hana_ml.text package
====================
This package contains a collection of algorithms for text related class and functions like text analysis, text mining and text chunking.

.. note::

   If you wish to use text mining-related functions, please note that the functionalities available in HANA On-Premise and HANA Cloud's text mining differ significantly. The functions supported by HANA On-Premise and HANA Cloud, along with their reference links, are listed below.

   To support both HANA On-Premise and HANA Cloud, `hana_ml` uses the same function names for equivalent functionalities. For example, `text_classification` maps to the `TM_CATEGORIZE_KNN` SQL procedure in HANA On-Premise and `PAL_TEXTCLASSIFICATION` in HANA Cloud. Additionally, certain parameters may be marked as supported only by HANA On-Premise.

   If the HANA system you are using does not support certain functions and you attempt to use them, an error will be raised.

   1. **HANA On-Premise** Text Mining

   - :func:`~hana_ml.text.tm.text_classification` (`TM_CATEGORIZE_KNN <https://help.sap.com/docs/SAP_HANA_PLATFORM/4fe29514fd584807ac9f2a04f6754767/3a31be4339c845a09bc6f2340bd02e25.html?q=text+classification>`_)
   - :class:`~hana_ml.text.tm.TextClassificationWithModel` (`PAL_TEXTCLASSIFICATION_TRAIN <https://help.sap.com/docs/SAP_HANA_PLATFORM/319d36de4fd64ac3afbf91b1fb3ce8de/text-classification-train.html>`_ / `PAL_TEXTCLASSIFICATION_PREDICT <https://help.sap.com/docs/SAP_HANA_PLATFORM/319d36de4fd64ac3afbf91b1fb3ce8de/text-classification-predict.html>`_) supported since HANA 2.0 SPS08.
   - :class:`~hana_ml.text.tm.TFIDF` (`PAL_TEXT_COLLECT/PAL_TEXT_TFIDF <https://help.sap.com/docs/SAP_HANA_PLATFORM/319d36de4fd64ac3afbf91b1fb3ce8de/tf-idf-calculation-ef2bad0.html>`_) supported since HANA 2.0 SPS07.
   - :func:`~hana_ml.text.tm.get_related_doc` (`TM_GET_RELATED_DOCUMENTS <https://help.sap.com/docs/SAP_HANA_PLATFORM/4fe29514fd584807ac9f2a04f6754767/0580f4f5464d4ec1bf2ea84880e5a387.html?q=text+classification>`_)
   - :func:`~hana_ml.text.tm.get_related_term` (`TM_GET_RELATED_TERMS <https://help.sap.com/docs/SAP_HANA_PLATFORM/4fe29514fd584807ac9f2a04f6754767/dcd2ee85b3d8416094612702bcc7dc93.html?q=text+classification>`_)
   - :func:`~hana_ml.text.tm.get_relevant_doc` (`TM_GET_RELEVANT_DOCUMENTS <https://help.sap.com/docs/SAP_HANA_PLATFORM/4fe29514fd584807ac9f2a04f6754767/2eb7483abed3475cb792e729c21e97fe.html?q=text+classification>`_)
   - :func:`~hana_ml.text.tm.get_relevant_term` (`TM_GET_RELEVANT_TERMS <https://help.sap.com/docs/SAP_HANA_PLATFORM/4fe29514fd584807ac9f2a04f6754767/a232dc2c0e63416ab36305678284bdf2.html?q=text+classification>`_)
   - :func:`~hana_ml.text.tm.get_suggested_term` (`TM_GET_SUGGESTED_TERMS <https://help.sap.com/docs/SAP_HANA_PLATFORM/4fe29514fd584807ac9f2a04f6754767/6c6e7f7309b244188dcfe023e2d3605f.html?q=text+classification>`_)

