Rohit Swami

Rohit Swami

Software Engineer
Kaggle 2x Expert
AI • ML • NLP

About Me

Jack of all trades, master of none!
Being brought up in a rural area of Haryana, computer was an alien thing for me back in 2008 when it was introduced in our school. Apart from using Microsoft Paint in school hours, I was keen on diving deeper into it.
Fast forward today, I pride myself as a software engineer who loves to build scalable system from scratch, uncover the hidden facts and meaningful insights from messy data, building and deploying secure APIs for consumers.
I, personally, love the idea of improving the world with a block of code.

personal information

Full Name
Rohit Swami
D.o.b.
21 Jan 1999
address
Hisar, Haryana, India
e-mail
[email protected]
phone
+91 80594 59498

specialization

Data Structure & Algorithms R Python SQL Data Science Machine Learning Statistics EC2 Lambda Functions S3 DynamoDB JavaScript Shiny Flask Tableau

work experience

Elucidata Logo Elucidata

New Delhi, India

Software Engineer

• Building pipelines and dashboards of biomedical molecular data for bio-informaticians.

Ignite Solutions Logo Ignite Solutions

Pune, India

Software Engineer

• Created and deployed demand forecasting machine learning models for retail energy provider to eliminate uncertainty with confidence and operate at their full potential.
• Conducted research on big data provided by MasterCard and came up with the probability to sell a product in a particular geo-area in United States. Built a back-end in Flask to support the analysis.
• Single-handedly built internal recruitment portal using GoogleAPIs and Flask framework.
• Developed RESTful APIs for a product definition app and performed routine data analysis for international clients.

InterviewBit Logo InterviewBit

Bengaluru, India

Software Engineer, Intern

• Implemented an end-to-end auto-suggestion tool to find the semantic similarity between the solution of student’s queries and deployed the model as a REST-API on AWS EC2 using Flask backend. The proposed system drastically reduced the query resolution time of 72% of students from 2 days to 13.3 minutes (average). Developed a dashboard to analyse the Key Performance Indicator (KPI) using SQL queries.
• Built an NLP tool to calculate the percentage of code and text in TA’s responses to increase the overall interaction of students and TAs.
• Wrote scripts to send emails and migrate 1500+ students from Flock to open-source platform Mattermost.
• Revamped InterviewBit’s webpages and worked on content creation of Data Science, Machine Learning and Deep Learning.

upGrad Logo upGrad

Remote

Data Science, Intern

• Fostered 200+ students to improve their skills by providing clear, positive and line-by-line actionable feedback on their submitted projects using upGrad's code review tool for data science courses.

MyGov Logo MyGov (MoEIT, India)

New Delhi, India

Data Analyst, Intern

• Analyzed sentiments of public on different government policies and campaigns on social media.
• Exported over 4000 tweets with Twitter API and built a hybrid solution to classify each tweet as positive or negative with KNN algorithm.
• Performed data mining operations on websites for various internal purposes.

MSTCLPU Logo MSTC, LPU

LPU, India

Lead Organizer

• MSTC host community events to guide professionals in different technologies. We strive to create a platform where like-minded individuals come together to share and learn about technology.
• As a lead speaker, I share my knowledge about front-end technologies.

Education

Data Scientist Nanodegree

Udacity

B.Tech (Computer Science & Engineering)

Lovely Professional University

5th - 12th

BSJD Convent School

Publications

Driver Fatigue Detection System with Mobile Notification Alarm

International Journal of Emerging Technologies and Innovative Research (www.jetir.org), 5(12), 598-605

ISSN: 2349-5162

Sentiment Analysis with Fully Supervised Speaker Diarization

Think India Journal, 22(3), 8382-8391

ISSN: 0971-1260

Automated Web Development: Theme Detection and Code Generation Using Mix-NLP

ACM - International Conference Proceedings Series (Jun, 2019)

DOI: 10.1145/3339311.3339356

Blogs

Certifications & Achievements

portfolio

Project CharityML

Finding Donors (CharityML)

Project CharityML

Finding Donors (CharityML)

machine learning
Date:
14 Sep 2018
Site link:
Jupyter Notebook URL
Algorithms:
Gaussian Naive Bayes (GaussianNB), Decision Tree Classifier, C-Support Vector Classification
Technology:
Python, Jupyter-Notebook

Problem Statement: Build an algorithm to best identify potential donors.

• My goal was to evaluate and optimize several different supervised learners to determine which algorithm will provide the highest donation yield while also reducing the total number of letters being sent.
• Implemented a pipeline in Python that will train and predict on the supervised learning algorithm given. I used the Grid Search method to tune the parameters of all algorithms and Gradient Boosting Classifier to extract features importance.

