Thyroid-Disease-Prediction 🩺

Thyroid Disease Prediction ML project

Data Description ℹ️

From Garavan Institute
Documentation: as given by Ross Quinlan
6 databases from the Garavan Institute in Sydney, Australia
Approximately the following for each database:

    ** 2800 training (data) instances and 972 test instances
    ** Plenty of missing data
    ** 29 or so attributes, either Boolean or continuously-valued 

2 additional databases, also from Ross Quinlan, are also here

    ** Hypothyroid.data and sick-euthyroid.data
    ** Quinlan believes that these databases have been corrupted
    ** Their format is highly similar to the other databases 

Workflows 🔧

1. Update config.yaml
2. Update schema.yaml
3. Update params.yaml
4. Update entity
5. Update configuration manager (configuration.py) in src config
6. Update components
7. Update pipeline
8. Update the main.py
9. Update the app.py

How to run the project

1. Clone the project

git clone https://github.com/tejas05in/Thyroid-Disease-Prediction.git

2. Change into the project directory

cd /Thyroid-Disease-Prediction

3. Create a conda environment

conda create -p env python==3.11.4 -y

4. Activate the conda environment

conda activate env/

5. Install the requirements

pip install -r requirements.txt

6. Start the streamlit app

streamlit run app.py
# This will redirect you to the end point in your browser

Initialization of training pipeline

python main.py

MLflow experiments 🔱

Optional: Run this to export the environemnt variables which will log the results in mlflow at dagshub:

export MLFLOW_TRACKING_URI=https://dagshub.com/tejas05in/Thyroid-Disease-Prediction.mlflow \
export MLFLOW_TRACKING_USERNAME=tejas05in \
export MLFLOW_TRACKING_PASSWORD=9efcb5c7b79d0e949378459b922b1462a80fa413

If the above variables are not exported then mlfow will store the results locally and it can be accessed by passing

mlflow ui --port 5000

docker pull tejas05in/tdpapp
docker run -p 5000:5000 tdpapp:latest

Model Drift Reports and Tests

• Drift Report : Contains information about the dataset and model drift parameters
• Tests : Contains information about the various tests performed on the dataset , model and features

Dagshub Repository :

Repo link : Directs you to the Dagshub repository

Pipline Version Control :