   2. **HANA Cloud** Text Mining

   - :func:`~hana_ml.text.tm.text_classification` (`PAL_TEXTCLASSIFICATION <https://help.sap.com/docs/hana-cloud-database/sap-hana-cloud-sap-hana-database-predictive-analysis-library/text-classification-text-classification-6425747>`_)
   - :class:`~hana_ml.text.tm.TextClassificationWithModel` (`PAL_TEXTCLASSIFICATION_TRAIN <https://help.sap.com/docs/hana-cloud-database/sap-hana-cloud-sap-hana-database-predictive-analysis-library/text-classification-train>`_ / `PAL_TEXTCLASSIFICATION_PREDICT <https://help.sap.com/docs/hana-cloud-database/sap-hana-cloud-sap-hana-database-predictive-analysis-library/text-classification-predict>`_)
   - :func:`~hana_ml.text.tm.tf_analysis` (`PAL_TF_ANALYSIS <https://help.sap.com/docs/hana-cloud-database/sap-hana-cloud-sap-hana-database-predictive-analysis-library/term-analysis-term-analysis-0dd1876>`_)
   - :class:`~hana_ml.text.tm.TFIDF` (`PAL_TEXT_COLLECT/PAL_TEXT_TFIDF <https://help.sap.com/docs/hana-cloud-database/sap-hana-cloud-sap-hana-database-predictive-analysis-library/tf-idf-calculation-tf-idf-calculation-ef2bad0>`_)
   - :func:`~hana_ml.text.tm.get_related_doc` (`PAL_TMGETRELATEDDOC <https://help.sap.com/docs/hana-cloud-database/sap-hana-cloud-sap-hana-database-predictive-analysis-library/get-related-documents-get-related-documents-7c0a97b>`_)
   - :func:`~hana_ml.text.tm.get_related_term` (`PAL_TMGETRELATEDTERM <https://help.sap.com/docs/hana-cloud-database/sap-hana-cloud-sap-hana-database-predictive-analysis-library/get-related-terms-get-related-terms-0eebec7>`_)
   - :func:`~hana_ml.text.tm.get_relevant_doc` (`PAL_TMGETRELEVANTDOC <https://help.sap.com/docs/hana-cloud-database/sap-hana-cloud-sap-hana-database-predictive-analysis-library/get-relevant-documents-get-relevant-documents-ea0b7cd>`_)
   - :func:`~hana_ml.text.tm.get_relevant_term` (`PAL_TMGETRELEVANTTERM <https://help.sap.com/docs/hana-cloud-database/sap-hana-cloud-sap-hana-database-predictive-analysis-library/get-relevant-terms-get-relevant-terms-bb2018a>`_)
   - :func:`~hana_ml.text.tm.get_suggested_term` (`PAL_TMGETSUGGESTEDTERM <https://help.sap.com/docs/hana-cloud-database/sap-hana-cloud-sap-hana-database-predictive-analysis-library/get-suggested-terms-get-suggested-terms-ceaf49e>`_)
   - :func:`~hana_ml.text.tm.search_docs_by_keywords` (`PAL_SEARCH_DOCS_BY_KEYWORDS <https://help.sap.com/docs/hana-cloud-database/sap-hana-cloud-sap-hana-database-predictive-analysis-library/bm25-search>`_)
   - :class:`~hana_ml.text.anns_model.ANNSModel` (`PAL_ANNS_MODEL_CREATE_BY_VECTOR/PAL_ANNS_MODEL_CREATE_BY_DOC <https://help.sap.com/docs/hana-cloud-database/sap-hana-cloud-sap-hana-database-predictive-analysis-library/no-content-for-file-anns-md>`_)

The algorithms are distributed across the following sub-packages.

.. automodule:: hana_ml.text
   :no-members:
   :no-inherited-members:

.. _text_tm-label:

.. currentmodule:: hana_ml.text

hana_ml.text.tm
---------------
.. autosummary::
   :toctree: text/
   :template: function.rst

   tm.tf_analysis
   tm.text_tokenize
   tm.text_classification
   tm.get_related_doc
   tm.get_related_term
   tm.get_relevant_doc
   tm.get_relevant_term
   tm.get_suggested_term
   tm.search_docs_by_keywords
   tm.text_log_parse

.. autosummary::
   :toctree: text/
   :template: class.rst

   tm.TFIDF
   tm.TextClassificationWithModel

.. _text_anns_model-label:

.. currentmodule:: hana_ml.text

hana_ml.text.anns_model
-----------------------
.. autosummary::
   :toctree: text/
   :template: class.rst

    anns_model.ANNSModel

.. autosummary::
   :toctree: text/
   :template: function.rst

   anns_model.list_models


.. _text_pal_embeddings-label:

.. currentmodule:: hana_ml.text

hana_ml.text.pal_embeddings
---------------------------
.. autosummary::
   :toctree: text/
   :template: class.rst

   pal_embeddings.PALEmbeddings

.. _text_pal_crossencoder-label:

.. currentmodule:: hana_ml.text

hana_ml.text.pal_cross_encoder
------------------------------
.. autosummary::
   :toctree: text/
   :template: class.rst

   pal_cross_encoder.PALCrossEncoder

.. _text_splitter-label:

.. currentmodule:: hana_ml.text

hana_ml.text.text_splitter
--------------------------
.. autosummary::
   :toctree: text/
   :template: class.rst

   text_splitter.TextSplitter

hana_ml.text.ta
--------------------------
.. autosummary::
   :toctree: text/
   :template: function.rst

   ta.text_analysis
   ta.pos_tag
   ta.named_entity_recognition
   ta.sentiment_analysis