更新 function.py

function.py

@@ -40,56 +40,27 @@ name = "章程鸿"
 
 
 # 这里写自己的代码实现
-import numpy as np
-from collections import Counter
 
-def classify0(inX, dataSet, labels, k=1):
-    """
-    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，默认为3。
-
-    Returns:
-    - int: 预测的分类标签。
-    """
-    # 计算距离
-    diffMat = inX - dataSet
-    sqDiffMat = diffMat ** 2
-    sqDistances = sqDiffMat.sum(axis=1)
-    distances = sqDistances ** 0.5
-    
-    # 排序并选取前k个最小距离
-    sortedDistIndices = distances.argsort()
-    classCount = {}
-
-    for i in range(k):
-        voteIlabel = labels[sortedDistIndices[i]]
-        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
-
-    # 返回出现频率最高的类别
-    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
-    return sortedClassCount[0][0]
-
-def load_data(file_path):
-    """
-    加载 TSV 格式数据文件。
-    """
-    data = np.loadtxt(file_path, delimiter="\t")
-    features = data[:, :-1]
-    labels = data[:, -1].astype(int)
-    return features, labels
-
-if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
-    train_file = "datingTrainSet2.tsv"
-    
-    train_data, train_labels = load_data(train_file)
-
-    # 测试数据点
-    test_point = np.array([65915, 3.868359, 0.128078])
-    predicted_label = classify0(test_point, train_data, train_labels)
-    print("预测的分类标签是:", predicted_label)
+def normalize_data(data):  
+    """  
+    对数据进行Min-Max归一化。  
+      
+    Args:  
+    - data (numpy array): 原始数据。  
+      
+    Returns:  
+    - numpy array: 归一化后的数据。  
+    """  
+    min_vals = np.min(data, axis=0)  
+    max_vals = np.max(data, axis=0)  
+    ranges = max_vals - min_vals  
+    norm_data = np.where(ranges == 0, 0, (data - min_vals) / ranges)  
+    return norm_data  
+  
+# 在加载数据后调用归一化函数  
+train_data_normalized = normalize_data(train_data)  
+test_point_normalized = normalize_data(test_point.reshape(1, -1))[0]  # 注意test_point需要reshape为二维数组  
+  
+# 使用归一化后的数据进行分类  
+predicted_label_normalized = classify0(test_point_normalized, train_data_normalized, train_labels)  
+print("归一化后预测的分类标签是:", predicted_label_normalized)