MateriApps
A Portal Site of Materials Science Simulation

now 307 Apps

Inquiry / Application Request
Detailed search

scikit-learn

  • Openness:3 ★★★
  • Document quality:3 ★★★

An open-source library for data mining and data analysis. This package implements various methods of machine learning such as supervised learning (data classification, data regression, etc.), unsupervised learning (data clustering, etc.), and data pre-processing. This package is implemented on Python numerical libraries, NumPy and Scipy, and supports parallel computation.

Tutorial of materials informatics using MateriApps LIVE! and scikit-learn
Last Update:2021/12/09
You already voted!

Author: MateriApps Development Team (2020/2/18 updated)

Materials for tutorial of materials informatics with scikit-learn is being developed by Dr. H. Kino at NIMS.

• https://bitbucket.org/kino_h/mi_python_tutorial_2020_public

In this document, we explain how to set up the environment for tutorials on MateriApps LIVE! and how to run the tutorials.

Version of software:

  • MateriApps LIVE! version 2.4 (Debian Stretch, Python 3.5.3)
  • scikit-learn 0.18

Installation of tools:

    • unzip, pandas, seaborn 
      $ sudo apt install zip python3-pandas python3-seaborn
    • cython 
      $ sudo pip3 install cython

 

  • pybtex, pymatgen, pymc3 
    $ sudo pip3 install pybtex pymatgen pymc3==3.6
  • scikit-learn 
    $ sudo apt install python3-sklearn

Download and extraction of tutorial materials:

$ wget https://bitbucket.org/kino_h/mi_python_tutorial_2020_public/get/10b86d126f56.zip
$ unzip 10b86d126f56.zip

Running tutorials:

$ cd kino_h-mi_python_tutorial_2020_public-10b86d126f56
$ ipython notebook

There is a list of tutorials in 0000.0010.Contents.ipynb. Tutorials for regression, clustering, classification, dimension reduction, exhaustive search, image reconstruction, structure search, Bayesian optimization, Bayesian regression are provided.

TOP