Merge branch 'master' of http://git.wanmeizhensuo.com/ML/ffm-baseline

eda/feededa/src/main/scala/com/gmei/EsmmData.scala

@@ -323,7 +323,7 @@ object EsmmPredData {
 
       val union_data_scity_id = sc.sql(
         s"""
-           |select a.stat_date,a.device_id,a.ucity_id,a.cid_id,a.diary_service_id,a.y,a.z,a.clevel1_id,a.slevel1_id,a.ccity_name,
+           |select distinct a.stat_date,a.device_id,a.ucity_id,a.cid_id,a.diary_service_id,a.y,a.z,a.clevel1_id,a.slevel1_id,a.ccity_name,
            |  d.city_id as scity_id
            |from union_data_ccity_name a
            |left join online.tl_meigou_service_view b on a.diary_service_id=b.id

tensnsorflow/ffm.py

@@ -35,8 +35,8 @@ def get_data():
     print("click data ok")
     # print(temp.head())
     df = pd.merge(esmm,temp,on = "device_id",how='left').fillna(0)
-
-    # print(df.shape)
+    print("合并后：")
+    print(df.shape)
 
     df["diary_service_id"] = df["diary_service_id"].astype("str")
     df["clevel1_id"] = df["clevel1_id"].astype("str")
@@ -67,8 +67,11 @@ def transform(df):
     df = df.drop(0, axis=1).drop("seq",axis=1)
     print("size")
     print(df.shape)
-    train = df[df["stat_date"] != "2018-11-25"].drop("stat_date",axis=1)
-    test = df[df["stat_date"] == "2018-11-25"].drop("stat_date",axis=1)
+    print(df.head())
+    train = df[df["stat_date"] != "2018-11-25"]
+    train = train.drop("stat_date",axis=1)
+    test = df[df["stat_date"] == "2018-11-25"]
+    test = test.drop("stat_date",axis=1)
     train.to_csv(path+"train.csv",index=None)
     test.to_csv(path + "test.csv", index=None)
     # yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')
@@ -194,5 +197,5 @@ class multiFFMFormatPandas:
 
 
 if __name__ == "__main__":
-    path = "/data/ffm/"
+    path = "/home/gmuser/ffm/"
     get_data()
\ No newline at end of file