From e1d57186c3a0ce3029912c5cc3e2ed1a4b3a5ed8 Mon Sep 17 00:00:00 2001
From: anye <513317375@qq.com>
Date: Tue, 8 Oct 2024 11:08:58 +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 | 24 +++++++++++++++++++-----
 1 file changed, 19 insertions(+), 5 deletions(-)

diff --git a/function.py b/function.py
index 3773fc2..b4bb6d3 100644
--- a/function.py
+++ b/function.py
@@ -1,5 +1,4 @@
 import numpy as np
-from sklearn.preprocessing import MinMaxScaler
 
 """
 qin
@@ -34,19 +33,34 @@ def classify0(inX, dataSet, labels, k=3):
 
     return predicted_label
 
+def normalize_data(data):
+    """
+    对数据进行归一化处理，将每个特征缩放到 [0, 1] 范围。
+
+    Args:
+    - data (numpy array): 待归一化的数据集。
+
+    Returns:
+    - numpy array: 归一化后的数据集。
+    """
+    min_vals = data.min(0)  # 每一列的最小值
+    max_vals = data.max(0)  # 每一列的最大值
+    ranges = max_vals - min_vals  # 每一列的取值范围
+    norm_data = (data - min_vals) / ranges  # 归一化公式
+    return norm_data, ranges, min_vals
+
 def load_data(file_path):
     """
-    加载 TSV 格式数据文件。
+    加载 TSV 格式数据文件，并对特征数据进行归一化。
     """
     data = np.loadtxt(file_path, delimiter="\t")
     features = data[:, :-1]
     labels = data[:, -1].astype(int)
     
     # 数据归一化
-    scaler = MinMaxScaler()
-    features = scaler.fit_transform(features)
+    norm_features, _, _ = normalize_data(features)
     
-    return features, labels
+    return norm_features, labels
 
 
 if __name__ == "__main__":