Skip to main content

Sample Implementation of Gradient Feature Auditing (GFA)

Project description

# Black Box Auditing and Certifying and Removing Disparate Impact

This repository contains a sample implementation of Gradient Feature Auditing (GFA) meant to be generalizable to most datasets. For more information on the repair process, see our paper on [Certifying and Removing Disparate Impact](http://arxiv.org/abs/1412.3756). For information on the full auditing process, see our paper on [Auditing Black-box Models for Indirect Influence](http://arxiv.org/abs/1602.07043).

# License

This code is licensed under an [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.html) license.

# Setup and Installation

1. Install the Python dependencies listed in the requirements.txt file.
2. Install python-matplotlib if you do not already have it (https://matplotlib.org/users/installing.html).
3. Install BlackBoxAuditing (`pip install BlackBoxAuditing`)

Many of the ModelVisitors rely on [Weka](http://www.cs.waikato.ac.nz/ml/weka/). Similarly, we use [TensorFlow](https://www.tensorflow.org/) for network-based machine learning. Any Python libraries that need to be installed are included in the `requirements.txt` file. Weka and Tensorflow should be downloaded during installation, but here's the download links just in case.

- Weka 3.6.13 [download](http://www.cs.waikato.ac.nz/ml/weka/downloading.html)
- TensorFlow [download](https://www.tensorflow.org/versions/master/get_started/os_setup.html) (original experiments run with version 0.6.0)


# Certifying and Removing Disparate Impact

After installing BlackBoxAuditing, you can run the data repair described in [Certifying and Removing Disparate Impact](http://arxiv.org/abs/1412.3756) using the command `BlackBoxAuditing-repair` on a terminal which will tell you the arguments the script takes.

# Black Box Auditing

To run GFA on a dataset (as in [Auditing Black-box Models for Indirect Influence](http://arxiv.org/abs/1602.07043)),


## Running as a Python Script

After installing BlackBoxAuditing, GFA can be run on a dataset (as in [Auditing Black-box Models for Indirect Influence](http://arxiv.org/abs/1602.07043)) using a simple python script. For reference, the following includes sample code:

```python
%python
# import BlackBoxAuditing
import BlackBoxAuditing as BBA
# import machine learning technique
from BlackBoxAuditing.model_factories import Weka_SVM, Weka_DecisionTree

"""
Using a preloaded dataset
"""
# load in preloaded dataset
data = BBA.load_data("german")

# initialize the auditor and set parameters
auditor = BBA.Auditor()
auditor.model = Weka_SVM

# call the auditor with the data
auditor(data)


"""
Using your own dataset
"""
# load your own data
datafile = 'path/to/datafile'
data = BBA.load_from_file(datafile)

# initialize the auditor and set parameters
auditor = BBA.Auditor()
auditor.model = Weka_DecisionTree

# call the auditor
auditor(data)

```

### More Advanced Script Options

#### Using a preloaded dataset

The BlackBoxAuditing package has a few datasets preloaded and ready to use for auditing. In a script, they are available via the function `load_data` which takes as input the name of the dataset and returns formatted data ready for auditing. The following is the list of preloaded datasets available for auditing:

* adult
* diabetes
* ricci
* german
* glass
* sample
* DRP

Refer to the Sources section down below for more information about the datasets

#### Using you own dataset

To use your own data for auditing, the function `load_from_file`, most simply, takes as input the path to your dataset and returns formatted data ready for auditing. `load_from_file` also includes other paramters which should be set to ensure that your data is processed correctly. Refer to the full function and its defaults:

```
load_from_file(datafile, testdata=None, correct_types=None, train_percentage=2.0/3.0,
response_header=None, features_to_ignore=None, missing_data_symbol=""
```

* *datafile*: path to your dataset
* *testdata*: path to the dataset used for testing a model. Assumes that *datafile* is the training dtata
* *correct_types*: list of the types (str, int, or float) of the features in the data. If not given, the types will be automatically generated by inspecting the values of each feature
* *train_percentage*: train/test split of the data given as floats
* *response_header*: name of the response column in the data. if not given, assumes that the last column in the data is the response
* *features_to_ignore*: list of the names of any feature than you wish to be ignored by the model
* *missing_data_symbol*: symbol that marks missing or unknown value in the data

#### Auditor options

After initializing the auditor `auditor = BlackBoxAuditor.Auditor()`, there are a few options that can be set to tune the auditor listed as follows:

