This project is aimed at predicting whether a patient will have stroke or not using 3 different machine learning algorithms, and determining which of the algorithms is most accurate for the prediction.
This prediction will help the patients in taking measures that will enable them to avert the future risk of getting stroke,
esepecially as it entails working in regards to the interractions between causal factors, predisposing factors and unhealthy lifestyles that can lead to stroke.
This is a drug development project involving chemoinformatics and pharmacology. The project was done to evaluate for bias, reproduce, and validate the Ersilia eos6oli, which is a SolTranNet Model that predicts aqueous solubility from a molecule's SMILES representation.
It is a Regression model that predicts LogS (log of the solubility) in order to help filter out insoluble compounds. Predicting aqeous solubility has remained one of the biggest challenges in drug discovery, however, with the introduction of machine learning models like SolTranNet,
this challenge is at the verge of being conquered.
This project aims to predict the cost of hospital insurance and analyse the various factors that influence the cost of insurance through an extensive Exploratory Data Analysis(EDA).
The prediction will be done using various regression models in order to determine which is best for it.
This project is aimed at analysing the factors that can lead to lung cancer, predicting whether or not a patient is at the risk of lung cancer through various classification algorithms,
and thereafter, employing an Ensembler, precisely, voting classifier to combine these classification algorithms and output a better result.
In this project, data from the 'Bundeslisga_stats table' which spans from the records obtained from the 2005/2006 season to the 2022/2023 season were cleaned and explored in order to gain meaningful insights that are data-driven..
In this project, four different models were employed to predict whether or not a patient has diabetes, and various evaluation metrics such as; accuracy score, classification report, recall score, f1 score, and confusion matrix were employed to determine which of the models performed best.
The aim of this project is to scrape data from a website of about 50 pages, transform the data into a CSV file, insert the CSV file into a database using pymongo of MongoDB,
and thereafter, retrieve the collection from the databse and read it into a DataFrame which can be analysed, manipulated, and processed for Data Science works.
The main aim of this project is to employ SQL queries to skillfully explore the COVID-19 dataset and derive meaningful insights from the analysis.
This houses my data visualization projects aimed at deriving data-driven insights using Tableau.