evaluate_knn

src/main.py

@@ -15,3 +15,11 @@ if __name__ == "__main__":
     print(f" - Training data shape: {data_train.shape}, Training labels shape: {labels_train.shape}")
     print(f" - Testing data shape: {data_test.shape}, Testing labels shape: {labels_test.shape}")
     
+    # We flatten the images
+    data_train = data_train.reshape(data_train.shape[0], -1)
+    data_test = data_test.reshape(data_test.shape[0], -1)
+
+    # Evaluate the k-NN algorithm
+    k = 3
+    accuracy = evaluate_knn(data_train, labels_train, data_test, labels_test, k)
+    
\ No newline at end of file

src/utils/__init__.py

@@ -4,6 +4,7 @@ ROOT = r"../../.."
 
 from .read_cifar import *
 from .split_data import *
+from .knn import *
 
 
 

src/utils/knn.py

@@ -7,9 +7,9 @@ def distance_matrix(matrix1, matrix2):
     Parameters
     ----------
     matrix1 : np.ndarray
-        First matrix of shape (n1, d).
+        First matrix of shape (n1, d). [must be the test set]
     matrix2 : np.ndarray
-        Second matrix of shape (n2, d).
+        Second matrix of shape (n2, d). [must be the train set]
     
     Returns
     -------
@@ -67,6 +67,39 @@ def knn_predict(dists, labels_train, k):
     
     return labels_pred
 
+def evaluate_knn(data_train, labels_train, data_test, labels_test, k):
+    """
+    Evaluate the k-nearest neighbors algorithm on the given dataset.
+    
+    Parameters
+    ----------
+    data_train : np.ndarray
+        Training data of shape (n_train, d).
+    labels_train : np.ndarray
+        Training labels of shape (n_train,).
+    data_test : np.ndarray
+        Testing data of shape (n_test, d).
+    labels_test : np.ndarray
+        Testing labels of shape (n_test,).
+    k : int
+        Number of neighbors to consider.
+    
+    Returns
+    -------
+    accuracy : float
+        Classification rate (accuracy) of the k-NN algorithm on the test set.
+    """
+    # Compute the distance matrix between the testing and training data
+    dists = distance_matrix(data_test, data_train)
+    
+    # Predict the labels for the test set
+    labels_pred = knn_predict(dists, labels_train, k)
+    
+    # Compute the accuracy
+    accuracy = np.mean(labels_pred == labels_test)
+    
+    return accuracy
+
 if __name__ == "__main__":
     # Example data and labels
     data_train = np.array([[1, 2], [3, 4], [5, 6], [7, 8]])
@@ -78,10 +111,16 @@ if __name__ == "__main__":
     print("Test data:", data_test)
     
     # Compute the distance matrix
-    dists = distance_matrix(data_train, data_test)
+    dists = distance_matrix(data_test,data_train)
     
     # Predict the labels for the test set
-    k = 3
+    k = 2
     labels_pred = knn_predict(dists, labels_train, k)
     
     print("Predicted labels:", labels_pred)
+
+    # Evaluate the k-NN algorithm
+    labels_test = np.array([0, 1])
+    accuracy = evaluate_knn(data_train, labels_train, data_test, labels_test, k)
+
+    print(f"Accuracy: {accuracy}")