Mencoba scikit-learn terbaru

Python di komputer saya diinstall dengan  Anaconda 4.3.1, dengan versi Python 3.6. Namun scikit-learn bawaaannya masih versi lama, jadi mesti install dulu scikit-learn terbaru. Lumayan juga mesti download sebanyak 151 MB.

Microsoft Windows [Version 6.1.7601]
Copyright (c) 2009 Microsoft Corporation.  All rights reserved.

C:\Windows\system32>pip install seaborn
Collecting seaborn
Installing collected packages: seaborn
Successfully installed seaborn-0.7.1

C:\Windows\system32>conda install scikit-learn
Fetching package metadata ...........
Solving package specifications: ..........

Package plan for installation in environment C:\Program Files\Anaconda3:

The following packages will be downloaded:

    package                    |            build
    ---------------------------|-----------------
    conda-env-2.6.0            |                0          498 B  defaults
    mkl-2017.0.1               |                0       128.8 MB  defaults
    numpy-1.12.1               |           py35_0         3.5 MB  defaults
    requests-2.13.0            |           py35_0         823 KB  defaults
    numexpr-2.6.2              |      np112py35_0         125 KB  defaults
    scipy-0.19.0               |      np112py35_0        12.8 MB  defaults
    scikit-learn-0.18.1        |      np112py35_1         4.5 MB  defaults
    pyopenssl-16.2.0           |           py35_0          70 KB  defaults
    conda-4.3.16               |           py35_0         553 KB  defaults
    ------------------------------------------------------------
                                           Total:       151.1 MB

The following NEW packages will be INSTALLED:

    conda-env:    2.6.0-0            defaults

The following packages will be UPDATED:

    conda:        4.2.9-py35_0       defaults --> 4.3.16-py35_0      defaults
    mkl:          11.3.3-1           defaults --> 2017.0.1-0         defaults
    numexpr:      2.6.1-np111py35_0  defaults --> 2.6.2-np112py35_0  defaults
    numpy:        1.11.1-py35_1      defaults --> 1.12.1-py35_0      defaults
    pyopenssl:    16.0.0-py35_0      defaults --> 16.2.0-py35_0      defaults
    requests:     2.11.1-py35_0      defaults --> 2.13.0-py35_0      defaults
    scikit-learn: 0.17.1-np111py35_1 defaults --> 0.18.1-np112py35_1 defaults
    scipy:        0.18.1-np111py35_0 defaults --> 0.19.0-np112py35_0 defaults

Proceed ([y]/n)? y

Fetching packages ...
conda-env-2.6. 100% |###############################| Time: 0:00:00 165.99 kB/s
mkl-2017.0.1-0   0% |                               | Time: 0:00:00   1.14 MB/s

Referensi

• http://bugra.github.io/work/notes/2014-11-22/an-introduction-to-supervised-learning-scikit-learn/
• http://scikit-learn.org/stable/modules/neural_networks_supervised.html
• A Beginner’s Guide to Neural Networks with Python and SciKit Learn 0.18! http://www.kdnuggets.com/2016/10/beginners-guide-neural-networks-python-scikit-learn.html