Untitled

# Import necessary libraries
import pandas as pd
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, accuracy_score
from imblearn.over_sampling import SMOTE

# Load and preprocess the data
df = pd.read_csv('/mnt/data/Diabetes.csv')
X = df.drop('Outcome', axis=1)
y = df['Outcome']

# Stratified sampling to split the data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)

# Handling class imbalance using SMOTE
smote = SMOTE(random_state=42)
X_train_resampled, y_train_resampled = smote.fit_resample(X_train, y_train)

# Train the KNN model
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(X_train_resampled, y_train_resampled)

# Make predictions and evaluate the model
y_pred = knn.predict(X_test)
print("Accuracy:", accuracy_score(y_test, y_pred))
print(classification_report(y_test, y_pred))