2024五一数学建模竞赛（五一赛）C题保姆级分析完整思路+代码+数据教学

C题 煤矿深部开采冲击地压危险预测

第一问 导入数据

以下仅展示部分，完整版看文末的文章

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split, cross_val_score, KFold
from sklearn.metrics import classification_report, accuracy_score, confusion_matrix
def preprocess_dataframe(df):
    window = '60s'  # 窗口大小
    features = df.groupby(pd.Grouper(key='时间 (time)', freq=window)).agg({
        '声波强度 (AE)': ['mean', 'std', 'max', 'min']
    }).rename(columns={
        'mean': 'EMR_mean',
        'std': 'EMR_std',
        'max': 'EMR_max',
        'min': 'EMR_min'
    })
    features.reset_index(inplace=True)
    features.fillna(0, inplace=True)

    def calculate_fft_features(signal):
        if isinstance(signal, pd.Series):
            signal = signal.values  # 将 Series 转换为 NumPy 数组
        if isinstance(signal, (list, tuple)):
            signal = np.array(signal)  # 将列表或元组转换为 NumPy 数组
        if isinstance(signal, (float, int)):
            signal = np.array([signal])  # 将单个数值转换为 NumPy 数组
        if signal.ndim > 1:
            signal = signal.squeeze()  # 如果信号的维度大于1，压缩维度为1
        # 快速傅里叶变换
        fft_values = np.fft.fft(signal)
        fft_abs = np.abs(fft_values)
        return np.mean(fft_abs), np.std(fft_abs), np.max(fft_abs)

    df['声波强度 (AE)'] = df['声波强度 (AE)'].astype(float)

    # 应用FFT并计算特征
    fft_features = df['声波强度 (AE)'].apply(calculate_fft_features)

    # 解压特征并添加到 DataFrame
    df['FFT_mean'], df['FFT_std'], df['FFT_max'] = zip(*fft_features)

    df['hour'] = df['时间 (time)'].dt.hour
    df['minute'] = df['时间 (time)'].dt.minute
    df['weekday'] = df['时间 (time)'].dt.weekday
    df['is_weekend'] = df['weekday'].apply(lambda x: 1 if x >= 5 else 0)

    rolling_window = 10  # 使用10个数据点的窗口
    df['rolling_mean'] = df['声波强度 (AE)'].rolling(window=rolling_window).mean()
    df['rolling_std'] = df['声波强度 (AE)'].rolling(window=rolling_window).std()
    df['rolling_mean'].fillna(df.iloc[10,-2], inplace=True)
    df['rolling_std'].fillna(df.iloc[10,-1], inplace=True)

    df['diff_1'] =  df['声波强度 (AE)'].diff(1)  # 一阶差分
    df['diff_2'] =  df['声波强度 (AE)'].diff(2)  # 二阶差分
    df['diff_1'].fillna(0, inplace=True)
    df['diff_2'].fillna(0, inplace=True)
    
#     q = np.percentile(df['声波强度 (AE)'], 75)
#     data_modified = [1 if x > q else 0 for x in df['声波强度 (AE)']]
#     df['高频信号'] = data_modified

    # 数据预处理
#     df['类别 (class)_encoded'], class_categories = pd.factorize(df['类别 (class)'])
    
    return df

train_df = pd.read_excel("./附件1 (Attachment 1).xlsx",sheet_name='AE')
train_df

processed_df = preprocess_dataframe(train_df)
processed_df['类别 (class)_encoded'], class_categories = pd.factorize(processed_df['类别 (class)'])
q = np.percentile(processed_df['声波强度 (AE)'], 80)
data_modified = [1 if x > q else 0 for x in processed_df['声波强度 (AE)']]
processed_df['干扰信号'] = data_modified
processed_df


# 分离特征和目标变量
X = processed_df.drop(['时间 (time)','类别 (class)','干扰信号','类别 (class)_encoded'], axis=1)  # 假设目标变量列名为'类别'
# X = processed_df.drop(['时间 (time)','类别 (class)','干扰信号'], axis=1)  # 假设目标变量列名为'类别'
y = processed_df['干扰信号']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
X_train.head()

集成随机森林代码：

rf_model = RandomForestClassifier(n_estimators=100, random_state=42)  # 100棵树

rf_model.fit(X_train, y_train)
y_pred = rf_model.predict(X_test)

# 打印准确率
print("Accuracy:", accuracy_score(y_test, y_pred))

# 打印分类报告
print("Classification Report:\n", classification_report(y_test, y_pred))

# 混淆矩阵
conf_matrix = confusion_matrix(y_test, y_pred)
print("Confusion Matrix:\n", conf_matrix)

# 可视化混淆矩阵
plt.figure(figsize=(8, 6))  
plt.imshow(conf_matrix, interpolation='nearest', cmap=plt.cm.Blues)
plt.title('Confusion Matrix')
plt.colorbar()
tick_marks = np.arange(len(np.unique(y)))
plt.xticks(tick_marks, np.unique(y), rotation=45)
plt.yticks(tick_marks, np.unique(y))
plt.xlabel('Predicted Label')
plt.ylabel('True Label')
plt.show()

第一问结果表：（csv文件）

第二问xgboost混淆矩阵：

from xgboost import XGBClassifier

xgb_model = XGBClassifier(n_estimators=100, learning_rate=0.1, max_depth=3)
xgb_model.fit(X_train, y_train)
y_pred_xgb = xgb_model.predict(X_test)
print("XGBoost Accuracy:", accuracy_score(y_test, y_pred_xgb))

conf_matrix = confusion_matrix(y_test, y_pred_xgb)
sns.heatmap(conf_matrix, annot=True, fmt='d')
plt.xlabel('Predicted Label')
plt.ylabel('True Label')
plt.title('Confusion Matrix')
plt.show()

第三问部分代码：

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, TensorDataset
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

# 转换为PyTorch张量
X_train_tensor = torch.tensor(X_train.values, dtype=torch.float32)
y_train_tensor = torch.tensor(y_train.values, dtype=torch.float32)
X_test_tensor = torch.tensor(X_test.values, dtype=torch.float32)
y_test_tensor = torch.tensor(y_test.values, dtype=torch.float32)

# 创建数据加载器
train_data = TensorDataset(X_train_tensor, y_train_tensor)
test_data = TensorDataset(X_test_tensor, y_test_tensor)
train_loader = DataLoader(train_data, batch_size=64, shuffle=True)

# 定义神经网络结构
class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__init__()
        self.layer1 = nn.Linear(X_train.shape[1], 64)
        self.layer2 = nn.Linear(64, 32)
        self.output_layer = nn.Linear(32, 1)
        self.relu = nn.ReLU()

    def forward(self, x):
        x = self.relu(self.layer1(x))
        x = self.relu(self.layer2(x))
        x = torch.sigmoid(self.output_layer(x))  # 使用sigmoid输出概率
        return x

# 实例化模型、定义损失函数和优化器
model = NeuralNetwork()
criterion = nn.BCELoss()  # 二元交叉熵损失函数
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 训练模型
num_epochs = 10
for epoch in range(num_epochs):
    for inputs, labels in train_loader:
        outputs = model(inputs)
        loss = criterion(outputs.squeeze(), labels)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
    print(f'Epoch {epoch+1}/{num_epochs}, Loss: {loss.item():.4f}')

其中更详细的思路，各题目思路、代码、讲解视频、成品论文及其他相关内容，可以点击下方群名片哦！