复现XGBoost
This commit is contained in:
林林
parent
7573a11ef5
commit
60118e85a4
|
|
@ -0,0 +1,136 @@
|
|||
import xgboost as xgb # 导入XGBoost
|
||||
import pandas as pd
|
||||
from sklearn import preprocessing
|
||||
import numpy as np
|
||||
from sklearn.model_selection import train_test_split
|
||||
# 移除了 torch 和 torch.nn 相关导入
|
||||
import matplotlib.pyplot as plt
|
||||
import seaborn as sns
|
||||
from sklearn.metrics import confusion_matrix, accuracy_score, classification_report # 增加评估指标
|
||||
from sklearn.feature_selection import SelectKBest, chi2
|
||||
from sklearn.utils.class_weight import compute_sample_weight # 用于计算样本权重
|
||||
|
||||
# 检查GPU可用性（XGBoost 可配置使用GPU，但方式不同，这里简化为CPU）
|
||||
# device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
# print(f"Using device: {device}")
|
||||
print("Using CPU for XGBoost (GPU can be configured if needed and available)")
|
||||
|
||||
# 1. 加载数据集
|
||||
df = pd.read_csv('sensor.csv', index_col=0)
|
||||
print("Dataset loaded.")
|
||||
|
||||
# 2. 数据预处理
|
||||
df.drop(columns=['sensor_50', 'sensor_51', 'sensor_15'], inplace=True)
|
||||
x = df.iloc[:, 1:50].fillna(method='ffill')
|
||||
|
||||
scaler = preprocessing.MinMaxScaler()
|
||||
x_scaled = scaler.fit_transform(x)
|
||||
x_scaled = pd.DataFrame(x_scaled, columns=df.iloc[:, 1:50].columns)
|
||||
print("Data scaled and NaNs filled.")
|
||||
|
||||
# 目标变量编码
|
||||
conditions = [(df['machine_status'] =='NORMAL'), (df['machine_status'] =='BROKEN'), (df['machine_status'] =='RECOVERING')]
|
||||
choices = [1, 0, 2] # BROKEN: 0, NORMAL: 1, RECOVERING: 2
|
||||
df['Operation'] = np.select(conditions, choices, default=0) # 保持原始编码
|
||||
# df.drop(['machine_status'],axis=1, inplace=True) # 保留原始列以便检查
|
||||
y = df['Operation'].values # 直接获取numpy数组
|
||||
print("Target variable encoded.")
|
||||
print("Class distribution in y:", np.bincount(y))
|
||||
|
||||
# 4. 特征选择 (在缩放后的数据上进行)
|
||||
selector = SelectKBest(score_func=chi2, k=20)
|
||||
# chi2要求非负特征，MinMaxScaler保证了这一点
|
||||
x_new = selector.fit_transform(x_scaled, y)
|
||||
selected_features_indices = selector.get_support(indices=True)
|
||||
selected_features_names = x_scaled.columns[selected_features_indices]
|
||||
print(f"Selected {len(selected_features_names)} features:", selected_features_names.tolist())
|
||||
|
||||
# 3. 构建时序输入数据 (仍需要创建窗口)
|
||||
def create_sequences(data, target, time_steps=24):
|
||||
X, y_seq = [], []
|
||||
print(f"Creating sequences with time_steps={time_steps}...")
