diff options
author | Joseph K. Bradley <joseph@databricks.com> | 2015-09-11 08:55:35 -0700 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2015-09-11 08:55:35 -0700 |
commit | 2e3a280754a28dc36a71b9ff988e34cbf457f6c3 (patch) | |
tree | 9e2ab19bf0265f82fa85fb4b6daadcc858fbadb0 /python/pyspark/ml | |
parent | 960d2d0ac6b5a22242a922f87f745f7d1f736181 (diff) | |
download | spark-2e3a280754a28dc36a71b9ff988e34cbf457f6c3.tar.gz spark-2e3a280754a28dc36a71b9ff988e34cbf457f6c3.tar.bz2 spark-2e3a280754a28dc36a71b9ff988e34cbf457f6c3.zip |
[MINOR] [MLLIB] [ML] [DOC] Minor doc fixes for StringIndexer and MetadataUtils
Changes:
* Make Scala doc for StringIndexerInverse clearer. Also remove Scala doc from transformSchema, so that the doc is inherited.
* MetadataUtils.scala: “ Helper utilities for tree-based algorithms” —> not just trees anymore
CC: holdenk mengxr
Author: Joseph K. Bradley <joseph@databricks.com>
Closes #8679 from jkbradley/doc-fixes-1.5.
Diffstat (limited to 'python/pyspark/ml')
-rw-r--r-- | python/pyspark/ml/feature.py | 16 |
1 files changed, 8 insertions, 8 deletions
diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py index 71dc636b83..97cbee73a0 100644 --- a/python/pyspark/ml/feature.py +++ b/python/pyspark/ml/feature.py @@ -985,17 +985,17 @@ class IndexToString(JavaTransformer, HasInputCol, HasOutputCol): """ .. note:: Experimental - A :py:class:`Transformer` that maps a column of string indices back to a new column of - corresponding string values using either the ML attributes of the input column, or if - provided using the labels supplied by the user. - All original columns are kept during transformation. + A :py:class:`Transformer` that maps a column of indices back to a new column of + corresponding string values. + The index-string mapping is either from the ML attributes of the input column, + or from user-supplied labels (which take precedence over ML attributes). See L{StringIndexer} for converting strings into indices. """ # a placeholder to make the labels show up in generated doc labels = Param(Params._dummy(), "labels", - "Optional array of labels to be provided by the user, if not supplied or " + - "empty, column metadata is read for labels") + "Optional array of labels specifying index-string mapping." + + " If not provided or if empty, then metadata from inputCol is used instead.") @keyword_only def __init__(self, inputCol=None, outputCol=None, labels=None): @@ -1006,8 +1006,8 @@ class IndexToString(JavaTransformer, HasInputCol, HasOutputCol): self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.IndexToString", self.uid) self.labels = Param(self, "labels", - "Optional array of labels to be provided by the user, if not " + - "supplied or empty, column metadata is read for labels") + "Optional array of labels specifying index-string mapping. If not" + + " provided or if empty, then metadata from inputCol is used instead.") kwargs = self.__init__._input_kwargs self.setParams(**kwargs) |