wine_data=pd.read_csv(r'C:\Users\20778\Desktop\batch1(xin).csv') data=wine_data.iloc[:,1:] target=wine_data.iloc[:,0] data1=wine_data.iloc[:,1:333] data2=wine_data.iloc[:,333:] y_known = data1=wine_data.iloc[:,1:333] y_unknown = data2=wine_data.iloc[:,333:] x_train, x_test, y_train, y_test = train_test_split(data1, y_known, test_size=0.2, random_state=1) model = Sequential() model.add(Dense(64, activation='relu', input_dim=x_train.shape[1])) model.add(Dense(64, activation='relu')) model.add(Dense(1, activation='sigmoid')) model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy']) model.fit(x_train, y_train, epochs=300)错误在哪

这段代码有一个错误：在定义y_known时，代码重复赋值了y_known和data1，导致y_known的取值与实际意图不符。下面是修改后的代码：

wine_data = pd.read_csv(r'C:\Users\20778\Desktop\batch1(xin).csv')
data = wine_data.iloc[:,1:]
target = wine_data.iloc[:,0]
data1 = wine_data.iloc[:,1:333]
data2 = wine_data.iloc[:,333:]
y_known = wine_data.iloc[:,0]  # 修改此行代码
y_unknown = data2
x_train, x_test, y_train, y_test = train_test_split(data1, y_known, test_size=0.2, random_state=1)
model = Sequential()
model.add(Dense(64, activation='relu', input_dim=x_train.shape[1]))
model.add(Dense(64, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=300)

修改后的代码将y_known的取值设为全部数据的第0列，即目标变量列。