更新 function.py

function.py

@@ -38,16 +38,17 @@ name = "焦国波"
 返回值:
 - int: 预测的分类标签。
 """
-
-
-import os
-import numpy as np
-from sklearn.model_selection import train_test_split
-from sklearn.neighbors import KNeighborsClassifier
-from sklearn.metrics import accuracy_score
-import time
-
 def load_data(directory):
+    """
+    加载数据集，将图像数据转换为向量形式，并提取标签。
+    
+    参数:
+    - directory (str): 数据集目录路径。
+    
+    返回值:
+    - images (numpy array): 图像数据。
+    - labels (list): 标签列表。
+    """
     images = []
     labels = []
     for filename in os.listdir(directory):
@@ -58,65 +59,47 @@ def load_data(directory):
             labels.append(label)
     return np.array(images), np.array(labels)
 
-# 加载训练集和测试集
-X_train, y_train = load_data('trainingDigits')
-X_test, y_test = load_data('testDigits')
+def classify(input_vector, dataSet, labels, k=3):
+    """
+    kNN 分类算法实现。
+    
+    参数:
+    - 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，默认值为 3。
+    
+    返回值:
+    - int: 预测的分类标签。
+    """
+    # 计算输入向量与数据集中每个样本的欧式距离
+    distances = np.sqrt(np.sum((dataSet - input_vector) ** 2, axis=1))
+    
+    # 获取 k 个最近邻的索引
+    sortedDistIndices = distances.argsort()
+    
+    # 获取 k 个最近邻的标签
+    classCount = {}
+    for i in range(k):
+        voteLabel = labels[sortedDistIndices[i]]
+        classCount[voteLabel] = classCount.get(voteLabel, 0) + 1
+    
+    # 多数表决，返回出现次数最多的标签
+    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
+    return sortedClassCount[0][0]
 
-# 数据预处理：将图像数据转换为向量形式
-X_train = X_train.reshape((X_train.shape[0], -1))
-X_test = X_test.reshape((X_test.shape[0], -1))
+# 以下代码用于测试和演示，实际使用时请删除或注释掉
+if __name__ == "__main__":
+    # 加载训练集和测试集
+    X_train, y_train = load_data('trainingDigits')
+    X_test, y_test = load_data('testDigits')
+    
+    # 测试分类函数
+    test_samples = X_test[:5]
+    for sample in test_samples:
+        predicted_label = classify(sample, X_train, y_train)
+        print(f"Input Vector: {sample}, Predicted Label: {predicted_label}")
 
-
-
-# 初始化KNN模型
-knn = KNeighborsClassifier(n_neighbors=3)
-
-# 训练模型
-start_time = time.time()
-knn.fit(X_train, y_train)
-end_time = time.time()
-print(f"Training time: {end_time - start_time} seconds")
-
-
-
-# 预测测试集
-start_time = time.time()
-y_pred = knn.predict(X_test)
-end_time = time.time()
-
-# 计算分类精度
-accuracy = accuracy_score(y_test, y_pred)
-print(f"Accuracy: {accuracy * 100:.2f}%")
-print(f"Prediction time: {end_time - start_time} seconds")
-
-
-from sklearn.model_selection import GridSearchCV
-
-# 参数网格
-param_grid = {
-    'n_neighbors': [3, 5, 7, 9],
-    'metric': ['euclidean', 'manhattan'],
-    'algorithm': ['auto', 'ball_tree', 'kd_tree']
-}
-
-# 网格搜索
-grid_search = GridSearchCV(KNeighborsClassifier(), param_grid, cv=5)
-grid_search.fit(X_train, y_train)
-
-# 最佳参数
-print("Best parameters:", grid_search.best_params_)
-
-# 使用最佳参数重新训练模型
-best_knn = grid_search.best_estimator_
-best_knn.fit(X_train, y_train)
-
-# 重新评估性能
-start_time = time.time()
-y_pred = best_knn.predict(X_test)
-end_time = time.time()
-accuracy = accuracy_score(y_test, y_pred)
-print(f"Optimized Accuracy: {accuracy * 100:.2f}%")
-print(f"Optimized Prediction time: {end_time - start_time} seconds")
         "00000000000000000111100000000000"
     )
     predicted_label = classify(