Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/thecoderpinar/diabetes_health_prediction_and_analysis

A comprehensive project to predict and analyze diabetes health data using advanced machine learning models, including Logistic Regression, Random Forest, and XGBoost. πŸ“ŠπŸ”
https://github.com/thecoderpinar/diabetes_health_prediction_and_analysis

analytics artificial-intelligence classification data-science data-visualization deep-learning diabetes-prediction health healthcare logistic-regression machine-learning medical-analysis mlops prediction python random-forest xgboost

Last synced: about 1 month ago
JSON representation

A comprehensive project to predict and analyze diabetes health data using advanced machine learning models, including Logistic Regression, Random Forest, and XGBoost. πŸ“ŠπŸ”

Awesome Lists containing this project

README 

        
# Diabetes Health Prediction and Analysis πŸŽ‰



![Diabetes Health Prediction](https://miro.medium.com/v2/resize:fit:828/format:webp/1*KkQbSEI9sT44_yxR9vscJA.gif)



---



Welcome to the **Diabetes Health Prediction and Analysis** project! This repository contains a comprehensive pipeline for predicting diabetes diagnosis using various machine learning and deep learning models, along with an in-depth exploratory data analysis and feature engineering steps.



## πŸš€ Project Overview



This project aims to provide a thorough analysis of diabetes-related health data, develop predictive models, and evaluate their performance. The key components of the project include:



- πŸ“Š Data Preprocessing

- πŸ” Exploratory Data Analysis (EDA)

- πŸ› οΈ Feature Engineering

- 🧠 Model Training

- πŸ“ˆ Model Evaluation

- πŸ“‘ Comprehensive Reports



## πŸ“‚ Project Structure



Here's an overview of the project directory structure:



```plaintext

Diabetes_Health_Prediction_and_Analysis/

β”œβ”€β”€ data/

β”‚   β”œβ”€β”€ raw/

β”‚   β”‚   └── diabetes_data.csv

β”‚   β”œβ”€β”€ processed/

β”‚   β”‚   β”œβ”€β”€ X_train.csv

β”‚   β”‚   β”œβ”€β”€ X_train_engineered.csv

β”‚   β”‚   β”œβ”€β”€ X_test.csv

β”‚   β”‚   β”œβ”€β”€ X_test_engineered.csv

β”‚   β”‚   β”œβ”€β”€ y_train.csv

β”‚   β”‚   └── y_test.csv

β”œβ”€β”€ app/

β”‚   β”œβ”€β”€ app.py

β”‚   β”œβ”€β”€ templates/

β”‚   β”‚   └── index.html

β”‚   └── static/

β”‚       └── styles.css

β”œβ”€β”€ models/

β”‚   β”œβ”€β”€ logistic_regression.pkl

β”‚   β”œβ”€β”€ random_forest.pkl

β”‚   └── xgboost.pkl

β”œβ”€β”€ notebooks/

β”‚   └── exploratory_data_analysis.ipynb

β”œβ”€β”€ scripts/

β”‚   β”œβ”€β”€ plots/

β”‚   β”œβ”€β”€ reports/

β”‚   β”œβ”€β”€ data_preprocessing.py

β”‚   β”œβ”€β”€ feature_engineering.py

β”‚   β”œβ”€β”€ model_training.py

β”‚   β”œβ”€β”€ model_evaluation.py

β”‚   └── model_performance_report.py

β”œβ”€β”€ tests/

β”‚   β”œβ”€β”€ models/

β”‚   β”œβ”€β”€ test_data_preprocessing.py

β”‚   β”œβ”€β”€ test_feature_engineering.py

β”‚   β”œβ”€β”€ test_model_training.py

β”œβ”€β”€ requirements.txt 

└── README.md

```



## πŸ”§ Setup and Installation



To get started with this project, follow the steps below:



1. **Clone the repository:**



    ```sh

    git clone https://github.com/ThecoderPinar/Diabetes_Health_Prediction_and_Analysis.git

    cd Diabetes_Health_Prediction_and_Analysis

    ```



2. **Create and activate a virtual environment:**



    ```sh

    python -m venv venv

    source venv/bin/activate  # On Windows use `venv\Scripts\activate`

    ```



3. **Install the required packages:**



    ```sh

    pip install -r requirements.txt

    ```



4. **Run the data preprocessing script:**



    ```sh

    python scripts/data_preprocessing.py

    ```



5. **Run the feature engineering script:**



    ```sh

    python scripts/feature_engineering.py

    ```



6. **Train the models:**



    ```sh

    python scripts/model_training.py

    ```



7. **Evaluate the models:**



    ```sh

    python scripts/model_evaluation.py

    ```



8. **Generate comprehensive model performance reports:**



    ```sh

    python script/comprehensive_model_report.py

    ```



## πŸš€ Usage



- **Exploratory Data Analysis**: Check the `notebooks/exploratory_data_analysis.ipynb` notebook for detailed data analysis and visualizations.

