Metadata-Version: 2.0
Name: photonai
Version: 2.0.0
Summary: 
Requires-Dist: dask
Requires-Dist: distributed
Requires-Dist: imbalanced-learn
Requires-Dist: joblib
Requires-Dist: keras
Requires-Dist: matplotlib
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: plotly
Requires-Dist: prettytable
Requires-Dist: pymodm
Requires-Dist: scikit-learn
Requires-Dist: scikit-optimize
Requires-Dist: scipy
Requires-Dist: seaborn
Requires-Dist: statsmodels

PHOTONAI
is a rapid prototyping framework enabling (not so experienced) users to build, train, optimize, evaluate,
and share even complex machine learning (ML) pipelines with very high efficiency.

By pre-registering state-of-the-art ML implementations, we create a system in which the user can select 
and arrange processing steps and learning algorithms in simple or parallel pipeline data streams. 

Importantly, PHOTONAI is capable to automatize the training and testing procedure including nested cross-validation and 
hyperparameter search, calculates performance metrics and conveniently visualizes the analyzed hyperparameter space.

It also enables the user persist and load your optimal model, including all preprocessing elements, 
with only one line of code.

Home-page: https://github.com/mmll-wwu/photonai.git
Author: PHOTONAI Team
Author-email: hahnt@wwu.de
License: UNKNOWN
Download-URL: https://github.com/wwu-mmll/photonai/archive/2.0.0.tar.gz
Description: UNKNOWN
Keywords: machine learning,deep learning,neural networks,hyperparameter
Platform: UNKNOWN
