StreamingLinearAlgorithm¶

class pyspark.mllib.regression.StreamingLinearAlgorithm(model: Optional[pyspark.mllib.regression.LinearModel])[source]¶

Base class that has to be inherited by any StreamingLinearAlgorithm.

Prevents reimplementation of methods predictOn and predictOnValues.

New in version 1.5.0.

Methods

`latestModel`()	Returns the latest model.
`predictOn`(dstream)	Use the model to make predictions on batches of data from a DStream.
`predictOnValues`(dstream)	Use the model to make predictions on the values of a DStream and carry over its keys.

Methods Documentation

latestModel() → Optional[pyspark.mllib.regression.LinearModel][source]¶: Returns the latest model.

New in version 1.5.0.

predictOn(dstream: DStream[VectorLike]) → DStream[float][source]¶

Use the model to make predictions on batches of data from a DStream.

New in version 1.5.0.

Returns

predictOnValues(dstream: DStream[Tuple[K, VectorLike]]) → DStream[Tuple[K, float]][source]¶

Use the model to make predictions on the values of a DStream and carry over its keys.

New in version 1.5.0.

Returns

IsotonicRegression

StreamingLinearRegressionWithSGD