diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..570df23 --- /dev/null +++ b/.gitignore @@ -0,0 +1,90 @@ +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod] + +# C extensions +*.so + +# Distribution / packaging +.Python +env/ +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +*.egg-info/ +.installed.cfg +*.egg + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover + +# Translations +*.mo +*.pot + +# Django stuff: +*.log + +# Sphinx documentation +docs/_build/ + +# PyBuilder +target/ + +# DotEnv configuration +.env + +# Database +*.db +*.rdb + +# Pycharm +.idea + +# VS Code +.vscode/ +*.code-workspace + +# Spyder +.spyproject/ + +# Jupyter NB Checkpoints +.ipynb_checkpoints/ + +# exclude data from source control by default +# /data/ + +# Mac OS-specific storage files +.DS_Store + +# vim +*.swp +*.swo + +# Mypy cache +.mypy_cache/ diff --git a/README.md b/README.md new file mode 100644 index 0000000..e69de29 diff --git a/references/folder_structure.txt b/references/folder_structure.txt new file mode 100644 index 0000000..bf69dae --- /dev/null +++ b/references/folder_structure.txt @@ -0,0 +1,44 @@ +├── LICENSE +├── Makefile <- Makefile with commands like `make data` or `make train` +├── README.md <- The top-level README for developers using this project. +├── data +│ ├── external <- Data from third party sources. +│ ├── interim <- Intermediate data that has been transformed. +│ ├── processed <- The final, canonical data sets for modeling. +│ └── raw <- The original, immutable data dump. +│ +├── docs <- A default Sphinx project; see sphinx-doc.org for details +│ +├── models <- Trained and serialized models, model predictions, or model summaries +│ +├── notebooks <- Jupyter notebooks. Naming convention is a number (for ordering), +│ the creator's initials, and a short `-` delimited description, e.g. +│ `1.0-jqp-initial-data-exploration`. +│ +├── references <- Data dictionaries, manuals, and all other explanatory materials. +│ +├── 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, e.g. +│ generated with `pip freeze > requirements.txt` +│ +├── setup.py <- Make this project pip installable with `pip install -e` +├── 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 +│ │ +│ ├── 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 +│ +└── tox.ini <- tox file with settings for running tox; see tox.readthedocs.io \ No newline at end of file diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..e69de29 diff --git a/src/__init__.py b/src/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/src/data/.gitkeep b/src/data/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/src/data/__init__.py b/src/data/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/src/data/make_dataset.py b/src/data/make_dataset.py new file mode 100644 index 0000000..e69de29 diff --git a/src/features/.gitkeep b/src/features/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/src/features/__init__.py b/src/features/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/src/features/build_features.py b/src/features/build_features.py new file mode 100644 index 0000000..e69de29 diff --git a/src/models/.gitkeep b/src/models/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/src/models/__init__.py b/src/models/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/src/models/predict_model.py b/src/models/predict_model.py new file mode 100644 index 0000000..e69de29 diff --git a/src/models/train_model.py b/src/models/train_model.py new file mode 100644 index 0000000..e69de29 diff --git a/src/visualization/.gitkeep b/src/visualization/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/src/visualization/__init__.py b/src/visualization/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/src/visualization/plot_settings.py b/src/visualization/plot_settings.py new file mode 100644 index 0000000..0e6c7ac --- /dev/null +++ b/src/visualization/plot_settings.py @@ -0,0 +1,18 @@ +import matplotlib as mpl +import matplotlib.pyplot as plt +from cycler import cycler + +colors = cycler(color=plt.get_cmap("tab10").colors) # ["b", "r", "g"] + +mpl.style.use("ggplot") +mpl.rcParams["figure.figsize"] = (20, 5) +mpl.rcParams["axes.facecolor"] = "white" +mpl.rcParams["axes.grid"] = True +mpl.rcParams["grid.color"] = "lightgray" +mpl.rcParams["axes.prop_cycle"] = colors +mpl.rcParams["axes.linewidth"] = 1 +mpl.rcParams["xtick.color"] = "black" +mpl.rcParams["ytick.color"] = "black" +mpl.rcParams["font.size"] = 12 +mpl.rcParams["figure.titlesize"] = 25 +mpl.rcParams["figure.dpi"] = 100 diff --git a/src/visualization/visualize.py b/src/visualization/visualize.py new file mode 100644 index 0000000..e69de29