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

tensnsorflow/ffm.py

@@ -192,6 +192,24 @@ def transform(a,validate_date):
 
     return model
 
+def get_user_feature():
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    sql = "select max(stat_date) from esmm_train_data"
+    validate_date = con_sql(db, sql)[0].values.tolist()[0]
+    print("validate_date:" + validate_date)
+    temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
+    start = (temp - datetime.timedelta(days=2)).strftime("%Y-%m-%d")
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    sql = "select e.device_id,e.y,e.z,e.stat_date,e.ucity_id,e.cid_id,e.clevel1_id,e.ccity_name," \
+          "u.device_type,u.manufacturer,u.channel,home.total" \
+          "from (esmm_train_data e left join user_feature u on e.device_id = u.device_id) " \
+          "left join home_tab_click home on e.device_id = home.device_id" \
+          "where e.stat_date >= '{}'".format(start)
+    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"})
+    print(df.head(2))
+
 def get_statistics():
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     sql = "select device_id,total,精选,直播,鼻部,眼部,微整,牙齿,轮廓,美肤抗衰," \
@@ -258,13 +276,15 @@ def get_predict_set(ucity_id, cid,model):
 
 
 if __name__ == "__main__":
+    get_user_feature()
+
     path = "/home/gmuser/ffm/"
     a = time.time()
-    df, validate_date, ucity_id, cid = get_data()
-    model = transform(df, validate_date)
-    get_predict_set(ucity_id, cid,model)
-    b = time.time()
-    print("cost(分钟)")
-    print((b-a)/60)
+    # df, validate_date, ucity_id, cid = get_data()
+    # model = transform(df, validate_date)
+    # get_predict_set(ucity_id, cid,model)
+    # b = time.time()
+    # print("cost(分钟)")
+    # print((b-a)/60)