示例#1
0
async def train_async(
    domain: Text,
    config: Text,
    training_files: Union[Text, List[Text]],
    output: Text = DEFAULT_MODELS_PATH,
    force_training: bool = False,
    kwargs: Optional[Dict] = None,
) -> Optional[Text]:
    """Trains a Rasa model (Core and NLU).

    Args:
        domain: Path to the domain file.
        config: Path to the config for Core and NLU.
        training_files: Paths to the training data for Core and NLU.
        output: Output path.
        force_training: If `True` retrain model even if data has not changed.
        kwargs: Additional training parameters.

    Returns:
        Path of the trained model archive.
    """
    config = get_valid_config(config, CONFIG_MANDATORY_KEYS)

    train_path = tempfile.mkdtemp()
    old_model = model.get_latest_model(output)
    retrain_core = True
    retrain_nlu = True

    story_directory, nlu_data_directory = data.get_core_nlu_directories(training_files)
    new_fingerprint = model.model_fingerprint(
        config, domain, nlu_data_directory, story_directory
    )

    dialogue_data_not_present = not os.listdir(story_directory)
    nlu_data_not_present = not os.listdir(nlu_data_directory)

    if dialogue_data_not_present and nlu_data_not_present:
        print_error(
            "No training data given. Please provide dialogue and NLU data in "
            "order to train a Rasa model."
        )
        return

    if dialogue_data_not_present:
        print_warning(
            "No dialogue data present. Just a Rasa NLU model will be trained."
        )
        return train_nlu(config, nlu_data_directory, output, None)

    if nlu_data_not_present:
        print_warning("No NLU data present. Just a Rasa Core model will be trained.")
        return await train_core_async(
            domain, config, story_directory, output, None, kwargs
        )

    if not force_training and old_model:
        unpacked = model.unpack_model(old_model)
        old_core, old_nlu = model.get_model_subdirectories(unpacked)
        last_fingerprint = model.fingerprint_from_path(unpacked)

        if not model.core_fingerprint_changed(last_fingerprint, new_fingerprint):
            target_path = os.path.join(train_path, "core")
            retrain_core = not model.merge_model(old_core, target_path)

        if not model.nlu_fingerprint_changed(last_fingerprint, new_fingerprint):
            target_path = os.path.join(train_path, "nlu")
            retrain_nlu = not model.merge_model(old_nlu, target_path)

    if force_training or retrain_core:
        await train_core_async(
            domain, config, story_directory, output, train_path, kwargs
        )
    else:
        print (
            "Dialogue data / configuration did not change. "
            "No need to retrain dialogue model."
        )

    if force_training or retrain_nlu:
        train_nlu(config, nlu_data_directory, output, train_path)
    else:
        print ("NLU data / configuration did not change. No need to retrain NLU model.")

    if retrain_core or retrain_nlu:
        output = create_output_path(output)
        model.create_package_rasa(train_path, output, new_fingerprint)

        print_success("Your bot is trained and ready to take for a spin!")

        return output
    else:
        print_success(
            "Nothing changed. You can use the old model stored at '{}'"
            "".format(os.path.abspath(old_model))
        )

        return old_model
示例#2
0
文件: train.py 项目: zhfneu/rasa_core
async def train_async(domain: Text,
                      config: Text,
                      training_files: Union[Text, List[Text]],
                      output: Text = DEFAULT_MODELS_PATH,
                      force_training: bool = False) -> Optional[Text]:
    """Trains a Rasa model (Core and NLU).

    Args:
        domain: Path to the domain file.
        config: Path to the config for Core and NLU.
        training_files: Paths to the training data for Core and NLU.
        output: Output path.
        force_training: If `True` retrain model even if data has not changed.

    Returns:
        Path of the trained model archive.
    """

    train_path = tempfile.mkdtemp()
    old_model = model.get_latest_model(output)
    retrain_core = True
    retrain_nlu = True

    story_directory, nlu_data_directory = data.get_core_nlu_directories(
        training_files)
    new_fingerprint = model.model_fingerprint(config, domain,
                                              nlu_data_directory,
                                              story_directory)
    if not force_training and old_model:
        unpacked = model.unpack_model(old_model)
        old_core, old_nlu = model.get_model_subdirectories(unpacked)
        last_fingerprint = model.fingerprint_from_path(unpacked)

        if not model.core_fingerprint_changed(last_fingerprint,
                                              new_fingerprint):
            target_path = os.path.join(train_path, "core")
            retrain_core = not model.merge_model(old_core, target_path)

        if not model.nlu_fingerprint_changed(last_fingerprint, new_fingerprint):
            target_path = os.path.join(train_path, "nlu")
            retrain_nlu = not model.merge_model(old_nlu, target_path)

    if force_training or retrain_core:
        await train_core_async(domain, config, story_directory,
                               output, train_path)
    else:
        print("Dialogue data / configuration did not change. "
              "No need to retrain dialogue model.")

