add

make_data.py

@@ -77,12 +77,17 @@ def doctor():
     name = ["merchant_id", "doctor_discount_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")
+    print(tmp.shape)
 
     df["merchant_id"] = df["merchant_id"].astype('int64')
     df["merchant_id"] = df["merchant_id"].astype("str")
     tmp["merchant_id"] = tmp["merchant_id"].astype("str")
     df = pd.merge(df, tmp, on='merchant_id')
 
+    print("merge")
+    print(df.shape)
+
     for i in ["service_exposure_pv_30", "service_ctr_30", "expert_exposure_pv_30", "expert_pv_30",
       "doctor_discount_30_days", "expand_rechange_amount_30", "service_pv_30",
      "mexpert_pv_30", "organization_pv_30"]:
@@ -90,10 +95,15 @@ def doctor():
 
     df["all_exposure"] = df["service_exposure_pv_30"] + df["expert_exposure_pv_30"]
     df = df[~df["expert_exposure_pv_30"].isin([0.0])]
+    print("expert_exposure_pv_30")
+    print(df.shape)
     df = df[~df["all_exposure"].isin([0.0])]
+    print("all_exposure")
+    print(df.shape)
     df["tmp"] = df["service_pv_30"] + df["mexpert_pv_30"] +df["organization_pv_30"]
     df = df[~df["tmp"].isin([0.0])]
-    print("aaaaaaaa")
+    print("tmp")
+    print(df.shape)
     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"])