# Copyright 2021 The SQLNet Company GmbH
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to
# deal in the Software without restriction, including without limitation the
# rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
# sell copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
# DEALINGS IN THE SOFTWARE.
Contains routines for preprocessing data frames.
from .preprocessor import _Preprocessor
A TextFieldSplitter splits columns with role :const:`getml.data.roles.text` into relational
bag-of-words representations to allow the feature learners to learn patterns based on
the prescence of certain words within the text fields.
Refer to the :ref:`User guide <text_fields>` for more information.
.. code-block:: python
text_field_splitter = getml.preprocessors.TextFieldSplitter()
pipe = getml.pipeline.Pipeline(
self.type = "TextFieldSplitter"