import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from collections import Counter
from sklearn.metrics import accuracy_score





dataset_path = 'data/diabetes.csv'
df = pd.read_csv(dataset_path)
# Show the first few rows of the dataset
df.head()





X = df.drop('Outcome', axis=1).values
y = df['Outcome'].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
X_train.shape, X_test.shape, y_train.shape, y_test.shape



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 = [np.linalg.norm(x - x_train) for x_train in self.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 among k nearest neighbors
        most_common = Counter(k_nearest_labels).most_common(1)
        return most_common[0][0]
# Initialize KNN classifier with k=3
knn = KNN(k=3)
# Fit the model with the training data
knn.fit(X_train, y_train)
# Make predictions on the test data
y_pred = knn.predict(X_test)
# Display some of the predictions
y_pred[:10]





accuracy = accuracy_score(y_test, y_pred)
accuracy