From 5d034ca174c9aac05192c9d8be36c55e47571609 Mon Sep 17 00:00:00 2001
From: kxz <2897100651@qq.com>
Date: Tue, 8 Oct 2024 20:23:32 +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 | 65 ++++++++++++++++++++---------------------------------
 1 file changed, 24 insertions(+), 41 deletions(-)

diff --git a/function.py b/function.py
index 2463910..907ba41 100644
--- a/function.py
+++ b/function.py
@@ -71,7 +71,7 @@ def classify0(inX, dataSet, labels, k=3):
     Returns:
     - int: 预测的分类标签。
     """
-    dists = np.sqrt(((dataSet - inX) ** 2).sum(axis=1))
+    dists = np.sum(np.abs(dataSet - inX), axis=1)
     sorted_index = np.argsort(dists)
     class_count = {}
     for i in range(k):
@@ -84,48 +84,31 @@ def classify0(inX, dataSet, labels, k=3):
         return -1
 
 if __name__ == "__main__":
-    # 加载数据
-    def load_data(file_path):
-        data = np.loadtxt(file_path, delimiter="\t")
-        features = data[:, :-1]
-        labels = data[:, -1].astype(int)
-        return features, labels
-
-    train_file_path = "datingTrainSet2.tsv"
-    test_file_path = "datingTestSet2.tsv"
-
-    train_features, train_labels = load_data(train_file_path)
-    test_features, test_labels = load_data(test_file_path)
-
-    # 归一化特征
-    def normalize(features):
-        min_vals = features.min(axis=0)
-        max_vals = features.max(axis=0)
-        ranges = max_vals - min_vals
-        normalized = (features - min_vals) / ranges
-        normalized[ranges == 0] = 0  # 防止除以零
-        return normalized
-
+    # 假设 load_data 和 normalize 函数已经定义
+    train_features, train_labels = load_data("datingTrainSet2.tsv")
+    test_features, test_labels = load_data("datingTestSet2.tsv")
     train_features = normalize(train_features)
     test_features = normalize(test_features)
 
-    correct_count = 0
-    for i in range(len(test_features)):
-        test_feature = test_features[i].reshape(1, -1)
-        predict_label = classify0(test_feature, train_features, train_labels, k=3)
-        if predict_label == -1:
-            continue
-        correct_count += (predict_label == test_labels[i])
+    best_k = 3
+    best_accuracy = 0.0
+
+    for k in range(1, 10):  # 尝试不同的 K 值
+        correct_count = 0
+        for i in range(len(test_features)):
+            test_feature = test_features[i].reshape(1, -1)
+            predict_label = classify0(test_feature, train_features, train_labels, k=k)
+            if predict_label == -1:
+                continue
+            correct_count += (predict_label == test_labels[i])
+
+        accuracy = correct_count / len(test_features)
+        print(f"Accuracy with k={k}: {accuracy:.2f}")
+        if accuracy > best_accuracy:
+            best_accuracy = accuracy
+            best_k = k
+
+    print(f"Best K: {best_k}, Best Accuracy: {best_accuracy:.2f}")
+
 
-    accuracy = correct_count / len(test_features)
-    print(f"Accuracy: {accuracy:.2f}")
-    correct_count = 0
-    for i in range(len(test_features)):
-        test_feature = test_features[i].reshape(1, -1)
-        predict_label = classify0(test_feature, train_features, train_labels, k=3)
-        if predict_label == -1:
-            continue
-        correct_count += (predict_label == test_labels[i])
 
-    accuracy = correct_count / len(test_features)
-    print(f"Accuracy: {accuracy:.2f}")