Skip to main content

MindsDB's goal is to make it very simple for developers to use the power of artificial neural networks in their projects.

Project description

MindsDB

Python supported PyPi Version PyPi Downloads MindsDB Community MindsDB Website

MindsDB is an Explainable AutoML framework for developers built on top of Pytorch. It enables you to build, train and test state of the art ML models in as simple as one line of code. Tweet

MindsDB Linux build
Windows build
macOS build

Try it out

Installation

  • Desktop: You can use MindsDB on your own computer in under a minute, if you already have a python environment setup, just run the following command:
 pip install mindsdb --user

Note: Python 64 bit version is required. Depending on your environment, you might have to use pip3 instead of pip in the above command.*

If for some reason this fail, don't worry, simply follow the complete installation instructions which will lead you through a more thorough procedure which should fix most issues.

  • Docker: If you would like to run it all in a container simply:
sh -c "$(curl -sSL https://raw.githubusercontent.com/mindsdb/mindsdb/master/distributions/docker/build-docker.sh)"

Usage

Once you have MindsDB installed, you can use it as follows:

Import MindsDB:

from mindsdb import Predictor

One line of code to train a model:

# tell mindsDB what we want to learn and from what data
Predictor(name='home_rentals_price').learn(
    to_predict='rental_price', # the column we want to learn to predict given all the data in the file
    from_data="https://s3.eu-west-2.amazonaws.com/mindsdb-example-data/home_rentals.csv" # the path to the file where we can learn from, (note: can be url)
)

One line of code to use the model:

# use the model to make predictions
result = Predictor(name='home_rentals_price').predict(when={'number_of_rooms': 2,'number_of_bathrooms':1, 'sqft': 1190})

# you can now print the results
print('The predicted price is ${price} with {conf} confidence'.format(price=result[0]['rental_price'], conf=result[0]['rental_price_confidence']))

Visit the documentation to learn more

  • Google Colab: You can also try MindsDB straight here Google Colab

Video Tutorial

Please click on the image below to load the tutorial:

here

(Note: Please manually set it to 720p or greater to have the text appear clearly)

MindsDB Graphical User Interface

You can also work with mindsdb via its graphical user interface (download here). Please click on the image below to load the tutorial:

here

MindsDB Lightwood: Machine Learning Lego Blocks

Under the hood of mindsdb there is lightwood, a Pytorch based framework that breaks down machine learning problems into smaller blocks that can be glued together seamlessly. More info about MindsDB lightwood's on GITHUB.

Contributing

In order to make changes to mindsdb, the ideal approach is to fork the repository than clone the fork locally PYTHONPATH.

For example: export PYTHONPATH=$PYTHONPATH:/home/my_username/mindsdb.

To test if your changes are working you can try running the CI tests locally: cd tests/ci_tests && python3 full_test.py

Once you have specific changes you want to merge into master, feel free to make a PR.

Report Issues

Please help us by reporting any issues you may have while using MindsDB.

License

Project details


Release history Release notifications | RSS feed

Download files

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

Source Distribution

MindsDB-1.16.0.tar.gz (63.6 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page