From 40056a63794689042f3b178bac7943bb051704e4 Mon Sep 17 00:00:00 2001
From: LufsX <lufsx@outlook.com>
Date: Sat, 28 Sep 2024 01:23:22 +0800
Subject: [PATCH] chore: adjust upstream

---
 function.py | 47 +++++++++++++++++++++--------------------------
 1 file changed, 21 insertions(+), 26 deletions(-)

diff --git a/function.py b/function.py
index d66135e..f304c35 100644
--- a/function.py
+++ b/function.py
@@ -38,7 +38,7 @@ name = "向兴宇"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels):
+def classify0(inX, dataSet, labels, k=9):
     """
     KNN 分类算法。
 
@@ -63,7 +63,7 @@ def classify0(inX, dataSet, labels):
     sortedDistIndices = np.argsort(distances)
 
     # 统计前 k 个样本的标签
-    classCount = np.bincount(labels[sortedDistIndices[:8]])
+    classCount = np.bincount(labels[sortedDistIndices[:k]])
 
     # 返回出现次数最多的标签
     return np.argmax(classCount)
@@ -73,16 +73,10 @@ def load_data(file_path):
     """
     加载 TSV 格式数据文件。
     """
-    features = []
-    labels = []
-
-    with open(file_path, "r") as file:
-        for line in file:
-            values = line.strip().split("\t")
-            features.append([float(x) for x in values[:-1]])
-            labels.append(int(values[-1]))
-
-    return np.array(features), np.array(labels)
+    data = np.loadtxt(file_path, delimiter="\t")
+    features = data[:, :-1]
+    labels = data[:, -1].astype(int)
+    return features, labels
 
 
 if __name__ == "__main__":
@@ -95,18 +89,19 @@ if __name__ == "__main__":
     train_data, train_labels = load_data(train_file)
     test_data, test_labels = load_data(test_file)
 
-    correct = 0
-    total = len(test_data)
+    for j in range(20):
+        correct = 0
+        total = len(test_data)
 
-    for i in range(total):
-        # 获取测试数据中的每个样本
-        result = classify0(test_data[i], train_data, train_labels)
-        if result == test_labels[i]:
-            correct += 1
-        else:
-            print(
-                f"第 {i+1} 次测试错误，数据 {test_data[i]} 被分类到 {result} 实际是 {test_labels[i]}"
-            )
-
-    accuracy = correct / total
-    print(f"测试集正确个数 {correct}，总个数 {total}，正确率 {accuracy}")
+        for i in range(total):
+            # 获取测试数据中的每个样本
+            result = classify0(test_data[i], train_data, train_labels, k=j + 1)
+            if result == test_labels[i]:
+                correct += 1
+            # else:
+            #     print(
+            #         f"第 {i+1} 次测试错误，数据 {test_data[i]} 被分类到 {result} 实际是 {test_labels[i]}"
+            #     )
+        if correct >= 96:
+            print(f"KNN 分类算法，k={j+1}")
+            print(f"{correct}% 正确率")