fix bugs

diary-training.py

@@ -128,16 +128,26 @@ data = ffm_train.fit_transform(data, y='y')
 print("done transform ffm")
 data.to_csv("/home/zhangyanzhao/data.csv",index=False)
 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
-data.loc[:n].to_csv("/home/zhangyanzhao/test.csv",index = False,header = None)
+test = data.loc[:n]
+print("测试集大小")
+print(test.shape)
+test.to_csv("/home/zhangyanzhao/test.csv",index = False,header = None)
 # 1/4的数据集用来做验证集
-data.loc[n+1:m].to_csv("/home/zhangyanzhao/validation.csv",index = False,header = None)
-# 剩余的数据集用来做验证集
-data.loc[m+1:].to_csv("/home/zhangyanzhao/train.csv",index = False,header = None)
-# 销毁data，目的是为了节省内存
-data = data.drop(data.index.tolist())
+validation = data.loc[n+1:m]
+validation.to_csv("/home/zhangyanzhao/validation.csv",index = False,header = None)
+print("验证集大小")
+print(validation.shape)
+# 剩余的数据集用来做训练集
+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()