add

make_data.py

@@ -129,7 +129,7 @@ def hospital():
           "left join hippo_merchantrelevance b on api.id = b.doctor_id " \
           "left join al_meigou_service_smart_rank_budan_payment budan on b.merchant_id = budan.merchant_id " \
           "where api.doctor_type = 1 and h.date = '{}' " \
-          "and budan.stat_date = '{}' limit 6;".format(date_str, date_tmp)
+          "and budan.stat_date = '{}';".format(date_str, date_tmp)
 
     db = pymysql.connect(host='172.16.30.143', port=3306, user='work', passwd='BJQaT9VzDcuPBqkd', db='zhengxing')
     cursor = db.cursor()
@@ -146,7 +146,7 @@ def hospital():
 
     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 " \
-          "where partition_date = '{}' limit 6;".format(date_str)
+          "where partition_date = '{}';".format(date_str)
 
     cursor = db.cursor()
     cursor.execute(sql)
@@ -158,34 +158,34 @@ def hospital():
     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')
-    #
-    # for i in ["hospital_exposure_pv_30","service_exposure_pv_30","expert_exposure_pv_30",
-    #           "service_ctr_30","hospital_ctr_30","expert_ctr_30",
-    #           "doctor_ad_money_30_days", "service_pv_30",
-    #           "mexpert_pv_30", "organization_pv_30", "budan_payment_30_days","doctor_discount_30_days"]:
-    #     df[i] = df[i].astype("float")
-    #
-    # df["all_exposure"] = df["hospital_exposure_pv_30"] + df["service_exposure_pv_30"] + df["expert_exposure_pv_30"]
-    # 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["hospital_exposure_pv_30"]/ df["all_exposure"] * df["hospital_ctr_30"] + \
-    #             df["expert_exposure_pv_30"]/df["all_exposure"] * df["expert_ctr_30"]
-    # 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["score"] = df["ctr"]**0.5 * (df["commission"] + df["cpt"])
-    # columns = ["score","ctr","commission","cpt","hospital_exposure_pv_30","service_exposure_pv_30",
-    #            "expert_exposure_pv_30",
-    #           "service_ctr_30","hospital_ctr_30","expert_ctr_30", "service_pv_30",
-    #           "mexpert_pv_30", "organization_pv_30"]
-    # data = df.loc[:, columns]
-    # print(data.head(6))
-    # data.to_csv('/home/gmuser/hospital.csv',index=False)
+    df["merchant_id"] = df["merchant_id"].astype("str")
+    tmp["merchant_id"] = tmp["merchant_id"].astype("str")
+    df = pd.merge(df, tmp, on='merchant_id')
+
+    for i in ["hospital_exposure_pv_30","service_exposure_pv_30","expert_exposure_pv_30",
+              "service_ctr_30","hospital_ctr_30","expert_ctr_30",
+              "doctor_ad_money_30_days", "service_pv_30",
+              "mexpert_pv_30", "organization_pv_30", "budan_payment_30_days","doctor_discount_30_days"]:
+        df[i] = df[i].astype("float")
+
+    df["all_exposure"] = df["hospital_exposure_pv_30"] + df["service_exposure_pv_30"] + df["expert_exposure_pv_30"]
+    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["hospital_exposure_pv_30"]/ df["all_exposure"] * df["hospital_ctr_30"] + \
+                df["expert_exposure_pv_30"]/df["all_exposure"] * df["expert_ctr_30"]
+    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["score"] = df["ctr"]**0.5 * (df["commission"] + df["cpt"])
+    columns = ["score","ctr","commission","cpt","hospital_exposure_pv_30","service_exposure_pv_30",
+               "expert_exposure_pv_30",
+              "service_ctr_30","hospital_ctr_30","expert_ctr_30", "service_pv_30",
+              "mexpert_pv_30", "organization_pv_30"]
+    data = df.loc[:, columns]
+    print(data.head(6))
+    data.to_csv('/home/gmuser/hospital.csv',index=False)
 
 if __name__ == "__main__":
     hospital()