按照用户去重应用列表样本

tensnsorflow/ffm.py

@@ -173,12 +173,12 @@ def get_data():
     df["top"] = df["top"].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)
-    df = df.fillna(0)
-    print(df.head(2))
     features = 0
-    for i in ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel"]:
+    for i in ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","top"]:
         features = features + len(df[i].unique())
         df[i] = df[i].fillna(0)
+    print(df.count())
+    print(df.head(2))
     print("fields:{}".format(df.shape[1]-1))
     print("features:{}".format(features+46))
     ccity_name = list(set(df["ccity_name"].values.tolist()))