add data

tensnsorflow/ffm.py

@@ -47,11 +47,13 @@ def get_data():
     print(df.head())
     print("shape")
     print(df.shape)
-    df = pd.merge(df,get_statistics(),on="device_id",how='left').fillna(0)
+    device_tuple = tuple(df["device_id"].values.tolist())
+    df = pd.merge(df,get_statistics(device_tuple),on="device_id",how='left').fillna(0)
     print("merge")
     print(df.head())
     print("shape")
     print(df.shape)
+    df = df.drop("device_id", axis=1)
     # transform(df)
 
 
@@ -93,10 +95,10 @@ def transform(df):
     #     pd.io.sql.to_sql(temp, table, yconnect, schema='jerry_test', if_exists='append', index=False)
     #     print("insert done")
 
-def get_statistics():
+def get_statistics(device_tuple):
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='eagle')
     sql = "select device_id,device_type,channel,total,精选,直播,鼻部,眼部,微整,牙齿,轮廓,美肤抗衰," \
-          "吸脂,脂肪填充,隆胸,私密,毛发管理,公立,韩国 from home_tab_click"
+          "吸脂,脂肪填充,隆胸,私密,毛发管理,公立,韩国 from home_tab_click where device_id in {}".format(device_tuple)
     df = con_sql(db, sql)
     df = df.rename(columns={0:"device_id",1:"device_type",2:"channel",3:"total"})
     for i in df.columns.difference(["device_id", "device_type","channel","total"]):