Tools for simulation-based model checking and diagnostics.
Tools for simulation-based model checking.
The checkrs package contains functions for creating 7 model checking/diagnostic plots described in
Brathwaite, Timothy. "Check yourself before you wreck yourself: Assessing discrete choice models through predictive simulations" arXiv preprint arXiv:1806.02307 (2018). https://arxiv.org/abs/1806.02307.
Beyond the plots described in this paper, checkrs enables the creation of reliability and marginal model plots that use continuous scatterplot smooths based on Extremely Randomized Trees as kernel estimators, as opposed to only allowing discrete smooths based on binning.
As for the name, checkrs is a play on the word "checkers," i.e., those tools one uses to check, or one who checks. The name is also a play on the phrases "check the research of scientists" and "check research scientists."
pip install checkrs
example_project is fictitious! This example is, literally, just an example.
from checkrs import ChartData, ViewSimCDF from example_project import load_data design, targets_observed, targets_simulated = load_data() chart_data = ChartData.from_raw( targets=targets_observed, # 1D Ndarray or Tensor targets_simulated=targets_simulated, # 2D Ndarray or Tensor design=design # DataFrame or None ) chart = ViewSimCDF.from_chart_data(chart_data) chart_plotnine = chart.draw(backend="plotnine") chart_altair = chart.draw(backend="altair") #### ## Save to a variety of formats #### # chart.save("temp_plot.png") # chart.save("temp_plot.pdf") # chart.save("temp_plot.json") # chart.save("temp_plot.html")
See docstrings for
- Add package to conda and conda-forge
To work on and edit checkrs, the following setup process may be useful.
- from the project root, create an environment
checkrswith the help of conda,
cd checkrs conda env create -n checkrs -f environment.yml
- activate the new environment with
conda activate checkrs
checkrsin an editable fashion using:
flit install --pth-file
Optional and needed only once after
- install several pre-commit git hooks with:
and checkout the configuration under
-n, --no-verifyflag of
git commitcan be used to deactivate pre-commit hooks temporarily.
Then take a look into the
Dependency Management & Reproducibility
Always keep your abstract (unpinned) dependencies updated in
requirements.in, and eventually in
pyproject.tomlif you want to ship and install the package via
environment.ymlfor dependencies that cannot be installed via
requirements.infor dependencies that can be installed via
pyproject.tomlfor dependencies that are needed for
checkrsto function at all, not just in development.
Create concrete dependencies as
requirements.txtfor the exact reproduction of your environment with:
Manually update any non-pip dependencies in
environment.yml, being sure to pin any such dependencies to a specific version.
Update your current environment using:
conda env update -f environment.yml
pip install -r requirements.txt
if you did not update any non-pip dependencies.
├── AUTHORS.rst <- List of developers and maintainers. ├── CHANGELOG.rst <- Changelog to keep track of new features and fixes. ├── LICENSE.txt <- License as chosen on the command-line. ├── README.md <- The top-level README for developers. ├── configs <- Directory for configurations of model & application. ├── 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 <- Directory for Sphinx documentation in rst or md. ├── environment.yaml <- The conda environment file for reproducibility. ├── 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 description, │ e.g. `1.0-fw-initial-data-exploration`. ├── references <- Data dictionaries, manuals, and all other materials. ├── reports <- Generated analysis as HTML, PDF, LaTeX, etc. │ └── figures <- Generated plots and figures for reports. ├── scripts <- Analysis and production scripts which import the │ actual PYTHON_PKG, e.g. train_model. ├── setup.cfg <- Declarative configuration of your project. ├── setup.py <- Use `python setup.py develop` to install for development or | or create a distribution with `python setup.py bdist_wheel`. ├── src │ └── checkrs <- Actual Python package where the main functionality goes. ├── tests <- Unit tests which can be run with `py.test`. ├── .coveragerc <- Configuration for coverage reports of unit tests. ├── .isort.cfg <- Configuration for git hook that sorts imports. └── .pre-commit-config.yaml <- Configuration of pre-commit git hooks.
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size checkrs-0.2.0-py3-none-any.whl (43.0 kB)||File type Wheel||Python version py3||Upload date||Hashes View|
|Filename, size checkrs-0.2.0.tar.gz (301.8 kB)||File type Source||Python version None||Upload date||Hashes View|