model.py

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.preprocessing import StandardScaler
import pickle

# Load dataset
df = pd.read_csv('./Assets/diabetes.csv')

# Splitting the dataset into features and target variable
X = df.drop('Outcome', axis=1)
y = df['Outcome']

# Splitting data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Standardizing the data
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)

# Training a KNN classifier
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(X_train_scaled, y_train)

# Saving the model and scaler to disk
with open('knn_model.pkl', 'wb') as model_file:
    pickle.dump(knn, model_file)
with open('scaler.pkl', 'wb') as scaler_file:
    pickle.dump(scaler, scaler_file)