add

make_data.py

@@ -75,12 +75,11 @@ def v1_doctor():
             "merchant_id","budan_payment_30_days"]
 
     df = df.rename(columns=dict(zip(list(range(len(name))), name)))
-    print(df.head(6))
 
     sql = "select merchant_id,doctor_ad_money_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)
-    print(sql)
+
     cursor = db.cursor()
     cursor.execute(sql)
     result = cursor.fetchall()
@@ -89,35 +88,33 @@ def v1_doctor():
     name = ["merchant_id", "doctor_ad_money_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)))
-    print(tmp.head(6))
 
     df["merchant_id"] = df["merchant_id"].astype("str")
     tmp["merchant_id"] = tmp["merchant_id"].astype("str")
     df = pd.merge(df, tmp, on='merchant_id')
-    print(df.head(6))
-
-    # 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",
-    #  "mexpert_pv_30", "organization_pv_30", "budan_payment_30_days"]:
-    #     df[i] = df[i].astype("float")
-    #
-    # df["all_exposure"] = df["service_exposure_pv_30"] + df["expert_exposure_pv_30"]
-    # df = df[~df["expert_exposure_pv_30"].isin([0.0])]
-    # df = df[~df["all_exposure"].isin([0.0])]
-    # df["tmp"] = df["service_pv_30"] + df["mexpert_pv_30"] +df["organization_pv_30"]
-    # df = df[~df["tmp"].isin([0.0])]
-    #
-    # 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["commission"] = (df["doctor_ad_money_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"])
-    # columns = ["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",
-    #         "mexpert_pv_30","organization_pv_30","budan_payment_30_days"]
-    # data = df.loc[:, columns]
-    # # print(data)
-    # data.to_csv('/home/gmuser/doctor.csv',index=False)
+
+    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",
+     "mexpert_pv_30", "organization_pv_30", "budan_payment_30_days"]:
+        df[i] = df[i].astype("float")
+
+    df["all_exposure"] = df["service_exposure_pv_30"] + df["expert_exposure_pv_30"]
+    df = df[~df["expert_exposure_pv_30"].isin([0.0])]
+    df = df[~df["all_exposure"].isin([0.0])]
+    df["tmp"] = df["service_pv_30"] + df["mexpert_pv_30"] +df["organization_pv_30"]
+    df = df[~df["tmp"].isin([0.0])]
+    print("aaaaaaaa")
+    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["commission"] = (df["doctor_ad_money_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"])
+    columns = ["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",
+            "mexpert_pv_30","organization_pv_30","budan_payment_30_days"]
+    data = df.loc[:, columns]
+    print(data.head(6))
+    data.to_csv('/home/gmuser/doctor.csv',index=False)
 
 
 def hospital():