kthnearest.py

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score, classification_report
from sklearn.datasets import load_iris

# Load the Iris dataset
iris = load_iris()
X = iris.data  # Features
y = iris.target  # Labels

# Split the data into training and test sets (80% train, 20% test)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create and train the k-NN model
k = 5  # Number of neighbors
knn = KNeighborsClassifier(n_neighbors=k)
knn.fit(X_train, y_train)

# Make predictions
y_pred = knn.predict(X_test)

# Evaluate accuracy
accuracy = accuracy_score(y_test, y_pred)

print("Model accuracy %.4f" % accuracy)

# Print classification report
print("\nClassification Report:\n", classification_report(y_test, y_pred))

# Print correct and incorrect predictions
print("\nPredictions Analysis:")

correct_predictions = []
incorrect_predictions = []

for i in range(len(y_test)):
    if y_test[i] == y_pred[i]:
        correct_predictions.append((X_test[i], y_test[i], y_pred[i]))
    else:
        incorrect_predictions.append((X_test[i], y_test[i], y_pred[i]))

# Print correct predictions
# Print all predictions with correctness

print("\nCorrect Predictions:")
for sample, true_label, pred_label in correct_predictions:
    print("Sample:", sample)
    print("True Label:", iris.target_names[true_label])
    print("Predicted Label:", iris.target_names[pred_label])
    print()

# Print incorrect predictions

if incorrect_predictions:
    print("\nIncorrect Predictions:")
    for sample, true_label, pred_label in incorrect_predictions:
        print(f"Sample: {sample}, True Label: {iris.target_names[true_label]}, Predicted Label: {iris.target_names[pred_label]}")
else:
    print("No incorrect predictions!")  

# for sample, true_label, pred_label in zip(X_test, y_test, y_pred):
#     label_true = iris.target_names[true_label]
#     label_pred = iris.target_names[pred_label]
#     status = "Correct" if true_label == pred_label else "Incorrect"
#     print(f"{status}: {label_true} → {label_pred}")
# print("No incorrect predictions")