Shivam Bansal's Blog

Full Stack Data Scientist; Kaggle Kernels Grandmaster (Current Rank : 2)
Machine Learning; Deep Learning; NLP; Visualizations; Core Analytics; Product Engineering; Data Pipelining;

Kaggle GitHub LinkedIn

Get Started with PyTorch – Learn How to Build Quick & Accurate Neural Networks

PyTorch v TensorFlow – how many times have you seen this polarizing question pop up on social media? The rise of deep learning in recent times has been fuelled by the popularity of these frameworks...


My Bot to Write Baseline Kaggle Kernels

Recently, Kaggle team updated the Kaggle public API with new features for creating and maintaining Kernels. Additionally, kaggle team also launched a bot — kerneler to write starter kernels for datasets ...


Data Science Glossary on Kaggle | Kaggle Kernel

Kaggle Kernels are one of the best resources on internet to understand the practical implementation of algorithms. I used the Meta Kaggle database to create a glossary of data science models, techniques and tools shared ...


A Hybrid Approach to Connect Donors to Projects | 1st Place Winning Kernel

In this kernel, I shared a hybrid approach to recommend donors to projects. Using Graph Embeddings and Externel Context, I created a contnet based model, using deep learning I used collaborative filtering approach ...


Interactice D3.js visualizations in Kaggle Kernels | Kaggle Kernel

This kernel showcases the interactive visualizations created in d3.js. The dataset used was the responses of stack overflow survey responses for the year 2018 ...


Convolutional Neural Networks | Kaggle Kernel

A Complete NN + CNN tutorial inspired from the deeplearning.ai course by Andrew NG ...


Comprehensive Guide : Text Classification in Python

One of the widely used natural language processing task in different business problems is “Text Classification”. The goal of text classification is to classify the text documents ...


Understanding the Working of Neural Networks

Artificial Intelligence, Machine Learning, Deep Learning, and Neural Networks are all buzzwords right now. This article is about understanding the concepts of deep learning and artificial intelligence ...


Healthcare Analysis : Medicare EDA + Clustering | Kaggle Kernel

A complete exploration of medicare data using bigquery, pandas and plotly.


Language Modelling using LSTM - Deep Learning for NLP

With the latest developments and improvements in the field of deep learning and artificial intelligence, many exacting tasks of Natural Language Processing are becoming facile to implement and execute ...


Building Data Science Pipelines in Python - using Luigi

Data science workflows require a series of tasks to be implemented in a step by step manner. Data Science pipeliens are an effective way to create manageable, scalable, and roust data science products ...


Computational Linguistics and Dependency Trees in Data Science

In recent years, the amalgam of deep learning fundamentals with Natural Language Processing techniques has shown a great improvement in the information mining tasks on unstructured text data ...


Visualising the journey of Google Acquisitions - Interactive

Since its inception in 1998, Google has acquired over 200 companies in eclectic categories (till the time of writing this article). Deja News was the first acquisition in February 2001 ...


30 Questions on Natural Language Processing

Humans are social animals and language is our primary tool to communicate with the society. But, what if machines could understand our language and then act accordingly? Natural Language Processing (NLP) is ...


An Example of Transcript - Descriptive Text Analysis

The Women's March was a worldwide protest on January 21, 2017, to advocate legislation and policies regarding human rights and other issues, including women's rights, immigration reform, healthcare reform. ...


8 Aspects in which Brands can leverage Social Media Analytics

There is no doubt that social media is an essential driver for a brand’s success. However, not many brands are using analytics and data science to gain social media benefits. ...


DataElixir: A framework to clean and deduplicate unstructured data

Applications that escapade data for decision making are the anodynes, of the myriad of business problems, in protean sectors such as healthcare, insurance, finance and social media ...


Natural Language Processing made easy using Spacy - in python

Natural Language Processing is a capacious field, some of the tasks in nlp are – text classification, entity detection, machine translation, question answering, and concept identification ...


Complete Guide for Natural Language Processing in python

According to industry estimates, only 21% of the available data is present in structured form. Data is being generated as we speak, as we tweet, as we send messages on ...


An automated Consumer Insights Engine For Brands

With the evolution of social and digital media in the last decade, the medium of communication and sharing information among brands & consumers has changed drastically. ...


Document Classification using Apache Spark in Scala

Email Spam Identification, category classification of news and organization of web pages by search engines are the modern world examples for document classification ...


Sociofuzz - Movie Reviews + Ratings + Trends using Social Analysis

Movie buffs rely on rating provider websites before watching a movie. A user based rating system incorporates inherent predilections, while a purely critic based system is biased ...


Beginners Guide to Topic Modeling in Python

Analytics Industry is all about obtaining the “Information” from the data. With the growing amount of data in recent years, that too mostly unstructured, it’s difficult to obtain the relevant and desired information. ...


Building a Recommendation Engine to Find Similar Brands

Since the amount of data has grown massively in last few years, the task of obtaining relevant information has become a challenge.


AV Data Hack - Rest API, Mining, Analysis, Visualizing

AV is a great website for discussions, articles, hacks related to data science and analytics. For the hackathon I started looking for ideas around the data from this website.


How Backpropagation Algorithm works - Neural Networks 2

In backpropagation algorithm, gradient of our cost function (delta change in cost) is calculated. This gradient (error) is back passed ...


Getting Started with Data Science - Data Munging

Data Munging is the crucial component of data science which involves all the activities of exploring, tweaking and customizing the dataset according to the problem statement.


Getting Started with Data Science - Data Mining

Data Mining is a process of collecting data, extraction of data and preparation of raw data set. It results in formation of a datasets which are in the ready to analyse formats.


Notes: Neural Network 1

This blog series will be series of notes about neural networks. Lets get started with first section about Perceptrons, Sigmoid neurons, gradient descent and neural network architecture. ...


Understanding the importance and meaning of data science

Data is everywhere around us, More than 200 million users on twitter, share content, videos and photos every day (Social Media Data). 500 Million smartphones are used for making calls, texts messaging


Social media data analysis and its industrial impact

Social media is a huge collection of communication streams comprised of large scale user inputs, user to user interactions, content sharing and collaboration. These channels engage millions of people


Practices to Improve Text Classification Model

A few months back, I was working on creating a sentiment classifier for Twitter data. After trying the common approaches, I was still struggling to get good accuracy ...


Basics of Recommendation Engines

Ever wondered, what algorithm google uses to maximize its target ads revenue?. What about the e-commerce websites which advocates you through options such as ...


Steps for text data cleaning

The days when one would get data in tabulated spreadsheets are truly behind us. A moment of silence for the data residing in the spreadsheet pockets. Today, more than 80% of the data is unstructured .


Everything you need to know about text parsing

Parsing is the process of analysing an object consisting of various datapoints according to either rules of a formal grammar or syntatical data patterns or both ...


Operational Transform

When multiple sites are collaborating on a single text document, Order of events occured at thses sites is important


Playing with Epoc Emotiv

Ever imagined, Controlling the world around with the help of brain, thoughts and emotions. Imagine if, someone's feelings producing an real time action like automated facebook chatting ...


Web Scraping in Python

Web Scraping is a process of extracting out useful information form any website. Sometimes it is also refered as web mining, web crawling and web parsing ...


Deploy Flask Application on Heroku

Heroku is one of the most popular cloud hosting service. It can be used to deploy the applications of Python, Php, Ruby, Node.js and many more online ...


Android Pc Voice Controller

The intent of this blog is to give an outline of my academic android project. After scouting for different app ideas, I decided to make a utility application on the android platform ...