shiivong27 Goto Github PK

analysing_and_predicting_uber_fare

Here, our task is to analyze and predict Uber fare data. There are many small tasks that are needed to be done before moving on to analysing and predicting on the Uber data such as data cleaning, data imputing and data prediction.

australian_real_estate_analysis

In this project, I have collated data from different government sources to create an overall picture of the real estate in Australia.

automated_feature_selection

Given a dataset and it's attributes, this R Shiny application determines the best model for the response variable given the set of attributes input.

big-data-processing

I have demonstrated some of the Big Data Processing knowledge that I recently acquired at University. Such as, creating Spark sessions, manipulating dataframes, reading and writing from and to MongoDB and some EDA.

business_process_mining

An all-purpose Business Process Mining R Shiny application which can perform computations on large event-log data to find out efficient resources, process bottlenecks, activity traces, processing time of resources and overall process summary of the data.

chatbot-with-reformer-models

child_language_analyser

In this project, I have implemented a language analyser which investigates the linguistic characteristics of children with some form of language disorder. The analyser can perform basic descriptive statistics on a number of linguistic features in the form of visualization.

classifying-song-genres-from-audio-data

Classifying Song Genres from Audio Data using Machine Learning

combat_simulator

This is a combat simulator which pits one army against another. The army combat is simulated through well defined rules, constraints and error handling.

credit_risk_modelling

we have addressed the problem of classifying highly unbalanced data using supervised machine learning algorithms. Unbalanced data is ubiquitous in nature, it’s dealt with in a wide range of fields including but not limited to that of business, bioinformatics, engineering and banking sector. We have focussed here on Credit Risk, which is defined as risk of default on a debt that may arise from a borrower failing to make required payments. In the first resort, the risk is that of the lender and includes lost principal and interest, disruption to cash flows, and increased collection costs. Usually in a Credit Risk problem, loan default is a rare phenomenon and that is why we have such unbalanced data.

cv-pretrained-model

A collection of computer vision pre-trained models.

dynamic_geospatial_mapping_of_dustbins

Based on a prototype of a dustbin status tracking device, this R Shiny application reports the live statuses of a number of dustbins across the city. This application was designed with the purpose of managing waste in a smart way. I have made use of the javascript library leaflet which helped me bring out the features in the app that makes it come to life. The application also shows the data collected and also some basic visual analytics on the data which further help in answering some basic questions about the problem of waste management itself. The Shiny application can be found at : https://shiivong27.shinyapps.io/dynamic_geo-spatial_mapping_of_dustbins/ R packages used: shiny leaflet ggplot2

electricity-usage-analysis

english-to-german-neural-machine-translation-with-lstms-with-attention

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

fastbook

Draft of the fastai book

forecasting-influenza-flu-cases-in-australia-with-xgboost-and-sarimax-

generating-music-with-lstm-s-in-keras

google_vs_amazon_hr_analytics

Based on the latest 500 tweets extracted from Twitter of the comapany reviews by the employees of Google and Amazon. This is a comparative study of of how the two giants differ based on work-life balance, salary and middle management and which one beats the other on an overall basis.

identifying-duplicate-questions-with-siamese-networks

ie_hygieia_shiny_apps

All the Shiny Application development that took place in the final semester's Industrial Experience project as part of the Hygieia team.

ieee-fraud-detection

https://www.kaggle.com/c/ieee-fraud-detection/

invisibility_cloak

This is a fun application of image processing which enables you to experience the magic of an invisibility cloak. Let's make our childhood fantasy of using an invisibility cloak come true.

invisiblitycloak

Emulate an invisibility cloak

machine-learning-with-big-data

named-entity-recognition-with-lstms

neural_prophet

NeuralProphet - A simple forecasting model based on Neural Networks in PyTorch

object-detection-with-yolov2-in-tensorflow

practicalai

📚 A practical approach to machine learning.

predicting-superconductor-critical-temperature-with-r