add user

tensnsorflow/ffm.py

@@ -167,12 +167,14 @@ def get_data():
                                        df["y"].values.tolist(),df["z"].values.tolist()], sep=",")
     df = df.drop(["z","device_id"], axis=1).fillna(0.0)
     print(df.head(2))
+    print("fields:{}".format(df.shape[1]-1))
+    print("features:{}".format(len(cid)))
     return df,validate_date,ucity_id,cid
 
 
 def transform(a,validate_date):
     model = multiFFMFormatPandas()
-    df = model.fit_transform(a, y="y", n=160000, processes=22)
+    df = model.fit_transform(a, y="y", n=160000, processes=26)
     df = pd.DataFrame(df)
     df["stat_date"] = df[0].apply(lambda x: x.split(",")[0])
     df["device_id"] = df[0].apply(lambda x: x.split(",")[1])
@@ -209,8 +211,13 @@ def get_predict_set(ucity_id, cid,model):
     df = con_sql(db, sql)
     df = df.rename(columns={0: "device_id", 1: "y", 2: "z", 3: "stat_date", 4: "ucity_id", 5: "cid_id",
                             6: "clevel1_id", 7: "ccity_name",26:"label"})
+    print("before filter:")
+    print(df.shape)
     df = df[df["cid_id"].isin(cid)]
+    print("after cid filter:")
+    print(df.shape)
     df = df[df["ucity_id"].isin(ucity_id)]
+    print("after ucity filter:")
     print(df.shape)
     df["clevel1_id"] = df["clevel1_id"].astype("str")
     df["cid_id"] = df["cid_id"].astype("str")
@@ -221,8 +228,6 @@ def get_predict_set(ucity_id, cid,model):
         [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"], axis=1).fillna(0.0)
-    print("df ok")
-    print(df.shape)
     print(df.head(2))
     df = model.transform(df,n=160000, processes=22)
     df = pd.DataFrame(df)