`auditor.measurers`: (*default = [accuracy, BCR]*) list of measurers to use for GFA

`auditor.model_options`: (*default = {}*) options for machine learning model

`auditor.verbose`: (*default = True*) Set to "True" to allow for more detailed status updates

`auditor.REPAIR_STEPS`: (*default = 10*) Number of repair steps take

`auditor.RETRAIN_MODEL_PER_REPAIR`: (*default = False*)

`auditor.WRITE_ORIGINAL_PREDICTIONS`: (*default = True*)

`auditor.ModelFactory`: (*default = Weka_SVM*) Available machine learning options: Weka_SVM, Weka_DecisionTree, TensorFlow

`auditor.kdd`: (*default = False*)


## Testing Code Changes

After BlackBoxAuditing has been installed, you can run the test suite using the command on a terminal `BlackBoxAuditing-test`.

Every python file should include test functions at the bottom that will be run when the file is run. This can be done by including the line `if __name__=="__main__": test()` as long as there is a function defined as `test`.

These tests should use print statements with `True` or `False` readouts indicating success or failure (where `True` should always be success). It is fine/good to have multiple of these per file.

Note: if a test requires reading data from the `test_data` directory, it should import the appropriate `load_data` file from the `experiments` directory.

## Implementing a New Machine-Learning Method

The best way to create a model would be to use a ModelFactory and ModelVisitors. A ModelVisitor should be thought of as a wrapper that knows how to load a machine-learning model of a given type and communicate with that model file in order to output predicted values of some test dataset. A ModelFactory simply knows how to "build" a ModelVisitor based on some provided training data. Check out the "Abstract" files in the `sample_experiment` directory for outlines of what these two classes should do; similarly, check out the "SVM_ModelFactory" files in the `sample_experiment` subdirectory for examples that use WEKA to create model files and produce predictions.

# Sources

Dataset Sources:
- adult.csv [link](https://archive.ics.uci.edu/ml/datasets/Adult)
- german_categorical.csv (Modified from [link](https://archive.ics.uci.edu/ml/datasets/Statlog+(German+Credit+Data))
- RicciDataMod.csv (Modified from [link](http://www.amstat.org/publications/jse/v18n3/RicciData.csv))
- DRP Datasets (Source and data-files coming soon.)
- Arrests/Recidivism Datasets [link](http://www.icpsr.umich.edu/icpsrweb/RCMD/studies/3355)
- Linear Datasets ("sample_2" Experiment) [link](https://github.com/jasonbaldridge/try-tf)

More information on DRP can be found at the [Dark Reactions Project](http://darkreactions.haverford.edu/) official site.

# Bug Reports and Feature-Requests

All bug reports and feature-requests should be submitted through the [Issue Tracker](https://github.com/cfalk/BlackBoxAuditing/issues).

Project details


Release history Release notifications

History Node

0.1.40

History Node

0.1.39

History Node

0.1.38

History Node

0.1.37

History Node

0.1.36

History Node

0.1.35

History Node

0.1.34

History Node

0.1.33

History Node

0.1.32

History Node

0.1.31

History Node

0.1.30

History Node

0.1.28

History Node

0.1.27

History Node

0.1.26

History Node

0.1.25

History Node

0.1.24

History Node

0.1.23

History Node

0.1.22

History Node

0.1.21

History Node

0.1.20

History Node

0.1.19

History Node

0.1.18

History Node

0.1.17

History Node

0.1.16

History Node

0.1.15

History Node

0.1.14

History Node

0.1.13

History Node

0.1.12

History Node

0.1.11

History Node

0.1.10

History Node

0.1.9

History Node

0.1.8

History Node

0.1.7

History Node

0.1.6

History Node

0.1.5

History Node

0.1.4

History Node

0.1.3

History Node

0.1.2

History Node

0.1.1

History Node

0.1.0

History Node

0.0.9

History Node

0.0.8

History Node

0.0.7

History Node

0.0.6

History Node

0.0.5

History Node

0.0.4

This version
History Node

0.0.3

History Node

0.0.2

History Node

0.0.1

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
BlackBoxAuditing-0.0.3.tar.gz (2.6 MB) Copy SHA256 hash SHA256 Source None Aug 13, 2017

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging CloudAMQP CloudAMQP RabbitMQ AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page