import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import (
confusion_matrix,
accuracy_score,
precision_score,
recall_score,
classification_report
)
plt.figure(figsize=(8,6))
sns.heatmap(df.corr(), annot=True, fmt=’.2f’, cmap=’coolwarm’)
plt.title(‘Feature Correlations’) #nikalo correlations
plt.show()
x = df.drop(columns=[‘Outcome’], axis=1)
y = df[‘Outcome’]
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)
scaler = StandardScaler() #only for independant values
x_train = scaler.fit_transform(x_train)
x_test = scaler.transform(x_test)
print(‘Train/test shapes:’, x_train.shape, x_test.shape)
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(x_train, y_train)
y_pred = knn.predict(x_test)
CM = confusion_matrix(y_test, y_pred)
acc = accuracy_score(y_test, y_pred)
err = 1 – acc
prec = precision_score(y_test, y_pred)
rec = recall_score(y_test, y_pred)
print(‘Confusion Matrix:\n’, CM)
print(f’Accuracy: {acc:.4f}’)
print(f’Error rate: {err:.4f}’)
print(f’Precision: {prec:.4f}’)
print(f’Recall: {rec:.4f}’)
print(‘\nClassification report:\n’, classification_report(y_test, y_pred))