Annif: Test the model and improve it

[hortongn]

Use the AWS EC2 instance and docker image to test Annif with sample documents. Log results on this issue.

• Customize/expand the projects.cfg, if needed.
• Gather sample documents for testing.
• Try all available backend, analyzers, and other options.
• Log the configuration used, the test documents, and the subject terms produced.

Starting the EC2 instance

1. Log into the AWS library dev account:
   • https://console.aws.amazon.com/console/home?nc2=h_ct&src=header-signin
   • IAM user
   • Account ID: 973299577490
2. Click on or search for EC2 page
3. Click on Instances
4. Click on the Annif Instance ID
5. Click Instance State -> Start Instance

ssh to EC2 instance

1. Download the Annif.pem keyfile from Teams
2. chmod 600 Annif.pem
3. ssh [email protected] -i Annif.pem (replace 1.2.3.4 with public IP of EC2 instance)

Stoping the EC2 instance

1. Click on or search for EC2 page
2. Click on Instances
3. Click on the Annif Instance ID
4. Click Instance State -> Stop Instance

[scherztc]

A Corpus : All text documents in Scholar
A Training Set : is a subset of the corpus, which has been tagged in some way to identify the characteristic you are looking for
A Test Set : collection of documents to be used for trialling the algorithm, to see how successfully it carries out the operation.
Example : Modified National Institute of Standards and Technology (MNIST) database of handwritten numbers,10
An Algorithm : The ‘algorithm’ is simply the tool that looks at each item in the corpus and enables a decision to be made. An algorithm may be as simple $