Diabetes_Prediction_System

Description

Various Machine Learning models have been trained using the PIMA Diabetes Dataset. The hyperparameter tuning of the model have been done using GridSeearchCV. The trained models include logistic regression, decision tree, random forest, gradient boosting classifier etc.

Dataset Link: https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database

Model Comparison

Required Librarires

1. matplotlib
2. pandas
3. seaborn
4. numpy
5. pickle
6. scikit-learn
7. xgboost

Data Preprocessing

1. Null Values Check
2. Replacing NA values
3. Outliers Detection
4. Feature Engineering
5. One Hot Encoding

EDA

1. PairPlot
2. HistPlot
3. BoxPlot
4. Correlation Heatmap

GUI

To Run this Project

1. Clone this Repository
2. Downlaod the dataset
3. Unzip the dataset in the same folder as python file (.ipynb)
4. run the file OR
5. use the trained model (gbc.pkl)

Diabetic Prediciton

Non - Diabetic Prediction