Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/7150#discussion_r39089963 --- Diff: python/pyspark/ml/feature.py --- @@ -1291,6 +1291,96 @@ class RFormulaModel(JavaModel): """ +@inherit_doc +class MinMaxScaler(JavaEstimator, HasInputCol, HasOutputCol): + """ + Rescale each feature individually to a common range [min, max] linearly using column summary + statistics, which is also known as min-max normalization or Rescaling. The rescaled value for + feature E is calculated as, + + Rescaled(e_i) = (e_i - E_min) / (E_max - E_min) * (max - min) + min + + For the case E_max == E_min, Rescaled(e_i) = 0.5 * (max + min) + + Note that since zero values will probably be transformed to non-zero values, output of the + transformer will be DenseVector even for sparse input. + + >>> from pyspark.mllib.linalg import Vectors + >>> df = sqlContext.createDataFrame([(Vectors.dense([0.0]),), (Vectors.dense([2.0]),)], ["a"]) + >>> mmScaler = MinMaxScaler(inputCol="a", outputCol="scaled") + >>> model = mmScaler.fit(df) + >>> model.transform(df).show() + +-----+------+ + | a|scaled| + +-----+------+ + |[0.0]| [0.0]| + |[2.0]| [1.0]| + +-----+------+ + ... + """ + + # a placeholder to make it appear in the generated doc + min = Param(Params._dummy(), "min", "Lower bound of the output feature range") + max = Param(Params._dummy(), "max", "Upper bound of the output feature range") + + @keyword_only + def __init__(self, min=0.0, max=1.0, inputCol=None, outputCol=None): + """ + __init__(self, min=0.0, max=1.0, inputCol=None, outputCol=None) + """ + super(MinMaxScaler, self).__init__() + self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.MinMaxScaler", self.uid) + self.min = Param(self, "min", "Lower bound of the output feature range") + self.max = Param(self, "max", "Upper bound of the output feature range") + self._setDefault(min=0.0, max=1.0) + kwargs = self.__init__._input_kwargs + self.setParams(**kwargs) + + @keyword_only + def setParams(self, min=0.0, max=1.0, inputCol=None, outputCol=None): + """ + setParams(self, min=0.0, max=1.0, inputCol=None, outputCol=None) + Sets params for this MinMaxScaler. + """ + kwargs = self.setParams._input_kwargs + return self._set(**kwargs) + + def setMin(self, value): + """ + Sets the value of :py:attr:`min`. + """ + self._paramMap[self.min] = value + return self + + def getMin(self): + """ + Gets the value of min or its default value. + """ + return self.getOrDefault(self.min) + + def setMax(self, value): + """ + Sets the value of :py:attr:`max`. + """ + self._paramMap[self.max] = value + return self + + def getMax(self): + """ + Gets the value of max or its default value. + """ + return self.getOrDefault(self.max) + + def _create_model(self, java_model): + return MinMaxScalerModel(java_model) + + +class MinMaxScalerModel(JavaModel): + """ + Model fitted by MinMaxScaler. --- End diff -- Nicer to write: ```:py:class:`MinMaxScaler````
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org