# 基于TensorFlow实现预测房价--回归问题

·  阅读 236

## 波士顿房价数据集

``````from tensorflow.keras.datasets import boston_housing

(train_data, train_targets), (test_data, test_targets) = boston_housing.load_data()

print(train_data.shape )
#(404, 13)
print(test_data.shape)
# (102, 13)

``````print(train_targets)
#array([ 15.2,  42.3,  50. ...  19.4,  19.4,  29.1])

## 准备数据

``````mean = train_data.mean(axis=0)
train_data -= mean
std = train_data.std(axis=0)
train_data /= std

test_data -= mean
test_data /= std

## 构建网络

``````def build_model():
model = models.Sequential()
model.add(layers.Dense(64, activation='relu',
input_shape=(train_data.shape[1],)))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(1))
model.compile(optimizer='rmsprop', loss='mse', metrics=['mae'])
return model

## 利用 K 折验证来验证你的方法

``````import numpy as np

k = 4
num_val_samples = len(train_data) // k
num_epochs = 100
all_scores = []

for i in range(k):
print('processing fold #', i)
val_data = train_data[i * num_val_samples: (i + 1) * num_val_samples]
val_targets = train_targets[i * num_val_samples: (i + 1) * num_val_samples]

partial_train_data = np.concatenate(
[train_data[:i * num_val_samples],
train_data[(i + 1) * num_val_samples:]],
axis=0)
partial_train_targets = np.concatenate(
[train_targets[:i * num_val_samples],
train_targets[(i + 1) * num_val_samples:]],
axis=0)

model = build_model()
model.fit(partial_train_data, partial_train_targets,
epochs=num_epochs, batch_size=1, verbose=0)
val_mse, val_mae = model.evaluate(val_data, val_targets, verbose=0)
all_scores.append(val_mae)

print(all_scores)

``````print(np.mean(all_scores))
#2.9947904173572462

``````num_epochs = 500
all_mae_histories = []
for i in range(k):
print('processing fold #', i)
val_data = train_data[i * num_val_samples: (i + 1) * num_val_samples]
val_targets = train_targets[i * num_val_samples: (i + 1) * num_val_samples]

partial_train_data = np.concatenate(
[train_data[:i * num_val_samples],
train_data[(i + 1) * num_val_samples:]],
axis=0)

partial_train_targets = np.concatenate(
[train_targets[:i * num_val_samples],
train_targets[(i + 1) * num_val_samples:]],
axis=0)

model = build_model()
history = model.fit(partial_train_data, partial_train_targets,
validation_data=(val_data, val_targets),
epochs=num_epochs, batch_size=1, verbose=0)
mae_history = history.history['val_mean_absolute_error']
all_mae_histories.append(mae_history)

``````average_mae_history = [
np.mean([x[i] for x in all_mae_histories]) for i in range(num_epochs)]

plt.plot(range(1, len(average_mae_history) + 1), average_mae_history)
plt.xlabel('Epochs')
plt.ylabel('Validation MAE')
plt.show()

• 删除前 10 个数据点，因为它们的取值范围与曲线上的其他点不同。
• 将每个数据点替换为前面数据点的指数移动平均值，以得到光滑的曲线。
``````def smooth_curve(points, factor=0.9):
smoothed_points = []
for point in points:
if smoothed_points:
previous = smoothed_points[-1]
smoothed_points.append(previous * factor + point * (1 - factor))
else:
smoothed_points.append(point)
return smoothed_points

smooth_mae_history = smooth_curve(average_mae_history[10:])

plt.plot(range(1, len(smooth_mae_history) + 1), smooth_mae_history)
plt.xlabel('Epochs')
plt.ylabel('Validation MAE')
plt.show()

``````model = build_model()
model.fit(train_data, train_targets,
epochs=80, batch_size=16, verbose=0)
test_mse_score, test_mae_score = model.evaluate(test_data, test_targets)

## 完整代码

``````from tensorflow.keras.datasets import boston_housing
from tensorflow.keras import models
from tensorflow.keras import layers
import matplotlib.pyplot as plt
import numpy as np

(train_data, train_targets), (test_data, test_targets) = boston_housing.load_data()

mean = train_data.mean(axis=0)
train_data -= mean
std = train_data.std(axis=0)
train_data /= std

test_data -= mean
test_data /= std

def build_model():
model = models.Sequential()
model.add(layers.Dense(64, activation='relu',
input_shape=(train_data.shape[1],)))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(1))
model.compile(optimizer='rmsprop', loss='mse', metrics=['mae'])
return model

k = 4
num_val_samples = len(train_data) // k
# num_epochs = 100
# all_scores = []

# for i in range(k):
#   print('processing fold #', i)
#   val_data = train_data[i * num_val_samples: (i + 1) * num_val_samples]
#   val_targets = train_targets[i * num_val_samples: (i + 1) * num_val_samples]

#   partial_train_data = np.concatenate(
#       [train_data[:i * num_val_samples],
#        train_data[(i + 1) * num_val_samples:]],
#        axis=0)
#   partial_train_targets = np.concatenate(
#       [train_targets[:i * num_val_samples],
#        train_targets[(i + 1) * num_val_samples:]],
#        axis=0)

#   model = build_model()
#   model.fit(partial_train_data, partial_train_targets,
#         epochs=num_epochs, batch_size=1, verbose=0)
#   val_mse, val_mae = model.evaluate(val_data, val_targets, verbose=0)
#   all_scores.append(val_mae)

# print(all_scores)

num_epochs = 500
all_mae_histories = []
for i in range(k):
print('processing fold #', i)
val_data = train_data[i * num_val_samples: (i + 1) * num_val_samples]
val_targets = train_targets[i * num_val_samples: (i + 1) * num_val_samples]

partial_train_data = np.concatenate(
[train_data[:i * num_val_samples],
train_data[(i + 1) * num_val_samples:]],
axis=0)
partial_train_targets = np.concatenate(
[train_targets[:i * num_val_samples],
train_targets[(i + 1) * num_val_samples:]],
axis=0)

model = build_model()
history = model.fit(partial_train_data, partial_train_targets,
validation_data=(val_data, val_targets),
epochs=num_epochs, batch_size=1, verbose=0)
mae_history = history.history['val_mean_absolute_error']
all_mae_histories.append(mae_history)

average_mae_history = [
np.mean([x[i] for x in all_mae_histories]) for i in range(num_epochs)]

plt.plot(range(1, len(average_mae_history) + 1), average_mae_history)
plt.xlabel('Epochs')
plt.ylabel('Validation MAE')
plt.show()