def load_data( resource_name: Union[Text, "TrainingDataImporter"], domain: "Domain", remove_duplicates: bool = True, unique_last_num_states: Optional[int] = None, augmentation_factor: int = 50, tracker_limit: Optional[int] = None, use_story_concatenation: bool = True, debug_plots: bool = False, exclusion_percentage: Optional[int] = None, ) -> List["TrackerWithCachedStates"]: """ Load training data from a resource. Args: resource_name: resource to load the data from. either a path or an importer domain: domain used for loading remove_duplicates: should duplicated training examples be removed? unique_last_num_states: number of states in a conversation that make the a tracker unique (this is used to identify duplicates) augmentation_factor: by how much should the story training data be augmented tracker_limit: maximum number of trackers to generate during augmentation use_story_concatenation: should stories be concatenated when doing data augmentation debug_plots: generate debug plots during loading exclusion_percentage: how much data to exclude Returns: list of loaded trackers """ from rasa.shared.core.generator import TrainingDataGenerator from rasa.shared.importers.importer import TrainingDataImporter if resource_name: if isinstance(resource_name, TrainingDataImporter): graph = resource_name.get_stories( exclusion_percentage=exclusion_percentage) else: graph = extract_story_graph( resource_name, domain, exclusion_percentage=exclusion_percentage) g = TrainingDataGenerator( graph, domain, remove_duplicates, unique_last_num_states, augmentation_factor, tracker_limit, use_story_concatenation, debug_plots, ) return g.generate() else: return []
def visualize_stories( story_steps: List[StoryStep], domain: Domain, output_file: Optional[Text], max_history: int, nlu_training_data: Optional["TrainingData"] = None, should_merge_nodes: bool = True, fontsize: int = 12, ) -> "networkx.MultiDiGraph": """Given a set of stories, generates a graph visualizing the flows in the stories. Visualization is always a trade off between making the graph as small as possible while at the same time making sure the meaning doesn't change to "much". The algorithm will compress the graph generated from the stories to merge nodes that are similar. Hence, the algorithm might create paths through the graph that aren't actually specified in the stories, but we try to minimize that. Output file defines if and where a file containing the plotted graph should be stored. The history defines how much 'memory' the graph has. This influences in which situations the algorithm will merge nodes. Nodes will only be merged if they are equal within the history, this means the larger the history is we take into account the less likely it is we merge any nodes. The training data parameter can be used to pass in a Rasa NLU training data instance. It will be used to replace the user messages from the story file with actual messages from the training data. """ story_graph = StoryGraph(story_steps) g = TrainingDataGenerator( story_graph, domain, use_story_concatenation=False, tracker_limit=100, augmentation_factor=0, ) completed_trackers = g.generate() event_sequences = [t.events for t in completed_trackers] graph = visualize_neighborhood( None, event_sequences, output_file, max_history, nlu_training_data, should_merge_nodes, max_distance=1, fontsize=fontsize, ) return graph
def provide(self, story_graph: StoryGraph, domain: Domain) -> List[TrackerWithCachedStates]: """Generates the training trackers from the training data. Args: story_graph: The story graph containing the test stories and rules. domain: The domain of the model. Returns: The trackers which can be used to train dialogue policies. """ generator = TrainingDataGenerator(story_graph, domain, **self._config) return generator.generate()