Main
Rajarshi Chattopadhyay
GitHub: github.com/likarajo
Website: likarajo.github.io
Portfolio: likarajo.github.io/Projects
LinkedIn: linkedin.com/in/likarajo
Articles: LinkedIn Articles
Blogs: likarajoblogs.wordpress.com
Digital Badges: youracclaim.com/users/likarajo
CV: likarajo.github.io/cv
Resume: likarajo.github.io/cv/resume
Email: likarajo@gmail.com
Phone: (469) 380-2696
Projects
Twitter Sentiments
Academic
University of Texas at Dallas
2019
- A Spark Streaming application for live tweets sentiment analysis.
Tech/Skills: Scala, SBT, Spark, Twitter API, Zookeeper, Kafka, ElasticSearch, Logstash, Kibana
Repo: github.com/likarajo/twitter_sentiments
Link: likarajo.github.io/twitter_sentiments
House Price Prediction
Academic
University of Texas at Dallas
2019
- Analyzing house price data from Kaggle and building a model using the data which can be used to predict the final price of a house.
Tech/Skills: Python, Feature-engineering, AWS S3 EC2 EMR, Spark, Scala, Regression
Repo: github.com/likarajo/house_price
Link: likarajo.github.io/house_price
Face recognition
Personal
N/A
2019
- Image recording, preparing image data, and training with pre-built Haar-cascade classifier to recognize face.
Tech/Skills: numpy, cv2, python, Haar-cascade classifier
Repo: github.com/likarajo/face_recognition
Link: likarajo.github.io/face_recognition
Chatbot
Personal
N/A
2019
- A chat bot designed to simulate conversation with users base on Artificial Intelligence.
Tech/Skills: AI, AIML, Python, Flask
Repo: github.com/likarajo/chatbot
Link: N/A
Sentiment of Movie Review
Personal
N/A
2020
- Deep Learning model built with NN, CNN, RNN using pretrained GloVe word embeddings from Stanford Core NLP
Tech/Skills: Keras, TensorFlow, Scikit-learn, NLP, Neural Networks, Python3
Repo: github.com/likarajo/movie_sentiment
Link: N/A
Customer Churn
Personal
N/A
2019
- Classification model to predict whether or not the customer is likely to leave the bank based on various customer characteristics using PyTorch
Tech/Skills: PyTorch, Classification, Python3
Repo: github.com/likarajo/customer_churn
Link: N/A
Passengers Count
Personal
N/A
2019
- Time Series Prediction to predict the count of traveling passengers based on historical data using Long Short Term Memory (LSTM) Neural Network
Tech/Skills: LSTM, Neural-Network, Time-Series-Prediction, Python3
Repo: github.com/likarajo/passengers_count
Link: N/A
Car Evaluation
Personal
N/A
2019
- Deep learning classification model to evaluate a car using Tensorflow2.0
Tech/Skills: TensorFlow2.0, Classification, Deep-Learning, Neural-Network, Python3
Repo: github.com/likarajo/car_evaluation
Link: N/A
Petrol Consumption
Personal
N/A
2019
- Deep learning regression model to predict petrol consumption using Tensorflow2.0
Tech/Skills: TensorFlow2.0, Regression, Deep-Learning, Neural-Network, Python3
Repo: github.com/likarajo/petrol_consumption
Link: N/A
Language Translation
Personal
N/A
2019
- Deep Learning language translation model built with Keras using LSTM Neural Machine Translation with seq2seq encoder-decoder architecture
Tech/Skills: Keras, Deep-Learning, LSTM, Neural-Machine-Translation, Python3
Repo: github.com/likarajo/language_translation
Link: N/A
Text Generation
Personal
N/A
2019
- Deep Learning model to predict the next word based on a sequence of input words built with Keras using LSTM Neural Network
Tech/Skills: Keras, Deep-Learning, LSTM, Neural-Network, Python3
Repo: github.com/likarajo/comment_toxicity
Link: N/A
Business reviews
Personal
N/A
2019
- Multi-Input classification model to classify user reviews regarding different businesses using deep-learning with Keras
Tech/Skills: Keras, Deep-Learning, Neural-Network, Classification, Python3
Repo: github.com/likarajo/business_reviews
Link: N/A
Customer Targeting
Personal
N/A
2020
- Binary Classification model to predict whether a customer will be interested on a particular advertisement based on customer Ad-Clicks data.
