Update knn.py

knn.py

@@ -1,61 +1,12 @@
+import numpy as np
 from sklearn.datasets import load_iris
 from sklearn.model_selection import train_test_split
-import numpy as np
+from sklearn.metrics import confusion_matrix, classification_report
 from collections import Counter
 
-
-# Load iris dataset
-iris = load_iris()
-X, y = iris.data, iris.target
-class_names = iris.target_names
-
-# Split dataset into training set and test set
+X, y, names = *load_iris(return_X_y=True), load_iris().target_names
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1)
+predict = lambda X: np.array([Counter(y_train[np.argsort([np.linalg.norm(x - x_train) for x_train in X_train])[:3]]).most_common(1)[0][0] for x in X])
+y_pred = predict(X_test)
 
-class KNN:
-    def __init__(self, k=3):
-        self.k = k
-
-    def fit(self, X, y):
-        self.X_train = X
-        self.y_train = y
-
-    def predict(self, X):
-        y_pred = [self._predict(x) for x in X]
-        return np.array(y_pred)
-
-    def _predict(self, x):
-        # Compute distances between x and all examples in the training set
-        distances = []
-        for x_train in self.X_train:
-            distances.append(np.linalg.norm(x - x_train)) 
-        # Sort by distance and return indices of the first k neighbors
-        k_indices = np.argsort(distances)[:self.k]
-        # Extract the labels of the k nearest neighbor training samples
-        k_nearest_labels = [self.y_train[i] for i in k_indices]
-        # return the most common class label
-        most_common = Counter(k_nearest_labels).most_common(1)
-        #print(most_common)
-        return most_common[0][0]
-
-# Create a k-NN classifier with 3 neighbors
-knn = KNN(k=3)
-
-# Train the model using the training sets
-knn.fit(X_train, y_train)
-
-# Predict the response for test dataset
-y_pred = knn.predict(X_test)
-print('Accuracy: %.4f' % np.mean(y_pred == y_test))
-print("Predictions:", class_names[y_pred])
-
-
-# Optional confusion matrix
-from sklearn.metrics import classification_report, confusion_matrix
-# Print confusion matrix
-print("\nConfusion Matrix:")
-print(confusion_matrix(y_test, y_pred))
-
-# Print classification report
-print("\nClassification Report:")
-print(classification_report(y_test, y_pred))
+print(f'Accuracy: {np.mean(y_pred == y_test):.4f}', "\nPredictions:", names[y_pred], "\nConfusion Matrix:\n", confusion_matrix(y_test, y_pred), "\nClassification Report:\n", classification_report(y_test, y_pred, target_names=names))