import tensorflow as tf
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt
import numpy as np
lospath = r'C:\Users\Administrator\PycharmProjects\pythonProject2\大作业\data.csv'
# 读取数据集
data = pd.read_csv(lospath)
# 数据清洗
data.dropna(inplace=True)
data.drop_duplicates(inplace=True)
# 特征选择
X = data.iloc[:, 0:8] # 获取前 8 列作为特征
y = data.iloc[:, 8] # 获取第 9 列作为目标变量
# 数据标准化
scaler = StandardScaler()
X = scaler.fit_transform(X)
# 拆分数据集为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
# 创建神经网络模型
model = tf.keras.Sequential([
tf.keras.layers.Dense(64, activation='relu', input_dim=X_train.shape[1]),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dense(32, activation='relu'),
tf.keras.layers.Dense(1)
])
# 编译模型
model.compile(optimizer='adam', loss='mean_squared_error', metrics=['mse', 'mae'])
# 训练模型
history = model.fit(X_train, y_train, validation_split=0.2, epochs=1000, batch_size=20)
# 绘制损失函数曲线
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Model Loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train', 'Validation'], loc='upper right')
plt.show()
# 计算测试集损失和指标
loss, mse, mae = model.evaluate(X_test, y_test)
print("测试损失:", loss)
print("测试均方误差:", mse)
print("测试平均绝对误差:\n", mae)
# 进行预测
y_pred = model.predict(X_test)
import matplotlib.pyplot as plt
# 将预测值和目标数据对比可视化
plt.plot(y_test.values)
plt.plot(y_pred)
plt.title('Comparison of Target and Prediction')
plt.ylabel('Value')
plt.xlabel('Index')
plt.legend(['Target', 'Prediction'], loc='upper right')
plt.show()
