Newest 'mleap' Questions - Stack Overflow

Questions tagged [mleap]

Deploy Spark Pipelines to Production. MLeap allows data scientists and engineers to deploy machine learning pipelines from Spark and Scikit-learn to a portable format and execution engine. Export a model with Scikit-learn or Spark and execute it using the MLeap Runtime (without dependencies on the Spark Context, or sklearn/numpy/pandas/etc)

1
vote
0answers
20 views

Is it possible to have more inputs for MLeap Transformer

I have a mleap Transformer which has to have around 14 inputs for transformation.I tried to create core model however i see the error when i increase the number of input variable else its does not ...
0
votes
0answers
13 views

Unable to run transform in Mleap runtime from Spark model

I'm currently testing the Mleap solution in order to perform prediction on Spark model. In order to do that, I've first implemented the Spark example for linear regression as described here: https://...
0
votes
1answer
16 views

curl -XPUT -H “content-type: application/json” -d '{“path”:“/models/testALS.zip”}' http://localhost:65327/model has error

when calling curl -XPUT -H "content-type: application/json" -d '{"path":"/models/testALS.zip"}' http://localhost:65327/model get error. I use spark-mllib trained an als model and save the model as ...
0
votes
0answers
20 views

Bundle a tensorflow model into an mleap bundle

Is it possible to serialize an existing TensorFlow model into an MLeap bundle? A bundle containing a TensorFlow model is provided in http://mleap-docs.combust.ml/tensorflow/bundle-serialization.html, ...
0
votes
3answers
76 views

How to Initiate as class member in scala?

I have a random number class which generate the random number.However i want it to be Initiate as class member so that we do not need to regenerate in every call.Below is the code at present. import ...
0
votes
1answer
50 views

How to create a custom transformer with out any input column?

We have requirement where in we wanted to generate scores of our model with some random values in between 0-1. To do that we wanted to have a custom transformer which will be generating random ...
0
votes
0answers
13 views

Why do I need to pass the prediction results to be serialized in a call to serializeToBundle

I cannot find an example which shows a Spark ML model being saved -- for processing with mleap later on -- without the Spark predicted Dataframe. What is the significance of the this Dataframe and ...
0
votes
0answers
45 views

Saving Spark Custom Tranformers using MLeap library

I am using Mleap to productionise models and have got one case where Spark MLLib has custom Transformer in Pipeline (by extending Transformer with DefaultParamsWritable). I want to save this as part ...
0
votes
0answers
102 views

Cannot serialize mleap pipeline: Object of type int64 is not JSON serializable

I'm trying to run the example airbnb-price-regression-scikit.ipynb from https://github.com/combust/mleap-demo/tree/master/notebooks The idea is to generate a simplified pipeline in Python, export it ...
0
votes
1answer
45 views

Unable to deserialize mleap bundle

I am getting a java.util.NoSuchElementException: None.get on the following code: // Deserialize a directory bundle val bundle = (for(bundleFile <- managed(BundleFile(bundle_path))) yield { ...
0
votes
0answers
27 views

MLeap serializeToBundle error for Pyspark custom Transformer

I have a Pyspark custom Transformer that I am trying to serialize to an mLeap bundle object for later model scoring but Im getting the following error: ---> 42 self._java_obj....
0
votes
1answer
80 views

Is MLeap actually a serialization “format”?

I began to work with MLeap as a serialization tool that allows to save model in Spark or scikit-learn and load it for inference using MLeap Runtime. It works well. Now my purpose is to load a model ...
0
votes
0answers
37 views

mleap spark one vs rest serealization error **Spark version 2.3, mleap 0.13**

I am getting the following error(Exception in thread "main" java.util.NoSuchElementException: key not found: org.apache.spark.ml.classification.OneVsRestModel) when trying to serialize the model (...
2
votes
0answers
152 views

Getting 'com.typesafe.config.ConfigException$Missing: No configuration setting found for key 'ml.combust.mleap.spark'` error

I am trying to run the sample MLeap code example provided here: http://mleap-docs.combust.ml/spark/ All of the code works on my Spark cluster. However, whenever I to execute the following code ...
3
votes
2answers
119 views

Export spark feature transformation pipeline to a file

PMML, Mleap, PFA currently only support row based transformations. None of them support frame based transformations like aggregates or groupby or join. What is the recommended way to export a spark ...
0
votes
0answers
42 views

MLeap model prediction time

I have to deploy a machine learning model in a real time system and I found MLeap library which seems to be able to predict an entry in less than 1ms. I loaded the MLeap model in a Spark app, ran it ...
0
votes
0answers
37 views

Is it possible to serialize/deserialize MLeap bundle to/from a byte stream?

