whittemore
所属分类：collect
开发工具：Jupyter Notebook
文件大小：0KB
下载次数：0
上传日期：2021-05-17 18:22:32
上 传 者：
sh-1993
说明： Clojure中的因果编程，
(Causal programming in Clojure,)
文件列表:
CHANGELOG.md (66, 2021-05-17)
LICENSE (11219, 2021-05-17)
data/ (0, 2021-05-17)
data/renal-calculi.csv (15986, 2021-05-17)
data/smoking.csv (9199, 2021-05-17)
notebooks/ (0, 2021-05-17)
notebooks/test-identify.ipynb (51196, 2021-05-17)
notebooks/test-infer.ipynb (32344, 2021-05-17)
notebooks/test-random.ipynb (31549, 2021-05-17)
project.clj (859, 2021-05-17)
src/ (0, 2021-05-17)
src/whittemore/ (0, 2021-05-17)
src/whittemore/core.clj (27644, 2021-05-17)
src/whittemore/graphviz.clj (3599, 2021-05-17)
src/whittemore/html_table.clj (1506, 2021-05-17)
src/whittemore/io.clj (1950, 2021-05-17)
src/whittemore/plot.clj (2759, 2021-05-17)
src/whittemore/protocols.clj (241, 2021-05-17)
src/whittemore/random.clj (2919, 2021-05-17)
src/whittemore/util.clj (446, 2021-05-17)
test/ (0, 2021-05-17)
test/whittemore/ (0, 2021-05-17)
test/whittemore/core_test.clj (4548, 2021-05-17)
# Whittemore
Causal programming in Clojure.
## Getting started
The easiest way to get started is with [Leiningen](https://leiningen.org) (requires [Java](https://openjdk.java.net/install/), OpenJDK 8 recommended). Once Leiningen is installed, create a new project:
lein new whittemore demo
cd demo
A REPL can be started from within the project directory:
lein repl
Rich output (HTML, images, LaTeX) is available in [Jupyter](https://jupyter.org/install) notebooks. Once Jupyter installed:
lein jupyter install-kernel # first time only
lein jupyter notebook
[Graphviz](https://graphviz.org/download/) is recommended for rendering causal diagrams. Whittemore will automatically fallback to [viz.cljc](https://github.com/jebberjeb/viz.cljc) if Graphviz is not installed, but this is much slower.
## Examples
The `notebooks` directory has several examples.
## References
[Whittemore paper](https://arxiv.org/abs/1812.11918), presented at the 2019 [AAAI-WHY](https://why19.causalai.net/papers.html) Symposium
Whittemore is based on the structural causal model / graphical causal model / "Pearlian" causality approach. A good survey is [On Pearl's Hierarchy and the Foundations of Causal Inference](https://causalai.net/r60.pdf) (Bareinboim et al 2020)
## License
Copyright 2018 Joshua Brule
Distributed under the Eclipse Public License either version 1.0 or (at
your option) any later version.
近期下载者：
相关文件：
收藏者：