R | Dutch Data Dude

Adding sequence numbers using R in Azure ML

on August 16, 2016

When going through data preparation sometimes sequence numbers need to be added. If you are like me, you probably spent some time looking for a component in Azure ML to do this. I never found it.

Turns out it is really easy to do this in R and as a result also very easy to do in Azure ML.

In your experiment, add an Execute R Script component and connect it to the data flow.

Edit the script and add a column to the dataset that equals:

seq.int(nrow(dataset1))

1	seq.int(nrow(dataset1))

See my code example:

# Map 1-based optional input ports to variables]
dataset1 <- maml.mapInputPort(1) # class: data.frame
dataset1$time=seq.int(nrow(dataset1)) 
# Select data.frame to be sent to the output Dataset port 
maml.mapOutputPort("dataset1");

# Map 1-based optional input ports to variables]

dataset1 <- maml.mapInputPort(1) # class: data.frame

dataset1$time=seq.int(nrow(dataset1))

# Select data.frame to be sent to the output Dataset port

maml.mapOutputPort("dataset1");

On the third line the column is added and defined as a sequence number. The resulting dataset indeed has an extra column (called time) that like this:

The small histogram at the top and the details that right confirm it has only unique values and starts at 1; our sequence column has been added!

R package for Azure Machine Learning

on September 15, 2015

by Jeroen ter Heerdt 0 Comments

A little while ago an R package for AzureML was released, which enables R users to interface with Azure Machine Learning (Azure ML). Specifically, it enables you to easily use one of the coolest features of Azure ML: publishing and consuming algorithms / experiments as web services.

Check it out: https://cran.r-project.org/web/packages/AzureML/vignettes/AzureML.html.

R Plotting using Azure Machine Learning

on January 20, 2015

by Jeroen ter Heerdt 0 Comments

Azure Machine Learning is Microsoft’s cloud data mining and machine learning solution. It features a studio that is fully web based. One of the best features is integration with R through the ‘Execute R Script’ component. One of the best things of R is the plotting capability and I recently decided to try to make R plots from Azure ML studio. It is amazing how easy this works and it really brings the power of Azure ML together with the great exploration, plotting and data manipulation capabilities of R.

Here is a very simple sample I made:

I used to Flight Delays sample dataset from Azure ML to make this. In the ML Studio you will need to create a new experiment and drag the ‘Flight Delays Data’ component to the canvas. The only other component you will need to drop on the canvas is ‘Execute R Script’ (I told you this was a very simple example). Drag a line from the data to the left most input port of the R script container like so:

Click on the R script component and edit the R script on the right. Here is my script:

dataset1 &lt;- maml.mapInputPort(1);
data.set = rbind(dataset1);
with(data.set,plot(DepDelay ~ DayOfWeek, col = "blue", pch = 20));
aml.mapOutputPort("data.set");

dataset1 <- maml.mapInputPort(1);

data.set = rbind(dataset1);

with(data.set,plot(DepDelay ~ DayOfWeek, col = "blue", pch = 20));

aml.mapOutputPort("data.set");

This script gets the data from the input port and rbinds it into data.set. Then I executed a very simple plot using the plot base R package to create the plot shown above. The last line of this code is not even necessary but it was there by default.

After running the experiment the plot can be seen by selecting the right output port of the ‘Execute R Script’ container and selecting ‘Visualize’: