8000 GitHub - scott-daily/flask-data-app
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

scott-daily/flask-data-app

Repository files navigation

This is a flask web application that was created to utilize a machine learning sentiment classification model.
A data set consisting of 500,000 Amazon product reviews was used to fine tune a Multinomial Naive Bayes classifier. Following training, the model had an accuracy rate of 93% on a test set. A K-means model was also created with 15 clusters to analyze the data set with various visualizations.

To try the program out, visit https://flask-sentiment-app.herokuapp.com --> Enter test in the password field to login.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0