|
||||
for i in range(len(data) - time_steps):
|
||||
X.append(data[i:i + time_steps, :])
|
||||
# 目标是预测 time_steps 之后的那个点的状态
|
||||
y_seq.append(target[i + time_steps])
|
||||
print(f"Finished creating sequences. X shape: {np.array(X).shape}, y shape: {np.array(y_seq).shape}")
|
||||
return np.array(X), np.array(y_seq)
|
||||
|
||||
time_steps = 24 # 定义时间窗口大小
|
||||
X_seq, y_seq = create_sequences(x_new, y, time_steps=time_steps)
|
||||
|
||||
# *** 重要：为XGBoost重塑数据 ***
|
||||
# 将 (n_samples, time_steps, n_features) 转换为 (n_samples, time_steps * n_features)
|
||||
n_samples, _, n_features = X_seq.shape
|
||||
X_reshaped = X_seq.reshape(n_samples, time_steps * n_features)
|
||||
print(f"Reshaped X for XGBoost. New shape: {X_reshaped.shape}")
|
||||
|
||||
# 4. 划分数据集 (使用重塑后的X和对应的y)
|
||||
X_train, X_test, y_train, y_test = train_test_split(
|
||||
X_reshaped, y_seq, test_size=0.2, random_state=42, stratify=y_seq # 使用stratify保持类别比例
|
||||
)
|
||||
print(f"Dataset split. Train shape: {X_train.shape}, Test shape: {X_test.shape}")
|
||||
print("Class distribution in y_train:", np.bincount(y_train))
|
||||
print("Class distribution in y_test:", np.bincount(y_test))
|
||||
|
||||
|
||||
# 计算样本权重以处理类别不平衡 (可选但推荐)
|
||||
# 使用 scikit-learn 的工具函数计算权重
|
||||
sample_weights = compute_sample_weight(class_weight='balanced', y=y_train)
|
||||
print("Sample weights computed for training.")
|
||||
|
||||
# 初始化 XGBoost 模型
|
||||
print("Initializing XGBoost Classifier...")
|
||||
# 如果需要GPU加速，且已安装GPU支持的XGBoost，可添加 tree_method='gpu_hist'
|
||||
model = xgb.XGBClassifier(
|
||||
objective='multi:softprob', # 输出每个类别的概率
|
||||
num_class=len(np.unique(y_seq)), # 类别数量
|
||||
eval_metric='mlogloss', # 多分类对数损失
|
||||
use_label_encoder=False, # 推荐设置，避免警告
|
||||
random_state=42,
|
||||
n_estimators=100, # 树的数量 (可调)
|
||||
learning_rate=0.1, # 学习率 (可调)
|
||||
max_depth=5, # 树的最大深度 (可调)
|
||||
# tree_method='gpu_hist' # 取消注释以尝试GPU加速
|
||||
# 其他超参数可根据需要调整...
|
||||
)
|
||||
|
||||
# --- 移除了 PyTorch 损失函数和优化器 ---
|
||||
|
||||
# --- 移除了 PyTorch 训练循环 ---
|
||||
|
||||
# 训练 XGBoost 模型
|
||||
print("Training XGBoost model...")
|
||||
# 使用 eval_set 进行早停可以防止过拟合，这里简化训练过程
|
||||
# eval_set = [(X_test, y_test)]
|
||||
# model.fit(X_train, y_train, sample_weight=sample_weights, eval_set=eval_set, early_stopping_rounds=10, verbose=True)
|
||||
model.fit(X_train, y_train, sample_weight=sample_weights, verbose=True) # 使用样本权重
|
||||
print("XGBoost training finished.")
|
||||
|
||||
|
||||
# 评估模型
|
||||
print("Evaluating XGBoost model...")
|
||||
y_pred = model.predict(X_test) # 直接预测类别标签
|
||||
|
||||
# 计算准确率
|
||||
accuracy = accuracy_score(y_test, y_pred)
|
||||
print(f"Test Accuracy: {accuracy * 100:.2f}%")
|
||||
|
||||
# 输出详细分类报告
|
||||
print("\nClassification Report:")
|
||||
print(classification_report(y_test, y_pred, target_names=['BROKEN', 'NORMAL', 'RECOVERING'])) # 确保标签顺序正确
|
||||
|
||||
# 输出混淆矩阵
|
||||
print("\nConfusion Matrix:")
|
||||
cm = confusion_matrix(y_test, y_pred)
|
||||
print(cm)
|
||||
|
||||
# 可视化混淆矩阵
|
||||
plt.figure(figsize=(8, 6))
|
||||
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',
|
||||
xticklabels=['BROKEN', 'NORMAL', 'RECOVERING'], # 与 choices 对应
|
||||
yticklabels=['BROKEN', 'NORMAL', 'RECOVERING'])
|
||||
plt.title("XGBoost Confusion Matrix")
|
||||
plt.xlabel("Predicted Label")
|
||||
plt.ylabel("True Label")
|
||||
plt.show()
|
||||
Loading…
Reference in New Issue