Classr Logo

Train microclassifiers in the cloud for spam detection, sentiment analysis and more.

Quickstart


GitHub, GitLab and Bitbucket logos
Sign in/up

We support sign-in with GitHub, GitLab or Bitbucket

Animation of a Classr logo slowly filling up with colour from bottom to top
Train your first microclassifier

Provide your training data as a CSV file mapping documents to classes

Animation of a Classr logo flashing green and red from left to right
Use your trained model

Query your model using our simple HTTP REST API

Training


Provide your training data to Classr as a 2-column CSV file.

This file must have a "label" column containing class labels and a "document" column containing documents. A maximum file size of 4MB is supported for training your microclassifier.

Usage


Each microclassifier you create gives you, and everyone who knows your microclassifier ID, the ability to use it for classification (a POST request) or retrieve information about it (a GET request).

Get microclassifier info (GET)

$ curl https://classr.dev/api/classifier/<classifier-uuid>

Use microclassifier (POST)

$ curl --header "Content-Type: application/json" --request POST --data '{"document":"The text of the unseen document to classify!"}' https://classr.dev/api/classifier/<classifier-uuid>

Or install an SDK!

Classr SDK for Node.jsClassr SDK for Python
Open-source on GitHub
Buy Me a Coffee at ko-fi.com