更新 function.py

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):
+if __name__ == "__main__":
-    """
+    train_file = "datingTestSet2.tsv"
-    使用交叉验证找到最佳 k 值。
+    train_data, train_labels = load_data(train_file)
-    """
+    
-    best_score = 0
+    # 预测结果
-    best_k = 3
+    print(classify0(np.array([65915, 3.868359, 0.128078]), train_data, train_labels, 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__":