Nischal HP

As data science partner of Hasgeek for the droidconIN 2016 event, a premier android conference held in Bangalore, India, we built a dashboard to understand the social media conversations for the event.

We at Unnati do social media analytics. After talking to people, we found out that setting up a data collection framework was a tedious task. To solve this problem, we built Tweezer. With Tweezer, you can start collecting streaming twitter data in under 5 mins.

Twitter streaming api has no rate limits, so it is simpler to use it. All we need to start collecting data is to have a twitter authorized app. Connect to the streaming api with the authorized app credentials and you are ready to… Mehr anzeigen

We at Unnati do social media analytics. After talking to people, we found out that setting up a data collection framework was a tedious task. To solve this problem, we built Tweezer. With Tweezer, you can start collecting streaming twitter data in under 5 mins.

Twitter streaming api has no rate limits, so it is simpler to use it. All we need to start collecting data is to have a twitter authorized app. Connect to the streaming api with the authorized app credentials and you are ready to fetch tweets in realtime.

We have a handy configuration file designed to manage the authorized app credentials, data store credentials and the tracks to fetch data for (hashtags / keywords)

For the JSFoo event, we used tweezer to fetch the twitter stream for tags related to the event and ran the service for 3 days. Here is the link to the dashboard : http://jsfoo2016.unnati.xyz Weniger anzeigen

After attending many technology conferences around the world and working on social media for a long time, we decided to create a dashboard to understand how a conference evolves over multiple days based on Twitter data.This involved building a temporal based word cloud and sentiment analyzer and ways to understand the top influencers and key topics.

“In theory, there is no difference between theory and practice. But in practice, there is.” - Yogi Berra

Once the task of prototyping a data science solution has been accomplished on a local machine, the real challenge begins in how to make it work in production. To ensure that the plumbing of the data pipeline will work in production at scale is both an art and a science. The science involves understanding the different tools and technologies needed to make the data pipeline connect… Mehr anzeigen

“In theory, there is no difference between theory and practice. But in practice, there is.” - Yogi Berra

Once the task of prototyping a data science solution has been accomplished on a local machine, the real challenge begins in how to make it work in production. To ensure that the plumbing of the data pipeline will work in production at scale is both an art and a science. The science involves understanding the different tools and technologies needed to make the data pipeline connect, while the art involves making the trade-offs needed to tune the data pipeline so that it flows.

In this workshop, you will learn how to build a scalable data science platform with set up and conduct data engineering using Pandas and Luigi, build a machine learning model with Apache Spark and deploy it as predictive api with Flask Weniger anzeigen

We conducted a tutorial introducing Deep Learning and Natural Langauge Processing at Pydata London.

Campaigns are hard to manage as they involve so many moving parts. Having an underlying intelligent platform that will help people manage campaigns by providing a better target audience pool and utilization of money.

This project involves building a robust data engineering pipeline to ensure we are working with the latest data and the system should scale irrespective of the size as data growth has been exponential in nature.

Achieving goals continuously is hard and this is when you need a coach. Coaching at the same time requires a lot of effort and analysis to be done. We merge the beauty of data science and psychometric analysis to enable coaching at scale.

Without using the data generated by your business , you are running blind. We are building a machine learning based credit risk analysis platform to empower better business decisions.

Conducted a workshop for Deep Learning.The workshop consisted of introduction to Artificial Neural Networks and building deep learning neural network models to understand the how it can be used in the field of Natural Language Processing. Build a RNN model to generate blog text as an example.

Framework to get tweets from different locations in the world , analyze the tweets and build a relationship between the tweets. The Idea behind tweetlyze is to see how twitter trends pick up across the world. This project also saw how trends died down and the unreasonable relationships between entities of trends.

The biggest problem in e-commerce is to get customers to buy, the more easy you make the buying the better are the chances of selling. Hence, based on the customer buying patterns built a mechanism of auto populating the cart to provide faster checkouts.

Built the code base to conduct a workshop at Bangpypers to understand how to start data analysis using python and introduction to libraries such as pandas,numpy and stats.

Conducted a workshop for Deep Learning with a Data scientist and a fellow engineer. I was in charge of building deep learning neural network models to understand the how it can be used in the field of Natural Language Processing. Build a RNN model to generate blog text as an example.

Built a sentiment analyzer using Googles state of the art Word2Vec approach. This sentiment analyzer is being used to understand social media content that is generated by customers, thereby helping teams reach out to customers to help them when there is a problem.

This project involves content that can be used to teach Text Mining and Analytics from scratch. Text mining is a huge umbrella that contains a lot of different techniques and use cases. In this project we see the following:

* Regular Expression
* Stopword Removal, Stemming
* Creating features from text
* Term Frequency and Inverse Document Frequency (TF-IDF)
* Visualising text data and models
* Sentiment Analysis (Using Naive Bayes Classifier)
* Topic Modelling - Latent… Mehr anzeigen

This project involves content that can be used to teach Text Mining and Analytics from scratch. Text mining is a huge umbrella that contains a lot of different techniques and use cases. In this project we see the following:

* Regular Expression
* Stopword Removal, Stemming
* Creating features from text
* Term Frequency and Inverse Document Frequency (TF-IDF)
* Visualising text data and models
* Sentiment Analysis (Using Naive Bayes Classifier)
* Topic Modelling - Latent Dirichlet Allocation (LDA) Weniger anzeigen