Keras 运用于波士顿房价预测
导入相关的包
import kerasfrom sklearn.datasets import load_bostonfrom keras.models import Sequentialfrom keras.layers import Densefrom keras.optimizers import SGD,Adamimport numpy as npfrom sklearn.model_selection import train_test_split
载入数据
因为数据各个特征取值范围各不相同，不能直接送到神经网络模型中进行处理。尽管网络模型能适应数据的多样性，但是相应的学习过程变得非常困难。一种常见的数据处理方法是特征归一化normalization—减均值除以标准差；数据0中心化，方差为1.
house = load_boston()x = house.datay = house.targetx_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.1)print(x.shape)print(y.shape)#归一化mean = x.mean(axis=0)std = x.std(axis=0)x_train -= meanx_train /= stdx_test -= meanx_test /= stdprint(x_train.shape)print(y_train.shape)print(x_test.shape)print(y_test.shape)
(506, 13)(506,)(455, 13)(455,)(51, 13)(51,)
模型构建
构建13-64-64-1神经网络
def build_model():model = Sequential()model.add(Dense(64, activation='relu',input_shape=(x_train.shape[1],)))model.add(Dense(64, activation='relu'))model.add(Dense(1))adam = Adam(lr = 0.001)pile(optimizer=adam, loss='mse', metrics=['accuracy'])return model
训练模型
K折交叉验证
当调整模型参数时，为了评估模型，我们通常将数据集分成训练集和验证集。但是当数据量过小时，验证集数目也变得很小，导致验证集上的评估结果相互之间差异性很大—与训练集和测试集的划分结果相关。评估结果可信度不高。
最好的评估方式是采用K折交叉验证–将数据集分成K份(K=4或5)，实例化K个模型，每个模型在K-1份数据上进行训练，在1份数据上进行评估，最后用K次评估分数的平均值做最后的评估结果。
k = 4num_val_samples = len(x_train) // knum_epochs = 100all_scores = []for i in range(k):print('processing fold #',i)val_data = x_train[i*num_val_samples : (i+1)*num_val_samples] # 划分出验证集部分val_targets = y_train[i*num_val_samples : (i+1)*num_val_samples]partial_train_data = np.concatenate([x_train[:i*num_val_samples],x_train[(i+1)* num_val_samples:] ],axis=0) # 将训练集拼接到一起partial_train_targets = np.concatenate([y_train[:i*num_val_samples],y_train[(i+1)* num_val_samples:] ],axis=0)model = build_model()model.fit(partial_train_data,partial_train_targets,epochs=num_epochs,batch_size=16,verbose=0)#模型训练silent模型val_mse, val_mae = model.evaluate(val_data, val_targets, verbose=0) # 验证集上评估all_scores.append(val_mae)
processing fold # 0processing fold # 1processing fold # 2processing fold # 3
model = build_model()for step in range(30001):cost = model.train_on_batch(x_train,y_train)
评估模型
#评估模型test_loss,test_accuracy = model.evaluate(x_test,y_test)print('loss:',test_loss)
51/51 [==============================] - 0s 6ms/steploss: 16.295210819618376
预测结果
y_pred = model.predict(x_test)y_test = y_test.reshape(-1,1)print(y_test.shape)print(y_pred.shape)y = np.concatenate((y_test,y_pred),axis=1)print(y)
(51, 1)(51, 1)[[22.4 29.00861359][26.4 20.00535774][19. 19.89637184][22.2 23.57507515][ 8.8 16.45183182][13.9 12.0325613 ][15.6 17.47181129][22.9 30.84517479][20.7 21.34505653][25. 24.71461678][ 9.7 14.47148418][13.8 14.16065502][20.8 21.88388634][32.2 32.33004379][21.2 20.74515915][34.9 37.37858963][18.4 14.51666927][25.2 27.09690285][36. 35.71841049][24.7 24.20606422][23.9 24.70848465][15.2 10.63304234][12.5 13.14098263][23.2 18.67226028][24.2 24.51757431][44.8 46.45916367][16.4 16.53090096][17.4 20.09835815][19.6 17.38390923][25.1 23.30638313][20.3 20.64103889][18.6 21.87194443][15.2 15.76328373][43.1 40.18106461][15.3 4.6482749 ][22.9 21.33856583][22.1 24.22558022][35.4 37.21940994][21.2 21.54840088][13.5 11.08192062][13.4 18.37044334][50. 61.65808868][28.7 24.61343956][26.5 31.44546509][12.7 16.45353699][50. 48.83145905][14.3 13.62646389][18.5 23.34628105][17.4 20.22313881][24. 13.78490162][30.7 29.4163208 ]]
小结
回归问题：损失函数通常为MSE均方误差；
模型评估监测指标通常为MAE(mean absolute error);
当数据取值范围不一致时，需要对特征进行预处理；
数据量小时，可以采用Ｋ折验证来衡量模型；
数据量小时，模型复杂度也应该相应的简单，可以避免模型过拟合。
