pv_30",
             "mexpert_pv_30", "organization_pv_30"]
     tmp = tmp.rename(columns=dict(zip(list(range(len(name))), name)))
 
@@ -42,7 +42,7 @@ def doctor():
     df = pd.merge(df, tmp, on='merchant_id')
 
     for i in ["service_exposure_pv_30", "service_ctr_30", "expert_exposure_pv_30", "expert_pv_30",
-      "doctor_ad_money_30_days", "expand_rechange_amount_30", "service_pv_30",
+      "doctor_discount_30_days", "expand_rechange_amount_30", "service_pv_30",
      "mexpert_pv_30", "organization_pv_30", "budan_payment_30_days"]:
         df[i] = df[i].astype("float")
 
@@ -55,10 +55,11 @@ def doctor():
     df["ctr"] = df["service_exposure_pv_30"] / df["all_exposure"] * df["service_ctr_30"] + \
                 df["expert_exposure_pv_30"]/df["all_exposure"] * (df["expert_pv_30"] / df["expert_exposure_pv_30"])
 
-    df.loc[df["doctor_ad_money_30_days"] < 0, ["doctor_ad_money_30_days"]] = 0
+    df.loc[df["doctor_discount_30_days"] < 0, ["doctor_discount_30_days"]] = 0
     df.loc[df["budan_payment_30_days"] < 0, ["budan_payment_30_days"]] = 0
+    df.loc[df["expand_rechange_amount_30"] < 0, ["expand_rechange_amount_30"]] = 0
 
-    df["commission"] = (df["doctor_ad_money_30_days"] + df["budan_payment_30_days"])/df["tmp"]
+    df["commission"] = (df["doctor_discount_30_days"] + df["budan_payment_30_days"])/df["tmp"]
     df["pv_ad"] = df["expand_rechange_amount_30"]/df["tmp"]
     df["score"] = df["ctr"]**0.5 * (df["commission"] + df["pv_ad"])
 
@@ -72,12 +73,12 @@ 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_ad_money_30_days","expand_rechange_amount_30","service_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"]
     data = df.loc[:, columns]
 
     data = data.drop_duplicates()
-    data.to_csv('/tmp/doctor.csv',index=False)
+    data.to_csv('/tmp/20_doctor.csv',index=False)
     print("doctor end")
 
 
@@ -106,10 +107,8 @@ def hospital():
 
     df = df.rename(columns=dict(zip(list(range(len(name))), name)))
 
-    print(df.head(6))
-
-    sql = "select merchant_id,doctor_ad_money_30_days," \
-          "service_pv_30,expert_pv_30,organization_pv_30,doctor_discount_30_days from statistic_merchant_rank_factor " \
+    sql = "select merchant_id,doctor_discount_30_days," \
+          "service_pv_30,expert_pv_30,organization_pv_30,expand_rechange_amount_30 from statistic_merchant_rank_factor " \
           "where partition_date = '{}';".format(date_str)
 
     cursor = db.cursor()
@@ -117,7 +116,7 @@ def hospital():
     result = cursor.fetchall()
     db.close()
     tmp = pd.DataFrame(list(result))
-    name = ["merchant_id", "doctor_ad_money_30_days","service_pv_30","mexpert_pv_30","organization_pv_30",
+    name = ["merchant_id", "doctor_discount_30_days","service_pv_30","mexpert_pv_30","organization_pv_30",
             "doctor_discount_30_days"]
     tmp = tmp.rename(columns=dict(zip(list(range(len(name))), name)))
     print(tmp.head(6))
@@ -128,8 +127,8 @@ def hospital():
 
     for i in ["hospital_exposure_pv_30","service_exposure_pv_30","expert_exposure_pv_30",
               "service_ctr_30","hospital_ctr_30","expert_ctr_30","budan_payment_30_days",
-              "doctor_ad_money_30_days","service_pv_30","mexpert_pv_30","organization_pv_30",
-              "doctor_discount_30_days"]:
+              "doctor_discount_30_days","service_pv_30","mexpert_pv_30","organization_pv_30",
+              "expand_rechange_amount_30"]:
         df[i] = df[i].astype("float")
 
     df["all_exposure"] = df["hospital_exposure_pv_30"] + df["service_exposure_pv_30"] + df["expert_exposure_pv_30"]
@@ -141,11 +140,12 @@ def hospital():
                 df["hospital_exposure_pv_30"]/ df["all_exposure"] * df["hospital_ctr_30"] + \
                 df["expert_exposure_pv_30"]/df["all_exposure"] * df["expert_ctr_30"]
 
-    df.loc[df["doctor_ad_money_30_days"] < 0, ["doctor_ad_money_30_days"]] = 0
+    df.loc[df["doctor_discount_30_days"] < 0, ["doctor_discount_30_days"]] = 0
     df.loc[df["budan_payment_30_days"] < 0, ["budan_payment_30_days"]] = 0
+    df.loc[df["expand_rechange_amount_30"] < 0, ["expand_rechange_amount_30"]] = 0
 
-    df["commission"] = (df["doctor_ad_money_30_days"] + df["budan_payment_30_days"])/df["tmp"]
-    df["cpt"] = df["doctor_discount_30_days"]/df["tmp"]
+    df["commission"] = (df["doctor_discount_30_days"] + df["budan_payment_30_days"])/df["tmp"]
+    df["cpt"] = df["expand_rechange_amount_30"]/df["tmp"]
     df["score"] = df["ctr"]**0.5 * (df["commission"] + df["cpt"])
 
     df.loc[df["all_exposure"] <= 1500, ["ctr"]] = 0.01
@@ -159,14 +159,14 @@ def hospital():
     columns = ["doctor_id","score","ctr","commission","cpt","hospital_id","hospital_exposure_pv_30",
                "service_exposure_pv_30","expert_exposure_pv_30",
               "service_ctr_30","hospital_ctr_30","expert_ctr_30","merchant_id","budan_payment_30_days",
-              "doctor_ad_money_30_days","service_pv_30","mexpert_pv_30","organization_pv_30",
-              "doctor_discount_30_days"]
+              "doctor_discount_30_days","service_pv_30","mexpert_pv_30","organization_pv_30",
+              "expand_rechange_amount_30"]
     data = df.loc[:, columns]
 
     data = data.drop_duplicates()
 
     print(data.head(6))
-    data.to_csv('/tmp/hospital.csv',index=False,encoding="utf_8_sig")
+    data.to_csv('/tmp/20_hospital.csv',index=False)
 
 
 if __name__ == "__main__":