Skip to content
Snippets Groups Projects
Select Git revision
  • working
  • baesline-eviction-with-logging
  • evict-by-size
  • master default protected
  • v2.3.0
  • v2.3.0-rc4
  • v2.3.0-rc3
  • v2.3.0-rc2
  • v2.3.0-rc1
  • v2.2.1
  • v2.2.1-rc2
  • v2.2.1-rc1
  • v2.1.2
  • v2.1.2-rc4
  • v2.1.2-rc3
  • v2.1.2-rc2
  • v2.1.2-rc1
  • v2.2.0
  • v2.1.1
  • v2.1.0
  • v2.0.2
  • v1.6.3
  • v2.0.1
  • v2.0.0
24 results
Compare
user avatar
[SPARK-14489][ML][PYSPARK] ALS unknown user/item prediction strategy
Nick Pentreath authored 
This PR adds a param to `ALS`/`ALSModel` to set the strategy used when encountering unknown users or items at prediction time in `transform`. This can occur in 2 scenarios: (a) production scoring, and (b) cross-validation & evaluation.

The current behavior returns `NaN` if a user/item is unknown. In scenario (b), this can easily occur when using `CrossValidator` or `TrainValidationSplit` since some users/items may only occur in the test set and not in the training set. In this case, the evaluator returns `NaN` for all metrics, making model selection impossible.

The new param, `coldStartStrategy`, defaults to `nan` (the current behavior). The other option supported initially is `drop`, which drops all rows with `NaN` predictions. This flag allows users to use `ALS` in cross-validation settings. It is made an `expertParam`. The param is made a string so that the set of strategies can be extended in future (some options are discussed in [SPARK-14489](https://issues.apache.org/jira/browse/SPARK-14489)).
## How was this patch tested?

New unit tests, and manual "before and after" tests for Scala & Python using MovieLens `ml-latest-small` as example data. Here, using `CrossValidator` or `TrainValidationSplit` with the default param setting results in metrics that are all `NaN`, while setting `coldStartStrategy` to `drop` results in valid metrics.

Author: Nick Pentreath <nickp@za.ibm.com>

Closes #12896 from MLnick/SPARK-14489-als-nan.
b4054665
History
user avatar b4054665
History
Name Last commit Last update
..
docs
lib
pyspark
test_support
.gitignore
MANIFEST.in
README.md
pylintrc
run-tests
run-tests.py
setup.cfg
setup.py
README.md

Apache Spark

Spark is a fast and general cluster computing system for Big Data. It provides high-level APIs in Scala, Java, Python, and R, and an optimized engine that supports general computation graphs for data analysis. It also supports a rich set of higher-level tools including Spark SQL for SQL and DataFrames, MLlib for machine learning, GraphX for graph processing, and Spark Streaming for stream processing.

http://spark.apache.org/

Online Documentation

You can find the latest Spark documentation, including a programming guide, on the project web page

Python Packaging

This README file only contains basic information related to pip installed PySpark. This packaging is currently experimental and may change in future versions (although we will do our best to keep compatibility). Using PySpark requires the Spark JARs, and if you are building this from source please see the builder instructions at "Building Spark".

The Python packaging for Spark is not intended to replace all of the other use cases. This Python packaged version of Spark is suitable for interacting with an existing cluster (be it Spark standalone, YARN, or Mesos) - but does not contain the tools required to setup your own standalone Spark cluster. You can download the full version of Spark from the Apache Spark downloads page.

NOTE: If you are using this with a Spark standalone cluster you must ensure that the version (including minor version) matches or you may experience odd errors.

Python Requirements

At its core PySpark depends on Py4J (currently version 0.10.4), but additional sub-packages have their own requirements (including numpy and pandas).