Project Indian Paper Currency Prediction

Indian Paper Currency Prediction

Project Indian Paper Currency Prediction

Indian Paper Currency Prediction

machine learning
Date:
June 2020
Code:
GitHub Repo
Demo:
https://indian-currency-prediction.herokuapp.com/
Algorithms:
Convolutional Neural Network (CNN)
Technology:
Python, Jupyter-Notebook, Flask

Problem Statement: Build an app to prediction indian paper currency.

• Collected the images from search engines and trained a Convolutional Neural Network (CNN) model to predict the 7 types of Indian paper currency i.e. 10, 20, 50, 100, 200, 500, 2000.
• Deployed the machine learning model on Heroku with Flask back-end and secured the app with CSRF protection.

Image Classification with PyTorch

Image Classification with PyTorch (Deep Learning)

Image Classification with PyTorch

Image Classification with PyTorch (Deep Learning)

machine learning
Date:
13 Nov 2018
Site link:
Github Repo URL
Technology:
PyTorch Framework, Python, Jupyter-Notebook

Problem Statement: Building a command-line application to predict flower class along with the probability.

• AI image classification and machine learning utilizing the PyTorch framework.
• Used transfer learning on pre-trained architectures including vgg11, vgg13, vgg16, vgg19, densenet121, densenet169, densenet161, and densenet201.
• Trained dynamic neural networks in Python with GPU acceleration with 85% accuracy.

Customer Churn Prediction (PySpark)

Customer Churn Prediction (PySpark)

Customer Churn Prediction (PySpark)

Customer Churn Prediction (PySpark)

machine learning
Date:
09 June 2019
Site link:
GitHub Repo URL
Blog:
https://medium.com/@rowhitswami/customer-churn-prediction-of-a-music-app-using-pyspark-d65b8f5be047
Algorithms:
PySpark, TF-IDF, SDGClassifier
Technology:
Python, Jupyter-Notebook

Problem Statement: Customer Churn Prediction from a Music App Spark

• Used PySpark to analyze the data of a fictional music app Sparkify to identify the factor affecting the customers who are most likely to churn.
• Trained machine learning model on IBM Cloud with the accuracy of 83.87%

StackOverflow Survey '17

StackOverflow Survey '17

StackOverflow Survey '17

StackOverflow Survey '17

machine learning
Date:
20 Feb 2019
Site link:
GitHub Repo URL
Blog:
https://medium.com/@rowhitswami/4-crunching-facts-of-stack-overflow-developer-survey-17-441eb082331f
Algorithms:
Exploratory Data Analysis
Technology:
Python, Jupyter-Notebook

Problem Statement: Analyzing the public data of StackOverflow Survey 2017

• Analyzed the StackOverflow public data of over 64,000 developers around the globe for the year 2017.
• Answered questions like, how education may influence the salary, gender ratio of developers across the world, the rate of increase in salary with years of experience and does more language implies more salary hike in IT sector.

Identify Customer Segments

Identify Customer Segments

Identify Customer Segments

Identify Customer Segments with Arvato

machine learning
Date:
24 Dec 2018
Site link:
Jupyter Notebook URL
Algorithms:
KMeans
Technology:
Python, Jupyter-Notebook

Problem Statement: Identify Customer Segments with Arvato Dataset

• The data and design for this project were provided by Arvato Financial Services. I applied unsupervised learning techniques on demographic and spending data for a sample of German households.
• Preprocessed the data, apply dimensionality reduction techniques, and implement clustering algorithms to segment customers with the goal of optimizing customer outreach for a mail order company.
• The objective was to find relationships between demographics features, organize the population into clusters, and see how prevalent customers are in each of the segments obtained.

Disaster Response Pipeline

Disaster Response Pipeline

Disaster Response Pipeline

Disaster Response Pipeline

machine learning
Date:
13 Apr 2019
Site link:
Github Repo URL
Technology:
Python, Jupyter-Notebook

Problem Statement: Building a machine learning pipeline

• Analyzed disaster data from Figure Eight to build a model for an API that classifies disaster messages.
• Created a machine learning pipeline to categorize the events so that it can send the messages to an appropriate disaster relief agency and deployed as a web app.

