参数为PTRATIO,RAD,ZN,CRIM写一个波士顿房价预测神经网络python代码并将数据可视化

好的，我可以帮你写一个简单的基于多层感知器（MLP）的波士顿房价预测神经网络python代码。首先需要导入必要的库和数据集：

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_boston
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.neural_network import MLPRegressor

# 加载波士顿房价数据集
boston = load_boston()
boston_df = pd.DataFrame(boston.data, columns=boston.feature_names)
boston_df['PRICE'] = boston.target

接下来，我们选择使用的特征和标签，将数据集进行划分和标准化处理：

# 选择特征和标签
X = boston_df[['PTRATIO', 'RAD', 'ZN', 'CRIM']]
y = boston_df['PRICE']

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 对特征进行标准化处理
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

然后，我们可以使用MLPRegressor模型来训练神经网络并进行预测：

# 创建并训练MLP模型
mlp = MLPRegressor(hidden_layer_sizes=(100, 50), activation='relu', solver='adam', max_iter=1000, verbose=False)
mlp.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = mlp.predict(X_test)

最后，我们可以将预测结果与真实值进行可视化比较：

# 绘制预测结果和真实值的散点图
plt.scatter(y_test, y_pred)
plt.plot([0, 50], [0, 50], '--k')
plt.xlabel('True Values')
plt.ylabel('Predictions')
plt.show()

完整代码如下所示：

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_boston
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.neural_network import MLPRegressor

# 加载波士顿房价数据集
boston = load_boston()
boston_df = pd.DataFrame(boston.data, columns=boston.feature_names)
boston_df['PRICE'] = boston.target

# 选择特征和标签
X = boston_df[['PTRATIO', 'RAD', 'ZN', 'CRIM']]
y = boston_df['PRICE']

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 对特征进行标准化处理
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# 创建并训练MLP模型
mlp = MLPRegressor(hidden_layer_sizes=(100, 50), activation='relu', solver='adam', max_iter=1000, verbose=False)
mlp.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = mlp.predict(X_test)

# 绘制预测结果和真实值的散点图
plt.scatter(y_test, y_pred)
plt.plot([0, 50], [0, 50], '--k')
plt.xlabel('True Values')
plt.ylabel('Predictions')
plt.show()

希望这个代码对你有帮助！