Tech/Skills: Scikit-learn, Classification, Logistic-Regression, Decision-Tree-Classifier, Python3
Repo: github.com/likarajo/customer_targeting
Link: N/A
Black Friday Shopping
Personal
N/A
2020
- Regression model to predict the amount of money that a person is likely to spend on Black Friday based on features like gender, occupation, age etc.
Tech/Skills: Scikit-learn, Regression, LinearRegression, Python3
Repo: github.com/likarajo/blackfriday_shopping
Link: N/A
Text Summarization
Personal
N/A
2020
- Automatic text summarization with simple NLP-based technique to summarize textual data from Wikipedia articles.
Tech/Skills: NLTK, Text-Summarization, NLP, Python3
Repo: github.com/likarajo/text_summarization
Link: N/A
Wine Quality
Personal
N/A
2020
- Classification model to predict the quality of wine based on different attributes.
Tech/Skills: Scikit-learn, Clustering, Hierarchical-Clustering, Agglomerative-Clustering, Python3
Repo: github.com/likarajo/wine_quality
Link: N/A
Shopping Trends
Personal
N/A
2020
- Clustering to segment customers into different groups based on their shopping trends using Hierarchical Agglomerative Clustering.
Tech/Skills: Scikit-learn, Classification, Bayes-Theorem, Naive-Bayes-Classifier, NLTK, Python3
Repo: github.com/likarajo/shopping_trends
Link: N/A
Spam SMS
Personal
N/A
2020
- Classification to detect Spam SMS using Naive Bayes’ Classifier.
Tech/Skills: Scikit-learn, Classification, Random-Forest-Classifier, Cross-Validation, Grid-Search, Python3
Repo: github.com/likarajo/spam_sms
Link: N/A
Glass Type
Personal
N/A
2020
- Classification to find the type of glass based on their oxide content after Dimensionality Reduction
Tech/Skills: Scikit-learn, Classification, Random-Forest-Classifier, Dimensionality-Reduction, PCA, LDA, Python3
Repo: github.com/likarajo/glass_type
Link: N/A
Currency Note Authenticity
Personal
N/A
2020
- Classification to predict if a bank currency note is authentic based on its image features using multiple classifiers.
Tech/Skills: Scikit-learn, Classification, Decision-Tree-Classifier, Random-Forest-Classifier, K-Nearest-Neibors, Support-Vector-Classifier, Python3
Repo: github.com/likarajo/currencynote_authenticity
Link: N/A
Weather Prediction
Personal
N/A
2020
- Regression to predict temperature based on different weather aspects
Tech/Skills: Scikit-learn, Regression, Linear-Regression, Python3
Repo: github.com/likarajo/weather_prediction
Link: N/A
Kinship
Personal
N/A
2017
- A tool that finds out what are the related words (kins) to a particular word that twitter users have tweeted.
Tech/Skills: Twitter API, Tkinter, Python3
Repo: github.com/likarajo/kinship
Link: likarajo.github.io/kinship
Personal Website V3
Personal
N/A
2019
- Version 3 of my portfolio website.
Tech/Skills: JS, Gatsby, Netlify, GitHub-Pages
Repo: github.com/likarajo/website
Link: likarajo.github.io
Movie Search
Academic
University of Texas at Dallas
2019
- Movies Search based on self-implemented TF-IDF values and Cosine-Similarity computed using movie plot summaries data taken from CMU Movie Summary Corpus.
Tech/Skills: TF-IDF, Cosine-Similarity, Spark, Scala
Repo: github.com/likarajo/MovieSearch
Link: N/A
Airport Rank
Academic
University of Texas at Dallas
2019
- Rank top airports based on self-implemented Page Rank values computed using their connections data from Bureau of Transportation Statistics.
Tech/Skills: Page rank, Spark, Scala
Repo: github.com/likarajo/AirportRank
Link: N/A
News Topic Modelling
Academic
University of Texas at Dallas
2019
- Find out topic of news from CNN news data
Tech/Skills: Latent-Dirichlet-Allocation, Spark, Scala
Repo: github.com/likarajo/topics
Link: N/A
Text to Number
Personal
Project
2019
- Implementation of Text Vectorization methods - Bag-of-words, TF-IDF, Ngrams
Tech/Skills: Scikit-learn, NLTK, Bag-of-words, TF-IDF, Ngrams, Python3
Repo: github.com/likarajo/text2number
Link: N/A
Crimes Analysis
Academic
University of Texas at Dallas
2019
- Finding the crimes cluster in a region using Kmeans clustering as silhouette.
