This is a set of tutorials for uisng pyDAAL, i.e. the Python API of Intel Data Analytics Acceleration Library. It is designed to provide a quick introduction to pyDAAL features and the API for Python developers who are already familiar with basic concepts and techniques in machine learning.

The tutorials are spread across a collection of Jupyter notebooks. The proper way of using these notebooks is to install Intel Distribution for Python on your computer, which consists of a large set of commonly used mathematic and statistical Python packages that are optimized for Intel architectures.

1. Install the latest version of Anaconda.

   • Choose the Python 3.5 version

2. From the shell prompt (on Windows, use Anaconda Prompt), execute these commands:

   conda config --add channels intel
   conda create --name idp intelpython3_full python=3
   source activate idp (on Linux and OS X)
   activate idp (on Windows)

More detailed instructions can be found from this online article.

• Data management in pyDAAL
• K-Means and PCA
• Linear regression
• SVM and multi-class classifier

Data files used in the tutorials are in the ./mldata folder. These data files are downloaded from the UCI Machine Learning Repository.