This application is in development phase
The objective of this application is to automate ML workflows and implement AutoML solutions.
-
The pipeline starts with ingesting raw data, which is then engineered to suit algorithm and domain requirements by leveraging data cleaning and feature engineering techniques. A ML model is then trained on this data and validated by hyperparameter tuning. The best performing model is then deployed and used for production. *
-
The essence of AutoML is to automate repetitive tasks such as pipeline creation and hyper-parameter tuning so that data scientists can spend more time on business problems on hand in practical scenarios. *
- improve efficiency by automatically running repetitive tasks. This allows data scientists to focus more on problems instead of models.
- Automated ML pipelines also help avoid potential errors caused by manual work.
- Democratization of machine learning features.
- Create a model, perform stratified cross validation and evaluate classification metrics
- Automatically tune the hyper-parameters of a classification model
- Analyze model performance using various plots
- Finalize the best model at the end of the experiment
- Make predictions on new / unseen data
- Save / load a model for future use
-
You can find the project here: https://github.com/imzaumza/Auto_ML_App.git
-
On right hand side of the screen click on download button.
-
After the file is downloaded, unzip it. Go into project folder in your terminal and run command "streamlit run app.py"
-
To run the demo version, paste "https://8189-102-89-34-12.eu.ngrok.io" in your browser
-
Other installation methods (HOW TO USE A GIT REPOSITORY AS A PIP DEPENDENCY), use this link https://matiascodesal.com/blog/how-use-git-repository-pip-dependency/