From 0efd997fd2a31cd82b671608d9a618568e969c8b Mon Sep 17 00:00:00 2001
From: 77 <3298722099@qq.com>
Date: Thu, 21 Nov 2024 09:20:31 +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 | 38 ++++++++++++++++++--------------------
 1 file changed, 18 insertions(+), 20 deletions(-)

diff --git a/function.py b/function.py
index 61e1489..a10fe07 100644
--- a/function.py
+++ b/function.py
@@ -46,8 +46,19 @@ name = "陈瑞琪祥"
 
 
 
-def classify0(inX, dataSet, labels, k):
-    result = classify0(test_data[i], train_data, train_labels, k=3)  # 假设 k=3 是你选择的值
+def classify0(inX, dataSet, labels, k=3):
+    """
+    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，默认值为 3。
+
+    Returns:
+    - int: 预测的分类标签。
+    """
     diffMat = np.tile(inX, (dataSet.shape[0], 1)) - dataSet
     sqDiffMat = diffMat**2
     sqDistances = sqDiffMat.sum(axis=1)
@@ -61,26 +72,15 @@ def classify0(inX, dataSet, labels, k):
     return sortedClassCount[0][0]
 
 def load_data(file_path):
+    """
+    加载 TSV 格式数据文件，并进行标准化处理。
+    """
     data = np.loadtxt(file_path, delimiter="\t")
     features = data[:, :-1]
     labels = data[:, -1].astype(int)
     features = (features - np.mean(features, axis=0)) / np.std(features, axis=0)
     return features, labels
 
-def find_best_k(train_data, train_labels):
-    best_accuracy = 0
-    best_k = 1
-    for k in range(1, 26, 2):  # 尝试奇数的 k 值，从 1 到 25
-        correct_count = 0
-        for i in range(train_data.shape[0]):
-            if classify0(train_data[i], train_data, train_labels, k) == train_labels[i]:
-                correct_count += 1
-        accuracy = correct_count / train_data.shape[0]
-        if accuracy > best_accuracy:
-            best_accuracy = accuracy
-            best_k = k
-    return best_k
-
 def preprocess_data(features):
     # 简单的异常值处理
     Q1 = np.percentile(features, 25, axis=0)
@@ -99,11 +99,9 @@ if __name__ == "__main__":
     train_data = preprocess_data(train_data)
     test_data = preprocess_data(test_data)
     
-    best_k = find_best_k(train_data, train_labels)
-    
     correct_count = 0
     for i in range(test_data.shape[0]):
-        if classify0(test_data[i], train_data, train_labels, best_k) == test_labels[i]:
+        if classify0(test_data[i], train_data, train_labels, k=3) == test_labels[i]:
             correct_count += 1
     
-    print(f"Accuracy with best k = {best_k}: {correct_count / test_data.shape[0] * 100:.2f}%")
\ No newline at end of file
+    print(f"Accuracy: {correct_count / test_data.shape[0] * 100:.2f}%")
\ No newline at end of file