Analysing missing and outlier values in breast cancer dataset.
Built a web application by which user can analyse missing data and also find the outlier data from the tabular records from the breast cancer data by uploading csv file from streamlit application.
Downloaded breast cancer data from NIH, Preprocessed it using Pandas , Modeling using SVM and KNN algorithms, built a front end on streamlit and deployed it on Heroku.
The target users can be potential bio statistician who works for the pharmaceutical company in developing drug.
Project Github Link Web App Demo