更新 function.py

function.py

@@ -1,8 +1,10 @@
 # function.py
 import numpy as np
 import pandas as pd
+from sklearn.model_selection import train_test_split, GridSearchCV
 from sklearn.preprocessing import StandardScaler
-
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.metrics import accuracy_score
 
 """
 挑战说明:
@@ -44,41 +46,6 @@ name = "熊浩燃"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels, k=3):
-    """
-    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，请**自行设置默认值**，评测时仅会使用其默认值，不修改默认值将**无法通过**评测，**成绩为零**。
-
-    Returns:
-    - int: 预测的分类标签。
-    """
-    # 标准化数据
-    scaler = StandardScaler()
-    dataSet = scaler.fit_transform(dataSet)
-    inX = scaler.transform([inX])[0]
-    
-    # 计算协方差矩阵的逆
-    cov_matrix = np.cov(dataSet, rowvar=False)
-    inv_cov_matrix = np.linalg.inv(cov_matrix)
-    
-    # 计算马氏距离
-    diff = dataSet - inX
-    distances = np.sqrt(np.sum(diff @ inv_cov_matrix * diff, axis=1))
-    
-    # 按距离排序并返回 k 个最近的标签
-    sorted_indices = distances.argsort()
-    nearest_labels = [labels[i] for i in sorted_indices[:k]]
-    
-    # 找出出现次数最多的标签
-    label_counts = np.bincount(nearest_labels)
-    return label_counts.argmax()
-
-
 def load_data(file_path):
     """
     加载 TSV 格式数据文件。
@@ -88,13 +55,43 @@ def load_data(file_path):
     labels = data[:, -1].astype(int)
     return features, labels
 
-
-
+def find_best_k(X_train, y_train):
+    """
+    使用交叉验证找到最佳的 k 值。
+    """
+    param_grid = {'n_neighbors': range(1, 21), 'weights': ['uniform', 'distance']}
+    knn = KNeighborsClassifier()
+    grid_search = GridSearchCV(knn, param_grid, cv=5)
+    grid_search.fit(X_train, y_train)
+    return grid_search.best_params_
 
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
+    # 加载数据
     train_file = "datingTestSet2.tsv"
-    train_data, train_labels = load_data(train_file)
+    X, y = load_data(train_file)
+
+    # 分割数据集
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+    # 标准化特征
+    scaler = StandardScaler()
+    X_train = scaler.fit_transform(X_train)
+    X_test = scaler.transform(X_test)
+
+    # 寻找最佳 k 值
+    best_params = find_best_k(X_train, y_train)
+    best_k = best_params['n_neighbors']
+    best_weights = best_params['weights']
+
+    # 使用最佳参数训练模型并评估
+    knn = KNeighborsClassifier(n_neighbors=best_k, weights=best_weights)
+    knn.fit(X_train, y_train)
+    y_pred = knn.predict(X_test)
+    
+    # 输出准确率
+    accuracy = accuracy_score(y_test, y_pred)
+    print(f"最佳 k 值: {best_k}, 权重: {best_weights}, 准确率: {accuracy:.2f}")
+
+
+
 
-    # 预测结果
-    print(classify0(np.array([65915, 3.868359, 0.128078]), train_data, train_labels, k=3))