From 4db30de3c245dbf9901184dd68ad3e2e877fed94 Mon Sep 17 00:00:00 2001
From: zhangchenghong <1598349064@qq.com>
Date: Tue, 8 Oct 2024 17:35:39 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20function.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 function.py | 52 ++++++++++++++++++++++------------------------------
 1 file changed, 22 insertions(+), 30 deletions(-)

diff --git a/function.py b/function.py
index b7ef69b..0dc7f22 100644
--- a/function.py
+++ b/function.py
@@ -46,6 +46,15 @@ from collections import Counter
 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。
     """
     # 计算距离
     diffMat = inX - dataSet
@@ -55,10 +64,15 @@ def classify0(inX, dataSet, labels, k=1):
     
     # 排序并选取前k个最小距离
     sortedDistIndices = distances.argsort()
-    classCount = Counter(labels[sortedDistIndices[:k]])
-    
+    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
-    return classCount.most_common(1)[0][0]
+    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
+    return sortedClassCount[0][0]
 
 def load_data(file_path):
     """
@@ -69,35 +83,13 @@ def load_data(file_path):
     labels = data[:, -1].astype(int)
     return features, labels
 
-def normalize_features(features):
-    """
-    特征预处理，包括归一化。
-    """
-    min_vals = features.min(axis=0)
-    max_vals = features.max(axis=0)
-    ranges = max_vals - min_vals
-    m = features.shape[0]
-    norm_features = features - np.tile(min_vals, (m, 1))
-    norm_features = norm_features / np.tile(ranges, (m, 1))
-    return norm_features
-
 if __name__ == "__main__":
+    # 以下代码可用于测试，可自行随意修改
     train_file = "datingTrainSet2.tsv"
     
     train_data, train_labels = load_data(train_file)
-    train_data_normalized = normalize_features(train_data)
 
-    # 选择几个有代表性的测试数据点
-    test_points = [
-        [26052, 1.441871, 0.805124],  # 实际标签是 1
-        [38344, 1.669788, 0.134296],  # 实际标签是 1
-        [28488, 10.528555, 1.304844], # 实际标签是 3
-        [22620, 5.297865, 0.638306],  # 实际标签是 2
-        [28567, 9.968648, 0.731232],  # 实际标签是 3
-        [41611, 0.230453, 1.151996]   # 实际标签是 1
-    ]
-    
-    for point in test_points:
-        normalized_point = normalize_features(np.array([point]))[0]
-        predicted_label = classify0(normalized_point, train_data_normalized, train_labels)
-        print(f"测试数据 {point} 预测标签: {predicted_label}")
\ No newline at end of file
+    # 测试数据点
+    test_point = np.array([65915, 3.868359, 0.128078])
+    predicted_label = classify0(test_point, train_data, train_labels)
+    print("预测的分类标签是:", predicted_label)
\ No newline at end of file