import tensorflow as tf import numpy as np import matplotlib.pyplot as plt import pandas as pd from sklearn.utils import shuffle from sklearn.preprocessing import scale df = pd.read_csv("C:\\boston.csv",header=0) ds = df.values from sklearn.datasets import load_boston boston = load_boston() X = boston.data y = boston.target from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) from sklearn.preprocessing import StandardScaler scaler = StandardScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense model = Sequential([ Dense(64, activation='relu', input_shape=(X_train.shape[1],)), Dense(64, activation='relu'), Dense(64, activation='relu'), Dense(1) ]) model.compile(loss='mean_squared_error', optimizer='adam') history = model.fit(X_train, y_train, validation_split=0.1, epochs=100, batch_size=32) from sklearn.metrics import mean_squared_error y_pred = model.predict(x_test)mse = mean_squared_error(y_test, y_pred)print('MSE:’, mse) import matplotlib.pyplot as plt plt.plot(history.history['accuracy'], label='train') plt.plot(history.history['val_accuracy'], label='validation') plt.legend() plt.show()

这段代码使用TensorFlow和Keras实现了一个神经网络模型，用于预测波士顿房价。以下是代码的解释： 首先，导入必要的库和模块： ``` import tensorflow as tf import numpy as np import matplotlib.pyplot as plt import pandas as pd from sklearn.utils import shuffle from sklearn.preprocessing import scale ``` 然后，读取波士顿房价数据集并对其进行预处理： ``` df = pd.read_csv("C:\\boston.csv",header=0) ds = df.values ``` 接着，从sklearn.datasets模块中加载波士顿房价数据集，并将其分为训练集和测试集： ``` from sklearn.datasets import load_boston boston = load_boston() X = boston.data y = boston.target from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) ``` 对训练集和测试集进行标准化处理： ``` from sklearn.preprocessing import StandardScaler scaler = StandardScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) ``` 定义一个包含4个Dense层的神经网络模型： ``` from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense model = Sequential([ Dense(64, activation='relu', input_shape=(X_train.shape[1],)), Dense(64, activation='relu'), Dense(64, activation='relu'), Dense(1) ]) ``` 编译模型并训练： ``` model.compile(loss='mean_squared_error', optimizer='adam') history = model.fit(X_train, y_train, validation_split=0.1, epochs=100, batch_size=32) ``` 使用模型对测试集进行预测，并计算均方误差： ``` from sklearn.metrics import mean_squared_error y_pred = model.predict(x_test) mse = mean_squared_error(y_test, y_pred) print('MSE:’, mse) ``` 最后，绘制模型的训练和验证准确率曲线： ``` import matplotlib.pyplot as plt plt.plot(history.history['accuracy'], label='train') plt.plot(history.history['val_accuracy'], label='validation') plt.legend() plt.show() ```