Metadata-Version: 2.1
Name: blocktorch
Version: 1.33.2
Summary: Blocktorch is a library that builds, optimizes, and evaluates machine learning pipelines
Home-page: https://github.com/blocktorch/blocktorch
Author: Blocktorch
Author-email: mike.w.casale@blocktorch.ai
License: UNKNOWN
Platform: UNKNOWN
Description-Content-Type: text/markdown
Requires-Dist: numpy (>=1.20.0)
Requires-Dist: numba (==0.53)
Requires-Dist: pandas (>=1.2.5)
Requires-Dist: scipy (>=1.5.0)
Requires-Dist: scikit-learn (>=0.24.0)
Requires-Dist: scikit-optimize (>=0.8.1)
Requires-Dist: pyzmq (>=20.0.0)
Requires-Dist: colorama (>=0.4.4)
Requires-Dist: cloudpickle (>=1.6.0)
Requires-Dist: click (>=7.1.2)
Requires-Dist: psutil (>=5.6.6)
Requires-Dist: requirements-parser (>=0.2.0)
Requires-Dist: shap (>=0.36.0)
Requires-Dist: texttable (>=1.6.2)
Requires-Dist: woodwork (<=0.8.1,>=0.6.0)
Requires-Dist: dask (==2021.7.0)
Requires-Dist: optuna (==2.3.0)
Requires-Dist: dask-optuna
Requires-Dist: dask-ml
Requires-Dist: featuretools (>=0.26.1)
Requires-Dist: nlp-primitives (>=1.1.0)
Requires-Dist: networkx (<2.6,>=2.5)
Requires-Dist: plotly (>=5.0.0)
Requires-Dist: kaleido (>=0.1.0)
Requires-Dist: ipywidgets (>=7.5)
Requires-Dist: xgboost (>=1.4.2)
Requires-Dist: lightgbm (>=2.3.1)
Requires-Dist: matplotlib (>=3.3.3)
Requires-Dist: seaborn (>=0.11.1)
Requires-Dist: category-encoders (>=2.2.2)
Requires-Dist: statsmodels (>=0.12.2)
Requires-Dist: imbalanced-learn (>=0.8.0)
Requires-Dist: pmdarima (==1.8.0)
Requires-Dist: graphviz (>=0.13) ; platform_system != "Windows"
Requires-Dist: sktime (>=0.7.0) ; python_version < "3.9"
Provides-Extra: complete
Requires-Dist: alteryx-open-src-update-checker (>=2.0.0) ; extra == 'complete'
Requires-Dist: cmdstan-builder (==0.0.4) ; extra == 'complete'
Provides-Extra: prophet
Requires-Dist: cmdstan-builder (==0.0.4) ; extra == 'prophet'
Provides-Extra: update_checker
Requires-Dist: alteryx-open-src-update-checker (>=2.0.0) ; extra == 'update_checker'

<p align="center">
<img width=50% src="https://jamesturrell.com/wp-content/uploads/2015/11/Stufe-White-1967_Sergio-Martucci1.jpg" alt="Blocktorch" />
</p>

[![GitHub Actions](https://github.com/blocktorch/actions/workflows/linux_unit_tests.yml/badge.svg?branch=main)](https://github.com/blocktorch/actions/workflows/linux_unit_tests.yml?query=branch%3Amain)
[![Codecov.io](https://codecov.io/gh/blocktorch/branch/main/graph/badge.svg?token=JDc0Ib7kYL)](https://codecov.io/gh/blocktorch)
[![PyPI](https://badge.fury.io/py/blocktorch.svg?maxAge=2592000)](https://badge.fury.io/py/blocktorch)
[![PyPI Stats](https://img.shields.io/pypi/dm/blocktorch.svg)](https://pypistats.org/packages/blocktorch)

blocktorch is an AutoML library which builds, optimizes, and evaluates machine learning pipelines using domain-specific objective functions.

**Key Functionality**

* **Automation** - Makes machine learning easier. Avoid training and tuning models by hand. Includes data quality checks, cross-validation and more.
* **Data Checks** - Catches and warns of problems with your data and problem setup before modeling.
* **End-to-end** - Constructs and optimizes pipelines that include state-of-the-art preprocessing, feature engineering, feature selection, and a variety of modeling techniques.
* **Model Understanding** - Provides tools to understand and introspect on models, to learn how they'll behave in your problem domain.
* **Domain-specific** - Includes repository of domain-specific objective functions and an interface to define your own.

## Install [from PyPI](https://pypi.org/project/blocktorch/)
```shell
pip install blocktorch
```
### Add-ons

#### Update checker

Receive automatic notifications of new blocktorch releases
```shell
pip install blocktorch[update_checker]
```

## Start

#### Load and split example data 
```python
import blocktorch
X, y = blocktorch.demos.load_breast_cancer()
X_train, X_test, y_train, y_test = blocktorch.preprocessing.split_data(X, y, problem_type='binary')
```

#### Run AutoML
```python
from blocktorch.automl import AutoMLSearch
automl = AutoMLSearch(X_train=X_train, y_train=y_train, problem_type='binary')
automl.search()
```

#### View pipeline rankings
```python
automl.rankings
```

#### Get best pipeline and predict on new data
```python
pipeline = automl.best_pipeline
pipeline.predict(X_test)
```

## Next Steps

Read more about blocktorch on our [documentation page](https://blocktorch.ai/):

* [Installation](https://blocktorch.ai/en/stable/install.html) and [getting started](https://blocktorch.ai/en/stable/start.html).
* [Tutorials](https://blocktorch.ai/en/stable/tutorials.html) on how to use blocktorch.
* [User guide](https://blocktorch.ai/en/stable/user_guide.html) which describes blocktorch's features.
* Full [API reference](https://blocktorch.ai/en/stable/api_reference.html)

## Built by Blocktorch
<a href="https://www.blocktorch.ai">
    <img width=50% src="https://jamesturrell.com/wp-content/uploads/2015/11/Stufe-White-1967_Sergio-Martucci1.jpg" alt="Blocktorch" />
</a>


