https://github.com/abshar-shihab/diabetes_prediction_using_machine_learning

The Diabetes Prediction Project uses a machine learning approach to predict whether a person is diabetic or not based on key health-related metrics. The project explores data preprocessing, feature scaling, and classification techniques using Python libraries.
https://github.com/abshar-shihab/diabetes_prediction_using_machine_learning

machine-learning ml prediction predictive-modeling svm-classifier univariate-bayesian

Last synced: 4 months ago
JSON representation

The Diabetes Prediction Project uses a machine learning approach to predict whether a person is diabetic or not based on key health-related metrics. The project explores data preprocessing, feature scaling, and classification techniques using Python libraries.

• Host: GitHub
• URL: https://github.com/abshar-shihab/diabetes_prediction_using_machine_learning
• Owner: Abshar-Shihab
• Created: 2024-11-21T20:01:50.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2024-11-21T20:14:43.000Z (8 months ago)
• Last Synced: 2025-01-24T15:27:59.732Z (6 months ago)
• Topics: machine-learning, ml, prediction, predictive-modeling, svm-classifier, univariate-bayesian
• Language: Jupyter Notebook
• Homepage:
• Size: 70.3 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Support: Support Vector Machine (SVM) Model/Diabetes_prediction_using_SVM_classifier.ipynb

Awesome Lists containing this project

README

        
# Diabetes_prediction_using_Machine_Learning

The Diabetes Prediction Project uses a machine learning approach to predict whether a person is diabetic or not based on key health-related metrics. The project explores data preprocessing, feature scaling, and classification techniques using Python libraries.

# Diabetes Prediction Project

This project uses machine learning techniques to predict whether a person is diabetic based on health-related parameters. The workflow includes data preprocessing, feature scaling, training, and evaluation of a classification model.

## Overview

Diabetes is a chronic illness that requires early detection for effective management. This project employs machine learning to analyze and classify individuals as diabetic or non-diabetic using a structured dataset. The pipeline is designed to process input data, train a classification model, and evaluate its performance.

## Dataset

The project uses the **PIMA Indian Diabetes Dataset**, which contains medical data for patients. The features include:

- `Pregnancies`: Number of times pregnant

- `Glucose`: Plasma glucose concentration

- `BloodPressure`: Diastolic blood pressure (mm Hg)

- `SkinThickness`: Triceps skinfold thickness (mm)

- `Insulin`: 2-hour serum insulin (mu U/ml)

- `BMI`: Body Mass Index (weight in kg/(height in m)^2)

- `DiabetesPedigreeFunction`: Diabetes likelihood based on family history

- `Age`: Patient's age

- `Outcome`: Target variable (0 = Non-diabetic, 1 = Diabetic)

The dataset is small and relatively clean, making it suitable for beginners in machine learning.

## Prerequisites

The following Python libraries are required:

- `numpy`

- `pandas`

- `scikit-learn`

Install them using:

```bash

pip install numpy pandas scikit-learn

```

## Workflow

1. **Load Dataset**:

   - The dataset is loaded using `pandas`.

2. **Explore Dataset**:

   - Examine structure, summary statistics, and value distributions.

3. **Preprocessing**:

   - Standardize features for uniform scale using `StandardScaler`.

4. **Split Data**:

   - Partition the data into training and testing sets using `train_test_split`.

5. **Model Training**:

   - Train a machine learning classifier on the training data.

6. **Model Evaluation**:

   - Evaluate accuracy on both training and test sets.

7. **Make Predictions**:

   - Use the trained model to predict the diabetes status for new inputs.

## Results

- **Training Accuracy**: ~X%

- **Testing Accuracy**: ~Y%

## How to Run the Project

1. Clone or download the project files.

2. Place the `diabetes.csv` dataset in the same directory as the script.

3. Run the Python script using:

   ```bash

   python diabetes_prediction.py

   ```

4. Test the model by providing custom input data.

## Future Enhancements

- Use additional classifiers like Random Forest, Gradient Boosting, or Neural Networks.

- Perform hyperparameter tuning for improved accuracy.

- Add data visualization to enhance exploratory analysis.

## Acknowledgments

- Dataset from the UCI Machine Learning Repository.

- Scikit-learn for providing machine learning utilities.

```