named_entity_recognition

hana_ml.text.ta.named_entity_recognition(data, lang=None, thread_ratio=None, timeout=None)

This is a wrapper of named entity recognition (NER) functionality for text analysis, which aims at facilitating users' use of text analysis targeted specially for named entity recognition.

dataDataFrame

The input data for text analysis, should be a DataFrame structured as follows:

  • 1st column : ID of input text, of type INT, VARCHAR if NVARCHAR

  • 2nd column : Text content, of type VARCHAR, NVARCHAR or NCLOB

  • 3rd column (optional) : Specifies the language of the text content, can be 'en', 'de', 'fr', 'es', 'pt' or NULL (means automatically detected).

lang{'en', 'de', 'fr', 'es', 'pt'}, optional

Specifies the language of the input texts in data.

Effective only when the language column in data is not provided (i.e. data has two columns).

thread_ratiofloat, optional

Specifies the ratio of threads that can be used by this function, with valid range from 0 to 1, where

  • 0 means only using a single thread.

  • 1 means using at most all the currently available threads.

Values outside valid range are ignored (no error thrown), and in such case the function heuristically determines the number of threads to use.

Defaults to 0.0.

timeoutint, optional

Specifies the maximum amount of time (in seconds) the client will wait for a response from the server.

Defaults to 10.

Returns
A tuple of DataFrames:

  • DataFrame 1 : The NER results for input texts

  • DataFrame 2 : Sentences result table

  • DataFrame 3 : Extra result table

Examples

>>> ner, sentences, extra = named_entity_recognition(data=df, thread_ratio=0.5, timeout=20)