fix bugs

diary-training.py

@@ -32,8 +32,8 @@ exposure = exposure.rename(columns={0:"cid",1:"device_id",2:"time"})
 print("成功获取曝光表里的数据")
 
 # 求曝光表和点击表的差集合
-exposure.append(click)
-exposure.append(click)
+exposure = exposure.append(click)
+exposure = exposure.append(click)
 subset = click.columns.tolist()
 exposure = exposure.drop_duplicates(subset=subset,keep=False)
 print("成功完成曝光表和点击表的差集合")
@@ -66,6 +66,8 @@ print(data.head(2))
 data = shuffle(data)
 
 print("start ffm transform")
+
+
 # ffm 格式转换函数、类
 class FFMFormatPandas:
     def __init__(self):
@@ -123,6 +125,7 @@ class FFMFormatPandas:
         t = df.dtypes.to_dict()
         return pd.Series({idx: self.transform_row_(row, t) for idx, row in df.iterrows()})
 
+
 ffm_train = FFMFormatPandas()
 data = ffm_train.fit_transform(data, y='y')
 print("done transform ffm")
@@ -131,6 +134,8 @@ data = pd.read_csv("/home/zhangyanzhao/data.csv",header=None)
 print("数据集大小")
 print(data.shape)
 print(data.head(2))
+
+'''
 n = np.rint(data.shape[0]/8)
 m = np.rint(data.shape[0]*(3/8))
 # 1/8的数据集用来做测试集
@@ -148,19 +153,22 @@ train = data.loc[m+1:]
 print("训练集大小")
 print(train.shape)
 train.to_csv("/home/zhangyanzhao/train.csv",index = False,header = None)
+'''
 
 print("start training")
 ffm_model = xl.create_ffm()
-ffm_model.setTrain("/home/zhangyanzhao/train.csv")
-ffm_model.setValidate("/home/zhangyanzhao/validation.csv")
+ffm_model.setTrain("/home/zhangyanzhao/data.csv")
+# ffm_model.setValidate("/home/zhangyanzhao/validation.csv")
 
-param = {'task':'binary', 'lr':0.2,
+param = {'task':'binary', 'lr':0.05,
          'lambda':0.002, 'metric':'auc'}
 
 ffm_model.fit(param, '/home/zhangyanzhao/model.out')
 
+'''
 ffm_model.setTest("/home/zhangyanzhao/test.csv")
 ffm_model.setSigmoid()
 
 ffm_model.predict("/home/zhangyanzhao/model.out", "/home/zhangyanzhao/output.txt")
+'''
 print("end")