From 5aff4622f51fdc4e27f3d03a3f46d7b04e45a804 Mon Sep 17 00:00:00 2001
From: kxz <2897100651@qq.com>
Date: Tue, 8 Oct 2024 20:16:23 +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 | 30 +++++++++++++++++++-----------
 1 file changed, 19 insertions(+), 11 deletions(-)

diff --git a/function.py b/function.py
index e214da1..5e3edf5 100644
--- a/function.py
+++ b/function.py
@@ -58,6 +58,7 @@ def load_data(file_path):
     return features, labels
 
 
+import numpy as np
 
 def classify0(inX, dataSet, labels, k=3):
     """
@@ -85,24 +86,31 @@ def classify0(inX, dataSet, labels, k=3):
         return -1
 
 
-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
-
 if __name__ == "__main__":
+    def load_data(file_path):
+        data = np.loadtxt(file_path, delimiter="\t")
+        features = data[:, :-1]
+        labels = data[:, -1].astype(int)
+        return features, labels
+
+    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  # Prevent division by zero
+        return normalized
+
     train_file_path = "datingTrainSet2.tsv"
     train_features, train_labels = load_data(train_file_path)
+    
     test_file_path = "datingTestSet2.tsv"
     test_features, test_labels = load_data(test_file_path)
-
-    # 归一化特征
+    
+    # Normalize features
     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)