Skip to content

F
ffm-baseline
Commit bb5a2b94 authored by 张彦钊's avatar 张彦钊
Browse files
Options

add

parent 66592d26
Hide whitespace changes
Inline Side-by-side
Showing with 55 additions and 39 deletions
make_data.py
View file @ bb5a2b94
...@@ -121,53 +121,69 @@ def hospital(): ...@@ -121,53 +121,69 @@ def hospital():
date_str = (datetime.datetime.now() - datetime.timedelta(days=1)).strftime("%Y%m%d") 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") 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," \ sql = "select api.id," \
"h.expert_exposure_pv_30,h.service_ctr_30,h.hospital_ctr_30,h.expert_ctr_30" \ "h.hospital_id,h.hospital_exposure_pv_30,h.service_exposure_pv_30,h.expert_exposure_pv_30," \
"api.id,b.merchant_id," \ "h.service_ctr_30,h.hospital_ctr_30,h.expert_ctr_30," \
"m.doctor_ad_money_30_days,m.expand_rechange_amount_30,m.service_pv_30,m.expert_pv_30,m.organization_pv_30," \ "b.merchant_id,budan.budan_payment_30_days " \
"budan.budan_payment_30_days " \ "from api_doctor api left join statistic_hospital_rank_factor h on api.hospital_id = h.hospital_id " \
"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 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 " \
"left join statistic_merchant_rank_factor m on b.merchant_id = m.merchant_id " \ "where api.doctor_type = 1 and h.partition_date = '{}' " \
"left join al_meigou_service_smart_rank_budan_payment budan on b.merchant_id = budan.merchant_id " \ "and budan.stat_date = '{}' limit 6;".format(date_str, date_tmp)
"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') db = pymysql.connect(host='172.16.30.143', port=3306, user='work', passwd='BJQaT9VzDcuPBqkd', db='zhengxing')
cursor = db.cursor() cursor = db.cursor()
cursor.execute(sql) cursor.execute(sql)
result = cursor.fetchall() result = cursor.fetchall()
df = pd.DataFrame(list(result)) df = pd.DataFrame(list(result))
name = ["doctor_id","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"]
name = ["hospital_id","hospital_exposure_pv_30","service_exposure_pv_30" \ df = df.rename(columns=dict(zip(list(range(len(name))), name)))
"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"] + \ print(df.head(6))
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"] # sql = "select merchant_id,doctor_ad_money_30_days,expand_rechange_amount_30," \
df["pv_ad"] = df["expand_rechange_amount_30"]/df["tmp"] # "service_pv_30,expert_pv_30,organization_pv_30 from statistic_merchant_rank_factor " \
df["score"] = df["ctr"]**0.5 * (df["commission"] + df["pv_ad"]) # "where partition_date = '{}';".format(date_str)
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", # cursor = db.cursor()
"mexpert_pv_30","organization_pv_30","budan_payment_30_days"] # cursor.execute(sql)
data = df.loc[:, columns] # result = cursor.fetchall()
# print(data) # db.close()
data.to_csv('/home/gmuser/doctor.csv',index=False) # 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)))
#
# 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 ["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)
if __name__ == "__main__": if __name__ == "__main__":
v1_doctor() hospital()
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment