更新 function.py

function.py

@@ -41,10 +41,42 @@ name = "章程鸿"
 
 # 这里写自己的代码实现
 import numpy as np
+from collections import Counter
 from sklearn.model_selection import GridSearchCV
 from sklearn.neighbors import KNeighborsClassifier
-from sklearn.preprocessing import MinMaxScaler
-from sklearn.metrics import accuracy_score
+
+def classify0(inX, dataSet, labels, k=1):
+    """
+    KNN 分类算法。
+
+    Args:
+    - inX (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，默认为3。
+
+    Returns:
+    - int: 预测的分类标签。
+    """
+    # 计算马氏距离
+    cov_matrix = np.cov(dataSet, rowvar=False)
+    inv_cov_matrix = np.linalg.inv(cov_matrix)
+    mean_vector = np.mean(dataSet, axis=0)
+
+    diffMat = inX - dataSet
+    mahalanobis_distances = np.sqrt(np.sum((diffMat @ inv_cov_matrix) * diffMat, axis=1))
+    
+    # 排序并选取前k个最小距离
+    sortedDistIndices = mahalanobis_distances.argsort()
+    classCount = {}
+
+    for i in range(k):
+        voteIlabel = labels[sortedDistIndices[i]]
+        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
+
+    # 返回出现频率最高的类别
+    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
+    return sortedClassCount[0][0]
 
 def load_data(file_path):
     """
@@ -55,18 +87,36 @@ def load_data(file_path):
     labels = data[:, -1].astype(int)
     return features, labels
 
-if __name__ == "__main__":
-    train_file = "datingTrainSet2.tsv"
-    test_file = "datingTestSet2.tsv"  # 假设您有一个测试集文件
-    
-    # 加载训练和测试数据
-    train_data, train_labels = load_data(train_file)
-    test_data, test_labels = load_data(test_file)
+def normalize_min_max(data):
+    """
+    对数据进行最小-最大缩放归一化。
 
-    # 使用MinMaxScaler进行归一化
-    scaler = MinMaxScaler()
-    train_data_normalized = scaler.fit_transform(train_data)
-    test_data_normalized = scaler.transform(test_data)
+    Args:
+    - data (numpy array): 待归一化的数据。
+
+    Returns:
+    - numpy array: 归一化后的数据。
+    - numpy array: 最小值。
+    - numpy array: 最大值。
+    """
+    min_vals = data.min(0)
+    max_vals = data.max(0)
+    ranges = max_vals - min_vals
+    # 避免除以零的情况
+    ranges[ranges == 0.0] = 1.0
+    m = data.shape[0]
+    norm_data = (data - min_vals) / ranges
+    return norm_data, min_vals, max_vals
+
+if __name__ == "__main__":
+    # 以下代码可用于测试，可自行随意修改
+    train_file = "datingTrainSet2.tsv"
+    
+    # 加载训练数据
+    train_data, train_labels = load_data(train_file)
+
+    # 归一化训练数据，并获取最小值和最大值
+    train_data_normalized, min_vals, max_vals = normalize_min_max(train_data)
 
     # 定义KNN分类器
     knn = KNeighborsClassifier()
@@ -86,14 +136,10 @@ if __name__ == "__main__":
     best_knn = KNeighborsClassifier(n_neighbors=optimal_k)
     best_knn.fit(train_data_normalized, train_labels)
 
-    # 对测试数据进行预测
-    predicted_labels = best_knn.predict(test_data_normalized)
+    # 测试数据点也需要用同样的方式归一化
+    test_point = np.array([65915, 3.868359, 0.128078])
+    test_point_normalized = (test_point - min_vals) / (max_vals - min_vals)
 
-    # 输出预测结果
-    print("预测的分类标签是:")
-    for i, (predicted, actual) in enumerate(zip(predicted_labels, test_labels)):
-        print(f"样本 {i+1}: 预测标签: {predicted}, 实际标签: {actual}")
-
-    # 计算并输出准确率
-    accuracy = accuracy_score(test_labels, predicted_labels)
-    print(f"模型在测试集上的准确率为: {accuracy * 100:.2f}%")
+    # 使用归一化后的数据进行预测
+    predicted_label = best_knn.predict([test_point_normalized])
+    print("预测的分类标签是:", predicted_label[0])