上传文件至 /

function.py

@@ -1,69 +1,84 @@
-import numpy as np
-from sklearn.ensemble import RandomForestClassifier
-from sklearn.preprocessing import PolynomialFeatures, StandardScaler
-from sklearn.impute import SimpleImputer
-from sklearn.metrics import accuracy_score
-from sklearn.model_selection import train_test_split
-
 id = "202210423104"
 name = "张钦诚"
 
+import numpy as np
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.model_selection import train_test_split
+
+def sigmoid(z):
+    return 1.0 / (1 + np.exp(-z))
+
+def compute_gradient(X_batch, y_batch, weights, lambda_reg):
+    z = np.dot(X_batch, weights)
+    h = sigmoid(z)
+    gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch)
+    gradient += (lambda_reg / len(y_batch)) * weights  # L2正则化
+    return gradient
+
+def train_logreg(X, y, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):
+    m, n = X.shape
+    weights = np.random.randn(n) * np.sqrt(2. / n)  # He初始化
+    best_weights = weights.copy()
+    best_accuracy = 0
+
+    for _ in range(iterations):
+        indices = np.random.permutation(m)
+        X_shuffled = X[indices]
+        y_shuffled = y[indices]
+
+        for j in range(0, m, batch_size):
+            X_batch = X_shuffled[j:j + batch_size]
+            y_batch = y_shuffled[j:j + batch_size]
+            gradient = compute_gradient(X_batch, y_batch, weights, lambda_reg)
+            weights -= learning_rate * gradient
+
+        # 计算训练集准确率
+        train_accuracy = accuracy(X, y, weights)
+        if train_accuracy > best_accuracy:
+            best_accuracy = train_accuracy
+            best_weights = weights.copy()
+
+        # 动态调整学习率
+        if _ % 100 == 0 and train_accuracy > 0.95:  # 达到高准确率时减小学习率
+            learning_rate *= 0.9
+
+    return best_weights
+
+def predict_logreg(X, weights):
+    z = np.dot(X, weights)
+    h = sigmoid(z)
+    return np.where(h >= 0.5, 1, 0)
+
 def load_data(filepath):
-    data = []
-    with open(filepath, 'r') as file:
-        for line in file:
-            line_data = line.strip().split()
-            if line_data:
-                try:
-                    data.append([float(x) if x != '?' else np.nan for x in line_data])
-                except ValueError as e:
-                    print(f"Error processing line: {line}. Error: {e}")
+    data, labels = [], []
+    with open(filepath, 'r') as f:
+        for line in f:
+            line = line.strip().split()
+            if len(line) >= 1 and line[-1].isdigit():
+                line_data = [0 if x == '?' else float(x) for x in line[:-1]]
+                data.append(line_data)
+                labels.append(int(line[-1]))
+
     data = np.array(data)
-    imputer = SimpleImputer(strategy='mean')
-    data = imputer.fit_transform(data)
+    labels = np.array(labels)
 
-    X = data[:, :-1]  # 特征
-    y = data[:, -1]  # 标签
-    return X, y
+    # 检查特征数量
+    num_features = data.shape[1]
 
-def preprocess_data(X):
-    scaler = StandardScaler()
-    X_standardized = scaler.fit_transform(X)
-    poly = PolynomialFeatures(degree=2, include_bias=False)
-    X_poly = poly.fit_transform(X_standardized)
-    return X_poly
+    # 特征选择：去掉特征3（索引2）和特征24~28（索引23~26），确保索引有效
+    indices_to_delete = [2]  # 特征3
+    if num_features > 24:  # 确保特征数量足够
+        indices_to_delete += list(range(24, 27))  # 特征24到27（索引23到26）
 
-def train_logreg(X, y):
-    X_processed = preprocess_data(X)  # 预处理训练数据
-    model = RandomForestClassifier(
-        n_estimators=300,  # 增加树的数量
-        max_depth=25,      # 调整最大深度
-        min_samples_split=5,
-        class_weight='balanced',  # 处理类别不平衡
-        random_state=42  # 固定随机种子
-    )
-    model.fit(X_processed, y)
-    return model  # 返回训练好的模型
+    # 删除特征
+    data = np.delete(data, indices_to_delete, axis=1)
 
-def predict_logreg(X, model):
-    if len(X.shape) == 1:
-        X = X.reshape(1, -1)  # 保持输入数据的形状为 (1, n)
-    X_processed = preprocess_data(X)  # 预处理测试数据
-    return model.predict(X_processed)[0]  # 确保 model 是训练好的模型
+    # 将标签二分类化，特征23（索引22）取值2和3合并为0，其余为1
+    target_variable = np.where((labels == 2) | (labels == 3), 0, 1)
 
-if __name__ == "__main__":
-    # 数据加载和预处理保持不变
-    X, y = load_data("./data/horse-colic.data")
+    return data, target_variable
 
-    # 划分训练集和测试集时固定随机种子
-    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+def accuracy(X, y, weights):
+    predictions = predict_logreg(X, weights)
+    return np.mean(predictions == y)
 
-    # 训练模型
-    model = train_logreg(X_train, y_train)
-
-    # 预测
-    y_pred = model.predict(preprocess_data(X_test))
-
-    # 计算准确率
-    accuracy = accuracy_score(y_test, y_pred)
-    print(f"Accuracy: {accuracy:.2f}")