baytune 0.2.5

Bayesian Tuning and Bandits

An open source project from Data to AI Lab at MIT.

A simple, extensible backend for developing auto-tuning systems.

Overview

Bayesian Tuning and Bandits is a simple, extensible backend for developing auto-tuning systems such as AutoML systems. It is currently being used in ATM (an AutoML system that allows tuning of classifiers) and MIT's system for the DARPA Data driven discovery of models program.

• Free software: MIT license
• Documentation: https://HDI-Project.github.io/BTB
• Homepage: https://github.com/HDI-Project/BTB

BTB is under active development. If you come across any issues, please report them here.

Installation

Install with pip

The easiest way to install BTB is using pip.

pip install baytune

Build from source

You can also clone the repository and build it from source.

git clone [e-mail]:HDI-Project/BTB.git
cd BTB
make install

Basic Usage

Tuners

In order to use a tuner we will create a Tuner instance indicating which parameters we want to tune, their types and the range of values that we want to try.

>>> from btb.tuning import GP
>>> from btb import HyperParameter, ParamTypes
>>> tunables = [
... ('n_estimators', HyperParameter(ParamTypes.INT, [10, 500])),
... ('max_depth', HyperParameter(ParamTypes.INT, [3, 20]))
... ]
>>> tuner = GP(tunables)

Then we perform the following three steps in a loop.

1. Let the Tuner propose a new set of parameters

   >>> parameters = tuner.propose()
   >>> parameters
   {'n_estimators': 297, 'max_depth': 3}
   

2. Fit and score a new model using these parameters

   >>> model = RandomForestClassifier(**parameters)
   >>> model.fit(X_train, y_train)
   RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
               max_depth=3, max_features='auto', max_leaf_nodes=None,
               min_impurity_decrease=0.0, min_impurity_split=None,
               min_samples_leaf=1, min_samples_split=2,
               min_weight_fraction_leaf=0.0, n_estimators=297, n_jobs=1,
               oob_score=False, random_state=None, verbose=0,
               warm_start=False)
   >>> score = model.score(X_test, y_test)
   >>> score
   0.77
   

3. Pass the used parameters and the score obtained back to the tuner

   tuner.add(parameters, score)
   

At each iteration, the Tuner will use the information about the previous tests to evaluate and propose the set of parameter values that have the highest probability of obtaining the highest score.

For more detailed examples, check scripts from the examples folder.

Selectors

The selectors are intended to be used in combination with tuners in order to find out and decide which model seems to get the best results once it is properly fine tuned.

In order to use the selector we will create a Tuner instance for each model that we want to try out, as well as the Selector instance.

>>> from sklearn.ensemble import RandomForestClassifier
>>> from sklearn.svm import SVC
>>> models = {
...     'RF': RandomForestClassifier,
...     'SVC': SVC
... }
>>> from btb.selection import UCB1
>>> selector = UCB1(['RF', 'SVC'])
>>> tuners = {
...     'RF': GP([
...         ('n_estimators', HyperParameter(ParamTypes.INT, [10, 500])),
...         ('max_depth', HyperParameter(ParamTypes.INT, [3, 20]))
...     ]),
...     'SVC': GP([
...         ('c', HyperParameter(ParamTypes.FLOAT_EXP, [0.01, 10.0])),
...         ('gamma', HyperParameter(ParamTypes.FLOAT, [0.000000001, 0.0000001]))
...     ])
... }

Then we perform the following steps in a loop.

1. Pass all the obtained scores to the selector and let it decide which model to test.

   >>> next_choice = selector.select({'RF': tuners['RF'].y, 'SVC': tuners['SVC'].y})
   >>> next_choice
   'RF'
   

2. Obtain a new set of parameters from the indicated tuner and create a model instance.

   >>> parameters = tuners[next_choice].propose()
   >>> parameters
   {'n_estimators': 289, 'max_depth': 18}
   >>> model = models[next_choice](**parameters)
   

3. Evaluate the score of the new model instance and pass it back to the tuner

   >>> model.fit(X_train, y_train)
   RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
               max_depth=18, max_features='auto', max_leaf_nodes=None,
               min_impurity_decrease=0.0, min_impurity_split=None,
               min_samples_leaf=1, min_samples_split=2,
               min_weight_fraction_leaf=0.0, n_estimators=289, n_jobs=1,
               oob_score=False, random_state=None, verbose=0,
               warm_start=False)
   >>> score = model.score(X_test, y_test)
   >>> score
   0.89
   >>> tuners[next_choice].add(parameters, score)
   

References

If you use BTB, please consider citing the following work:

• Laura Gustafson. Bayesian Tuning and Bandits: An Extensible, Open Source Library for AutoML. Masters thesis, MIT EECS, June 2018. (pdf)

  @MastersThesis{Laura:2018,
    title = "Bayesian Tuning and Bandits: An Extensible, Open Source Library for AutoML",
    author = "Laura Gustafson",
    month = "May",
    year = "2018",
    url = "https://dai.lids.mit.edu/wp-content/uploads/2018/05/Laura_MEng_Final.pdf",
    type = "M. Eng Thesis",
    address = "Cambridge, MA",
    school = "Massachusetts Institute of Technology",
  }
  

# History

## 0.2.5

### Bug Fixes

* Issue #115: HyperParameter subclass instantiation not working properly

## 0.2.4

### Internal Improvements

* Issue #62: Test for `None` in `HyperParameter.cast` instead of `HyperParameter.__init__`

### Bug fixes

* Issue #98: Categorical hyperparameters do not support `None` as input
* Issue #89: Fix the computation of `avg_rewards` in `BestKReward`

## 0.2.3

### Bug Fixes

* Issue #84: Error in GP tuning when only one parameter is present bug
* Issue #96: Fix pickling of HyperParameters
* Issue #98: Fix implementation of the GPEi tuner

## 0.2.2

### Internal Improvements

* Updated documentation

### Bug Fixes

* Issue #94: Fix unicode `param_type` caused error on python 2.

## 0.2.1

### Bug fixes

* Issue #74: `ParamTypes.STRING` tunables do not work

## 0.2.0

### New Features

* New Recommendation module
* New HyperParameter types
* Improved documentation and examples
* Fully tested Python 2.7, 3.4, 3.5 and 3.6 compatibility
* HyperParameter copy and deepcopy support
* Replace print statements with logging

### Internal Improvements

* Integrated with Travis-CI
* Exhaustive unit testing
* New implementation of HyperParameter
* Tuner builds a grid of real values instead of indices
* Resolve Issue #29: Make args explicit in `__init__` methods
* Resolve Issue #34: make all imports explicit

### Bug Fixes

* Fix error from mixing string/numerical hyperparameters
* Inverse transform for categorical hyperparameter returns single item

## 0.1.2

* Issue #47: Add missing requirements in v0.1.1 setup.py
* Issue #46: Error on v0.1.1: 'GP' object has no attribute 'X'

## 0.1.1

* First release.