add

make_data.py

@@ -44,9 +44,8 @@ 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")
 
-    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 " \
-          "from statistic_doctor_rank_factor 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 from statistic_doctor_rank_factor d " \
           "left join hippo_merchantrelevance b on d.doctor_id = b.doctor_id " \
           "where d.partition_date = '{}';".format(date_str)
 
@@ -64,6 +63,7 @@ def doctor():
     df = df.dropna(subset=["merchant_id"])
     print("drop")
     print(df.shape)
+    print(df.head(6))
 
     sql = "select merchant_id,doctor_discount_30_days,expand_rechange_amount_30," \
           "service_pv_30,expert_pv_30,organization_pv_30 from statistic_merchant_rank_factor " \
@@ -79,6 +79,7 @@ def doctor():
     tmp = tmp.rename(columns=dict(zip(list(range(len(name))), name)))
     print("tmp")
     print(tmp.shape)
+    print(tmp.head(6))
 
     df["merchant_id"] = df["merchant_id"].astype('int64')
     df["merchant_id"] = df["merchant_id"].astype("str")
@@ -123,6 +124,7 @@ def doctor():
     df.loc[df["pv_ad"] < 0.01, ["pv_ad"]] = 0.01
 
     df["score"] = df["ctr"] ** 0.5 * (df["commission"] + df["pv_ad"])
+    print(df.shape)
 
     columns = ["doctor_id","score","ctr","commission","pv_ad","service_exposure_pv_30",
                "service_ctr_30","expert_exposure_pv_30","expert_pv_30",
@@ -317,9 +319,9 @@ def old():
 
 
 if __name__ == "__main__":
-    # doctor()
+    doctor()
     # hospital()
-    old()
+    # old()