Hivemall: Hive scalable machine learning library

Hivemall is a scalable machine learning library that runs on Apache Hive, licensed under the LGPL 2.1.
Hivemall is designed to be scalable to the number of training instances as well as the number of training features.

Supported Algorithms

Hivemall provides machine learning functionality as well as feature engineering functions through UDFs/UDAFs/UDTFs of Hive.

Classfication

Perceptron
Passive Aggressive (PA, PA1, PA2)
Confidence Weighted (CW)
Adaptive Regularization of Weight Vectors (AROW)
Soft Confidence Weighted (SCW1, SCW2)

Regression

Logistic Regression using Stochastic Gradient Descent (parameter mixing and iterative parameter mixing)
Passive Aggressive Regression (PA1, PA2)
AROW regression

Recommendation

Minhash (LSH with jaccard index)

k-Nearest Neighbor

Minhash (LSH with jaccard index)
b-Bit minhash
Brute-force search using cosine similarity

Feature engineering

Feature hashing (MurmurHash, SHA1)
Feature scaling (Min-Max Normalization, Z-Score)
Feature instances amplifier that reduces iterations on training
Bias clause
Data generator for one-vs-the-rest classifiers

System requirements

Hive 0.9 and later (Tested for v0.9 - v0.12)
Hadoop 0.20.x (CDH3 is our target)

Basic Usage

SELECT 
  feature, 
  CAST(avg(weight) as FLOAT) as weight
FROM
 (SELECT logress(features,label) as (feature,weight) FROM training_features) t
GROUP BY feature;

Find more examples on our wiki page.

License

GNU Lesser General Public License 2.1
http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html

According to LGPL 2.1, softwares that modifies/copies Hivemall MUST open their source codes upon requests.
On the other hand, softwares that uses the Hivemall jar package without any modification are no need to show their sources. See GNU's LGPL and Java page for detail.

The LGPL does not require you to distribute source code of programs as far as just using/linking Hivemall in your application, so you can use Hivemall in closed-source apps and for most commercial uses.

Copyright

Put the above copyrights for the services/softwares that use Hivemall.

Support

Support is through the issue list.

References

Please refer the following paper for research uses:

Makoto Yui. ``Hivemall: Scalable Machine Learning Library for Apache Hive'', 2014 Hadoop Summit, June 2014. [slide]
Makoto Yui and Isao Kojima. ``Hivemall: Hive scalable machine learning library'' (demo paper), NIPS 2013 Workshop on Machine Learning Open Source Software: Towards Open Workflows, Dec 2013.
Makoto Yui and Isao Kojima. ``A Database-Hadoop Hybrid Approach to Scalable Machine Learning'',
Proc. IEEE 2nd International Congress on Big Data, July 2013 [paper] [slide]

Acknowledgment

This work was supported in part by a JSPS grant-in-aid for young scientists (B) #24700111 and a JSPS grant-in-aid for scientific research (A) #24240015.

About

Scalable machine learning library for Hive/Hadoop

GNU Lesser General Public License v2.1