更新 function.py

function.py

@@ -7,45 +7,113 @@ from sklearn.preprocessing import StandardScaler
 id = "202210423206"
 name = "詹宇豪"
 
-def train_logreg(X, y, random_state=42):
-    model = LogisticRegression(solver='liblinear', random_state=random_state)
-    model.fit(X, y)
-    return model
 
-def predict_logreg(inX, model):
-    return int(model.predict([inX])[0])
+def classify(input_vector, dataSet, labels, k=1):
+    """
+    KNN 分类算法。
+
+    Args:
+    - input_vector (numpy array): 输入待分类的样本。
+    - dataSet (numpy array): 训练数据集。
+    - labels (list or numpy array): 训练集对应的标签。
+    - k (int): kNN 算法参数，请**自行设置默认值**，评测时仅会使用其默认值，不修改默认值将**无法通过**评测，**成绩为零**。
+
+    Returns:
+    - int: 预测的分类标签。
+    """
+    # 计算欧氏距离
+    distances = np.linalg.norm(dataSet - input_vector, axis=1)
+    # 获取距离最近的 k 个样本的索引
+    nearest_neighbors_indices = distances.argsort()[:k]
+    # 获取这些样本的标签
+    nearest_labels = np.array(labels)[nearest_neighbors_indices]
+    # 统计出现次数最多的标签并返回
+    predicted_label = np.bincount(nearest_labels).argmax()
+    return predicted_label
+
+# 这里也写自己的代码实现
+def load_dataset(directory):
+    """
+    从文件夹中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
+
+    Args:
+    - directory (str): 数据文件夹路径。
+
+    Returns:
+    - np.array: 特征数据。
+    - np.array: 标签数据。
+    """
+    labels = []
+    data_list = []
+    for filename in os.listdir(directory):
+        if filename.endswith(".txt"):  # 确保读取的是 txt 文件
+            label = int(filename.split('_')[0])
+            labels.append(label)
+            vector = img_to_vector(os.path.join(directory, filename))
+            data_list.append(vector)
+    return np.array(data_list), np.array(labels)
+
+# 这里还写自己的代码实现
+def img_to_vector(filename):
+    """
+    将二值图像转换为向量。
+    该部分应为 load_dataset 函数的辅助子函数，可单独在这里实现，也可直接集成至 load_dataset 函数中。
+
+    Args:
+    - filename (str): 图像文件路径。
+
+    Returns:
+    - np.array: 二值图像向量。
+    """
+    with open(filename, 'r') as f:  # 确保使用文本模式读取
+        lines = f.readlines()
+    vector = np.zeros((1024,), dtype=int)  # 将其改为 (1024,) 的一维数组
+    for i in range(32):
+        for j in range(32):
+            vector[32 * i + j] = int(lines[i][j])
+    return vector
 
-def load_data(filepath):
-    data = np.genfromtxt(filepath, delimiter=' ', missing_values='?', filling_values=0)
-    labels = data[:, -1].astype(int)
-    data = data[:, :-1]
-    labels = np.where((labels == 2) | (labels == 3), 0, labels)
-    if data.shape[1] >= 3:
-        data = np.delete(data, 2, axis=1)  
-    scaler = StandardScaler()
-    data = scaler.fit_transform(data)
-    return data, labels
 
-# 测试代码
 if __name__ == "__main__":
-    # 指定数据文件路径
-    filepath = "./data/horse-colic.data"
+    # 测试代码
+    train_data, train_labels = load_dataset("trainingDigits")
+
+    test_data = (
+        "00000000000000110000000000000000"
+        "00000000000011111000000000000000"
+        "00000000000011111100000000000000"
+        "00000000001111111110000000000000"
+        "00000000001111111110000000000000"
+        "00000000001111111100000000000000"
+        "00000000011111111000000000000000"
+        "00000000111111111000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111111111000000000000"
+        "00000001111111111111111000000000"
+        "00000001111111111111111100000000"
+        "00000011111111111111111110000000"
+        "00000011111111111111111110000000"
+        "00000001111111111111111110000000"
+        "00000001111111111111111110000000"
+        "00000000111111111100111111100000"
+        "00000000111111111000111111100000"
+        "00000000011111111001111111100000"
+        "00000000011111111111111111000000"
+        "00000000001111111111111111000000"
+        "00000000000111111111111111000000"
+        "00000000000011111111111100000000"
+        "00000000000001111111110000000000"
+        "00000000000000000111100000000000"
+    )
     
-    # 加载数据
-    X, y = load_data(filepath)
-    print("数据加载成功。")
-
-    # 训练模型
-    model = train_logreg(X, y)
-    print("模型训练完成。")
-
-    # 随机一个样本进行预测测试
-    sample = X[0]
-    actual_label = y[0]
-    predicted_label = predict_logreg(sample, model)
-    print(f"预测结果: {predicted_label}, 实际结果: {actual_label}")
-
-    # 计算测试集上的准确率
-    correct_predictions = sum(predict_logreg(X[i], model) == y[i] for i in range(len(y)))
-    accuracy = correct_predictions / len(y)
-    print(f"测试集准确率: {accuracy:.2f}")
+    test_vector = np.array([int(char) for char in test_data]).reshape(1, 1024)
+    
+    predicted_label = classify(test_vector, train_data, train_labels)
+    print(f"预测的标签: {predicted_label}")