From 3647f7c3cb6a6bc82d70a33f9d89c87f90831ffa Mon Sep 17 00:00:00 2001
From: Xionghaoran <719929980@qq.com>
Date: Mon, 14 Oct 2024 21:50:55 +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 | 51 +++++++--------------------------------------------
 1 file changed, 7 insertions(+), 44 deletions(-)

diff --git a/function.py b/function.py
index e95bc5d..d16310e 100644
--- a/function.py
+++ b/function.py
@@ -1,7 +1,5 @@
 # function.py
 import numpy as np
-import pandas as pd
-from sklearn.preprocessing import StandardScaler
 
 """
 挑战说明:
@@ -45,22 +43,17 @@ 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，使用马氏距离。
+    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，默认值为 3。
+    - 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)
@@ -81,45 +74,15 @@ def load_data(file_path):
     """
     加载 TSV 格式数据文件。
     """
-    data = pd.read_csv(file_path, sep='\t', header=None).values
+    data = np.loadtxt(file_path, delimiter="\t")
     features = data[:, :-1]
     labels = data[:, -1].astype(int)
     return features, labels
 
-def find_best_k(X_train, y_train):
-    """
-    寻找最佳 k 值。
-    """
-    best_k = 1
-    best_accuracy = 0
-
-    for k in range(1, 21):
-        # 使用 classify0 进行预测
-        y_pred = [classify0(x, X_train, y_train, k) for x in X_train]
-        accuracy = np.mean(y_pred == y_train)
-
-        if accuracy > best_accuracy:
-            best_accuracy = accuracy
-            best_k = k
-
-    return best_k, best_accuracy
 
 if __name__ == "__main__":
-    train_file = "datingTestSet2.tsv"
-    X, y = load_data(train_file)
+    # 以下代码可用于测试，可自行随意修改
 
-    # 标准化特征
-    scaler = StandardScaler()
-    X = scaler.fit_transform(X)
-
-    # 寻找最佳 k 值
-    best_k, best_accuracy = find_best_k(X, y)
-
-    # 输出最佳 k 值和对应的准确率
-    print(f"最佳 k 值: {best_k}, 准确率: {best_accuracy:.2f}")
-
-    # 进行预测
-    sample = np.array([65915, 3.868359, 0.128078])
-    sample = scaler.transform([sample])[0]  # 标准化样本
-    predicted_label = classify0(sample, X, y, best_k)
-    print(f"预测结果: {predicted_label}")
+    train_file = "datingTrainSet2.tsv"
+    train_data, train_labels = load_data(train_file)
+    print(classify0(np.array([65915, 3.868359, 0.128078]), train_data, train_labels))
\ No newline at end of file