NamedEntitiesExplorer

Explorer

DashAI.back.exploration.explorers.NamedEntitiesExplorer

---

Find the people, organizations and places named in text items.

Uses Davlan/xlm-roberta-base-ner-hrl, trained on ten languages including English, Spanish, Portuguese, German, French and Chinese. Entities are counted by their text and type; the chart shows the most frequent ones next to a table with counts and types.

Parameters

top_n : integer, default=20

How many entities to show, between 1 and 200.

min_score : number, default=0.6

Lowest model confidence, between 0 and 1, for an entity to count.

device : string, default=CPU

Device the model runs on. A GPU is much faster than the CPU.

Methods

find_entities(self, values: List[str]) -> List[Tuple[str, str]]

Defined on NamedEntitiesExplorer

Return the confident entities of the texts.

Parameters

values : List[str]

The texts.

Returns

List[Tuple[str, str]]

(entity text, type label) for every confident mention.

launch_exploration(self, dataset: 'DashAIDataset', explorer_info: DashAI.back.dependencies.database.models.Explorer) -> Any

Defined on NamedEntitiesExplorer

Build a table and a bar chart of the most named entities.

Parameters

dataset : DashAIDataset

The selected text.

explorer_info : Explorer

The explorer record.

Returns

plotly.graph_objects.Figure

The entity table above the bar chart.

load_pretrained(self, source: str) -> Any

Defined on NamedEntitiesExplorer

Load the token classification pipeline.

Parameters

source : str

A local directory or the Hub repo id.

Returns

transformers.Pipeline

A pipeline that groups word pieces into whole entities.

component_dir(cls) -> pathlib.Path

Defined on DownloadableMixin

Return this component's own storage directory.

Returns

pathlib.Path

<COMPONENT_PATH>/<ClassName>.

delete(cls) -> None

Defined on DownloadableMixin

Remove the component's downloaded artifacts.

download(cls, report: Optional[Callable[[Optional[float], Optional[str]], NoneType]] = None) -> None

Defined on HFDownloadableMixin

Download all repos listed in hf_repos() into component_dir().

Parameters

report : ProgressReporter, optional

Callback invoked before each repo download with report(None, "Downloading <repo_id>"). None means no progress reporting.

get_credential(self, name: str)

Defined on ConfigObject

Resolve a registered credential component by name.

Parameters

name : str

Credential component class name (e.g. "HuggingFaceCredential").

Returns

BaseCredential

An instance of the requested credential component.

get_metadata(cls) -> Dict[str, Any]

Defined on BaseExplorer

Get metadata for the explorer, used by the DashAI frontend.

Returns

Dict[str, Any]

Dictionary containing display name, description, image preview path, category, icon, color, allowed semantic types, allowed dtypes, input cardinality constraints, and any optional capability flags declared by the explorer.

get_results(self, exploration_path: str, options: Dict[str, Any]) -> List[Any]

Defined on TextAnalysisExplorer

Load the saved figure as a plotly artifact.

Parameters

exploration_path : str

The file written by save_notebook.

options : Dict[str, Any]

Rendering options (unused).

Returns

List[Artifact]

One plotly artifact.

get_schema(cls) -> dict

Defined on ConfigObject

Generates the component related Json Schema.

Returns

dict

Dictionary representing the Json Schema of the component.

hf_repos(cls)

Defined on HFPretrainedDownloadMixin

Derive the single repo entry from MODEL_NAME.

Returns

list of tuple of (str, str)

[(MODEL_NAME, "model")] or an empty list when unset.

is_downloaded(cls) -> bool

Defined on HFDownloadableMixin

Return whether all repo directories exist and are non-empty.

Returns

bool

True when every repo listed in hf_repos() has a non-empty local directory; False otherwise (including when the list is empty).

prepare_dataset(self, loaded_dataset: Any, columns: List[Dict[str, Any]]) -> Any

Defined on TextAnalysisExplorer

Keep the selected column and the item columns a document provides.

Parameters

loaded_dataset : DashAIDataset

The loaded explorer input.

columns : List[Dict[str, Any]]

The selected columns.

Returns

DashAIDataset

The selected columns, followed by kind, page and position when the input has them.

pretrained(self) -> Any

Defined on PretrainedTool

Return the loaded model, loading it on first use.

Returns

Any

The value :meth:load_pretrained returned.

save_notebook(self, notebook_info: Any, explorer_info: Any, save_path: Any, result: Any) -> str

Defined on TextAnalysisExplorer

Save the plotly figure of the exploration as JSON.

Parameters

notebook_info : Notebook

The notebook record (unused).

explorer_info : Explorer

The explorer record, whose id names the file.

save_path : Path

The directory to save into.

result : plotly.graph_objects.Figure

The figure from launch_exploration.

Returns

str

The saved file path as a POSIX string.

set_context(self, context: Dict[str, Any]) -> None

Defined on BaseExplorer

Set optional runtime context for explorers that need extra inputs.

setup_device(self, label: Optional[str]) -> None

Defined on PretrainedTool

Choose the device and forget any loaded model.

Parameters

label : str, optional

The device parameter.

text_column(dataset: Any, explorer_info: Any) -> List[str]

Defined on TextAnalysisExplorer

Return the selected text values, with missing values as empty text.

Parameters

dataset : DashAIDataset

The prepared dataset.

explorer_info : Explorer

The explorer record naming the selected column.

Returns

List[str]

The values of the first selected column.

validate_and_transform(self, raw_data: dict) -> dict

Defined on ConfigObject

It takes the data given by the user to initialize the model and returns it with all the objects that the model needs to work.

Parameters

raw_data : dict

A dictionary with the data provided by the user to initialize the model.

Returns

dict

A validated dictionary with the necessary objects.

validate_columns(cls, explorer_info: DashAI.back.dependencies.database.models.Explorer, column_spec: Dict[str, Dict[str, str]]) -> bool

Defined on BaseExplorer

Validate that the selected columns satisfy the explorer's constraints.

Parameters

explorer_info : Explorer

The database record for the explorer instance, including the selected columns.

column_spec : Dict[str, Dict[str, str]]

A mapping from column name to a dict with at least "type" (semantic type name) and "dtype" (dtype string).

Returns

bool

True if all column constraints are satisfied, False otherwise.

validate_parameters(cls, params: Dict[str, Any]) -> bool

Defined on BaseExplorer

Validate explorer parameters against the explorer's schema.

Parameters

params : Dict[str, Any]

The configuration parameters to validate.

Returns

BaseExplorerSchema

The validated and parsed schema instance. Subclasses that override this method may return a bool to indicate pass/fail without returning the model instance.