https://github.com/yupbank/tree_to_tensorflow

export tree family algo to tensorflow
https://github.com/yupbank/tree_to_tensorflow

Last synced: 4 months ago
JSON representation

export tree family algo to tensorflow

• Host: GitHub
• URL: https://github.com/yupbank/tree_to_tensorflow
• Owner: yupbank
• Created: 2018-01-22T22:22:57.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2020-02-18T20:01:35.000Z (over 5 years ago)
• Last Synced: 2025-01-31T02:21:59.840Z (4 months ago)
• Language: Python
• Size: 67.4 KB
• Stars: 9
• Watchers: 0
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml

Awesome Lists containing this project

README

        
# Covert Tree Models to Tensorflow Tree.

---

[![CircleCI](https://circleci.com/gh/yupbank/tree_to_tensorflow/tree/master.svg?style=svg)](https://circleci.com/gh/yupbank/tree_to_tensorflow/tree/master)

[![PyPI version](https://badge.fury.io/py/TFTree.svg)](https://badge.fury.io/py/TFTree)

[![codecov](https://codecov.io/gh/yupbank/tree_to_tensorflow/branch/master/graph/badge.svg)](https://codecov.io/gh/yupbank/tree_to_tensorflow)

[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)

# The Goal is to have one unified tree runtime

	* Convert a xgboost Tree/Forest into Tensorflow Graph.

	* Convert a sciki-learn Tree/Forest into Tensorflow Graph.

### Example

Convert fitted 

- `sklearn.DecisionTreeClassifier` 

- `sklearn.DecisionTreeRegressor`

- `sklearn.RandomForestRegressor`

- `sklearn.RandomForestClassifier`

- `xgboost.XGBClassifier`

- `xgboost.XGBRegressor`

to `tensorflow.saved_model`

All you need to do is pass your desired `model_dir`, `'./tmp'` in  this example and a fitted classifier.

```python

    

    from ttt import export_decision_tree

    clf = sklearn.ensemble.RandomForestClassifier()

    clf.fit(X, y)

    features = {'features': tf.placeholder(tf.float64, [None, X.shape[1]])}

    export_decision_tree(clf, features, 'sklearn_saved_model')

    xgb_model = xgboost.XGBClassifier().fit(X, y)

    export_decision_tree(xgb_model, features, 'xgb_saved_model')

    

```

And then you can server this model with tf/serving using 'saved_model'