anandexplore opened a new pull request, #52519:
URL: https://github.com/apache/spark/pull/52519
<!--
Thanks for sending a pull request! Here are some tips for you:
1. If this is your first time, please read our contributor guidelines:
https://spark.apache.org/contributing.html
2. Ensure you have added or run the appropriate tests for your PR:
https://spark.apache.org/developer-tools.html
3. If the PR is unfinished, add '[WIP]' in your PR title, e.g.,
'[WIP][SPARK-XXXX] Your PR title ...'.
4. Be sure to keep the PR description updated to reflect all changes.
5. Please write your PR title to summarize what this PR proposes.
6. If possible, provide a concise example to reproduce the issue for a
faster review.
7. If you want to add a new configuration, please read the guideline first
for naming configurations in
'core/src/main/scala/org/apache/spark/internal/config/ConfigEntry.scala'.
8. If you want to add or modify an error type or message, please read the
guideline first in
'common/utils/src/main/resources/error/README.md'.
-->
### What changes were proposed in this pull request?
This pull request adds a new estimator, ArimaRegression, to Spark MLlib
under org.apache.spark.ml.regression. It implements the ARIMA (AutoRegressive
Integrated Moving Average) model for univariate time series forecasting, along
with its corresponding model class ArimaRegressionModel.
The contribution includes:
Scala implementation of ArimaRegression and ArimaRegressionModel
Support for ARIMA parameters: p, d, and q
PySpark API bindings for both classes
Unit tests for Scala and Python
Model save/load support via MLWritable/MLReadable
Example usage in examples/ml/ArimaRegressionExample.scala
### Why are the changes needed?
Spark MLlib currently lacks built-in support for statistical time series
forecasting models.
ARIMA is one of the most widely used models for univariate time series
prediction.
Adding ArimaRegression enables users to build forecasting pipelines using
standard MLlib APIs.
It improves feature completeness and allows end-to-end time series modeling
without relying on external Python libraries.
### Does this PR introduce _any_ user-facing change?
Yes.
New user-facing APIs introduced in both Scala and Python:
org.apache.spark.ml.regression.ArimaRegression
org.apache.spark.ml.regression.ArimaRegressionModel
pyspark.ml.regression.ArimaRegression
pyspark.ml.regression.ArimaRegressionModel
These follow standard Spark ML APIs and integrate with Pipeline, ParamMap,
Model.save/load, and transform() interfaces.
### How was this patch tested?
Added Scala unit tests in ArimaRegressionSuite.scala:
Fit/transform behavior
Parameter defaults and setters
Model persistence (save/load)
Added PySpark unit tests in test_regression.py
Manually tested in:
spark-shell (Scala)
pyspark (Python)
Verified predictions and schema of transformed output
### Was this patch authored or co-authored using generative AI tooling?
No.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
