Testing ML models has never been easier

  • checkmark Run all common test methods with one command
  • checkmark Easily share the results with colleagues and stakeholders
  • checkmark Compare the test results over time
GitHub Repo
illustration

Learn More About Our Project And Team

Not testing and explaining machine learning models can lead to significant consequences and negative publicity.

“The algorithm repeatedly sent officers to neighborhoods with a high proportion of racial minotrities regardless of the true crime rate of the areas.”

2016

“The image recognition algorithms in Google Photos were classifying black people as gorillas.”

2017

wired

“The algorithm reportedly downgraded resumes containing the words "women's" and filtered out candidates who had attended women-only colleges.”

2018

With Algoneer you can build systems that are robust, fair and understandable.

Automate testing of ML systems

Share and track your results

Run locally and in the cloud

Get reliable and actionable results

Open-Source

MIT license

Enterprise ready

Access control

Easily extensible

Plug & Play

Continous testing

coming soon

You can freely use Algoneer within your organization and inspect the entire codebase.

We keep adding and improving test methods and other modules of Algoneer, so your ML testing gets better and more insightful without any effort.

Workflow

1. Tell Algoneer about your data

First, use Algoneer's data schema description capabilities to annotate your data.

from algoneer import DataSchema, AttributeSchema as AS

class MySchema(DataSchema):

  temperature = AS(type=AS.Numerical, roles=["x"])
  humidity = AS(type=AS.Numerical, roles=["x"])
  count = AS(type=AS.Numerical, roles=["y"])

2. Load your dataset

Next up you load your dataset. Algoneer supports pandas dataframes (more formats coming soon).

from algoneer.dataset.pandas import PandasDataset
import pandas as pd

#Import your dataset
df = pd.read_csv("my-data.csv")

dataset = PandasDataset(df)

3. Connect your ML models

To manage your ML models and algorithms with Algoneer. Currently, Algoneer supports sklearn algorithms, with more libraries (tensorflow, pytorch) coming soon.

from algoneer.algorithm.sklearn import SklearnAlgorithm

from sklearn.ensemble import RandomForest

algo = SklearnAlgorithm(RandomForest, n_estimators=100)
model = algo.train(dataset)

4. Test your models & data

Using the data and algorithm schemas that you defined, Algoneer can automatically run tests on your models and datasets. Results can be viewed and analyzed offline or sent to the Algonaut API.

# Test machine learning models
model_results = model.test()
# Test datasets
dataset_results = dataset.test()
for name, result in model_results.items():
  print(result.format('text'))

Technical Specs

Tests

Explainability: LIME, SHAP, PDP, ALE

Robustness, Bias, Security: coming soon

Data libraries

Pandas

Supported libraries

Scikit-learn TensorFlow Keras

Supported model types

Classification

Regression

Supported data types

Categorical

Numerical

Supported languages

Python

License

MIT License

Ready for a new level of testing?

1. Install the Python library

pip install algoneer

2. Read our Get started guide

Open Docs

3. Join the Algoneer cloud beta

illustration