change transform

tensnsorflow/ffm.py

@@ -52,7 +52,7 @@ def get_data():
     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", axis=1)
-    print(df.head())
+    print(df.head(2))
     print("shape")
     print(df.shape)
     df = pd.merge(df,get_statistics(),how='left').fillna(0)
@@ -67,7 +67,7 @@ def get_data():
 
 def transform(df,validate_date):
     model = multiFFMFormatPandas()
-    df = model.fit_transform(df, y="y", n=80000, processes=18)
+    df = model.fit_transform(df, y="y", n=100000, processes=18)
     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])
@@ -107,14 +107,20 @@ 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"
+          "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()
     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 = 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
 
+
 class multiFFMFormatPandas:
     def __init__(self):
         self.field_index_ = None
@@ -222,5 +228,6 @@ class multiFFMFormatPandas:
 
 if __name__ == "__main__":
     path = "/home/gmuser/ffm/"
-    get_data()
+    # get_data()
+    get_statistics()