Skip to content

Latest commit

 

History

History
374 lines (292 loc) · 17.4 KB

readme.md

File metadata and controls

374 lines (292 loc) · 17.4 KB
Raw

sklearn-porter

Build Status PyPI PyPI GitHub license Join the chat at https://gitter.im/nok/sklearn-porter

Transpile trained scikit-learn estimators to C, Java, JavaScript and others.
It's recommended for limited embedded systems and critical applications where performance matters most.

Machine learning algorithms

Algorithm Programming language
Classifier Java * JS C Go PHP Ruby
svm.SVC ✓, ✓ ᴵ ✓ ✓ ✓ ✓
svm.NuSVC ✓, ✓ ᴵ ✓ ✓ ✓ ✓
svm.LinearSVC ✓, ✓ ᴵ ✓ ✓ ✓ ✓ ✓
tree.DecisionTreeClassifier ✓, ✓ ᴱ, ✓ ᴵ ✓, ✓ ᴱ ✓, ✓ ᴱ ✓, ✓ ᴱ ✓, ✓ ᴱ ✓, ✓ ᴱ
ensemble.RandomForestClassifier ✓ ᴱ, ✓ ᴵ ✓ ᴱ ✓ ᴱ ✓ ᴱ ✓ ᴱ
ensemble.ExtraTreesClassifier ✓ ᴱ, ✓ ᴵ ✓ ᴱ ✓ ᴱ ✓ ᴱ ✓ ᴱ
ensemble.AdaBoostClassifier ✓ ᴱ, ✓ ᴵ ✓ ᴱ, ✓ ᴵ ✓ ᴱ
neighbors.KNeighborsClassifier ✓, ✓ ᴵ ✓, ✓ ᴵ
naive_bayes.GaussianNB ✓, ✓ ᴵ ✓
naive_bayes.BernoulliNB ✓, ✓ ᴵ ✓
neural_network.MLPClassifier ✓, ✓ ᴵ ✓, ✓ ᴵ
Regressor
neural_network.MLPRegressor ✓

✓ = is full-featured,　ᴱ = with embedded model data,　ᴵ = with imported model data,　* = default language

Installation

$ pip install sklearn-porter

If you want the latest changes, you can install the module from the master branch:

$ pip uninstall -y sklearn-porter
$ pip install --no-cache-dir https://github.com/nok/sklearn-porter/zipball/master

Minimum requirements

- python>=2.7.3
- scikit-learn>=0.14.1

If you want to transpile a multilayer perceptron, you have to upgrade the scikit-learn package:

- python>=2.7.3
- scikit-learn>=0.18.0

Usage

Export

The following example shows how you can port a decision tree estimator to Java:

from sklearn.datasets import load_iris
from sklearn.tree import tree
from sklearn_porter import Porter

# Load data and train the classifier:
samples = load_iris()
X, y = samples.data, samples.target
clf = tree.DecisionTreeClassifier()
clf.fit(X, y)

# Export:
porter = Porter(clf, language='java')
output = porter.export(embed_data=True)
print(output)

The exported result matches the official human-readable version of the decision tree.

Prediction

Run the prediction(s) in the target programming language directly:

# ...
porter = Porter(clf, language='java')

# Prediction(s):
Y_java = porter.predict(X)
y_java = porter.predict(X[0])
y_java = porter.predict([1., 2., 3., 4.])

Integrity

Always compute and test the integrity between the original and the transpiled estimator:

# ...
porter = Porter(clf, language='java')

# Accuracy:
integrity = porter.integrity_score(X)
print(integrity)  # 1.0

Command-line interface

First of all have a quick view on the available arguments:

$ python -m sklearn_porter [-h] --input <PICKLE_FILE> [--output <DEST_DIR>] \
                           [--class_name <CLASS_NAME>] [--method_name <METHOD_NAME>] \
                           [--c] [--java] [--js] [--go] [--php] [--ruby] \
                           [--export] [--checksum] [--data] [--pipe]

The following example shows how you can save an trained estimator to the pickle format:

# ...

# Extract estimator:
joblib.dump(clf, 'estimator.pkl')

After that the estimator can be transpiled to JavaScript by using the following command:

$ python -m sklearn_porter -i estimator.pkl --js

The target programming language is changeable on the fly:

$ python -m sklearn_porter -i estimator.pkl --c
$ python -m sklearn_porter -i estimator.pkl --go
$ python -m sklearn_porter -i estimator.pkl --php
$ python -m sklearn_porter -i estimator.pkl --java
$ python -m sklearn_porter -i estimator.pkl --ruby

For further processing the argument --pipe can be used to pass the result:

$ python -m sklearn_porter -i estimator.pkl --js --pipe > estimator.js

For instance the result can be minified by using UglifyJS:

$ python -m sklearn_porter -i estimator.pkl --js --pipe | uglifyjs --compress -o estimator.min.js

Further information will be shown by using the --help argument:

$ python -m sklearn_porter --help
$ python -m sklearn_porter -h

Development

Environment

Install the required environment modules by executing the script environment.sh:

$ bash ./scripts/environment.sh
#!/usr/bin/env bash

conda env create -c conda-forge -n sklearn-porter python=2 -f environment.yml
source activate sklearn-porter

The following compilers or intepreters are required to cover all tests:

Testing

The tests cover module functions as well as matching predictions of transpiled estimators. Run all tests by executing the script test.sh:

$ bash ./scripts/test.sh
#!/usr/bin/env bash

python -m unittest discover -vp '*Test.py'

The test files have a specific pattern: '[Algorithm][Language]Test.py':

$ python -m unittest discover -vp 'RandomForest*Test.py'
$ python -m unittest discover -vp '*JavaTest.py'

While you are developing new features or fixes, you can reduce the test duration by setting the number of tests:

$ N_RANDOM_FEATURE_SETS=15 N_EXISTING_FEATURE_SETS=30 python -m unittest discover -vp '*Test.py'

Quality

It's highly recommended to ensure the code quality. For that I use Pylint, which you can run by executing the script lint.sh:

$ bash ./scripts/lint.sh
#!/usr/bin/env bash

find ./sklearn_porter -name '*.py' -exec pylint {} \;

Citation

If you use this implementation in you work, please add a reference/citation to the paper. You can use the following BibTeX entry:

@misc{SkPoDaMo,
  author = {Darius Morawiec},
  title = {sklearn-porter: Transpile trained scikit-learn estimators to C, Java, JavaScript and others},
  url = {https://github.com/nok/sklearn-porter},
  year = {2016--2017}
}

License

The module is Open Source Software released under the MIT license.

Questions?

Don't be shy and feel free to contact me on Twitter or Gitter.