medcat.utils.ner.helpers
Module Contents
Functions
|
De-identify text. |
|
|
|
|
|
Creates a new CDB or updates an existing one with new |
- medcat.utils.ner.helpers._deid_text(cat, text, redact=False)
De-identify text.
De-identified text. If redaction is enabled, identifiable entities will be replaced with starts (e.g *****). Otherwise, the replacement will be the CUI or in other words, the type of information that was hidden (e.g [PATIENT]).
- Parameters:
cat (CAT) – The CAT object to use for deid.
text (str) – The input document.
redact (bool) – Whether to redact. Defaults to False.
- Returns:
str – The de-identified document.
- Return type:
str
- medcat.utils.ner.helpers.replace_entities_in_text(text, entities, get_cui_name, redact=False)
- Parameters:
text (str) –
entities (Dict) –
get_cui_name (Callable[[str], str]) –
redact (bool) –
- Return type:
str
- medcat.utils.ner.helpers.deid_text(*args, **kwargs)
- Return type:
str
- medcat.utils.ner.helpers.make_or_update_cdb(json_path, cdb=None, min_count=0)
Creates a new CDB or updates an existing one with new concepts if the cdb argument is provided. All concepts that are less frequent than min_count will be ignored.
- Parameters:
json_path (str) – The json path
cdb (Optional[CDB]) – The CDB if present. Defaults to None.
min_count (int) – Minimum count to include. Defaults to 0.
- Returns:
CDB – The same or new CDB.
- Return type: