mleap

mleap copied to clipboard

[Question] What is the best way to use MLeap XGBoost in python?

1

I have a model trainer python project that needs support for serializing XGBoost models. I am trying to call the Scala APIs via the jvm following the [XGBoostClassificationModelParitySpec](https://github.com/combust/mleap/blob/eb8ef4e51c2059bd4cbac76db44be58de958840f/mleap-xgboost-spark/src/test/scala/ml/dmlc/xgboost4j/scala/spark/mleap/XGBoostClassificationModelParitySpec.scala#L126) example, but...

tinaxi

It'd be helpful to adopt a python formatter like [Black](https://pypi.org/project/black/) to standardize the syntax and code style.

lucagiovagnoli

I am new to both spark and MLeap and am working in a Java codebase trying to update our prediction service to use MLeap (v0.12.0) to predict on spark (v2.3.1)...

will-m-buchanan

Add support for spark-deep-learning (e.g. DeepImageFeaturizer)

4

Databricks has its own packge for running Deep Learning on Spark: https://github.com/databricks/spark-deep-learning Wondering if MLeap supports this or not? Thanks!

FredYao

Serialized then deserialized model does not have the same results (all zero's)

4

It's not clear to me why this is happening. I was first using spark 2.4.3 but then changed back to 2.3.3 (as I believe support for 2.4 was being considered...

aaditya3

Cannot load Bundle in java assembly jar: object scala.Predef not found

4

I am trying to create a KSQL UDF serving a Mleap model. The code for a toy example can be found here: [https://gitlab.com/jan-teichmann/ksql-iris-classifier-udf](https://gitlab.com/jan-teichmann/ksql-iris-classifier-udf ) I am loading a pipeline from...

teichmaj

Adding Batch leap frame and a sample batch tf transformer

4

Currently in mleap we only have default leapframe which applies transformation to the dataset row by row. However, as TF does support predictions over a batch of requests and is...

sushrutikhar

How to deserialize pyspark bundle in python without the dependency on a sparkcontext?

4

I have a "bundle.zip" serialized from pyspark. I want to deserialize this pipeline object in my python application without needing a spark context. according to the documentation this is possible:...

vincentclaes

how to use mleap model to do prediction?

2

i just run the image and put a model to localhost:65327,the question is how can i use this model to do prediction? ``` docker run -p 65327:65327 -v /tmp/models:/models combustml/mleap-serving:0.9.0-SNAPSHOT...

topxxuki

MLeap BinaryLogisticRegressionModel calculating result differs with the Spark model

2

Hi there. I tried to train a Spark `BinaryLogisticRegressionModel` with a dataset whose labels are the same value and used this model to make predictions. ``` Scala // data val...

ihainan