def test_train_nlu_persist_nlu_data(
run_in_simple_project: Callable[..., RunResult]) -> None:
run_in_simple_project(
"train",
"nlu",
"-c",
"config.yml",
"--nlu",
"data/nlu.md",
"--out",
"train_models",
"--persist-nlu-data",
)
assert os.path.exists("train_models")
files = rasa.shared.utils.io.list_files("train_models")
assert len(files) == 1
assert os.path.basename(files[0]).startswith("nlu-")
model_dir = model.get_model("train_models")
assert model_dir is not None
metadata = Metadata.load(os.path.join(model_dir, "nlu"))
assert metadata.get("training_data") is not None
assert os.path.exists(
os.path.join(model_dir, "nlu",
training_data.DEFAULT_TRAINING_DATA_OUTPUT_PATH))
def test_train_persist_nlu_data(run_in_simple_project: Callable[...,
RunResult]):
temp_dir = os.getcwd()
run_in_simple_project(
"train",
"-c",
"config.yml",
"-d",
"domain.yml",
"--data",
"data",
"--out",
"train_models",
"--fixed-model-name",
"test-model",
"--persist-nlu-data",
)
assert os.path.exists(os.path.join(temp_dir, "train_models"))
files = rasa.shared.utils.io.list_files(
os.path.join(temp_dir, "train_models"))
assert len(files) == 1
assert os.path.basename(files[0]) == "test-model.tar.gz"
model_dir = model.get_model("train_models")
assert model_dir is not None
metadata = Metadata.load(os.path.join(model_dir, "nlu"))
assert metadata.get("training_data") is not None
assert os.path.exists(
os.path.join(model_dir, "nlu",
training_data.DEFAULT_TRAINING_DATA_OUTPUT_PATH))
def test_train(run_in_default_project):
temp_dir = os.getcwd()
run_in_default_project(
"train",
"-c",
"config.yml",
"-d",
"domain.yml",
"--data",
"data",
"--out",
"train_models",
"--fixed-model-name",
"test-model",
)
assert os.path.exists(os.path.join(temp_dir, "train_models"))
files = io_utils.list_files(os.path.join(temp_dir, "train_models"))
assert len(files) == 1
assert os.path.basename(files[0]) == "test-model.tar.gz"
model_dir = model.get_model("train_models")
assert model_dir is not None
metadata = Metadata.load(os.path.join(model_dir, "nlu"))
assert metadata.get("training_data") is None
assert not os.path.exists(
os.path.join(model_dir, "nlu",
training_data.DEFAULT_TRAINING_DATA_OUTPUT_PATH))
def _read_model_metadata(self, model_name, model_dir):
if model_name is None:
data = Project._default_model_metadata()
return Metadata(data, model_name)
else:
if model_dir is not None:
path = model_dir
elif not os.path.isabs(model_name) and self._path:
path = os.path.join(self._path, model_name)
else:
path = model_name
# download model from cloud storage if needed and possible
if not os.path.isdir(path):
self._load_model_from_cloud(model_name, path)
return Metadata.load(path)
def test_train_nlu(run_in_default_project):
run_in_default_project(
"train",
"nlu",
"-c",
"config.yml",
"--nlu",
"data/nlu.md",
"--out",
"train_models",
)
assert os.path.exists("train_models")
files = io_utils.list_files("train_models")
assert len(files) == 1
assert os.path.basename(files[0]).startswith("nlu-")
model_dir = model.get_model("train_models")
assert model_dir is not None
metadata = Metadata.load(os.path.join(model_dir, "nlu"))
assert metadata.get("training_data") is None
assert not os.path.exists(
os.path.join(model_dir, "nlu",
training_data.DEFAULT_TRAINING_DATA_OUTPUT_PATH))
def interpreter_for_model(component_builder, model_dir):
metadata = Metadata.load(model_dir)
return Interpreter.create(metadata, component_builder)
"被盗狼青狗特征：是一条1年半的狼青狗，高约60公分，长约80公分，现市场价值2000余元。" \
"涉案总价值2000余元。案件性质关键词：撬门压锁。, 出生地北京，现居住在新疆"
text = "小明，男，身高180cm，上个月去北京站坐G22到新疆，与他同行的有30岁的小黑，他们开着一辆白色法拉利逃跑。"
context = {}
time = datetime.datetime.now()
default_output_attributes = {
"intent": {
"name": None,
"confidence": 0.0
},
"entities": []
}
message = Message(text, data=default_output_attributes, time=time)
model_dir = './models/link/model_20190517-113416'
model_metadata = Metadata.load(model_dir)
jieba_meta = model_metadata.for_component(index=0)
jie = JiebaTokenizer.load(meta=jieba_meta,
model_dir=model_dir,
model_metadata=Metadata.load(model_dir))
pprint.pprint(message.data)
jie.process(message)
ltp_meta = model_metadata.for_component(index=5)
ltp = LtpHelper.load(meta=ltp_meta,
model_dir=model_dir,
model_metadata=Metadata.load(model_dir))
pprint.pprint(message.data)
