更新 function.py

function.py

@@ -41,64 +41,34 @@ name = "李劲"
 """
 
   
-python
+def classify(input_vector, dataSet, labels, k=3):  
-复制代码
+    cov_matrix = np.cov(dataSet, rowvar=False)  
-	def classify(input_vector, dataSet, labels, k=3):  
+    inv_cov_matrix = np.linalg.inv(cov_matrix)  
+    diffMat = dataSet - input_vector  
+    left_term = np.dot(diffMat, inv_cov_matrix)  
+    mahalanobis_distances = np.sqrt(np.sum(left_term * diffMat, axis=1))  
+    k_indices = np.argsort(mahalanobis_distances)[:k]  
+    k_nearest_labels = [labels[i] for i in k_indices]  
+    most_common = max(set(k_nearest_labels), key=k_nearest_labels.count)  
+    return most_common
 
-	    cov_matrix = np.cov(dataSet, rowvar=False)  
+def load_dataset(directory):  
-
+    features = []  
-	    inv_cov_matrix = np.linalg.inv(cov_matrix)  
+    labels = []  
-
+    for filename in os.listdir(directory):  
-	    diffMat = dataSet - input_vector  
+        if filename.endswith(".txt"):  
-
+            filepath = os.path.join(directory, filename)  
-	    left_term = np.dot(diffMat, inv_cov_matrix)  
+            label = int(filename.split('_')[0])  
-
+            image_vector = img_to_vector(filepath)  
-	    mahalanobis_distances = np.sqrt(np.sum(left_term * diffMat, axis=1))  
+            features.append(image_vector)  
-
+            labels.append(label)  
-	    k_indices = np.argsort(mahalanobis_distances)[:k]  
+    return np.array(features), np.array(labels)
-
-	    k_nearest_labels = [labels[i] for i in k_indices]  
-
-	    most_common = max(set(k_nearest_labels), key=k_nearest_labels.count)  
-
-	    return most_common
   
-python
+def img_to_vector(filename):  
-复制代码
+    with open(filename) as file:  
-	def load_dataset(directory):  
+        lines = file.readlines()  
-
+        image_vector = np.array([int(char) for line in lines for char in line.strip()])  
-	    features = []  
+    return image_vector
-
-	    labels = []  
-
-	    for filename in os.listdir(directory):  
-
-	        if filename.endswith(".txt"):  
-
-	            filepath = os.path.join(directory, filename)  
-
-	            label = int(filename.split('_')[0])  
-
-	            image_vector = img_to_vector(filepath)  
-
-	            features.append(image_vector)  
-
-	            labels.append(label)  
-
-	    return np.array(features), np.array(labels) 
-  
-python
-复制代码
-	def img_to_vector(filename):  
-
-	    with open(filename) as file:  
-
-	        lines = file.readlines()  
-
-	        image_vector = np.array([int(char) for line in lines for char in line.strip()])  
-
-	    return image_vector
-
 if __name__ == "__main__":
     # 以下代码可用于测试，可自行随意修改
     train_data, train_labels = load_dataset("trainingDigits")