change transform

tensnsorflow/ffm.py

@@ -107,20 +107,14 @@ def transform(df,validate_date):
 def get_statistics():
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='eagle')
     sql = "select device_id,device_type,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 limit 200"
-    df = con_sql(db, sql).drop_duplicates()
+          "吸脂,脂肪填充,隆胸,私密,毛发管理,公立,韩国 from home_tab_click"
+    df = con_sql(db, sql)
     df = df.rename(columns={0:"device_id",1:"os",2:"total"})
     for i in df.columns.difference(["device_id", "os","total"]):
         df[i] = df[i]/df["total"]
         df[i] = df[i].apply(lambda x: format(x,".4f"))
         df[i] = df[i].astype("float")
     df = df.drop("total", axis=1)
-
-    df["y"] = 1
-    model = multiFFMFormatPandas()
-    df = model.fit_transform(df, y="y", n=100000, processes=18)
-    df = pd.DataFrame(df)
-    print(df.head())
     return df
 
 
@@ -231,6 +225,6 @@ class multiFFMFormatPandas:
 
 if __name__ == "__main__":
     path = "/home/gmuser/ffm/"
-    # get_data()
-    get_statistics()
+    get_data()
+