IPL Live Updates

IPL Live Updates (Python)

IPL Live Updates

IPL Live Updates (Python)

fun projects
Date:
3 Apr 2019
Site link:
Github Repo URL
Technology:
Python

Problem Statement: Get real-time updates of cricket matches on your desktop

• Get real-time push notifications on your desktop on every Four, Six and fall of a wicket of Indian Premier League's matches
• Used an HTTP persistent-connection to extract the live score from a webpage

ContinentInfo (Python Package)

ContinentInfo (Python Package)

ContinentInfo (Python Package)

ContinentInfo (Python Package)

fun projects
Date:
3 Mar 2019
Site link:
PyPi Index URL
Technology:
Python
Installation:
pip install ContinentInfo

Problem Statement: Get the name of the continent in which a country is located in.

• Built a pretty simple Python package to understand how packages work on PyPi.

Shortto

Shortto.com - URL Shortner

Shortto

Shortto.com - URL Shortner

web development
Site link:
www.shortto.com
Contributor:
Soumyajit Dutta, Biswarup Benerjee
Technology:
HTML, CSS, JavaScript

A Project made under Microsoft Technical Community LPU

• The project centers around developing an URL shortening service. You have got long URLs that are hard to remember. Use shortTo.com to shorten your URL and give them an easy to remember URL.
• Hosted on AWS, we used Flask in the backend. The bootstrap framework and javascript with media queries are used to make the UX/UI even more responsive and interactive.

Project Twitter Sentiment Analysis

Twitter Sentiment Analysis (Hadoop)

Project Twitter Sentiment Analysis

Twitter Sentiment Analysis using Hadoop

Big Data
Date:
Oct 2017 - Mar 2018
Client:
Personal
Technology:
Hadoop, Flume, Hive, Twitter Streaming API, Python

Twitter, one of the largest social media site receives tweets in millions every day. This huge amount of raw data can be used for industrial or business purpose by organizing according to our requirement and processing. This project provides a way of sentiment analysis using hadoop which will process the huge amount of data on a hadoop cluster faster in real time

Hacktoberfest Status Checker

Hacktoberfest Status Checker

Hacktoberfest Status Checker

Hacktoberfest Status Checker

web development
Date:
Oct 2017
Site link:
https://www.openstalk.tech/
Technology:
HTML, CSS, JavaScript, Bootstrap, Git REST API v3
Contributor:
See Complete List

• Hacktoberfest is a month-long celebration of open source software in partnership with Github, in which participants need to make 4 Pull Request across the Github.
• Hacktoberfest Status Checker is an open-source tool to know the status of your Hacktoberfest activities in the month of October.

Project Data Analysis

Data Analysis (Freelancing)

Project Data Analysis

Data Analysis (Freelancing)

machine learning
Date:
24 Apr 2018
Site link:
GitHub Repo
Client:
Lcodi56
Technology:
Python

Sales data was given in CSV format and the task of this project was to derive valuable insights from the raw data, like:

• Which product was most sold?
• What payment modes were used for purchasing products?
• What is the most common payment method for the United States?
• What was the earliest time of the day a transaction occurred?
• Were there repeat customers? Discuss possible issues.

Smart Q-Labs

Smart Q-Labs

Smart Q-Labs

Smart Q-Labs

web development
Date:
Sep 2017
Site link:
GitHub Repo
Technology:
HTML, CSS, jQuery, PHP, Java
Platform:
Web, PWA, Android
Contributor
Shriom Tripathi, Soumyajit Dutta, Biswarup Benerjee

• Smart Q Labs is a dynamic queue management solution which take care of your queue number and gives you notification time by time. Not only that we provide analytics for the outlets so that they can manage as well as enjoy managing queue.
• I designed the mobile website using the concept of PWA (Progressive Web Apps), specially designed to work in the offline mode or bad network connection. PWA uses modern web capabilities to deliver an app-like experience to users. It uses the app-shell model to provide app-style navigation and interactions.

Project Data Analysis

Data Analysis (Freelancing)

Project Data Analysis

Data Analysis (Freelancing)

machine learning
Date:
04 May 2018
Site link:
GitHub Repo
Client:
Lcodi56
Technology:
Python

The dataset contains information of people die from "Diabetes Mellitus" between 1999-2015. The task of this project was to derive valuable insights from the raw data, like:

• In what state has the most deaths occurred?
• Over what period (start and end) was the data collected?
• What were the total number of deaths for 2006?
• What state had the least deaths in 2001?
• How many people die from "Diabetes mellitus" over the entire reporting period?

SkinLEDLight

SkinLEDLight

SkinLEDLight

SkinLEDLight

web development
Date:
Jul 2017
Site link:
www.skinledlight.com
Client:
Tony Alvarado

contact me

Scan QR code to chat now

Rohit Swami WhatsApp Number

Connect with me on social media :)