Comments (6)
Could this be used for models built with older version of H2O?
First, define "old".
The latest JPMML-H2O release version should work fine with all H2O.ai versions in 3.34 -- 3.42 range. When exceeding the "lower bound" of the version range, then the "supported state" will vary from one MOJO type to another. For example, random forests may work, and GLM may not, and so on.
Will the MOJO file be different?
The MOJO content is mostly unchanged. But the MOJO public API field names, method signatures etc. may change, which will lead to all sort of JVM-level class incompatibility errors.
from jpmml-h2o.
The JPMML-H2O project has been around for five years now (ie. since July 2018).
If you know that your MOJO was created in May 2020 (for example), then go to JPMML-H2O release archives, and choose the version that was released around the same time:
https://github.com/jpmml/jpmml-h2o/releases
Should be the highest success rate approach.
from jpmml-h2o.
My model (h2o.xgboost) was built in 2020 using h2o 3.30.0.7; any suggestions?
Thank you.
from jpmml-h2o.
My model was built in 2020 using h2o 3.30.0.7
Any early JPMML-H2O 1.1 version should be fine (1.1.0 -- 1.1.3).
My model (h2o.xgboost)
However, XGBoost is a special case, because it is "external" to H2O.ai.
With XGBoost models, I'd first give the latest JPMML-H2O version a try - that would be version 1.2.8 (as of today).
from jpmml-h2o.
Thank you! One more question:
I've found the POJO file of the old model; is there an easier way to convert it to pmml, please?
from jpmml-h2o.
I've found the POJO file of the old model
Have not dealt with the POJO data format under this project.
Yesterday, I published some notes about the current state of Scikit-Learn H2O.ai pipelines:
https://openscoring.io/blog/2023/07/17/converting_sklearn_h2o_pipeline_pmml/
from jpmml-h2o.
Related Issues (15)
- openscoring can't read output .pmml HOT 1
- Throws error when I change the max_depth > 5 and ntrees = 100 for a GBM HOT 3
- Throws and error when converting a poisson GBM to PMML HOT 3
- Detect feature promotion from (high cardinality-) categorical to pseudo-numeric HOT 4
- Missing number of values in the array HOT 2
- Capturing variable importances
- release 1.0.10 is not compatible with h2o-3.28.x HOT 2
- Handling of missing values HOT 1
- Downgrading PMML 4.4 to PMML 4.2 HOT 4
- Score mismatch between PMML file and H2O Mojo prediction HOT 1
- Support for `quantile` distribution in GBM
- Output PMML file too big in size HOT 2
- Support of categorical variables HOT 2
- Use H2O.ai node identifiers (aka "nodeNumbers")
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from jpmml-h2o.