    if force_training or retrain_nlu:
        train_nlu(config, nlu_data_directory, output, train_path)
    else:
        print("NLU data / configuration did not change. "
              "No need to retrain NLU model.")

    if retrain_core or retrain_nlu:
        output = create_output_path(output)
        model.create_package_rasa(train_path, output, new_fingerprint)

        print("Train path: '{}'.".format(train_path))

        print_success("Your bot is trained and ready to take for a spin!")

        return output
    else:
        print("Nothing changed. You can use the old model stored at {}"
              "".format(os.path.abspath(old_model)))

        return old_model
示例#3
0
文件: train.py 项目: quickyue/rasa
async def train_async(
    domain: Optional,
    config: Text,
    training_files: Optional[Union[Text, List[Text]]],
    output_path: Text = DEFAULT_MODELS_PATH,
    force_training: bool = False,
    fixed_model_name: Optional[Text] = None,
    uncompress: bool = False,
    kwargs: Optional[Dict] = None,
) -> Optional[Text]:
    """Trains a Rasa model (Core and NLU).

    Args:
        domain: Path to the domain file.
        config: Path to the config for Core and NLU.
        training_files: Paths to the training data for Core and NLU.
        output_path: Output path.
        force_training: If `True` retrain model even if data has not changed.
        fixed_model_name: Name of model to be stored.
        uncompress: If `True` the model will not be compressed.
        kwargs: Additional training parameters.

    Returns:
        Path of the trained model archive.
    """
    config = get_valid_config(config, CONFIG_MANDATORY_KEYS)

    train_path = tempfile.mkdtemp()
    old_model = model.get_latest_model(output_path)
    retrain_core = True
    retrain_nlu = True

    skill_imports = SkillSelector.load(config)
    try:
        domain = Domain.load(domain, skill_imports)
    except InvalidDomain as e:
        print_error(e)
        return None

    story_directory, nlu_data_directory = data.get_core_nlu_directories(
        training_files, skill_imports)
    new_fingerprint = model.model_fingerprint(config, domain,
                                              nlu_data_directory,
                                              story_directory)

    dialogue_data_not_present = not os.listdir(story_directory)
    nlu_data_not_present = not os.listdir(nlu_data_directory)

    if dialogue_data_not_present and nlu_data_not_present:
        print_error(
            "No training data given. Please provide dialogue and NLU data in "
            "order to train a Rasa model.")
        return

    if dialogue_data_not_present:
        print_warning(
            "No dialogue data present. Just a Rasa NLU model will be trained.")
        return _train_nlu_with_validated_data(
            config=config,
            nlu_data_directory=nlu_data_directory,
            output=output_path,
            fixed_model_name=fixed_model_name,
            uncompress=uncompress,
        )

    if nlu_data_not_present:
        print_warning(
            "No NLU data present. Just a Rasa Core model will be trained.")
        return await _train_core_with_validated_data(
            domain=domain,
            config=config,
            story_directory=story_directory,
            output=output_path,
            fixed_model_name=fixed_model_name,
            uncompress=uncompress,
            kwargs=kwargs,
        )

    if not force_training and old_model:
        unpacked = model.unpack_model(old_model)
        old_core, old_nlu = model.get_model_subdirectories(unpacked)
        last_fingerprint = model.fingerprint_from_path(unpacked)

        if not model.core_fingerprint_changed(last_fingerprint,
                                              new_fingerprint):
            target_path = os.path.join(train_path, "core")
            retrain_core = not model.merge_model(old_core, target_path)

        if not model.nlu_fingerprint_changed(last_fingerprint,
                                             new_fingerprint):
            target_path = os.path.join(train_path, "nlu")
            retrain_nlu = not model.merge_model(old_nlu, target_path)

    if force_training or retrain_core:
        await _train_core_with_validated_data(
            domain=domain,
            config=config,
            story_directory=story_directory,
            output=output_path,
            train_path=train_path,
            fixed_model_name=fixed_model_name,
            uncompress=uncompress,
            kwargs=kwargs,
        )
    else:
        print("Dialogue data / configuration did not change. "
              "No need to retrain dialogue model.")

    if force_training or retrain_nlu:
        _train_nlu_with_validated_data(
            config=config,
            nlu_data_directory=nlu_data_directory,
            output=output_path,
            train_path=train_path,
            fixed_model_name=fixed_model_name,
            uncompress=uncompress,
        )
    else:
        print(
            "NLU data / configuration did not change. No need to retrain NLU model."
        )

    if retrain_core or retrain_nlu:
        output_path = create_output_path(output_path,
                                         fixed_name=fixed_model_name)
        model.create_package_rasa(train_path, output_path, new_fingerprint)

        if uncompress:
            output_path = decompress(output_path)

        print_success("Your Rasa model is trained and saved at '{}'.".format(
            output_path))

        return output_path
    else:
        print_success(
            "Nothing changed. You can use the old model stored at '{}'"
            "".format(os.path.abspath(old_model)))

        return old_model