Keras Deep Learning

 

Rapidminer has recently launched the Keras deep learning extension that allows users to easily access, and implementing deep learning components within their model in Rapidminer.

With this extension, Keras offers users a set of operators that allows an easy visual representation of deep learning network structures and layers. The operators offered from Keras calculate through a python based backend library in which the users have the option to leverage the computing power of GPUs and grid environments.

The basic idea behind Keras is to allow users to enable fast experimentation with deep learning. The operators provided in the extension offers a more focused approach to deep learning or Deep Neural Networks (DNN). The basic of machine learning to the majority composes of task-specific algorithms. While this can be relatively simple and clear cut, these algorithms have its limitations. Deep learning on the other hand is an approach based on feature learning that is a system, which automatically detects representation, and classify from the given data. From this, the classification obtained will be inputted into a neural net, which is loosely based on biological brain functions such as information processing and communication patterns. Deep learning has been in fact utilized in a wide range of fields such as: computer vision, speech recondition, and natural language processing.

The following information showcases several options to obtain Keras extension for Rapidminer.

Anaconda on MacOS

1.Download and install Anaconda from:https://www.continuum.io/downloads#macos

2.Create a new environment by typing in command line:conda create -n keras

3.Activate the created environment by typing in the command line:source activate keras

4.Install pandas by typing in the command line:conda install pandas

5.Install scikit-learn by typing in the command line:conda install scikit-learn

6.Install keras by typing in the command line:conda install -c conda-forge keras

7.Install graphviz by typing in the command line:conda install -c anaconda graphviz

8.Install pydotplus by typing in the commandline :conda install –c anaconda graphviz

9.9.In RapidMiner Studio Keras and Python Scripting panels in preferences, specify the path to your new conda environment Python executable.


Anaconda on Windows

Warning: Due to issues with package dependencies, it is not currently possible to install graphviz and pydot in a conda environment on Windows, and consequently to visualise the model graph in the results panel.

1.Download and install Anaconda from:https://www.continuum.io/downloads#windows

2.Create a new environment with Python 3.5.2 by typing in command line:conda create -n Python35 python = 3.5.2

3.Activate the created environment by typing in the command line:activate Python35

4.Install pandas by typing in the command line:conda install pandas

5.Install scikit-learn by typing in the command line:conda install scikit-learn

6.Install keras by typing in the command line:conda install -c jaikumarm keras = 2.0.4

7.In RapidMiner Studio Keras and Python Scripting panels in preferences, specify the path to your new conda environment Python executable.


Windows 

1.Download and install Python 3.5.2:https://www.python.org/downloads/release/python-352/

Only python 3.5.2 works for windows.

2.Install numpy with Intel Math Kernel library.

•Download the file 13.1+mklcp35cp35mwin_amd64.whl from http://www.lfd.uci.edu/~gohlke/pythonlibs/#numpy

•cd to the directory where you have downloaded the file and from the command line run:pip3 install 13.1 + mklcp35cp35mwin_amd64.whl

3.Install pandas from the command line:pip3 install pandas

4.Install graphviz from the command line:pip3 install graphviz

5.Install pydot from the command line:pip3 install pydot

6.nstall TensorFlow.

•If you would like to install TensorFlow with GPU support, please see the instructions here:https://www.tensorflow.org/install/install_windows

•If you would like to install TensorFlow only with CPU support, from the command line run:pip3 install -upgrade tensorflow

7.Install Keras from the command line:pip3 install keras 


Rapidminer Extension                 

1.Install the Keras extension from the RapidMiner Marketplace

2.Install RapdiMiner Python Scripting extension from the marketplace if not already installed.

3.Restart RapidMiner Studio.

4.Inside your Studio Client go to Settings (Menu) > Preferences and navigate to “Python Scripting” tab/page on the left. Provide path to Python executable and click test to ensure it is successful.

5.Inside your Studio Client go to Settings (Menu) >Preferences and navigate to “Keras” tab/page on the left. Provide path to Python executable and click test to ensure it is successful.


Sample Processes