1  导入必要的库

import pandas as pd  
from sklearn.model_selection import train_test_split, cross_val_score, KFold  
import xgboost as xgb  
from sklearn.model_selection import train_test_split  
from sklearn.metrics import mean_squared_error, r2_score  
import matplotlib.pyplot as plt  
import seaborn as sns  
import pandas as pd  
import numpy as np   
from sklearn.metrics import confusion_matrix, classification_report, accuracy_score  
from sklearn.model_selection import RandomizedSearchCV 
from sklearn.tree import plot_tree  
import matplotlib.pyplot as plt  
import seaborn as sns
import missingno as msno
# 忽略Matplotlib的警告（可选）  
import warnings  
warnings.filterwarnings("ignore") 
# 设置中文显示和负号正常显示
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import tensorflow as tf    
from tensorflow.keras.models import Sequential    
from tensorflow.keras.layers import Dense    
from tensorflow.keras.regularizers import l2  # 导入l2正则化  
from sklearn.model_selection import train_test_split    
from sklearn.preprocessing import StandardScaler  

2 加载数据与预处理

df = pd.read_excel('10.xls')  
for column in ['Fault type', 'lithology']:  
    df[column] = pd.factorize(df[column])[0]
df

3 模型构建

# 假设df已经定义并包含了数据  
# 分离特征和标签    
X = df.drop('magnitude', axis=1)    
y = df['magnitude']    
  
# 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)    
  
# 特征缩放    
scaler = StandardScaler()    
X_train_scaled = scaler.fit_transform(X_train)    
X_test_scaled = scaler.transform(X_test)    
  
# 构建模型，添加L2正则化  
model = Sequential([    
    Dense(64, activation='relu', input_shape=(X_train_scaled.shape[1],), kernel_regularizer=l2(0.01)),  # 对第一个Dense层的权重添加L2正则化  
    Dense(32, activation='relu', kernel_regularizer=l2(0.01)),  # 对第二个Dense层的权重也添加L2正则化  
    Dense(1, activation='linear')  # 回归问题，输出层使用线性激活函数  
])    
  
# 编译模型，使用回归损失函数  
model.compile(optimizer='adam', loss='mean_squared_error', metrics=['mean_absolute_error'])    
  
# 训练模型    
history = model.fit(X_train_scaled, y_train, epochs=100, validation_split=0.2, verbose=1)

图 3-1 

4 模型评估

import matplotlib.pyplot as plt  
  
# 假设你已经通过model.fit()训练了模型，并得到了history对象  
# 这里我们直接使用你提供的history变量  
  
# 绘制训练损失和验证损失  
plt.figure(figsize=(10, 3))  
plt.plot(history.history['loss'], color='lime',label='Training Loss')  
plt.plot(history.history['val_loss'],  color='black', label='Validation Loss')  
plt.title('Training and Validation Loss')  
plt.xlabel('Epoch')  
plt.ylabel('Loss')  
plt.legend()  
plt.grid(True)  
  
# 如果你还想绘制平均绝对误差（MAE），确保在model.compile时添加了它作为metrics之一  
# 如果添加了，可以这样绘制：  
if 'mean_absolute_error' in history.history:  
    plt.figure(figsize=(10, 3))  
    plt.plot(history.history['mean_absolute_error'],color='red',label='Training MAE')  
    plt.plot(history.history['val_mean_absolute_error'], color='lime',  label='Validation MAE')  
    plt.title('Training and Validation Mean Absolute Error')  
    plt.xlabel('Epoch')  
    plt.ylabel('MAE')  
    plt.legend()  
    plt.grid(True)  
  
# 显示图表  
plt.show()

图 4-1