修改ffm转化函数，改成features累计相加

tensnsorflow/ffm.py

@@ -187,7 +187,8 @@ def get_data():
     ucity_id = list(set(df["ucity_id"].values.tolist()))
     manufacturer = list(set(df["manufacturer"].values.tolist()))
     channel = list(set(df["channel"].values.tolist()))
-    return df,validate_date,ucity_id,ccity_name,manufacturer,channel
+    level2_ids = list(set(df["level2_ids"].values.tolist()))
+    return df,validate_date,ucity_id,ccity_name,manufacturer,channel,level2_ids
 
 
 def transform(a,validate_date):
@@ -219,7 +220,7 @@ def transform(a,validate_date):
     return model
 
 
-def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
+def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel,level2_ids):
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     sql = "select e.y,e.z,e.label,e.ucity_id,e.clevel1_id,e.ccity_name," \
           "u.device_type,u.manufacturer,u.channel,c.top,df.level2_ids,e.device_id,e.cid_id " \
@@ -250,6 +251,10 @@ def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
     print("after channel filter:")
     print(df.shape)
 
+    df = df[df["level2_ids"].isin(level2_ids)]
+    print("after level2_ids filter:")
+    print(df.shape)
+
     df["cid_id"] = df["cid_id"].astype("str")
     df["clevel1_id"] = df["clevel1_id"].astype("str")
     df["top"] = df["top"].astype("str")
@@ -302,9 +307,9 @@ def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
 if __name__ == "__main__":
     path = "/home/gmuser/esmm_data/"
     a = time.time()
-    temp, validate_date, ucity_id,ccity_name,manufacturer,channel = get_data()
+    temp, validate_date, ucity_id,ccity_name,manufacturer,channel,level2_ids = get_data()
     model = transform(temp, validate_date)
-    get_predict_set(ucity_id,model,ccity_name,manufacturer,channel)
+    get_predict_set(ucity_id,model,ccity_name,manufacturer,channel,level2_ids)
     b = time.time()
     print("cost(分钟)")
     print((b-a)/60)