https://github.com/corusm/mlops-project

https://github.com/corusm/mlops-project

Last synced: 29 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/corusm/mlops-project
• Owner: corusm
• License: other
• Created: 2024-01-06T11:30:01.000Z (12 months ago)
• Default Branch: main
• Last Pushed: 2024-01-19T20:46:36.000Z (11 months ago)
• Last Synced: 2024-10-15T06:36:56.579Z (2 months ago)
• Language: Jupyter Notebook
• Size: 6.44 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# MLOps Project Group 62

## Project Goal

The main goal of this project is to forecast wind power production at the Klim Windfarm. 

## Used frameworks

The project will initially employ the pytorch-forecasting library for model construction. Due to limited experience with this framework, there is consideration for a potential transition to PyTorch Lightning, known for its simpler model implementation approach compared to standard PyTorch.

## Data

We will use the following dataset -> http://www.imm.dtu.dk/courses/02427/comp_ex_4_scripts_2011.zip. However, we intend to migrate to an alternative dataset that provides a continuous stream of new and diverse data.

## Models

We expect to use some kind of auto-regressive model like RNN, LSTM or Transformer. Variations might be interesting too for better forecasting results, like the Temporal Fusion Transformer.

## Project structure

The directory structure of the project looks like this:

```txt

├── Makefile             <- Makefile with convenience commands like `make data` or `make train`

├── README.md            <- The top-level README for developers using this project.

├── data

│   ├── processed        <- The final, canonical data sets for modeling.

│   └── raw              <- The original, immutable data dump.

│

├── docs                 <- Documentation folder

│   │

│   ├── index.md         <- Homepage for your documentation

│   │

│   ├── mkdocs.yml       <- Configuration file for mkdocs

│   │

│   └── source/          <- Source directory for documentation files

│

├── models               <- Trained and serialized models, model predictions, or model summaries

│

├── notebooks            <- Jupyter notebooks.

│

├── pyproject.toml       <- Project configuration file

│

├── reports              <- Generated analysis as HTML, PDF, LaTeX, etc.

│   └── figures          <- Generated graphics and figures to be used in reporting

│

├── requirements.txt     <- The requirements file for reproducing the analysis environment

|

├── requirements_dev.txt <- The requirements file for reproducing the analysis environment

│

├── tests                <- Test files

│

├── mlops_project  <- Source code for use in this project.

│   │

│   ├── __init__.py      <- Makes folder a Python module

│   │

│   ├── data             <- Scripts to download or generate data

│   │   ├── __init__.py

│   │   └── make_dataset.py

│   │

│   ├── models           <- model implementations, training script and prediction script

│   │   ├── __init__.py

│   │   ├── model.py

│   │

│   ├── visualization    <- Scripts to create exploratory and results oriented visualizations

│   │   ├── __init__.py

│   │   └── visualize.py

│   ├── train_model.py   <- script for training the model

│   └── predict_model.py <- script for predicting from a model

│

└── LICENSE              <- Open-source license if one is chosen

```

![Diagram](/mlops_diagram.jpeg)

Created using [mlops_template](https://github.com/SkafteNicki/mlops_template),

a [cookiecutter template](https://github.com/cookiecutter/cookiecutter) for getting

started with Machine Learning Operations (MLOps).