The MLeap documentation shows how bundle can be written to a file and then deserialized and loaded from the same file. http://mleap-docs.combust.ml/spark/ Would it be possible to serizalze/...
1
vote
1answer
397 views

'JavaPackage' object is not callable - MLeap

When I try to serialize a model using MLeap using the following code: import mleap.pyspark from mleap.pyspark.spark_support import SimpleSparkSerializer # Import standard PySpark Transformers and ...
0
votes
0answers
170 views

After loading Mleap bundle returning org.apache.spark.ml.PipelineModel object instead of ml.combust.mleap.runtime.frame.Transformer

I am trying to use mleap-xgboost-spark library in my Java project and I am successfully able to train and save xgboost model. In the below code I am trying to load the model back in memory so I can ...
1
vote
0answers
174 views

Using Custom spark transformers in pyspark

How can I use a custom transformer written in scala in a pyspark pipeline. class UpperTransformer(override val uid: String) extends UnaryTransformer[String, String, UpperTransformer] { def ...
0
votes
1answer
116 views

Text field concatenation in sklearn pipeline

I have a multi line json dataset that contains multiple fields that can or cannot exists and can contain textual data in either string, list of strings or more complicated mapping (list of dicts) eg.:...
1
vote
0answers
40 views

Transformer's Op name isn't available when setting opName

I created my custom transformer (simple model that adds a string to a column value) to test Mleap serialization, but while writing my Op file for Mleap and Spark serialization, I couldn't my ...
1
vote
0answers
108 views

Generating mleap bundle from my TensorFlow program

I have a TensorFlow model which I am trying to serialise into a MLeap bundle, so that I can use MLeap based predictor to score. But I could not find any API to do so from my TensorFlow code. The ...
1
vote
0answers
117 views

Installing Mleap spark

when I use spark shell with --packages ml.combust.mleap:mleap-spark_2.11:0.8.1 I got the errors as below :::: ERRORS unknown resolver null unknown resolver null unknown resolver null ...
0
votes
3answers
752 views

mleap AttributeError: 'Pipeline' object has no attribute 'serializeToBundle'

I am having problems executing the example code from the mleap repository. I wish to run the code in a script instead of a jupyter notebook (which is how the example is run). My script is as follows:...
1
vote
1answer
93 views

Serving Wine Classifcation model in mleap

I have a wine classification model trained and saved using mleap. Note: For now I am using TrueCar version of mleap. Planning to update it soon. Now, when I try to start a server for serving this ...
0
votes
1answer
236 views

Unable to serialize logistic regressing in mleap

java.lang.AssertionError: assertion failed: This op only supports binary logistic regression I am trying to serialize a spark pipeline in mleap. I am using Tokenizer, HashingTF and ...
2
votes
1answer
441 views

Scala to Java 8 MLeap Translation

I would like to use MLeap to deploy Spark ML machine learning models and use them to predict in real-time. The creators put out a Scala tutorial, but I need to support a Java 8 codebase. How would ...
0
votes
1answer
367 views

Unable to serialize a apache spark transformer in mleap

I use Spark 2.1.0 and Scala 2.11.8. I am trying to build a twitter sentiment analysis model in apache spark and service it using MLeap. When I am running the model without using mleap, things work ...
0
votes
1answer
145 views

Not able to create object of SparkBundlecontext in mleap

I have imported required packages. I am even able to import SparkBundleContext import org.apache.spark.ml.bundle.SparkBundleContext But then when I do val sbc = SparkBundleContext() I get this ...