Tech/Skills: Kmeans-clustering, Spark, Scala
Repo: github.com/likarajo/crimes
Link: N/A
Car Analysis
Academic
University of Texas at Dallas
2019
- Classify cars as automatic or manual.
- Predict mileage of cars.
Tech/Skills: Support-Vector-Classifier, Decision-Tree, Logistic-regression, Linear-Regression, Spark, Scala
Repo: github.com/likarajo/car_analysis
Link: N/A
Sentiment on US Airline
Academic
University of Texas at Dallas
2019
- Analyzing sentiment on US Airlines with Logistic Regression, Random Forest classifier, Naive-Bayes classifier using tweets data on US Airline.
Tech/Skills: Classification, Spark, Scala
Repo: github.com/likarajo/usairline_sentiment
Link: N/A
Sentiment of a sentence
Academic
University of Texas at Dallas
2019
- Used dataset of labelled sentences from Yelp, Amazon, IMDB to learn a model and use the same to analyze the sentiment of new sentences.
Tech/Skills: TF-IDF, Classification, Scala
Repo: github.com/likarajo/sentence_sentiment
Link: N/A
Earthquakes
Personal
N/A
2019
- Fetch data from USGS and plot areas across the world that had a 4.5+ earthquake in the last 24 hours.
Tech/Skills: Basemap, Conda, Python
Repo: github.com/likarajo/earthquakes
Link: N/A
Temperature Anomaly
Personal
N/A
2019
- Fetch data from NASA and plot regions on map that are fire hazards with high temperature anomaly.
Tech/Skills: Basemap, Conda, Python
Repo: github.com/likarajo/hightemp
Link: N/A
Recommender System
Academic
University of Texas at Dallas
2019
- A recommender systems built using Collaborative filtering on ratings data.
- Used Alternating least squares (ALS) algorithm to learn the latent factors.
Tech/Skills: Collaborative-Filtering, Alternating-Least-Squares-Algorithm, Latent-factors, Spark, Scala
Repo: github.com/likarajo/recommender
Link: N/A
Dimensionality Reduction
Academic
University of Texas at Dallas
2019
- Built a Support Vector Machine (SVM) Classifier model with Stochastic Gradient Decent (SGD) for Principal Component Analysis and Spectral Clustering.
Tech/Skills: SVM-Classifier, Principal-Component-Analysis, Spectral-Clustering, Python3
Repo: github.com/likarajo/dimensionality_reduction
Link: N/A
Ensemble Methods
Academic
University of Texas at Dallas
2019
- Self-implementation of Bagging and Boosting on Decision Tree ID3 algorithm.
- Comparing it with Scikit Learn implementation using Mushroom Data Set.
Tech/Skills: Scikit-Learn, Decision-Tree, ID3, Bagging, Boosting, Python3
Repo: github.com/likarajo/decision_tree_ensemble
Link: N/A
Decison Tree ID3
Academic
University of Texas at Dallas
2019
- Self-implementation of Decision Tree ID3 algorithm.
- Comparing it with Scikit Learn implementation using MONK’s Problems and Tic-Tac-Toe Endgame Data Set.
Tech/Skills: Scikit-Learn, Decision-Tree, ID3, Python3
Repo: github.com/likarajo/decision_tree
Link: N/A
Breast Cancer Diagnosis
Academic
University of Texas at Dallas
2019
- Model built for diagnosing and predicting Breast Cancer with Support Vector Machine using Wisconsin Breast Cancer diagnostic data set.
Tech/Skills: Scikit-Learn, Support-Vector-Classifier, Python3
Repo: github.com/likarajo/breastcancer_diagnosis
Link: N/A
Titanic Survival
Personal
N/A
2019
- Titanic survival prediction with Decision Tree classifier using dataset from Kaggle Competetion.
Tech/Skills: Decision-Tree-Classifier, Spark, Scala
Repo: github.com/likarajo/titanic_survival
Link: N/A
Tetris Game
Academic
University of Texas at Dallas
2019
- A tetris UI game built as part of Computer Graphics curriculum.
