This is a network science project that tries to show the green product evolution for the two economically rich states of US (i.e. Texas and Florida)

• View Project

This project aims at identifying the most important features to consider while predicting patient’s survival suffering with heart failure. I have used different classification models like Logistic regression, Random Forest, XGBoost etc. to make accurate predictions while selecting features that based on importance scores.

• View Project

The key objective of this project is to find the optimum number of clusters in the wine dataset based on its attributes. Elbow method, silhouette plot & gap statistics are used to find the best K value that can be used to run K-means clustering algorithm. K-means(), clara(), fanny() & pam() partitioning algorithms were used to obtain the ideal number of clusters.

• View Project

The key objective of this project is to analyze the sentiment of customers that are reviewing food products on amazon.com. The analysis done in this project would enable the organization to take strategic decisions based on their customers sentiments

• View Project

This project is to To visualize change in life expectancy of people over the years and examine how various factors like mortality rate, drinking water & sanitization services,GDP, health care workforce, road accidents, communicable & non-communicable diseases etc. influence life expectancy.Extracted data from WHO’s Athena API to build interactive visualization that help analyze factors that are influencing life expectancy of people over the years. Observable notebook which is built on D3.js and JavaScript was used to make interactive visualizations

• View Project