add level2

eda/esmm/Feature_pipline/data2ffm.py

@@ -146,26 +146,28 @@ def get_data():
     print(start)
     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.stat_date,e.ucity_id,e.clevel1_id,e.ccity_name," \
-          "u.device_type,u.manufacturer,u.channel,c.top,cid_time.time,e.device_id " \
+          "u.device_type,u.manufacturer,u.channel,c.top,df.level2_ids,e.device_id " \
           "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 " \
+          "left join cid_type_top c on e.device_id = c.device_id " \
+          "left join diary_feat df on e.cid_id = df.diary_id " \
           "where e.stat_date >= '{}'".format(start)
     df = con_sql(db, sql)
     print(df.shape)
     df = df.rename(columns={0: "y", 1: "z", 2: "stat_date", 3: "ucity_id",4: "clevel1_id", 5: "ccity_name",
-                            6:"device_type",7:"manufacturer",8:"channel",9:"top",10:"time",11:"device_id"})
+                            6:"device_type",7:"manufacturer",8:"channel",9:"top",10:"level2_ids",11:"device_id"})
     print("esmm data ok")
-    print(df.head(2))
+    # print(df.head(2)
 
     df["clevel1_id"] = df["clevel1_id"].astype("str")
     df["y"] = df["y"].astype("str")
     df["z"] = df["z"].astype("str")
     df["top"] = df["top"].astype("str")
     df["y"] = df["stat_date"].str.cat([df["device_id"].values.tolist(),df["y"].values.tolist(),df["z"].values.tolist()], sep=",")
-    df = df.drop(["z","stat_date","device_id"], axis=1).fillna(0.0)
+
+    df = df.drop(["z","stat_date","device_id"], axis=1).fillna("na")
     print(df.head(2))
     features = 0
-    for i in ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel"]:
+    for i in ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","level2_ids","top"]:
         features = features + len(df[i].unique())
     print("fields:{}".format(df.shape[1]-1))
     print("features:{}".format(features))
@@ -196,8 +198,9 @@ def transform(a,validate_date):
     train = train.drop("stat_date",axis=1)
     test = df[df["stat_date"] == validate_date]
     test = test.drop("stat_date",axis=1)
-    # print("train shape")
-    # print(train.shape)
+    print("train shape")
+    print(train.shape)
+
     train.to_csv(path + "tr.csv", sep="\t", index=False)
     test.to_csv(path + "va.csv", sep="\t", index=False)
 
@@ -207,23 +210,35 @@ def transform(a,validate_date):
 def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
     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,cid_time.time,e.device_id,e.cid_id " \
+          "u.device_type,u.manufacturer,u.channel,c.top,df.level2_ids,e.device_id,e.cid_id " \
           "from esmm_pre_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"
+          "left join cid_type_top c on e.device_id = c.device_id " \
+          "left join diary_feat df on e.cid_id = df.diary_id " \
+          "where e.device_id = '358035085192742'"
     df = con_sql(db, sql)
     df = df.rename(columns={0: "y", 1: "z", 2: "label", 3: "ucity_id", 4: "clevel1_id", 5: "ccity_name",
-                            6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "time",
+                            6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "level2_ids",
                             11:"device_id",12:"cid_id"})
+
     print("before filter:")
     print(df.shape)
+
     df = df[df["ucity_id"].isin(ucity_id)]
     print("after ucity filter:")
     print(df.shape)
+
     df = df[df["ccity_name"].isin(ccity_name)]
+    print("after ccity_name filter:")
+    print(df.shape)
+
     df = df[df["manufacturer"].isin(manufacturer)]
+    print("after manufacturer filter:")
+    print(df.shape)
+
     df = df[df["channel"].isin(channel)]
-    print("after ccity_name filter:")
+    print("after channel 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")
@@ -234,9 +249,12 @@ def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
         [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","cid_id"], axis=1).fillna(0.0)
-    print(df.head(2))
-    df = model.transform(df,n=160000, processes=22)
-    df = pd.DataFrame(df)
+    print("before transform")
+    print(df.shape)
+    temp_series = model.transform(df,n=160000, processes=22)
+    df = pd.DataFrame(temp_series)
+    print("after transform")
+    print(df.shape)
     df["label"] = 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])
@@ -249,26 +267,33 @@ def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
     df = df.drop([0, "seq"], axis=1)
     print(df.head())
 
+    print(df.loc[df["device_id"] == "358035085192742"].shape)
     native_pre = df[df["label"] == "0"]
     native_pre = native_pre.drop("label", axis=1)
+    print("native")
+    print(native_pre.shape)
+    print(native_pre.loc[native_pre["device_id"] == "358035085192742"].shape)
     native_pre.to_csv(path+"native.csv",sep="\t",index=False)
-    # print("native_pre shape")
-    # print(native_pre.shape)
+    print("native_pre shape")
+    print(native_pre.shape)
 
     nearby_pre = df[df["label"] == "1"]
     nearby_pre = nearby_pre.drop("label", axis=1)
+    print("nearby")
+    print(nearby_pre.shape)
+    print(nearby_pre.loc[nearby_pre["device_id"] == "358035085192742"].shape)
     nearby_pre.to_csv(path + "nearby.csv", sep="\t", index=False)
-    # print("nearby_pre shape")
-    # print(nearby_pre.shape)
+    print("nearby_pre shape")
+    print(nearby_pre.shape)
 
 
 
 if __name__ == "__main__":
     path = "/home/gmuser/esmm_data/"
     a = time.time()
-    df, validate_date, ucity_id,ccity_name,manufacturer,channel = get_data()
-    model = transform(df, validate_date)
-    get_predict_set(ucity_id,model,ccity_name,manufacturer,channel)
+    temp, validate_date, ucity_id, ccity_name, manufacturer, channel = get_data()
+    model = transform(temp, validate_date)
+    get_predict_set(ucity_id, model, ccity_name, manufacturer, channel)
     b = time.time()
     print("cost(分钟)")
-    print((b-a)/60)
+    print((b - a) / 60)

tensnsorflow/ffm.py

@@ -290,7 +290,7 @@ def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
 
 
 if __name__ == "__main__":
-    path = "/home/gmuser/ffm/"
+    path = "/home/gmuser/esmm_data/"
     a = time.time()
     temp, validate_date, ucity_id,ccity_name,manufacturer,channel = get_data()
     model = transform(temp, validate_date)