coderjolly

chest-x-ray-classification

This study tries to compare the detection of lung diseases using xray scans from three different datasets using three different neural network architectures using Pytorch and perform an ablation study by changing learning rates. The dimensional understanding is visualised using t-SNE and Grad-CAM for visualisation of diseases in x-ray scans.

data-ingestion-pipeline

It is kubernetes microservice that ingests Steam data, deployed as a service using sQLite for storing processes followed by an event driven message queue controlled by RabbitMQ. This message queue is also deployed as a service with an interconnection with celery workers integrated with Elasticsearch and Redis for caching and ingestion.

Deep-LearningAI

🇦🇮 Deep Learning AI course on Coursera (Andrew Ng)

eeg-signal-analysis

EEG signals can be used to detect the mental state of a person which can have applications in machine learning. This repo gives an introduction to EEG signal analysis using MNE python library and describes the setup, the data preprocessing, data visualization and segmentation into epochs.

employee-information-retrieval-system

An information retrieval system constructed using Flask to perform ETL operations while ingesting New York Payroll data and provide a frontend user interface for manipulating filters and queries.

football-player-prediction

There is an intense transfer speculation that surrounds all major player transfers today. An important part of negotiations is predicting the fair market price for a player. Therefore, we are predicting this Market Value of a player using the data provided in csv format.

fraud-detection-credit-card

Credit card fraud refers to any unauthorized or fraudulent use of someone else's credit card information to make purchases or obtain funds. It is a criminal activity and a form of identity theft. This repository contains an implementation of a credit card fraud detection system using machine learning techniques.

ipu-engineering-notes

This repository contains notes required by CSE/ IT students for IP University. They are managed in respective folders along with some relevant PDFs also.

news-recommender

This is a news recommender system that uses beautiful-soup to scrape news articles, their categories and descriptions to create a data dump. It then uses word embedding techniques such tf-idf, word2vec for content based news recommendation and LightRF, LightFM to explore hybrid and collaborative filtering based recommender models.

processing-advertisements

Processing image advertisements to predict the context conveyed through them using CNNs. The images are further visualised using GradCAM to understand how the first and the last layers perceive the image dataset for the classification.

coderjolly/ipu-engineering-notes

This repository contains notes required by CSE/ IT students for IP University. They are managed in respective folders along with some relevant PDFs also.

coderjolly/football-player-prediction

There is an intense transfer speculation that surrounds all major player transfers today. An important part of negotiations is predicting the fair market price for a player. Therefore, we are predicting this Market Value of a player using the data provided in csv format.

coderjolly/chest-x-ray-classification

This study tries to compare the detection of lung diseases using xray scans from three different datasets using three different neural network architectures using Pytorch and perform an ablation study by changing learning rates. The dimensional understanding is visualised using t-SNE and Grad-CAM for visualisation of diseases in x-ray scans.

coderjolly/credit-card-fraud-detection

Credit card fraud refers to any unauthorized or fraudulent use of someone else's credit card information to make purchases or obtain funds. It is a criminal activity and a form of identity theft. This repository contains an implementation of a credit card fraud detection system using machine learning techniques.

coderjolly/data-ingestion-pipeline

It is kubernetes microservice that ingests Steam data, deployed as a service using sQLite for storing processes followed by an event driven message queue controlled by RabbitMQ. This message queue is also deployed as a service with an interconnection with celery workers integrated with Elasticsearch and Redis for caching and ingestion.

coderjolly/eeg-signal-analysis

EEG signals can be used to detect the mental state of a person which can have applications in machine learning. This repo gives an introduction to EEG signal analysis using MNE python library and describes the setup, the data preprocessing, data visualization and segmentation into epochs.

coderjolly/spotify-api-data-analysis

The project leverages Apache Airflow for automating Spotify API data analysis, focusing on user activity. Extracting, transforming, and loading data efficiently, it provides insights via PowerBI dashboards.

coderjolly/bird-call

There are already many projects underway to extensively monitor birds by continuously recording natural soundscapes over long periods. However, as many living and nonliving things make noise, the analysis of these datasets is often done manually by domain experts. These analyses are painstakingly slow, and results are often incomplete.

coderjolly/cat-dog-classifier

This is classifier that uses pictures of cats and dogs to train itself and then is capable enough to predicts whether the picture is of a dog or cat. The number of training and testing images are mentioned in the repo.

coderjolly/employee-information-retrieval-system

An information retrieval system constructed using Flask to perform ETL operations while ingesting New York Payroll data and provide a frontend user interface for manipulating filters and queries.

coderjolly/news-recommender

This is a news recommender system that uses beautiful-soup to scrape news articles, their categories and descriptions to create a data dump. It then uses word embedding techniques such tf-idf, word2vec for content based news recommendation and LightRF, LightFM to explore hybrid and collaborative filtering based recommender models.

coderjolly/processing-advertisements

Processing image advertisements to predict the context conveyed through them using CNNs. The images are further visualised using GradCAM to understand how the first and the last layers perceive the image dataset for the classification.

coderjolly/sociogram

SocioGram is an application that allows users to upload various pictures and share it on their profile. Other users can leave a comment or a like on the pictures accordingly. It is build on Ruby on Rails framework with screenshots attached.

coderjolly/coderjolly

coderjolly/customer-churn-prediction

It is prediction strategy used to understand the the factors required to retains customers. Showcased classical machine learning algorithm to analyse and understand the telecom customer dataset using SVMs, Decisions Trees, Random Forests etc.

coderjolly/Data-Science-Portofolio

coderjolly/Data_Science_Masters_Program_2021

coderjolly/findhelp

Java SpringBoot backend for a depression consultation portal where patients fill an evaluation form, followed by a counsellor viewing it to decide whether a counselling is required or if the patient needs to be directed to a doctor for and online meeting.

coderjolly/grok_sdi_educative

Grokking the System Design Interview Course

coderjolly/hacker-scripts

Based on a true story

coderjolly/hackingtool

ALL IN ONE Hacking Tool For Hackers

coderjolly/health-analytics-using-ML-and-wearble-sensors

coderjolly/home-decor-classification-api

A timed company task aiming to build & deploy an end-to-end DL based image classification for furniture images using Tensorflow and Flask that returns the predicted label as output when accessed using an API. This is dockerized and can be deployed on AWS as well.

coderjolly/insurance-claims-prediction

coderjolly/Machine-Learning-and-Data-Science

This is a repository which contains all my work related Machine Learning, AI and Data Science. This includes my graduate projects, machine learning competition codes, algorithm implementations and reading material.

coderjolly/ML-DTU-workshop

coderjolly/ML_Python

coderjolly/pyspark-yelp-data-analysis

A comparative study to understand the computing efficiencies of Pyspark architectures vs python based distributed programming methodologies such as MPI, multi-threading or multi-processing on the Yelp kaggle dataset.

coderjolly/sentiment-synthesis-LLMs

coderjolly/utilisation-analysis

This provides a small glimpse of the IISc's, Supercomputer Education Research Centre (SERC) resource data, and how it was ingested, extracted to produced relevant results for data analysis between actual resource utilisation and simulated resource utilisation.