Skip to main content

Posts

Data Cleansing Tools in Azure Machine Learning

Recent posts

Microsoft Bot Framework Basics: Building Intelligent Bots – Adding Sentiment Analytics (Part 4)

ScopeThe following articles demonstrates the use of the Text Analytics API from Microsoft Cognitive Services in a bot using the Microsoft Bot Framework. This article will build on the previous articles about Bot Framework where the basics of building a bot,  the integration of Language Understanding API and Bing News API was demonstrated.
The objective of this article is to demonstrate how the bot can use sentiment analytics to determine whether a news item is positive or negative and reply the user accordingly. Text Analytics APIText Analytics API is a suite of text analytics Services built with Azure Machine Learning. It currently offers APIs for sentiment analysis, key phrase extraction, and topic detection for English text, as well as language detection for 120 languages.

Microsoft Bot Framework Basics: Building Intelligent Bots – Adding Bing News API (Part 3)

Scope The following articles demonstrates the use of the Bing News API from Microsoft Cognitive Services in a bot using the Microsoft Bot Framework. This article will build on the previous articles about Bot Framework where the basics of building a bot and the integration of Language Understanding API was demonstrated.
The objective is to allow a user to send a message to the bot, the bot will use language understanding capability to understand the message, fetch news based on the user input using Bing API and return the results to the user. Introduction The News API provides a similar (but not exact) experience to Bing.com/News. The News API lets you send a search query to Bing and get back a list of relevant news articles.
Bing News API also includes authoritative images of the news article, related news and categories, provider information, article URLs, and dates when images were added.
Adding the Bing News API At this stage, we have setup our project and we have successfully impleme…

Microsoft Bot Framework Basics: Building Intelligent Bots - Adding Language Understanding Capability (Part 2)

Scope
The following article demonstrates how to use LUIS to add conversational intelligence to your apps. The focus will be about creating and consuming Language Understanding Models. We'll add Language Understanding capabilities to the news bot from the previous article. After this article, the bot will be able to interpret English language and map sentences to specific functions in the code.

Introduction Microsoft’s Language Understanding Intelligent Service (LUIS) offers a fast and effective way of adding language understanding to applications. With LUIS, you can use pre-existing, world-class, pre-built models from Bing and Cortana whenever they suit your purposes – and when you need specialized models, LUIS guides you through the process of quickly building them. Before proceeding, it is important that you understand the basic concepts of LUIS.
a. Intents: Consider intent as an intention or action. What action should a sentence trigger? Search for a news? Look for help? Procee…

C# Corner Conference 2017 - Building Intelligent Bots

The C# Corner Annual Conference 2017 was a three-day annual event for software professionals and developers held in New Delhi, India. First day was exclusive for C# Corner MVPs only. The second day was open to the public, and includes presentations from many top names in the industry. The third day events are, again, exclusively for C# Corner MVPs.

The conference was awesome with about 600+ attendees in total. There were 3 tracks running in parallel each having a accommodating 200+ attendees.




Cloud, IoT, & Future of Tech Conference - Getting Started with Machine Learning

In April 2017 I was invited to speak at the C# Corner Conference in Delhi, India. As part of this trip, the organizers also invited me to speak at the Cloud, IoT, & Future of Tech Conference at the GLA University in Mathura, India.
Mathura is a city in the North Indian state of Uttar Pradesh and is about 5 hours drive from Delhi where I was staying. So, we had to wake up at 5 am and leave the hotel at 6 am to have a chance to speak at the conference at about 11. Yes - that's a long drive, but worth it! We could admire the nature and culture of the country while travelling from a city to a more rural area. We also had a great chat with our friend from the C# Corner team Ravi who explained us a lot about India and the culture. That was just some story about the trip:)


Well, we reached the university at about 11:30 and as we stepped in, we were all surprised by the big banner having all the speaker's names. Our surprise does not end here! As we entered the conference room, th…

Developers Conference 2017 - Improving Machine Learning Models

The third edition of the developers conference of Mauritius was held between the 30th of March and 1st of April 2017. The conference ran on 3 days with 3 tracks in parallel and had about 330+ attendees and 50+ speakers.
My third session at the DevCon was about the techniques that can be used to improve the performance of machine learning models. The session was just after the introduction to Data Science that was presented by Arwin and myself.


I started with a summary of the data science process and presented the data set that shall be used in the demo. Next, I explained the steps of data cleansing and made a live demo of same. The attendees were quite surprised that the model got an increase in accuracy of 10% just by doing the cleansing properly. I then proceeded with more advanced techniques such as Feature Selection, Feature Scaling, Parameter Tuning and Cross Validation.