66666666

function.py

@@ -1,11 +1,11 @@
 # function.py
 import numpy as np
-from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score
 from sklearn.preprocessing import StandardScaler
-from sklearn.metrics import accuracy_score, roc_auc_score
+from sklearn.metrics import accuracy_score, roc_auc_score, f1_score
-from sklearn.ensemble import RandomForestClassifier
+from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier, VotingClassifier
 from sklearn.linear_model import LogisticRegression
-from sklearn.ensemble import VotingClassifier
+from sklearn.svm import SVC
 """
 实验说明:
 - 自行编写实现数据加载与预测病马死亡的对率回归算法。
@@ -30,18 +30,9 @@ id = "202210423221"
 name = "廖子豪"
 
 
-# 这里写自己的代码实现
+
+
 def load_data(filepath):
-    """
-    从文件中加载数据。
-
-    Args:
-    - filepath (str): 数据文件路径。
-
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
     file = open(filepath)
     fr = file.readlines()
     data_list = []
@@ -68,75 +59,38 @@ def load_data(filepath):
     return X_train, y_train
 
 def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_reg=0.01):
-    """
+    m, n = X.shape
-    对率回归训练函数，加入L2正则化。
+    weights = np.zeros(n)
-
-    Args:
-    - X (numpy array): 特征数据。
-    - y (numpy array): 标签数据。
-    - numIter (int): 迭代次数。默认为1000。
-    - learning_rate (float): 学习率。默认为0.06。
-    - batch_size (int): 批量大小。默认为128。
-    - lambda_reg (float): L2正则化参数。默认为0.01。
-
-    Returns:
-    - numpy array: 训练得到的权重。
-    """
-    m, n = X.shape  # m: 样本数, n: 特征数
-    weights = np.zeros(n)  # 参数初始化
-
     for j in range(numIter):
-        # 随机打乱样本顺序
         dataIndex = np.random.permutation(m)
         for i in range(0, m, batch_size):
             end = min(i + batch_size, m)
-            # 批量梯度上升
             batch_X = X[dataIndex[i:end]]
             batch_y = y[dataIndex[i:end]]
-            
-            # 计算梯度
             z = np.dot(batch_X, weights)
-            h = 1 / (1 + np.exp(-z))  # 计算h
+            h = 1 / (1 + np.exp(-z))
-            error = batch_y - h  # 计算误差
+            error = batch_y - h
-            gradient = np.dot(batch_X.T, error) / len(batch_y)  # 计算梯度
+            gradient = np.dot(batch_X.T, error) / len(batch_y)
-            # 添加L2正则化
             reg_term = 2 * lambda_reg * weights
             gradient -= reg_term / len(batch_y)
-            weights += learning_rate * gradient  # 更新权重
+            weights += learning_rate * gradient
-
     return weights
 
 def predict_logreg(inX, weights):
-    """
+    z = np.dot(inX, weights)
-    对率回归预测函数。
+    prob = 1 / (1 + np.exp(-z))
-
+    return 1 if prob >= 0.5 else 0
-    Args:
-    - inX (numpy array): 输入待分类的样本。
-    - weights (numpy array): 训练得到的权重。
-
-    Returns:
-    - int: 预测的分类标签。
-    """
-    z = np.dot(inX, weights)  # 线性组合
-    prob = 1 / (1 + np.exp(-z))  # 计算概率
-    return 1 if prob >= 0.5 else 0  # 返回分类标签
 
 if __name__ == "__main__":
-    # 加载训练集
     X_train, y_train = load_data("./data/horse-colic.data")
-
-    # 加载测试集
     X_test, y_test = load_data("./data/horse-colic.test")
 
-    # 特征缩放
     scaler = StandardScaler()
     X_train = scaler.fit_transform(X_train)
     X_test = scaler.transform(X_test)
 
-    # 划分训练集和验证集
     X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)
 
-    # 训练对率回归模型，使用早停法
     best_weights = None
     best_auc = 0
     for iter in range(1, 1001):
@@ -147,9 +101,8 @@ if __name__ == "__main__":
             best_auc = auc
             best_weights = weights
         if iter > 10 and auc == best_auc:
-            break  # 早停
+            break
 
-    # 使用最佳权重在测试集上评估模型
     y_pred_test = [predict_logreg(x, best_weights) for x in X_test]
     accuracy_test = accuracy_score(y_test, y_pred_test)
     print(f"Test Accuracy: {accuracy_test}")
@@ -173,4 +126,19 @@ if __name__ == "__main__":
     voting_clf = VotingClassifier(estimators=[('lr', log_clf), ('rf', rnd_clf)], voting='soft')
     voting_clf.fit(X_train, y_train)
     y_pred = voting_clf.predict(X_test)
-    print("Voting classifier accuracy:", accuracy_score(y_test, y_pred))
+    print("Voting classifier accuracy:", accuracy_score(y_test, y_pred))
+
+    # 梯度提升机模型
+    gb_clf = GradientBoostingClassifier()
+    gb_clf.fit(X_train, y_train)
+    y_pred = gb_clf.predict(X_test)
+    print("Gradient Boosting classifier accuracy:", accuracy_score(y_test, y_pred))
+
+    # 使用K折交叉验证评估模型性能
+    scores = cross_val_score(gb_clf, X_train, y_train, cv=5, scoring='accuracy')
+    print("Cross-validation scores:", scores)
+    print("Average cross-validation score:", np.mean(scores))
+
+    # 使用F1分数评估模型性能
+    f1 = f1_score(y_test, y_pred)
+    print("F1 Score:", f1)