From 23452be944463dae72a35b58551040556dd3aeb5 Mon Sep 17 00:00:00 2001 From: Xiangrui Meng Date: Fri, 29 May 2015 00:51:12 -0700 Subject: [SPARK-7912] [SPARK-7921] [MLLIB] Update OneHotEncoder to handle ML attributes and change includeFirst to dropLast This PR contains two major changes to `OneHotEncoder`: 1. more robust handling of ML attributes. If the input attribute is unknown, we look at the values to get the max category index 2. change `includeFirst` to `dropLast` and leave the default to `true`. There are couple benefits: a. consistent with other tutorials of one-hot encoding (or dummy coding) (e.g., http://www.ats.ucla.edu/stat/mult_pkg/faq/general/dummy.htm) b. keep the indices unmodified in the output vector. If we drop the first, all indices will be shifted by 1. c. If users use `StringIndex`, the last element is the least frequent one. Sorry for including two changes in one PR! I'll update the user guide in another PR. jkbradley sryza Author: Xiangrui Meng Closes #6466 from mengxr/SPARK-7912 and squashes the following commits: a280dca [Xiangrui Meng] fix tests d8f234d [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into SPARK-7912 171b276 [Xiangrui Meng] mention the difference between our impl vs sklearn's 00dfd96 [Xiangrui Meng] update OneHotEncoder in Python 208ddad [Xiangrui Meng] update OneHotEncoder to handle ML attributes and change includeFirst to dropLast --- python/pyspark/ml/feature.py | 58 +++++++++++++++++++++++++------------------- 1 file changed, 33 insertions(+), 25 deletions(-) (limited to 'python/pyspark/ml') diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py index b0479d9b07..ddb33f427a 100644 --- a/python/pyspark/ml/feature.py +++ b/python/pyspark/ml/feature.py @@ -324,65 +324,73 @@ class Normalizer(JavaTransformer, HasInputCol, HasOutputCol): @inherit_doc class OneHotEncoder(JavaTransformer, HasInputCol, HasOutputCol): """ - A one-hot encoder that maps a column of label indices to a column of binary vectors, with - at most a single one-value. By default, the binary vector has an element for each category, so - with 5 categories, an input value of 2.0 would map to an output vector of - (0.0, 0.0, 1.0, 0.0, 0.0). If includeFirst is set to false, the first category is omitted, so - the output vector for the previous example would be (0.0, 1.0, 0.0, 0.0) and an input value - of 0.0 would map to a vector of all zeros. Including the first category makes the vector columns - linearly dependent because they sum up to one. - - TODO: This method requires the use of StringIndexer first. Decouple them. + A one-hot encoder that maps a column of category indices to a + column of binary vectors, with at most a single one-value per row + that indicates the input category index. + For example with 5 categories, an input value of 2.0 would map to + an output vector of `[0.0, 0.0, 1.0, 0.0]`. + The last category is not included by default (configurable via + :py:attr:`dropLast`) because it makes the vector entries sum up to + one, and hence linearly dependent. + So an input value of 4.0 maps to `[0.0, 0.0, 0.0, 0.0]`. + Note that this is different from scikit-learn's OneHotEncoder, + which keeps all categories. + The output vectors are sparse. + + .. seealso:: + + :py:class:`StringIndexer` for converting categorical values into + category indices >>> stringIndexer = StringIndexer(inputCol="label", outputCol="indexed") >>> model = stringIndexer.fit(stringIndDf) >>> td = model.transform(stringIndDf) - >>> encoder = OneHotEncoder(includeFirst=False, inputCol="indexed", outputCol="features") + >>> encoder = OneHotEncoder(inputCol="indexed", outputCol="features") >>> encoder.transform(td).head().features - SparseVector(2, {}) + SparseVector(2, {0: 1.0}) >>> encoder.setParams(outputCol="freqs").transform(td).head().freqs - SparseVector(2, {}) - >>> params = {encoder.includeFirst: True, encoder.outputCol: "test"} + SparseVector(2, {0: 1.0}) + >>> params = {encoder.dropLast: False, encoder.outputCol: "test"} >>> encoder.transform(td, params).head().test SparseVector(3, {0: 1.0}) """ # a placeholder to make it appear in the generated doc - includeFirst = Param(Params._dummy(), "includeFirst", "include first category") + dropLast = Param(Params._dummy(), "dropLast", "whether to drop the last category") @keyword_only - def __init__(self, includeFirst=True, inputCol=None, outputCol=None): + def __init__(self, dropLast=True, inputCol=None, outputCol=None): """ __init__(self, includeFirst=True, inputCol=None, outputCol=None) """ super(OneHotEncoder, self).__init__() self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.OneHotEncoder", self.uid) - self.includeFirst = Param(self, "includeFirst", "include first category") - self._setDefault(includeFirst=True) + self.dropLast = Param(self, "dropLast", "whether to drop the last category") + self._setDefault(dropLast=True) kwargs = self.__init__._input_kwargs self.setParams(**kwargs) @keyword_only - def setParams(self, includeFirst=True, inputCol=None, outputCol=None): + def setParams(self, dropLast=True, inputCol=None, outputCol=None): """ - setParams(self, includeFirst=True, inputCol=None, outputCol=None) + setParams(self, dropLast=True, inputCol=None, outputCol=None) Sets params for this OneHotEncoder. """ kwargs = self.setParams._input_kwargs return self._set(**kwargs) - def setIncludeFirst(self, value): + def setDropLast(self, value): """ - Sets the value of :py:attr:`includeFirst`. + Sets the value of :py:attr:`dropLast`. """ - self._paramMap[self.includeFirst] = value + self._paramMap[self.dropLast] = value return self - def getIncludeFirst(self): + def getDropLast(self): """ - Gets the value of includeFirst or its default value. + Gets the value of dropLast or its default value. """ - return self.getOrDefault(self.includeFirst) + return self.getOrDefault(self.dropLast) @inherit_doc -- cgit v1.2.3