Merge pull request #1157 from PrasDev4/main

Increasing model performance using hyperparameter tuning

Machine_Learning/Diabetes-Prediction/Diabetes Predictor - Deployment.py

@@ -2,6 +2,8 @@
 import numpy as np
 import pandas as pd
 import pickle
+from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.ensemble import RandomForestClassifier
 
 # Loading the dataset
 df = pd.read_csv('kaggle_diabetes.csv')
@@ -20,17 +22,31 @@
 df_copy['Insulin'].fillna(df_copy['Insulin'].median(), inplace=True)
 df_copy['BMI'].fillna(df_copy['BMI'].median(), inplace=True)
 
-# Model Building
-from sklearn.model_selection import train_test_split
+# Splitting the data into features and target variable
 X = df.drop(columns='Outcome')
 y = df['Outcome']
+
+# Splitting into training and testing sets
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=0)
 
-# Creating Random Forest Model
-from sklearn.ensemble import RandomForestClassifier
-classifier = RandomForestClassifier(n_estimators=20)
+# Hyperparameter tuning using GridSearchCV
+param_grid = {
+    'n_estimators': [10, 50, 100],
+    'max_depth': [None, 10, 20],
+    'min_samples_split': [2, 5, 10]
+}
+
+grid_search = GridSearchCV(estimator=RandomForestClassifier(), param_grid=param_grid, cv=5)
+grid_search.fit(X_train, y_train)
+
+# Best parameters found
+best_params = grid_search.best_params_
+print(f"Best hyperparameters: {best_params}")
+
+# Building Random Forest Model with best hyperparameters
+classifier = RandomForestClassifier(**best_params)
 classifier.fit(X_train, y_train)
 
 # Creating a pickle file for the classifier
 filename = 'diabetes-prediction-rfc-model.pkl'
-pickle.dump(classifier, open(filename, 'wb'))
+pickle.dump(classifier, open(filename, 'wb'))