sagemaker-sparkml-serving-container
sagemaker-sparkml-serving-container copied to clipboard
aws
This code is used to build & run a Docker container for performing predictions against a Spark ML Pipeline.
Hello, I would like to understand why this limitation is in place. Presumably most machine learning models take in much more than 16 features. I created a model and had...
* upgraded Spark to 2.4.8 * upgraded Mleap to 0.17.0 since it's the last one for Spark 2.4 *Issue #, if available:* *Description of changes:* By submitting this pull request,...
Hi, I am trying to build the docker image in this repository, and the build fails at - Step 6/20 : RUN apt -y install python3.6 Due to compliance and...
I am trying to deploy bundled a Spark ML NaiveBayesModel with sagemaker-sparkml-serving-container. I am running sagemaker-sparkml-serving-container with following command: ``` SCHEMA='{"input":[{"name":"features","type":"double","struct":"vector"}],"output":{"name":"prediction","type":"double"}}' BUNDLE=/tmp/naivebayes_bundle docker run -p 8080:8080 -e SAGEMAKER_SPARKML_SCHEMA="$SCHEMA" -v $BUNDLE:/opt/ml/model...
Hi! How can this container be used for batch transfrom in sagemaker. Because my env variable holds schema for 561 columns which is very long. to pass as env variable....
Hi, I was referring to this repo to build a custom docker image that does the feature transformation and use lightGBM model for prediction. I wanted to use mleap to...
After deploying mleap model artifact on sagemaker endpoint, during the inferencing stage, how can I get probabilities of prediction rather than binary outcome? I tried changing output column from prediction...
Hello, is there a plan to upgrade the sparkml serving containers to support pipeline models generated using Spark 2.4.3 and serialized using Mleap 0.14.0. Greatly appreciate if some could please...
Issue #, if available: Description of changes: accepting csv multilines request accepting jsonlines request in order to process multiple responses in the same time By submitting this pull request, I...
I am trying to create Pipeline model that combines the SparkML model with the BlazingText model for a text classification task. The SparkML model is used to pre-process the input...
