更新 function.py

function.py

@@ -2,8 +2,7 @@
 import numpy as np
 from collections import Counter
 from scipy.spatial import distance
-from sklearn.preprocessing import StandardScaler
-from sklearn.model_selection import KFold
+
 
 """
 挑战说明:
@@ -76,61 +75,28 @@ def load_data(file_path):
     features = data[:, :-1]
     labels = data[:, -1].astype(int)
     return features, labels
-# 交叉验证
-def cross_validate(train_data, train_labels, k_values, n_splits=8):
-    kf = KFold(n_splits=n_splits)
-    accuracies = {k: [] for k in k_values}
-
-    # 计算协方差矩阵并求逆矩阵
-    cov_matrix = np.cov(train_data, rowvar=False)
-    inv_cov_matrix = np.linalg.inv(cov_matrix)
-
-    for k in k_values:
-        for train_index, val_index in kf.split(train_data):
-            X_train, X_val = train_data[train_index], train_data[val_index]
-            y_train, y_val = train_labels[train_index], train_labels[val_index]
-
-            # 预测验证集
-            correct_count = sum(
-                classify0(X_val[i], X_train, y_train, inv_cov_matrix, k) == y_val[i]
-                for i in range(len(X_val))
-            )
-
-            accuracy = correct_count / len(X_val)
-            accuracies[k].append(accuracy)
-
-    # 计算每个 k 值的平均准确率
-    avg_accuracies = {k: np.mean(v) for k, v in accuracies.items()}
-    best_k = max(avg_accuracies, key=avg_accuracies.get)
-
-    return best_k, avg_accuracies
 
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
     train_file = "datingTrainSet2.tsv"
     test_file = "datingTestSet2.tsv"
 
     train_data, train_labels = load_data(train_file)
     test_data, test_labels = load_data(test_file)
 
-    # 特征缩放
-    scaler = StandardScaler()
-    train_data = scaler.fit_transform(train_data)
-    test_data = scaler.transform(test_data)
+    # 计算协方差矩阵并求逆矩阵
+    cov_matrix = np.cov(train_data, rowvar=False)
+    inv_cov_matrix = np.linalg.inv(cov_matrix)
 
-    # 使用交叉验证选择最佳的 k 值
-    k_values = range(1, 21)  # 尝试的 k 值范围
-    best_k, avg_accuracies = cross_validate(train_data, train_labels, k_values)
+    # 测试 classify0 函数
+    test_sample = test_data[0]  # 使用测试集中的第一个样本进行测试
+    predicted_label = classify0(test_sample, train_data, train_labels, inv_cov_matrix)
+    print(f"Predicted label: {predicted_label}, Actual label: {test_labels[0]}")
 
-    print(f"Best k: {best_k}")
-    print("Average accuracies for each k:", avg_accuracies)
-
-    # 使用最佳 k 值测试分类器性能
+    # 遍历整个测试集来评估分类器的性能
     correct_count = sum(
-        classify0(test_data[i], train_data, train_labels, np.linalg.inv(np.cov(train_data, rowvar=False)), best_k) ==
-        test_labels[i]
+        classify0(test_data[i], train_data, train_labels, inv_cov_matrix) == test_labels[i]
         for i in range(len(test_data))
     )
     accuracy = correct_count / len(test_data)
-    print(f"Accuracy with best k ({best_k}): {accuracy * 100:.2f}%")
+    print(f"Accuracy: {accuracy * 100:.2f}%")