TensorFlow2 开发指南 | 02 回归问题之汽车燃油效率预测

# 下载AUTO-MPG数据集
dataset_path = keras.utils.get_file("auto-mpg.data", "http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data")

# 使用pandas导入数据集
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)
dataset = raw_dataset.copy()
dataset.tail()

复制

dataset.isna().sum()  # 数据集中包括一些未知值
dataset = dataset.dropna()  # 删除未知行

# origin列实际上代表分类，将origin列转换为独热码（one-hot）
origin = dataset.pop('Origin')  
dataset['USA'] = (origin == 1)*1.0
dataset['Europe'] = (origin == 2)*1.0
dataset['Japan'] = (origin == 3)*1.0
dataset.tail()

复制

# 拆分训练数据集和测试数据集
train_dataset = dataset.sample(frac=0.8, random_state=0)
test_dataset = dataset.drop(train_dataset.index)

复制

# 使用seaborn进行数据检查
sns.pairplot(train_dataset[["MPG", "Cylinders", "Displacement", "Weight"]], diag_kind="kde")  

复制

train_labels = train_dataset.pop('MPG')
test_labels = test_dataset.pop('MPG')

复制

def norm(x):
  return (x - train_stats['mean']) / train_stats['std']
normed_train_data = norm(train_dataset)
normed_test_data = norm(test_dataset)

复制

model = keras.Sequential([
    layers.Dense(64, activation='relu', input_shape=[len(train_dataset.keys())]),
    layers.Dense(64, activation='relu'),
    layers.Dense(1)
  ])

复制

optimizer = tf.keras.optimizers.RMSprop(0.001)
model.compile(loss='mse',
                optimizer=optimizer,
                metrics=['mae', 'mse'])

复制

EPOCHS = 1000
history = model.fit(
  normed_train_data, train_labels,
  epochs=EPOCHS, validation_split=0.2, verbose=2)

复制

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)

复制

# 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=1, callbacks=[early_stop])

复制

# 平均预测误差
loss, mae, mse = model.evaluate(normed_test_data, test_labels, verbose=2)
print("Testing set Mean Abs Error: {:5.2f} MPG".format(mae))
test_predictions = model.predict(normed_test_data).flatten()

# 可视化预测效果：prediction-truth图
plt.figure()
plt.scatter(test_labels, test_predictions)
plt.xlabel('True Values [MPG]')
plt.ylabel('Predictions [MPG]')
plt.axis('equal')
plt.axis('square')
plt.xlim([0,plt.xlim()[1]])
plt.ylim([0,plt.ylim()[1]])
_ = plt.plot([-100, 100], [-100, 100])

# 误差分布图
plt.figure()
error = test_predictions - test_labels
plt.hist(error, bins = 25)
plt.xlabel("Prediction Error [MPG]")
_ = plt.ylabel("Count")
plt.show()

复制

Testing set Mean Abs Error:  1.98 MPG

复制