medcat.utils.regression.results

Module Contents

Classes

FailReason

str(object='') -> str

FailDescriptor

SingleResultDescriptor

ResultDescriptor

MultiDescriptor

class medcat.utils.regression.results.FailReason

Bases: str, enum.Enum

str(object=’’) -> str str(bytes_or_buffer[, encoding[, errors]]) -> str

Create a new string object from the given object. If encoding or errors is specified, then the object must expose a data buffer that will be decoded using the given encoding and error handler. Otherwise, returns the result of object.__str__() (if defined) or repr(object). encoding defaults to sys.getdefaultencoding(). errors defaults to ‘strict’.

CONCEPT_NOT_ANNOTATED = 'CONCEPT_NOT_ANNOTATED'

The concept was not annotated by the model

INCORRECT_CUI_FOUND = 'INCORRECT_CUI_FOUND'

A different CUI with the same name was found

INCORRECT_SPAN_BIG = 'INCORRECT_SPAN_BIG'

The concept was a part of an annotation made by the model

INCORRECT_SPAN_SMALL = 'INCORRECT_SPAN_SMALL'

Only a part of the concept was annotated

CUI_NOT_FOUND = 'CUI_NOT_FOUND'

The CUI was not found in the context database

CUI_PARENT_FOUND = 'CUI_PARENT_FOUND'

The CUI annotated was the parent of the concept

CUI_CHILD_FOUND = 'CUI_CHILD_FOUND'

The CUI annotated was a child of the concept

NAME_NOT_FOUND = 'NAME_NOT_FOUND'

The name specified was not found in the context database

UNKNOWN = 'UNKNOWN'

Unknown reason for failure

class medcat.utils.regression.results.FailDescriptor

Bases: pydantic.BaseModel

cui: str
name: str
reason: FailReason
extra: str = ''
classmethod get_reason_for(cui, name, res, translation)

Get the fail reason for the failure of finding the specifeid CUI and name where the resulting entities are presented.

Parameters:

  • cui (str) – The cui that was expected

  • name (str) – The name that was expected

  • res (dict) – The entities that were annotated

  • translation (TranslationLayer) – The translation layer

Returns:

FailDescriptor – The corresponding fail descriptor

Return type:

FailDescriptor

class medcat.utils.regression.results.SingleResultDescriptor

Bases: pydantic.BaseModel

name: str

The name of the part that was checked

success: int = 0

Number of successes

fail: int = 0

Number of failures

failures: List[FailDescriptor] = []

The description of failures

report_success(cui, name, success, fail_reason)

Report a test case and its successfulness

Parameters:

  • cui (str) – The CUI being checked

  • name (str) – The name being checked

  • success (bool) – Whether or not the check was successful

  • fail_reason (Optional[FailDescriptor]) – The reason for the failure (if applicable)

Return type:

None

get_report()

Get the report associated with this descriptor

Returns:

str – The report string

Return type:

str

class medcat.utils.regression.results.ResultDescriptor

Bases: SingleResultDescriptor

per_phrase_results: Dict[str, SingleResultDescriptor]
report(cui, name, phrase, success, fail_reason)

Report a test case and its successfulness

Parameters:

  • cui (str) – The CUI being checked

  • name (str) – The name being checked

  • phrase (str) – The phrase being checked

  • success (bool) – Whether or not the check was successful

  • fail_reason (Optional[FailDescriptor]) – The reason for the failure (if applicable)

Return type:

None

get_report(phrases_separately=False)

Get the report associated with this descriptor

Parameters:

phrases_separately (bool) – Whether to output descriptor for each phrase separately

Returns:

str – The report string

Return type:

str

class medcat.utils.regression.results.MultiDescriptor

Bases: pydantic.BaseModel

property success: int

The total number of successes.

Returns:

int – The total number of sucesses.

Return type:

int

property fail: int

The total number of failures.

Returns:

int – The total number of failures.

Return type:

int

name: str

The name of the collection being checked

parts: List[ResultDescriptor] = []

The parts kept track of

get_report(phrases_separately, hide_empty=False, show_failures=True)

Get the report associated with this descriptor

Parameters:

  • phrases_separately (bool) – Whether to include per-phrase information

  • hide_empty (bool) – Whether to hide empty cases

  • show_failures (bool) – Whether to show failures

Returns:

str – The report string

Return type:

str