From 91c0d80be06f398370d09c66b367a272162730de Mon Sep 17 00:00:00 2001
From: Xionghaoran <719929980@qq.com>
Date: Mon, 14 Oct 2024 21:38:24 +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 | 27 ++++++++++++---------------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/function.py b/function.py
index a412777..0935b82 100644
--- a/function.py
+++ b/function.py
@@ -1,7 +1,8 @@
 # function.py
 import numpy as np
+import pandas as pd
 from sklearn.preprocessing import StandardScaler
-from sklearn.model_selection import cross_val_score
+
 
 """
 挑战说明:
@@ -77,28 +78,24 @@ def classify0(inX, dataSet, labels, k=3):
     label_counts = np.bincount(nearest_labels)
     return label_counts.argmax()
 
+
 def load_data(file_path):
     """
     加载 TSV 格式数据文件。
     """
-    data = np.loadtxt(file_path, delimiter="\t")
+    data = pd.read_csv(file_path, sep='\t', header=None).values
     features = data[:, :-1]
     labels = data[:, -1].astype(int)
     return features, labels
 
-def find_best_k(dataSet, labels):
-    """
-    使用交叉验证找到最佳 k 值。
-    """
-    best_score = 0
-    best_k = 3
-    for k in range(1, 11):
-        predictions = [classify0(x, dataSet, labels, k) for x in dataSet]
-        score = np.mean(predictions == labels)
-        if score > best_score:
-            best_score = score
-            best_k = k
-    return best_k
+if __name__ == "__main__":
+    train_file = "datingTestSet2.tsv"
+    train_data, train_labels = load_data(train_file)
+    
+    # 预测结果
+    print(classify0(np.array([65915, 3.868359, 0.128078]), train_data, train_labels, k=3))
+
+    
 
 
 if __name__ == "__main__":