See Realtime Machine Learning predictions with Kafka and H2O.ai.
File: data/housedata.csv
Data types:
date
: timeprice
: numericbedrooms
: numericbathrooms
: numericsqft_living
: numericsqft_lot
: numericfloors
: numericwaterfront
: enumview
: enumcondition
: enumsqft_above
: numericsqft_basement
: numericyr_built
: numericyr_renovated
: numericstreet
: stringcity
: enumstatezip
: enumcountry
: enum
Splits:
- 70% for training
- 20% for validation
- 10% for test
- Type: Gradient Boosting Machine
- Training frame: 70%
- Validation frame: 20%
- Response column:
price
- Ignored columns:
date
ntrees
: 120
$ kafka-topics --zookeeper localhost:2181 --create --topic housing --replication-factor 1 --partitions 4
$ kafka-topics --zookeeper localhost:2181 --create --topic predictions --replication-factor 1 --partitions 4
$ kafka-topics --zookeeper localhost:2181 --create --topic zipcodes --replication-factor 1 --partitions 4