Name: Nisaharan Genhatharan
Type: User
Company: University of Louisville
Bio: Experienced data professional, leveraging the power of data to create a more prosperous, inclusive, and sustainable world.
Location: Louisville, KY, USA
Blog: https://www.linkedin.com/in/nisaharan-genhatharan/
Nisaharan Genhatharan's Projects
In this project, I performed sentiment analysis on movie reviews using various classification algorithms. The goal was to classify movie reviews as either positive or negative based on their content.
I did Principal Component Analysis (PCA) in order to reduce the number of variables and identify underlying patterns in the data.
This repository consist of ERD and SQL queries needed to fetch information from database.
Customer segmentation is a marketing technique companies use to identify and group users who display similar characteristics. For instance, if you visit Starbucks only during the summer to purchase cold beverages, you can be segmented as a “seasonal shopper” and enticed with special promotions curated for the summer season.
This repository contains PySpark code that implements three machine learning models for predicting diabetes readmission: Decision Forest, Random Forest, and Gradient Boosted models. These models are trained and evaluated using patient information.
This repo is for the Linkedin Learning course: End-to-End Data Engineering Project
Developed a function with the inputs of date and season that returns the league standings for the date and season specified. The season specified accepts the current seasons and both of the two most recently completed seasons.
This project aims to develop a machine learning model for predicting the time of delay for each flight. The main objective is to assist travelers, airlines, and travel companies in managing their schedules more efficiently by providing accurate predictions of flight delays.
The Higgs classification is accomplished through the utilization of algorithms to identify and categorize particles detected in high-energy physics experiments based on their properties and characteristics.
This project provides an understanding of the housing market for an area of Boston in the past. You are asked to build a model to predict house prices given certain characteristics. The data dictionary is provided at the end of this document.
Modelled the Medical insurance charges with the help of distributed computing platform Pyspark in Databricks. Used 2 models for this purpose. Linear Regression Logistic regression
K-means clustering was applied to this dataset using PySpark on Databricks. PySpark is a Python library that enables distributed data processing using Apache Spark. Databricks provides a cloud-based platform for big data processing and analytics.
This repository contains PySpark code that implements Neural Network models for predicting diabetes readmission. These models are trained and evaluated using patient information.
The source to opensearch.org
🔎 Open source distributed and RESTful search engine.
🧰 OpenSearch / OpenSearch-Dashboards Build Systems
In the case study I've considered chemical vapor deposition of diamond
Using the wikitext dataset with the distilbert-base-cased model checkpoint.
I learnt natural language processing (NLP) basics, such as how to identify and separate words, how to extract topics in a text, and how to build my own fake news classifier. I also learnt how to use basic libraries such as NLTK, alongside libraries which utilize deep learning to solve common NLP problems.
Modelling topics for amazon Alexa review using unsupervised learning techniques