A shap wrapper for fastai
Project description
# FastSHAP (V1) > This project brings in part of the SHAP library into fastai (V1) and make it compatible. Thank you to Nestor Demeure for his assistance with the project!
## Install
pip install fastshap
## How to use
First we’ll quickly train a ADULTS tabular model
` from fastai2.tabular.all import * `
` path = untar_data(URLs.ADULT_SAMPLE) df = pd.read_csv(path/'adult.csv') `
` dep_var = 'salary' cat_names = ['workclass', 'education', 'marital-status', 'occupation', 'relationship', 'race'] cont_names = ['age', 'fnlwgt', 'education-num'] procs = [Categorify, FillMissing, Normalize] `
` splits = IndexSplitter(list(range(800,1000)))(range_of(df)) to = TabularPandas(df, procs, cat_names, cont_names, y_names="salary", splits=splits) dls = to.dataloaders() `
` learn = tabular_learner(dls, layers=[200,100], metrics=accuracy) learn.fit(1, 1e-2) `
And now for some example usage!
` from fastshap.interp import * `
` exp = ShapInterpretation(learn, df.iloc[:100]) `
` exp.dependence_plot('age') `
Classification model detected, displaying score for the class <50k. (use class_id to specify another class)
![png](docs/images/output_13_2.png)
For more examples see [01_Interpret](https://muellerzr.github.io/fastshap//interpret)
For more unofficial fastai extensions, see the [Fastai Extensions Repository](https://github.com/nestordemeure/fastai-extensions-repository).
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for fastshapv1-0.0.10-py2-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2614d5834319a55605ec1bfc3231f5109abf4b30aef26147005e7867d49fdc55 |
|
MD5 | 4cdef439d6e81daa41b4958194a57cb6 |
|
BLAKE2b-256 | ca137c31a09c9094c69df8b689b1335c37d8468aab69574a1516fb1cddc5b68e |