add

make_data.py

@@ -54,31 +54,28 @@ def doctor():
     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.loc[df["doctor_ad_money_30_days"] < 0, ["doctor_ad_money_30_days"]] = 0
+    df.loc[df["budan_payment_30_days"] < 0, ["budan_payment_30_days"]] = 0
+
     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"])
+
+    df.loc[df["all_exposure"] <= 1500, ["ctr"]] = 0.01
+    df.loc[df["ctr"] < 0.01, ["ctr"]] = 0.01
+    df.loc[df["ctr"] > 0.2, ["ctr"]] = 0.2
+    df.loc[df["commission"] > 20, ["commission"]] = 20
+    df.loc[df["commission"] < 0.01, ["commission"]] = 0.01
+    df.loc[df["pv_ad"] > 20, ["pv_ad"]] = 20
+    df.loc[df["pv_ad"] < 0.01, ["pv_ad"]] = 0.01
+
     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",
             "mexpert_pv_30","organization_pv_30","budan_payment_30_days"]
     data = df.loc[:, columns]
- #    renames = {'doctor_id': '医生id',
- # 'score': '得分',
- # 'ctr': '点击率',
- # 'commission': '单pv佣金贡献',
- # 'pv_ad': '单pv广告消耗',
- # 'service_exposure_pv_30': '30天内美购曝光pv',
- # 'service_ctr_30': '30天内美购ctr',
- # 'expert_exposure_pv_30': '医生曝光次数-30天',
- # 'expert_pv_30': '医生主页PV-30天',
- # 'merchant_id': '商户id',
- # 'doctor_ad_money_30_days': '商户名下非医生、机构账号的验证订单抽成之和',
- # 'expand_rechange_amount_30': '统计期内该商户的广告消耗（CPC+CPT+其他',
- # 'service_pv_30': '该商户名下所有美购的美购详情页PV',
- # 'mexpert_pv_30': '该商户名下所有医生主页PV',
- # 'organization_pv_30': '该商户名下机构主页PV',
- # 'budan_payment_30_days': '30天已补订单佣金'}
- #    data = data.rename(columns=renames)
+
     data = data.drop_duplicates()
     data.to_csv('/tmp/doctor.csv',index=False)
     print("doctor end")
@@ -143,36 +140,29 @@ def hospital():
     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.loc[df["doctor_ad_money_30_days"] < 0, ["doctor_ad_money_30_days"]] = 0
+    df.loc[df["budan_payment_30_days"] < 0, ["budan_payment_30_days"]] = 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["score"] = df["ctr"]**0.5 * (df["commission"] + df["cpt"])
+
+    df.loc[df["all_exposure"] <= 1500, ["ctr"]] = 0.01
+    df.loc[df["ctr"] < 0.01, ["ctr"]] = 0.01
+    df.loc[df["ctr"] > 0.2, ["ctr"]] = 0.2
+    df.loc[df["cpt"] > 20, ["cpt"]] = 20
+    df.loc[df["cpt"] < 0.01, ["cpt"]] = 0.01
+    df.loc[df["commission"] > 20, ["commission"]] = 20
+    df.loc[df["commission"] < 0.01, ["commission"]] = 0.01
+
     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"]
     data = df.loc[:, columns]
- #    renames = {'doctor_id': '机构管理者id',
- # 'score': '得分',
- # 'ctr': '点击率',
- # 'commission': '单pv佣金贡献',
- # 'cpt': '单pv的CPT消耗',
- # 'hospital_id': '医院id',
- # 'hospital_exposure_pv_30': '该医院卡片的曝光-30天',
- # 'service_exposure_pv_30': '该医院名下所有美购的曝光-30天',
- # 'expert_exposure_pv_30': '机构名下所有医生卡片曝光-30天',
- # 'service_ctr_30': '机构名下所有美购ctr-30天',
- # 'hospital_ctr_30': '医院卡片ctr-30天',
- # 'expert_ctr_30': '机构名下所有医生ctr-30天',
- # 'merchant_id': '商户id',
- # 'budan_payment_30_days': '30天已补订单佣金',
- # 'doctor_ad_money_30_days': '商户名下非医生、机构账号的验证订单抽成之和',
- # 'service_pv_30': '该商户名下所有美购的美购详情页PV',
- # 'mexpert_pv_30': '该商户名下所有医生主页PV',
- # 'organization_pv_30': '该商户名下机构主页PV',
- # 'doctor_discount_30_days': '该商户的CPT纯消耗金额'}
- #
- #    data = data.rename(columns=renames)
+
     data = data.drop_duplicates()
 
     print(data.head(6))