Download as PDF, PPTX
![5
A Lego For Your Database
Key
"I'm a Plain Text String!"
{ A: “foo”, B: “bar”, C: “baz” }
Strings/Blobs/Bitmaps
Hash Tables (objects!)
Linked Lists
Sets
Sorted Sets
Geo Sets
HyperLogLog
{ A , B , C , D , E }
[ A → B → C → D → E ]
{ A: 0.1, B: 0.3, C: 100, D: 1337 }
{ A: (51.5, 0.12), B: (32.1, 34.7) }
00110101 11001110 10101010](https://image.slidesharecdn.com/sparkmlredis2-161121091417/75/Boosting-Machine-Learning-with-Redis-Modules-and-Spark-5-2048.jpg)
![27
Using Redis-ML With Spark
scala> import com.redislabs.client.redisml.MLClient
scala> import com.redislabs.provider.redis.ml.Forest
scala> val rfModel =
pipelineModel.stages.last.asInstanceOf[RandomForestClassificationModel]
scala> val f = new Forest(rfModel.trees)
scala> f.loadToRedis("forest-test", "localhost")
scala> val jedis = new Jedis("localhost")
scala> jedis.getClient.sendCommand(MLClient.ModuleCommand.FOREST_RUN,
"forest-test", makeInputString (0))
scala> jedis.getClient.getStatusCodeReply
res53: String = 1](https://image.slidesharecdn.com/sparkmlredis2-161121091417/75/Boosting-Machine-Learning-with-Redis-Modules-and-Spark-27-2048.jpg)
Uploaded byDvir Volk
Boosting Machine Learning with Redis Modules and Spark
Redis modules allow for new capabilities like machine learning models to be added to Redis. The Redis-ML module stores machine learning models like random forests and supports operations like model training, evaluation, and prediction directly from Redis for low latency. Spark can be used to train models which are then saved as Redis modules, allowing models to be easily deployed and accessed from services and clients.
More Related Content
Similar to Boosting Machine Learning with Redis Modules and Spark
Boosting Machine Learning with Redis Modules and Spark
- 1. Boosting Machine Learningwith Redis Modules and Spark Dvir Volk, Redis Labs, November 2016
- 2. 2 Hello World Open source.The leading in-memory database The open source home and commercial provider of Redis - cloud and on-premise Senior System Architect at Redis Labs. Redis user and contributor for ~6 years @dvirsky dvirvolk
- 3. 3 A Brief Overviewof Redis ● Started in 2009 by Salvatore Sanfilippo ● Mostly a one man show ● Most popular KV store ● Notable Users: ○ Twitter, Netflix, Uber, Groupon, Twitch ○ Many, many more...
- 4. 4 A Brief Overviewof Redis ▪ Key => Data Structure server ▪ In memory disk backed ▪ Optional cluster mode ▪ Embedded Lua scripting ▪ Single Threaded! ▪ Key features: Fast, Flexible, Simple
- 5. 5 A Lego ForYour Database Key "I'm a Plain Text String!" { A: “foo”, B: “bar”, C: “baz” } Strings/Blobs/Bitmaps Hash Tables (objects!) Linked Lists Sets Sorted Sets Geo Sets HyperLogLog { A , B , C , D , E } [ A → B → C → D → E ] { A: 0.1, B: 0.3, C: 100, D: 1337 } { A: (51.5, 0.12), B: (32.1, 34.7) } 00110101 11001110 10101010
- 6. 6 Redis In Practice ▪“Front End Database” ▪ Real Time Counters ▪ Ad Serving ▪ Message Queues ▪ Geo Database ▪ Time Series ▪ Cache ▪ Session State ▪ Etc
- 7. 7 But Can RedisDo X? Secondary Index? Time Series? Full Text Search? Graph? Machine Learning? AutoComplete? SQL?
- 8. 8 So You Wanta New Feature? ▪ Try a Lua script ▪ Convince @antirez ▪ Fork Redis ▪ Build Your Own Database!
- 9. 9 Enter Redis Modules ▪In development since March 2016 ▪ Redis 4.0 RC out soon ▪ Several modules already exist ▪ Key paradigm shift for Redis
- 10. 10 New Capabilities What ModulesActually Are ▪ Dynamic libraries loaded to redis ▪ Written in C/C++ ▪ Use a C ABI/API isolating redis internals ▪ Near Zero latency access to data New Commands New Data Types
- 11.
