Emily Cooke 81a4ed143d Fix (again) formatting of README project organization 2 years ago
data e4bb7e42e8 Add zipping and unzipping raw data files to Makefile. Include compressed raw data. 2 years ago
models e470d32d14 Create data/ and model/ directories needed for code to save output. 2 years ago
notebooks ca75b2228f Fix bugs: cross-sectional data features are correctly lagged by 1 hour; energy data no longer shuffled; outlier feature does not include target information; and weekend feature is formulated properly. Add full commentary to train_model scripts to explain neural network training code. 2 years ago
reports 647852b5d7 Remove text "reports" and figures from repository. 2 years ago
src f73b13eca1 Change workflow for weather prediction: use model tuned on all features to test feature subset performance during feature selection. Also, reduce number of hidden nodes tested in both models. 2 years ago
.gitignore 647852b5d7 Remove text "reports" and figures from repository. 2 years ago
LICENSE f78cb40bec Switch license from MIT to Apache 2.0 2 years ago
Makefile 1edf9852ff Correct false confirmation of conda environment creation. 2 years ago
README.md 81a4ed143d Fix (again) formatting of README project organization 2 years ago
env.yaml 0acf76a694 Add scikit-learn package to energy-prediction requirements. No longer support for Windows. 2 years ago
test_environment.py 89ad9e894b Put weather model in separate subdirectory. 2 years ago



A deployable reference solution for DAIR participants to observe and study application of machine learning techniques in time-series predictions. This solution builds a wind speed predictor.

Project Organization

├── Makefile           <- Makefile with commands like `make data` or `make model`
├── README.md          <- The top-level README for developers using this project.
├── data
│   ├── interim        <- Intermediate data that has been transformed.
│   ├── processed      <- The final, canonical data sets for modeling.
│   └── raw            <- The original, immutable data dump.
├── env.yaml           <- File to re-create development environment.
├── models             <- Trained models and model predictions
├── notebooks          <- Jupyter notebooks.
├── reports
│   └── figures        <- Generated graphics and figures to be used in reporting
└── src                <- Source code for use in this project.
    ├── __init__.py    <- Makes src a Python module
    ├── data           <- Scripts to download or generate data
    │   └── make_dataset.py
    ├── features       <- Scripts to turn raw data into features for modeling
    │   └── build_features.py
    │   └── select_features.py
    ├── models         <- Scripts to train models and then use trained models to make
    │   │                 predictions
    │   ├── predict_model.py
    │   └── train_model.py
    └── visualization  <- Scripts to create exploratory and results oriented visualizations
        └── visualize.py

Project based on the cookiecutter data science project template. #cookiecutterdatascience