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

tensnsorflow/ffm.py

@@ -14,7 +14,7 @@ def con_sql(db,sql):
     try:
         cursor.execute(sql)
         result = cursor.fetchall()
-        df = pd.DataFrame(list(result)).dropna()
+        df = pd.DataFrame(list(result))
     except Exception:
         print("发生异常", Exception)
         df = pd.DataFrame()
@@ -138,38 +138,34 @@ class multiFFMFormatPandas:
 
 def get_data():
     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_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=15)).strftime("%Y-%m-%d")
+    start = (temp - datetime.timedelta(days=18)).strftime("%Y-%m-%d")
     print(start)
     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.jingxuan,home.zhibo,home.nose,home.eyes,home.weizheng,home.teeth,home.lunkuo," \
-          "home.meifu,home.xizhi,home.zhifang,home.longxiong,home.simi,home.maofa,home.gongli,home.korea " \
-          "from esmm_train_test 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 " \
+    sql = "select e.y,e.z,e.stat_date,e.ucity_id,e.clevel1_id,e.ccity_name," \
+          "u.device_type,u.manufacturer,u.channel,c.top,cid_time.time " \
+          "from esmm_train_data e left join user_feature u on e.device_id = u.device_id " \
+          "left join cid_type_top c on e.device_id = c.device_id left join cid_time on e.cid_id = cid_time.cid_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.shape)
+    df = df.rename(columns={0: "y", 1: "z", 2: "stat_date", 3: "ucity_id",4: "clevel1_id", 5: "ccity_name"})
     print("esmm data ok")
     print(df.head(2))
     ucity_id = list(set(df["ucity_id"].values.tolist()))
-    cid = list(set(df["cid_id"].values.tolist()))
     df["clevel1_id"] = df["clevel1_id"].astype("str")
-    df["cid_id"] = df["cid_id"].astype("str")
     df["y"] = df["y"].astype("str")
     df["z"] = df["z"].astype("str")
-    df["y"] = df["stat_date"].str.cat([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","device_id"], axis=1).fillna(0.0)
+    df["y"] = df["stat_date"].str.cat([df["y"].values.tolist(),df["z"].values.tolist()], sep=",")
+    df = df.drop(["z","stat_date"], axis=1).fillna(0.0)
     print(df.head(2))
+    features = len(df["ucity_id"].unique())
     print("fields:{}".format(df.shape[1]-1))
-    print("features:{}".format(len(cid)))
-    return df,validate_date,ucity_id,cid
+    print("features:{}".format(features))
+    return df,validate_date,ucity_id
 
 
 def transform(a,validate_date):
@@ -177,13 +173,10 @@ def transform(a,validate_date):
     df = model.fit_transform(a, y="y", n=160000, processes=22)
     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])
-    df["city_id"] = df[0].apply(lambda x: x.split(",")[2])
-    df["cid"] = df[0].apply(lambda x: x.split(",")[3])
     df["number"] = np.random.randint(1, 2147483647, df.shape[0])
     df["seq"] = list(range(df.shape[0]))
     df["seq"] = df["seq"].astype("str")
-    df["data"] = df[0].apply(lambda x: ",".join(x.split(",")[4:]))
+    df["data"] = df[0].apply(lambda x: ",".join(x.split(",")[1:]))
     df["data"] = df["seq"].str.cat(df["data"], sep=",")
     df = df.drop([0,"seq"], axis=1)
     print(df.head(2))
@@ -200,27 +193,21 @@ def transform(a,validate_date):
     return model
 
 
-def get_predict_set(ucity_id, cid,model):
+def get_predict_set(ucity_id,model):
     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.jingxuan,home.zhibo,home.nose,home.eyes,home.weizheng,home.teeth,home.lunkuo," \
-          "home.meifu,home.xizhi,home.zhifang,home.longxiong,home.simi,home.maofa,home.gongli,home.korea,e.label " \
+    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,cid_time.time " \
           "from esmm_pre_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"
+          "left join cid_type_top c on e.device_id = c.device_id left join cid_time on e.cid = cid_time.cid_id"
+
     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"})
+    df = df.rename(columns={0: "y", 1: "z", 2: "label", 3: "ucity_id", 4: "clevel1_id", 5: "ccity_name"})
     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")
     df["y"] = df["y"].astype("str")
     df["z"] = df["z"].astype("str")
     df["label"] = df["label"].astype("str")
@@ -258,13 +245,12 @@ def get_predict_set(ucity_id, cid,model):
 
 
 if __name__ == "__main__":
-    path = "/home/gaoyazhe/esmm/data/"
+    path = "/home/gmuser/ffm/"
     a = time.time()
-    df, validate_date, ucity_id, cid = get_data()
+    df, validate_date, ucity_id = get_data()
     model = transform(df, validate_date)
-    get_predict_set(ucity_id, cid,model)
+    # get_predict_set(ucity_id,model)
     b = time.time()
     print("cost(分钟)")
     print((b-a)/60)
 
-