- 12. 12 LEFTPAD Example 127.0.0.1:6379> MODULELOAD "./example.so" OK 127.0.0.1:6379> COMMAND INFO EXAMPLE.LEFTPAD 1) 1) "example.leftpad" ... 127.0.0.1:6379> EXAMPLE.LEFTPAD "foo" 8 foo 127.0.0.1:6379> EXAMPLE.LEFTPAD "foo" 8 "_" _____foo
- 13. 13 Real Module: RediSearch ▪From-Scratch search index over redis ▪ Uses Strings for holding compressed index data ▪ Includes stemming, exact phrase match, etc. ▪ Fast Fuzzy Auto-complete ▪ Up to X5 faster than Elastic / Solr > FT.SEARCH “lcd tv” FILTER price 100 +inf > FT.SUGGET “lcd” FUZZY
- 14. 14 More Modules OutThere ▪ Native JSON Support ▪ Time Series ▪ Secondary Indexing ▪ Encryption ▪ Bloom Filters ▪ Online Neural Network ▪ Many Many more...
- 15. 15 Spark ML +Redis modules
- 16. 16 Redis + SparkSo Far ▪ Current connector: - RDD abstraction - SparkSQL - Streaming Source ▪ ML is not addressed specifically ▪ Used for pre-computed results ▪ We felt that we can take it further
- 17. 17 Addressing The MLPain ▪ The missing piece of ML: Serving your model - Not standardized - Vendor-lock with cloud platforms - Reliable services are hard to do - If only we had a “database” for this! - Well, maybe we do?
- 18. 18 Why Modules forML? With modules we can: ▪ Define data structures for models ▪ Store training output as “hot model” ▪ Perform evaluation directly in Redis ▪ Easily integrate existing C/C++ libs
- 19. 19 Spark + Modules= AWESOME ▪ Train ML model on Spark ▪ Save model to Redis and get: - High availability - Clustering - Persistence - Performance - Client libraries
- 20. 20 Spark-ML End-to-End Flow SparkTraining Custom Server Model saved to Parquet file Data Loaded to Spark Pre-computed results Batch Evaluation ? ClientApp
- 21. 21 Adding Redis IntoThe Mix Redis-ML “Active Model” Any Training Platform ClientApp Spark Training Data Loaded to Spark
- 22. 22 Redis Module Tree Ensembles LinearRegression Logistic Regression Matrix + Vector Operations More to come... The Redis-ML Module
- 23.
- 24. 24 Forest Data Type ▪A collection of decision trees ▪ Supports classification & regression ▪ Splitter Node can be - Categorical (e.g. day == “Sunday”) - Numerical (e.g. age < 43)
- 25. 25 Decision Tree Example Thefamous Titanic survival predictor sex=male?yes no Survived Died Age > 9.5? sibsp > 2.5? Died Survived *sibsp = siblings + spouses
- 26. 26 Forest Data TypeExample > MODULE LOAD "./redis-ml.so" OK > ML.FOREST.ADD myforest 0 . CATEGORIC sex “male” .L LEAF 1 .R LEAF 0 OK > ML.FOREST.RUN myforest sex:male "1" > ML.FOREST.RUN myforest sex:yes_please "0"
- 27. 27 Using Redis-ML WithSpark scala> import com.redislabs.client.redisml.MLClient scala> import com.redislabs.provider.redis.ml.Forest scala> val rfModel = pipelineModel.stages.last.asInstanceOf[RandomForestClassificationModel] scala> val f = new Forest(rfModel.trees) scala> f.loadToRedis("forest-test", "localhost") scala> val jedis = new Jedis("localhost") scala> jedis.getClient.sendCommand(MLClient.ModuleCommand.FOREST_RUN, "forest-test", makeInputString (0)) scala> jedis.getClient.getStatusCodeReply res53: String = 1
- 28. 28 Benchmarking Redis-ML - Spark+ Parquet Spark + Redis ML Model Preparation + Save 3785ms 292ms Model Load 2769ms 0ms (model is on memory) Classification (AVG) 13ms 1ms ● Forest size: 15000 trees ● Data: $(SPARK_HOME)/data/mllib/sample_libsvm_data.txt
- 29. 29 Going Forward -More Features ▪ Implement more Spark-ML model types - SVM - Naive Bayes Classifier - Neural Networks ▪ Integration with Redis’ native types ▪ Data Processing (e.g. Word2Vec, TF-IDF) ▪ PMML Support
- 30. 30 PS: Neural Redis ▪Developed by Salvatore ▪ Training is done inside redis ▪ Online continuous training process ▪ Builds Fully Connected NNs
- 31.
- 32.