pyspark.ml.feature.
RobustScaler
RobustScaler removes the median and scales the data according to the quantile range. The quantile range is by default IQR (Interquartile Range, quantile range between the 1st quartile = 25th quantile and the 3rd quartile = 75th quantile) but can be configured. Centering and scaling happen independently on each feature by computing the relevant statistics on the samples in the training set. Median and quantile range are then stored to be used on later data using the transform method. Note that NaN values are ignored in the computation of medians and ranges.
New in version 3.0.0.
Examples
>>> from pyspark.ml.linalg import Vectors >>> data = [(0, Vectors.dense([0.0, 0.0]),), ... (1, Vectors.dense([1.0, -1.0]),), ... (2, Vectors.dense([2.0, -2.0]),), ... (3, Vectors.dense([3.0, -3.0]),), ... (4, Vectors.dense([4.0, -4.0]),),] >>> df = spark.createDataFrame(data, ["id", "features"]) >>> scaler = RobustScaler() >>> scaler.setInputCol("features") RobustScaler... >>> scaler.setOutputCol("scaled") RobustScaler... >>> model = scaler.fit(df) >>> model.setOutputCol("output") RobustScalerModel... >>> model.median DenseVector([2.0, -2.0]) >>> model.range DenseVector([2.0, 2.0]) >>> model.transform(df).collect()[1].output DenseVector([0.5, -0.5]) >>> scalerPath = temp_path + "/robust-scaler" >>> scaler.save(scalerPath) >>> loadedScaler = RobustScaler.load(scalerPath) >>> loadedScaler.getWithCentering() == scaler.getWithCentering() True >>> loadedScaler.getWithScaling() == scaler.getWithScaling() True >>> modelPath = temp_path + "/robust-scaler-model" >>> model.save(modelPath) >>> loadedModel = RobustScalerModel.load(modelPath) >>> loadedModel.median == model.median True >>> loadedModel.range == model.range True >>> loadedModel.transform(df).take(1) == model.transform(df).take(1) True
Methods
clear(param)
clear
Clears a param from the param map if it has been explicitly set.
copy([extra])
copy
Creates a copy of this instance with the same uid and some extra params.
explainParam(param)
explainParam
Explains a single param and returns its name, doc, and optional default value and user-supplied value in a string.
explainParams()
explainParams
Returns the documentation of all params with their optionally default values and user-supplied values.
extractParamMap([extra])
extractParamMap
Extracts the embedded default param values and user-supplied values, and then merges them with extra values from input into a flat param map, where the latter value is used if there exist conflicts, i.e., with ordering: default param values < user-supplied values < extra.
fit(dataset[, params])
fit
Fits a model to the input dataset with optional parameters.
fitMultiple(dataset, paramMaps)
fitMultiple
Fits a model to the input dataset for each param map in paramMaps.
getInputCol()
getInputCol
Gets the value of inputCol or its default value.
getLower()
getLower
Gets the value of lower or its default value.
getOrDefault(param)
getOrDefault
Gets the value of a param in the user-supplied param map or its default value.
getOutputCol()
getOutputCol
Gets the value of outputCol or its default value.
getParam(paramName)
getParam
Gets a param by its name.
getRelativeError()
getRelativeError
Gets the value of relativeError or its default value.
getUpper()
getUpper
Gets the value of upper or its default value.
getWithCentering()
getWithCentering
Gets the value of withCentering or its default value.
getWithScaling()
getWithScaling
Gets the value of withScaling or its default value.
hasDefault(param)
hasDefault
Checks whether a param has a default value.
hasParam(paramName)
hasParam
Tests whether this instance contains a param with a given (string) name.
isDefined(param)
isDefined
Checks whether a param is explicitly set by user or has a default value.
isSet(param)
isSet
Checks whether a param is explicitly set by user.
load(path)
load
Reads an ML instance from the input path, a shortcut of read().load(path).
read()
read
Returns an MLReader instance for this class.
save(path)
save
Save this ML instance to the given path, a shortcut of ‘write().save(path)’.
set(param, value)
set
Sets a parameter in the embedded param map.
setInputCol(value)
setInputCol
Sets the value of inputCol.
inputCol
setLower(value)
setLower
Sets the value of lower.
lower
setOutputCol(value)
setOutputCol
Sets the value of outputCol.
outputCol
setParams(self, \*[, lower, upper, …])
setParams
Sets params for this RobustScaler.
setRelativeError(value)
setRelativeError
Sets the value of relativeError.
relativeError
setUpper(value)
setUpper
Sets the value of upper.
upper
setWithCentering(value)
setWithCentering
Sets the value of withCentering.
withCentering
setWithScaling(value)
setWithScaling
Sets the value of withScaling.
withScaling
write()
write
Returns an MLWriter instance for this ML instance.
Attributes
params
Returns all params ordered by name.
Methods Documentation
Creates a copy of this instance with the same uid and some extra params. This implementation first calls Params.copy and then make a copy of the companion Java pipeline component with extra params. So both the Python wrapper and the Java pipeline component get copied.
Extra parameters to copy to the new instance
JavaParams
Copy of this instance
extra param values
merged param map
New in version 1.3.0.
pyspark.sql.DataFrame
input dataset.
an optional param map that overrides embedded params. If a list/tuple of param maps is given, this calls fit on each param map and returns a list of models.
Transformer
fitted model(s)
New in version 2.3.0.
collections.abc.Sequence
A Sequence of param maps.
_FitMultipleIterator
A thread safe iterable which contains one model for each param map. Each call to next(modelIterator) will return (index, model) where model was fit using paramMaps[index]. index values may not be sequential.
Gets the value of a param in the user-supplied param map or its default value. Raises an error if neither is set.
Attributes Documentation
Returns all params ordered by name. The default implementation uses dir() to get all attributes of type Param.
dir()
Param