更新 function.py

function.py

@@ -41,24 +41,20 @@ def classify(input_vector, dataSet, labels, k=2):
     Returns:
     - int: 预测的分类标签。
     """
-    num_samples = dataSet.shape[0]
-    mu = np.mean(dataSet, axis = 0)
-    cov = np.cov(dataSet.T)
-    try:
-        inv_cov = np.linalg.inv(cov)
-    except np.linalg.LinAlgError:
-        # 如果协方差矩阵不可逆，使用伪逆
-        inv_cov = np.linalg.pinv(cov)
-    distances = []
-    for i in range(num_samples):
-        diff = (input_vector - dataSet[i])
-        distance = np.sqrt(np.dot(np.dot(diff, inv_cov), diff.T))
-        distances.append(distance)
-    distances = np.array(distances)
-    sorted_indices = np.argsort(distances)
-    k_nearest_labels = [labels[i] for i in sorted_indices[:k]]
-    unique_labels, counts = np.unique(k_nearest_labels, return_counts = True)
-    return unique_labels[np.argmax(counts)]
+    dataSet_size = dataSet.shape[0]
+    # 计算欧氏距离
+    diff_mat = np.tile(input_vector, (dataSet_size, 1)) - dataSet
+    sq_diff_mat = diff_mat ** 2
+    sq_distances = sq_diff_mat.sum(axis=1)
+    distances = np.sqrt(sq_distances)
+    # 对距离进行排序
+    sorted_indices = distances.argsort()
+    class_count = {}
+    for i in range(k):
+        vote_label = labels[sorted_indices[i]]
+        class_count[vote_label] = class_count.get(vote_label, 0) + 1
+    sorted_class_count = sorted(class_count.items(), key=lambda x: x[1], reverse=True)
+    return sorted_class_count[0][0]
 
 
 def img_to_vector(filename):
@@ -72,9 +68,13 @@ def img_to_vector(filename):
     Returns:
     - np.array: 二值图像向量。
     """
-    with open(filename, 'r') as f:
-        lines = f.readlines()
-        return np.array([int(char) for line in lines for char in line.strip()])
+    return_vector = np.zeros((1, 1024))
+    with open(filename) as f:
+        for i in range(32):
+            line = f.readline()
+            for j in range(32):
+                return_vector[0, 32 * i + j] = int(line[j])
+    return return_vector
 
 
 def load_dataset(directory):
@@ -88,15 +88,15 @@ def load_dataset(directory):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-    data = []
+    data_set = []
     labels = []
-    for filename in os.listdir(directory):
-        if filename.endswith(".txt"):
-            label = int(filename[0])
-            vector = img_to_vector(os.path.join(directory, filename))
-            data.append(vector)
-            labels.append(label)
-    return np.array(data), np.array(labels)
+    for root, dirs, files in os.walk(directory):
+        for file in files:
+            if file.endswith('.txt'):
+                label = int(file.split('_')[0])
+                labels.append(label)
+                data_set.append(img_to_vector(os.path.join(root, file)))
+    return np.array(data_set).reshape(len(data_set), -1), np.array(labels)
 
 
 if __name__ == "__main__":