均方误差(MSE)是用于回归问题的常见损失函数。用于回归的评估指标与分类不同。 常见的回归指标是平均绝对误差(MAE)。
当数字输入数据特征的值存在不同范围时,每个特征应独立缩放到相同范围。
如果训练数据不多,一种方法是选择隐藏层较少的小网络,以避免过度拟合。
早期停止是一种防止过度拟合的有效技术。
# 自定义的callback,通过为每个完成的时期打印一个点来显示训练进度
class PrintDot(keras.callbacks.Callback):
def on_epoch_end(self, epoch, logs):
if epoch % 100 == 0: print('')
print('.', end='')
model = build_model()
# patience 值用来检查改进 epochs 的数量
early_stop = keras.callbacks.EarlyStopping(monitor='val_loss', patience=10)
history = model.fit(normed_train_data, train_labels, epochs=EPOCHS,
validation_split = 0.2, verbose=0, callbacks=[early_stop, PrintDot()])
plot_history(history)
归一化的方法:
train_stats = train_dataset.describe()
def norm(x):
return (x - train_stats['mean']) / train_stats['std']
normed_train_data = norm(train_dataset)
normed_test_data = norm(test_dataset)
DataFrame数据按比例进行分割:
train_dataset = dataset.sample(frac=0.8,random_state=0)
test_dataset = dataset.drop(train_dataset.index)
对数据列进行分列one-hot编码:
origin = dataset.pop('Origin')
dataset['USA'] = (origin == 1)*1.0
dataset['Europe'] = (origin == 2)*1.0
dataset['Japan'] = (origin == 3)*1.0
dataset.tail()
pandas读取csv更详细的使用:
column_names = ['MPG','Cylinders','Displacement','Horsepower','Weight',
'Acceleration', 'Model Year', 'Origin']
raw_dataset = pd.read_csv(dataset_path, names=column_names,
na_values = "?", comment='\t',
sep=" ", skipinitialspace=True)
Keras下载数据:
dataset_path = keras.utils.get_file("auto-mpg.data", "http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data")
dataset_path
seaborn绘制简单的关联关系:
sns.pairplot(train_dataset[["MPG", "Cylinders", "Displacement", "Weight"]], diag_kind="kde")
绘制history的loss等曲线:
def plot_history(history):
hist = pd.DataFrame(history.history)
hist['epoch'] = history.epoch
plt.figure()
plt.xlabel('Epoch')
plt.ylabel('Mean Abs Error [MPG]')
plt.plot(hist['epoch'], hist['mae'],
label='Train Error')
plt.plot(hist['epoch'], hist['val_mae'],
label = 'Val Error')
plt.ylim([0,5])
plt.legend()
plt.figure()
plt.xlabel('Epoch')
plt.ylabel('Mean Square Error [$MPG^2$]')
plt.plot(hist['epoch'], hist['mse'],
label='Train Error')
plt.plot(hist['epoch'], hist['val_mse'],
label = 'Val Error')
plt.ylim([0,20])
plt.legend()
plt.show()
plot_history(history)
使用test数据评估训练后的模型:
loss, mae, mse = model.evaluate(normed_test_data, test_labels, verbose=2)
print("Testing set Mean Abs Error: {:5.2f} MPG".format(mae))