The post BSi Steel sees 20% growth thanks to digital transformation with KAISPE and Microsoft products appeared first on KAISPE.

With Azure Machine Learning, rapidly build and deploy machine learning models using tools that meet your needs regardless of skill level. Use the no-code designer to get started, or use built-in Jupyter notebooks for a code-first experience. Accelerate model creation with the automated machine learning UI, and access built-in feature engineering, algorithm selection, and hyperparameter sweeping to develop highly accurate models.

Power BI tranforms your company’s data into rich visuals for you to collect and organize so you can focus on what matters to you. Stay in the know, spot trends as they happen, and push your business further.

You can find more about the dashboard here.

The post KAISPE Employee Churn Dashboard appeared first on KAISPE.

In today’s blog we will discover some useful insights about using a created model on Azure Machine Learning Studio and call that model in our power bi so we have data in power bi and use that API as a tool for machine learning.

Before we move any further let me remind you that there are various options to consume machine learning in power bi but for this blog post we will only be covering couple of them.

So, first we will be covering Microsoft Standard to invoke an Azure Machine Learning Studio (classic) model into Power BI. Here the following steps you can follow to invoke a machine learning model into power bi:
1- create an Azure ML model if you don’t already have a model and publish it.
2- Next we have to access  Azure Machine Learning model from power bi, To do that we have to get a Reader role from Azure subscription.
3- Now we have to create a Dataflow in power bi whom you granted access to Azure Machine Learning Model. After you signed in:
– create a workspace and navigate to a workspace on your dedicated capacity that has
the AI preview enabled and Select Add new entities.
– Upload the dataset Text/CSV File as our data source
4- In the last step we will apply insights from Azure Machine Learning model, navigate to AI Insights button in the ribbon, and from Azure Machine Learning Models folder navigate to the Azure ML models to which you’ve been granted access are listed as Power Query functions with a prefix AzureML.

To invoke an Azure Machine Learning model, we will specify our input parameters such as (timestamp, air pressure, angular speed, piston speed and piston vibration). In last step, select Invoke to view the preview of the Azure ML model’s output as a new column in the entity table.

Now, we can also consume a machine learning webservice in power bi which is much easier to integrate for free. To achieve the task, we have to follow these steps:
1- You should have an Azure Machine Learning model and deployed as a webservice.
2- Import the dataset from your local computer and navigate to the query editor
3- next we need to navigate to the Run R script where we connect our Azure Machine Learning model with Power BI. For the following step you have to have the following credentials from Azure Machine Learning Studio workspace: (1) workspace Id (2) Authentication token (3) Service name. Next hit the OK button to view the result in output column.

I hope you found this blog post helpful. If you have any questions, please feel free to contact info@kaispe.com.

The post Microsoft Power BI and Azure Machine Learning appeared first on KAISPE.

First of all, we need to install the Visual Studio Code and Node JS to set up the Lab Environment. Then use the Azure subscription we have so we can create the Azure side of IoT components.

Afterward, we create a Resource Group and Azure IoT Hub service using Azure Portal.

Ok, now its time to set up the hardware and register it with IoT hub. For this post, we will be using Raspberry Pi 3. We need to install the OS Raspbian Jessie on our Raspberry Pi device.

To configure the connection string, I have used Visual Studio Code and make sure that my VS code uses the bash on Ubuntu (on Windows) shell in Integrated Terminal Panel. Below is the code snippet to get Raspberry Pi connected with IoT Hub:

After we build and run the code, we must be able to send messages from Raspberry Pi to Azure IoT Hub as you can see below:

Awesome! Now as you can see the IoT Hub shows messages and a connected device, which in this case is our Raspberry Pi.

Now let’s connect a Photocell Sensor with our IoT device, so we can get some real data from the device. For this scenario, we are using the Light Dependent Resistor (LDR).

We will give different manual inputs to the sensor, so we can have brightness data to analyze.

Finally, we get reading from the photocell sensor to the cloud. However, we receive continuous data in the cloud as the sensor keeps emitting brightness readings and we cannot just use it as is, so how to handle it? We will use Stream Analytics that makes it easier to set up real-time data computation.

In order to configure Stream Analytics, we need to configure Input, Output, and Query to get the required data. We will also create a Service bus queue for data storage and perform Stream Analytics on it.

Stream Analytics Input:

Events from a data source are called Input. So, we will create a Stream Analytics Job in which we can use one of the following sources as an input for the Job.

• Blob Storage
• IoT Hub
• Event Hub

In our Scenario, we are using IoT Hub. IoT Hub is used to collect data from connected devices and provide two-way communication between Cloud to Device and Device to Cloud.

Stream Analytics Output:

Stream Analytics job takes incoming data and converts it to a stream of Data Output events. The processed data can be used on real time dashboard, to generate alerts or for batch processing.

Now let’s create a Stream Analytics job. We can use one of the following sources as Output for the job.

• Azure Data Lake Store
• Azure SQL Database
• Blob Storage
• Event Hub
• Table Storage
• Service Bus Queue
• Service Bus Topic
• Azure Cosmos DB
• etc.

In our Scenario, we will use Service Bus Queue. It offers FIFO (First In First Out) method and scalable message structure.

Stream Analytics Query:

Now the final part of our Stream Analytics Job is Query where we will specify the logic of our Stream Analytics job. The good thing is Stream Analytics Query syntax is very similar to the Structured Query Language (SQL), so you can easily write the queries here.

Our Stream Analytics query is:

SELECT

    brightness

INTO

    [ServiceBusQueue]

FROM

    [Hub]

WHERE

    brightness > 5

If we now run the Stream Analytics job, it will only show the data where brightness is greater than 5 and filter out the rest of the output messages.

So, as you can see above, it shows 80 input events and 44 output events because of the filtering we have done using Stream Analytics query.

Next is we want to visualize the data using some kind of BI dashboard, so we can have better insights. For this purpose, let’s use Microsoft Power BI.

Following are the steps to create a Power BI dashboard:

• Create a dashboard using Power BI desktop application
• Add a Consumer Group to our IoT Hub. The consumer group is used by all applications to read data from Azure IoT hub
• Use the same Stream Analytics Job as we created above and have Power BI as the Output of job
• Once the above steps are completed, we can visualize Real-Time data into our dashboard

I hope you have found this blog post helpful. For any queries, please feel free to contact me farrukh.ahmed@kaispe.com.

The post Visualize Real-Time Device Data using Microsoft Azure IoT and Power BI Dashboard appeared first on KAISPE.