- **Scripts**: All scripts for data preprocessing, feature engineering, model training, and evaluation are located in the `scripts/` directory.

- **Tests**: To ensure code quality and correctness, tests are included in the `tests/` directory. Run them with `pytest`.



## πŸ“Š Models



The following models are trained and evaluated in this project:



---



### Logistic Regression



#### ROC Curve:

![Logistic Regression ROC Curve](/scripts/plots/Logistic%20Regression_roc_curve.png)



*The ROC curve illustrates the true positive rate (sensitivity) versus the false positive rate (1-specificity) for different threshold settings. A higher area under the curve (AUC) indicates better model performance.*



#### Confusion Matrix:

![Logistic Regression Confusion Matrix](/scripts/plots/Logistic%20Regression_confusion_matrix.png)



*The confusion matrix provides a summary of the prediction results on the classification problem. It shows the number of true positive (TP), true negative (TN), false positive (FP), and false negative (FN) predictions.*



---



### Random Forest



#### ROC Curve:

![Random Forest ROC Curve](/scripts/plots/Random%20Forest_roc_curve.png)



*The ROC curve illustrates the true positive rate (sensitivity) versus the false positive rate (1-specificity) for different threshold settings. A higher area under the curve (AUC) indicates better model performance.*



#### Confusion Matrix:

![Random Forest Confusion Matrix](/scripts/plots/Random%20Forest_confusion_matrix.png)



*The confusion matrix provides a summary of the prediction results on



## 🎯 Performance Metrics



The performance of the models is evaluated using the following metrics:



- **Accuracy**

- **Precision**

- **Recall**

- **F1 Score**

- **ROC AUC Score**

- **Confusion Matrix**



### Logistic Regression



- **Accuracy (Doğruluk):** %78.99

- **Precision (Kesinlik):** %73.19

- **Recall (DuyarlΔ±lΔ±k):** %70.63

- **F1 Score:** %71.89

- **ROC AUC:** %83.86



**Confusion Matrix:**

```plaintext

[[196  37]

 [ 42 101]]

```

Model dosyasΔ±: 

```sh

models/logistic_regression.pkl

```



### Random Forest



- **Accuracy (Doğruluk):** %91.22

- **Precision (Kesinlik):** %94.35

- **Recall (DuyarlΔ±lΔ±k):** %81.82

- **F1 Score:** %87.64

- **ROC AUC:** %97.69



**Confusion Matrix:**

```plaintext

[[226   7]

 [ 26 117]]

```

Model dosyasΔ±: 

```sh

models/random_forest.pkl

```

##### Explanations:



1. [x] **_Accuracy:_** The ratio of correctly predicted instances to the total instances.

2. [x] **_Precision:**_ The ratio of true positive predictions to the total predicted positives. It measures the accuracy of positive predictions.

3. [x] **_Recall:_** The ratio of true positive predictions to the actual positives. It measures the model's ability to identify positive instances.

4.  [x] **_F1 Score:_** The harmonic mean of precision and recall. It provides a balance between precision and recall.

5.  [x] **_ROC AUC:_** The area under the ROC curve. It summarizes the model's ability to distinguish between classes.



**Confusion Matrix:**



* True Positive (TP): 117 - The number of actual positive cases correctly identified by the model.

* True Negative (TN): 226 - The number of actual negative cases correctly identified by the model.

* False Positive (FP): 7 - The number of actual negative cases incorrectly identified as positive by the model.

* False Negative (FN): 26 - The number of actual positive cases incorrectly identified as negative by the model.



##### Explanations:

1. [x] **_Accuracy:_** The ratio of correctly predicted instances to the total instances.

2. [x] **_Precision:_** The ratio of true positive predictions to the total predicted positives. It measures the accuracy of positive predictions.

3. [x] **_Recall:_** The ratio of true positive predictions to the actual positives. It measures the model's ability to identify positive instances.

4. [x] **_F1 Score:_** The harmonic mean of precision and recall. It provides a balance between precision and recall.

5. [x] **_ROC AUC:_** The area under the ROC curve. It summarizes the model's ability to distinguish between classes.



