add df.count

eda/esmm/Feature_pipline/data2ffm.py

@@ -177,8 +177,10 @@ def get_data():
     df["time"] = df["time"].astype("str")
     df["y"] = df["stat_date"].str.cat([df["device_id"].values.tolist(),df["y"].values.tolist(),df["z"].values.tolist()], sep=",")
 
-    df = df.drop(["z","stat_date","device_id"], axis=1).fillna("na")
+    df = df.drop(["z","stat_date","device_id"], axis=1)
+    df = df.fillna("na")
     print(df.head(2))
+    print(df.count())
     features = 0
     l = ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","level2_ids","top","time"]
     for i in l:
@@ -248,9 +250,11 @@ def get_predict_set(model,columns):
     df["y"] = df["label"].str.cat(
         [df["device_id"].values.tolist(), df["ucity_id"].values.tolist(), df["cid_id"].values.tolist(),
          df["y"].values.tolist(), df["z"].values.tolist()], sep=",")
-    df = df.drop(["z","label","device_id","cid_id"], axis=1).fillna("na")
+    df = df.drop(["z","label","device_id","cid_id"], axis=1)
+    df = df.fillna("na")
     print("before transform")
     print(df.shape)
+    print(df.count())
     temp_series = model.transform(df,n=160000, processes=22)
     df = pd.DataFrame(temp_series)
     print("after transform")