add

ai_test.py

@@ -15,7 +15,7 @@ param_dict={}
 # param_detail = {"device_id": 'xx',"size": 10,"offset":0, "query": "双眼皮","user_city_tag_id": 328,"is_officer":False}
 
 param_dict["method"]="doris/search/bangdan"
-param_detail = {"device_id": '2',"size": 10,"offset":0, "user_city_tag_id": 328,"is_officer":True}
+param_detail = {"device_id": '2',"size": 10,"offset":0, "user_city_tag_id": 328,"is_officer":False,"unit_ids":[]}
 
 
 # a = [105, 2941, 780, 102, 873, 2060, 187, 2935, 2108, 912, 928, 2059, 4437, 822, 2866, 2778, 824, 821, 2938]

make_data.py

@@ -2,6 +2,7 @@ import datetime
 import pymysql
 import pandas as pd
 
+
 def doctor():
     date_str = (datetime.datetime.now() - datetime.timedelta(days=1)).strftime("%Y%m%d")
     date_tmp = (datetime.datetime.now() - datetime.timedelta(days=1)).strftime("%Y-%m-%d")
@@ -54,6 +55,116 @@ def doctor():
     data.to_csv('/home/gmuser/doctor.csv',index=False)
 
 
+def v1_doctor():
+    date_str = (datetime.datetime.now() - datetime.timedelta(days=1)).strftime("%Y%m%d")
+    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 "
+    "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 = '{}' limit 6;".format(date_str, date_tmp)
+
+    db = pymysql.connect(host='172.16.30.143', port=3306, user='work', passwd='BJQaT9VzDcuPBqkd', db='zhengxing')
+    cursor = db.cursor()
+    cursor.execute(sql)
+    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"]
+
+    df = df.rename(columns=dict(zip(list(range(len(name))), name)))
+    print(df)
+
+    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 = '{}'; limit 6".format(date_str)
+
+    cursor = db.cursor()
+    cursor.execute(sql)
+    result = cursor.fetchall()
+    tmp = pd.DataFrame(list(result))
+    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)
+
+    # 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)
+
+
+def hospital():
+    date_str = (datetime.datetime.now() - datetime.timedelta(days=1)).strftime("%Y%m%d")
+    date_tmp = (datetime.datetime.now() - datetime.timedelta(days=1)).strftime("%Y-%m-%d")
+
+    sql = "select h.hospital_id,h.hospital_exposure_pv_30,h.service_exposure_pv_30," \
+          "h.expert_exposure_pv_30,h.service_ctr_30,h.hospital_ctr_30,h.expert_ctr_30" \
+    "api.id,b.merchant_id," \
+    "m.doctor_ad_money_30_days,m.expand_rechange_amount_30,m.service_pv_30,m.expert_pv_30,m.organization_pv_30," \
+    "budan.budan_payment_30_days " \
+    "from statistic_hospital_rank_factor h left join api_doctor api on h.hospital_id = api.hospital_id " \
+    "left join hippo_merchantrelevance b on api.id = b.doctor_id " \
+    "left join statistic_merchant_rank_factor m on b.merchant_id = m.merchant_id " \
+    "left join al_meigou_service_smart_rank_budan_payment budan on b.merchant_id = budan.merchant_id " \
+    "where h.partition_date = '{}' and m.partition_date = '{}' " \
+    "and budan.stat_date = '{}';".format(date_str,date_str,date_tmp)
+
+    db = pymysql.connect(host='172.16.30.143', port=3306, user='work', passwd='BJQaT9VzDcuPBqkd', db='zhengxing')
+    cursor = db.cursor()
+    cursor.execute(sql)
+    result = cursor.fetchall()
+    df = pd.DataFrame(list(result))
+
+    name = ["hospital_id","hospital_exposure_pv_30","service_exposure_pv_30" \
+          "h.expert_exposure_pv_30,h.service_ctr_30,h.hospital_ctr_30,h.expert_ctr_30","id",
+            "merchant_id","doctor_ad_money_30_days","expand_rechange_amount_30","service_pv_30",
+            "mexpert_pv_30","organization_pv_30","budan_payment_30_days"]
+
+    df = df.rename(columns=dict(zip(list(range(len(name))),name)))
+    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)
+
 if __name__ == "__main__":
-    doctor()
+    v1_doctor()