**Confusion Matrix:**



* True Positive (TP): 117 - The number of actual positive cases correctly identified by the model.

* True Negative (TN): 226 - The number of actual negative cases correctly identified by the model.

* False Positive (FP): 7 - The number of actual negative cases incorrectly identified as positive by the model.

* False Negative (FN): 26 - The number of actual positive cases incorrectly identified as negative by the model.



### XGBoost



- **Accuracy (Doğruluk):** %91.76

- **Precision (Kesinlik):** %93.08

- **Recall (DuyarlΔ±lΔ±k):** %84.62

- **F1 Score:** %88.64

- **ROC AUC:** %98.41



**Confusion Matrix:**

```plaintext

[[224   9]

 [ 22 121]]

```

Model dosyasΔ±: 

```sh

models/xgboost.pkl

```

##### Explanations:



1. [x] **_Accuracy_:** The ratio of correctly predicted instances to the total instances.

2. [x] **_Precision:_** The ratio of true positive predictions to the total predicted positives. It measures the accuracy of positive predictions.

3. [x] **_Recall:_** The ratio of true positive predictions to the actual positives. It measures the model's ability to identify positive instances.

4. [x] _**F1 Score:**_ The harmonic mean of precision and recall. It provides a balance between precision and recall.

5. [x] **_ROC AUC:_** The area under the ROC curve. It summarizes the model's ability to distinguish between classes.



**Confusion Matrix:**



* True Positive (TP): 121 - The number of actual positive cases correctly identified by the model.

* True Negative (TN): 224 - The number of actual negative cases correctly identified by the model.

* False Positive (FP): 9 - The number of actual negative cases incorrectly identified as positive by the model.

* False Negative (FN): 22 - The number of actual positive cases incorrectly identified as negative by the model.



## πŸ“ˆ Results



Model performance reports and evaluation metrics are saved and displayed in the `comprehensive_model_report.py` script output.



## πŸ’‘ Future Work



- Implement more advanced deep learning models (e.g., Neural Networks, LSTM).

- Perform hyperparameter tuning to optimize model performance.

- Explore feature selection techniques to improve model accuracy.

- Integrate additional health datasets for broader analysis.



## 🀝 Contributing



Contributions are welcome! Please feel free to submit a Pull Request. 



Whether it's improving the documentation, adding new features, or fixing bugs, your contributions are highly appreciated. Let's make this project better together! πŸš€



### How to Contribute:



1. **Fork the Repository**: Click on the 'Fork' button at the top right corner of this page to create a copy of this repository in your GitHub account.



2. **Clone the Forked Repository**: 

    ```bash

    git clone https://github.com/your-username/Diabetes_Health_Prediction_and_Analysis.git

    ```



3. **Create a New Branch**: 

    ```bash

    git checkout -b feature/your-feature-name

    ```



4. **Make Your Changes**: Implement your feature, bug fix, or improvement.



5. **Commit Your Changes**: 

    ```bash

    git commit -m "Add your commit message here"

    ```



6. **Push to Your Forked Repository**: 

    ```bash

    git push origin feature/your-feature-name

    ```



7. **Open a Pull Request**: Go to the original repository on GitHub and click on the 'New Pull Request' button. Compare changes from your forked repository and submit the pull request.



---



Thank you for your contributions! Together, we can build a more robust and efficient Diabetes Health Prediction and Analysis tool. 🌟



## πŸ“„ License



This project is licensed under the MIT License.



## πŸ“¬ Contact



If you have any questions or suggestions, feel free to open an issue or contact me directly. I am always open to feedback and would love to hear from you!



---



### How to Reach Me:



- **Email:** [[email protected]](mailto:[email protected])

- **GitHub Issues:** [Open an Issue](https://github.com/ThecoderPinar/Diabetes_Health_Prediction_and_Analysis/issues)

- **LinkedIn:** [Your LinkedIn Profile](https://www.linkedin.com/in/piinartp/)



---



Thank you for your interest in the Diabetes Health Prediction and Analysis project! Your feedback and suggestions are invaluable in making this project better and more useful for everyone. 🌟



![Contact Us](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhgcxnmPWgrukdZFkZONlQ4vUIKWJakRLZqvQUfzkDUbS2nAbQyIxR23-OwOis99pE6UQSxXmxwwuugHQWmwRFfZdw4QKGnk9S_n4yFrfPFTSbKIL6sKUKTwFUyG-8no5Y_9dCLI0LUJIo/s1600/welovehearingfromu.png!)



---



---



⭐️ Don't forget to give this project a star if you found it useful! ⭐️