Testing Your Assistant

End-to-End Testing

Rasa Open Source lets you test dialogues end-to-end by running through test conversations and making sure that both NLU and Core make correct predictions.

To do this, you need some stories in the end-to-end format, which includes both the NLU output and the original text. Here are some examples:

By default Rasa Open Source saves conversation tests to tests/conversation_tests.md. You can test your assistant against them by running:

$ rasa test

Note: Custom Actions are not executed as part of end-to-end tests. If your custom actions append any events to the tracker, this has to be reflected in your end-to-end tests.

Evaluating an NLU Model

A standard technique in machine learning is to keep some data separate as a test set. You can split your NLU training data into train and test sets using:

rasa data split nlu

If you’ve done this, you can see how well your NLU model predicts the test cases using this command:

rasa test nlu -u train_test_split/test_data.md --model models/nlu-20180323-145833.tar.gz

If you don’t want to create a separate test set, you can still estimate how well your model generalises using cross-validation. To do this, add the flag --cross-validation:

rasa test nlu -u data/nlu.md --config config.yml --cross-validation

Comparing NLU Pipelines

By passing multiple pipeline configurations (or a folder containing them) to the CLI, Rasa will run a comparative examination between the pipelines.

$ rasa test nlu --config pretrained_embeddings_spacy.yml supervised_embeddings.yml \
 --nlu data/nlu.md --runs 3 --percentages 0 25 50 70 90

Intent Classification

The evaluation script will produce a report, confusion matrix, and confidence histogram for your model. The report logs precision, recall and f1 measure for each intent and entity, as well as providing an overall average. You can save these reports as JSON files using the --report argument.

Entity Extraction

The CRFEntityExtractor is the only entity extractor which you train using your own data, and so it is the only one that will be evaluated. Rasa NLU will report recall, precision, and f1 measure for each entity type that CRFEntityExtractor is trained to recognize.

Evaluating a Core Model

You can evaluate your trained model on a set of test stories by using the evaluate script:

rasa test core --stories test_stories.md --out results

This will print the failed stories to results/failed_stories.md. We count any story as failed if at least one of the actions was predicted incorrectly.

Comparing Core Configurations

To choose a configuration for your core model, or to choose hyperparameters for a specific policy, you want to measure how well Rasa Core will generalise to conversations which it hasn’t seen before. Rasa Core has some scripts to help you choose and fine-tune your policy configuration. To do this:

$ rasa train core -c config_1.yml config_2.yml \
 -d domain.yml -s stories_folder --out comparison_models --runs 3 \
 --percentages 0 5 25 50 70 95

Once this script has finished, you can use the evaluate script in compare mode to evaluate the models you just trained:

$ rasa test core -m comparison_models --stories stories_folder
--out comparison_results --evaluate-model-directory

This will evaluate each of the models on the provided stories (can be either training or test set) and plot some graphs to show you which policy performs best.