async def test_nlu_comparison(
tmp_path: Path, monkeypatch: MonkeyPatch, nlu_as_json_path: Text
):
config = {
"language": "en",
"pipeline": [
{"name": "WhitespaceTokenizer"},
{"name": "KeywordIntentClassifier"},
{"name": "RegexEntityExtractor"},
],
}
# the configs need to be at a different path, otherwise the results are
# combined on the same dictionary key and cannot be plotted properly
configs = [write_file_config(config).name, write_file_config(config).name]
# mock training
monkeypatch.setattr(Interpreter, "load", Mock(spec=RasaNLUInterpreter))
monkeypatch.setattr(sys.modules["rasa.nlu"], "train", AsyncMock())
monkeypatch.setattr(
sys.modules["rasa.nlu.test"],
"get_eval_data",
Mock(return_value=(1, None, (None,),)),
)
monkeypatch.setattr(
sys.modules["rasa.nlu.test"],
"evaluate_intents",
Mock(return_value={"f1_score": 1}),
)
output = str(tmp_path)
test_data_importer = TrainingDataImporter.load_from_dict(
training_data_paths=[nlu_as_json_path]
)
test_data = test_data_importer.get_nlu_data()
await compare_nlu_models(
configs, test_data, output, runs=2, exclusion_percentages=[50, 80]
)
assert set(os.listdir(output)) == {
"run_1",
"run_2",
"results.json",
"nlu_model_comparison_graph.pdf",
}
run_1_path = os.path.join(output, "run_1")
assert set(os.listdir(run_1_path)) == {"50%_exclusion", "80%_exclusion", "test.yml"}
exclude_50_path = os.path.join(run_1_path, "50%_exclusion")
modelnames = [os.path.splitext(os.path.basename(config))[0] for config in configs]
modeloutputs = set(
["train"]
+ [f"{m}_report" for m in modelnames]
+ [f"{m}.tar.gz" for m in modelnames]
)
assert set(os.listdir(exclude_50_path)) == modeloutputs
def test_nlu_comparison(tmp_path: Path):
config = {
"language":
"en",
"pipeline": [
{
"name": "WhitespaceTokenizer"
},
{
"name": "KeywordIntentClassifier"
},
{
"name": "RegexEntityExtractor"
},
],
}
# the configs need to be at a different path, otherwise the results are
# combined on the same dictionary key and cannot be plotted properly
configs = [
write_file_config(config).name,
write_file_config(config).name,
]
output = str(tmp_path)
compare_nlu_models(configs,
DEFAULT_DATA_PATH,
output,
runs=2,
exclusion_percentages=[50, 80])
assert set(os.listdir(output)) == {
"run_1",
"run_2",
"results.json",
"nlu_model_comparison_graph.pdf",
}
run_1_path = os.path.join(output, "run_1")
assert set(os.listdir(run_1_path)) == {
"50%_exclusion", "80%_exclusion", "test.md"
}
exclude_50_path = os.path.join(run_1_path, "50%_exclusion")
modelnames = [
os.path.splitext(os.path.basename(config))[0] for config in configs
]
modeloutputs = set(["train"] + [f"{m}_report" for m in modelnames] +
[f"{m}.tar.gz" for m in modelnames])
assert set(os.listdir(exclude_50_path)) == modeloutputs
def test_invalid_pipeline_template():
args = {"pipeline": "my_made_up_name"}
f = write_file_config(args)
with pytest.raises(config.InvalidConfigError) as execinfo:
config.load(f.name)
assert "unknown pipeline template" in str(execinfo.value)
def test_pipeline_looksup_registry():
pipeline_template = list(registered_pipeline_templates)[0]
args = {"pipeline": pipeline_template}
f = write_file_config(args)
final_config = config.load(f.name)
components = [c.get("name") for c in final_config.pipeline]
assert components == registered_pipeline_templates[pipeline_template]
def test_pipeline_registry_lookup(pipeline_template: Text):
args = {"pipeline": pipeline_template}
f = write_file_config(args)
final_config = config.load(f.name)
components = [c for c in final_config.pipeline]
assert json.dumps(components, sort_keys=True) == json.dumps(
registered_pipeline_templates[pipeline_template], sort_keys=True)
def config_path_duplicate() -> Text:
return write_file_config({
"language":
"en",
"pipeline": [
{
"name": "WhitespaceTokenizer"
},
{
"name": "CRFEntityExtractor",
EPOCHS: 1,
RANDOM_SEED: 42
},
{
"name": "CountVectorsFeaturizer"
},
{
"name": "DIETClassifier",
EPOCHS: 1,
RANDOM_SEED: 42
},
],
}).name
def test_blank_config(blank_config):
file_config = {}
f = write_file_config(file_config)
final_config = config.load(f.name)
assert final_config.as_dict() == blank_config.as_dict()