Tech/Skills: Java, AWT, Swing
Repo: github.com/likarajo/tetris
Link: N/A
CICD
Personal
N/A
2018
- Continuous Integration and continuous deployment using Jenkins.
Tech/Skills: Jenkins, DevOps
Repo: github.com/likarajo/devops-helloworld
Link: likarajo.github.io/devops-helloworld
911Calls
Personal
N/A
2018
- Data Science and visualization on 911 calls data.
Tech/Skills: Python3
Repo: github.com/likarajo/ds911calls
Link: N/A
MQ Reporting Tools
Professional
IBM
2015
- Developed a Java UI for daily queue status report generation for the core application on a single click eliminating manual effort.
Tech/Skills: Java, SWT, Unix, Bash
Repo: github.com/likarajo/mqreporting
Link: N/A
MQ Statistics Tools
Professional
IBM
2015
- Automated daily queue status monitoring and reporting for the core application eliminating manual effort.
Tech/Skills: Unix, Bash
Repo: github.com/likarajo/mqstats
Link: N/A
Rock Paper Scissor game
Personal
N/A
2017
- A One-player rock paper scissor game built using Python
Tech/Skills: Python3, TKinter
Repo: github.com/likarajo/rock-paper-scissor
Link: likarajo.github.io/rock-paper-scissor
Dallas Care
Academic
N/A
2018
- Relational database designed for a hospital
Tech/Skills: N/A
Repo: github.com/likarajo/DallasCare
Link: N/A
Clock
Personal
N/A
2017
- An online clock that can be customized; can be reused in any web page.
Tech/Skills: HTML, CSS, JS
Repo: github.com/likarajo/clock
Link: likarajo.github.io/clock
Brick Breaker Game
Personal
N/A
2016
- A One-player brick breaker game built using Javascript
Tech/Skills: HTML, CSS, JS
Repo: github.com/likarajo/brickbreaker
Link: likarajo.github.io/brickbreaker
Writings
Containerization
Personal
N/A
2018
- A beginners guide for Creating and Publishing Docker Image for a Python app.
Tech/Skills: Containerization, Docker
Repo: N/A
Link: likarajoblogs.wordpress.com/2018/10/02/creating-and-publishing-docker-image-for-a-python-app
CICD
Personal
N/A
2018
- A guide to learn the use of Jenkins for Continuous Integration and Continuous Deployment of projects.
Tech/Skills: Containerization, Docker, Jenkins, DevOps
Repo: N/A
Link: likarajoblogs.wordpress.com/2018/12/29/devops-continuous-integration-and-continuous-deployment
Python UI Game
Personal
N/A
2018
- A guide to build and containerize a GUI application
Tech/Skills: Containerization, Docker, Jenkins, Python3, Tkinter
Repo: N/A
Link: linkedin.com/pulse/basics-python-tkinter-rajarshi-chattopadhyay
Summer 2019 Internship Experience
Professional
Copart Inc
2019
- An article based on my learning outcomes and experience during my Summer internship at Copart
Tech/Skills: N/A
Repo: N/A
Link: linkedin.com/pulse/software-engineer-internship-experience-summer-2019-chattopadhyay
RISC Processor using Harvard Architecture
Academic
West Bengal University of Technology
2014
- Based on my Bachelor’s Thesis: Overview of designing and developing a Reduced Instruction Set Computing microprocessor, using Harvard Architecture.
Tech/Skills: RISC, Harvard-Architecture, Microprocessor, Assembly-language
Repo: N/A
Link: likarajoblogs.wordpress.com/2018/06/08/risc-using-harvard
Functional and Object Oriented Programming
Personal
N/A
2019
- An article based on my learning outcomes from attending and informational session on Functional Programming.
Tech/Skills: Fucntional-Programming, OOP
Repo: N/A
Link: linkedin.com/pulse/functional-vs-object-oriented-programming-rajarshi-chattopadhyay
Big Data in Agriculture
Personal
N/A
2018
- My thoughts on use of big data in agriculture in the modern modern world.
Tech/Skills: N/A
Repo: N/A
Link: likarajoblogs.wordpress.com/2018/06/04/bigdatainagriculture
Disclaimer
Made w/ pagedown
Last updated on 2020-01-10
Comment Toxicity
Personal
N/A
2019
Tech/Skills: Keras, Deep-Learning, Neural-Network, Classification, Python3
Repo: github.com/likarajo/text_generation
Link: N/A