Stack Overflow
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)

Website: https://github.com/combust/mleap

Documentation: http://mleap-docs.combust.ml/

35 questions
1
vote
1 answer

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 transformer's name. My reference.conf file looks like…
L. Ivica
  • 11
  • 1
1
vote
0 answers

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 unknown resolver null :: USE VERBOSE OR DEBUG MESSAGE LEVEL FOR…
chxiaol
  • 11
  • 1
1
vote
1 answer

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 model I am successfully able to start the server…
yashdosi
  • 1,186
  • 1
  • 18
  • 40
0
votes
0 answers

How to combine scores from two models in Pyspark to create a new PipelineModel that is compatible with mleap?

I want to build a custom PipelineModel transformer in Pyspark that is based on two pre-trained models (objects of PipelineModel). The objective is to feed data to model1 and model2, then get class-1 probabilities from both models, then multiply…
exAres
  • 4,806
  • 16
  • 53
  • 95
0
votes
0 answers

StackOverflowError while testing mleap pipeline

I am using mleap to serialize spark pipeline. I have also added checkpoint stages in the bundle, however, I am still facing StackOverflowError while calling transform on the pipeline, the checkpoint also seems to be working as the rdds are being…
Obaid Ur Rehman
  • 23
  • 4
0
votes
1 answer

use both XGBoostPredictorClassification and XGBoostClassification in the same project

from https://github.com/combust/mleap/pull/645, XGBoostPredictorClassification improve performance by only predicting probability I wonder if we use both XGBoostPredictorClassification and XGBoostClassification in the same project, because now we…
netpot
  • 1
  • 1
0
votes
0 answers

Serialize Scala spark model with MLEAP and serve in Python environment

Is it possible to train a model in scala environment, serialize it with mleap and then serve on a different python server? I've read the docs, but it still isn't clear to me how compatible those things are
Nurgling96
  • 566
  • 5
  • 18
0
votes
1 answer

How to use MLeap DenseTensor in Java

I am using MLeap to run a Pyspark logistic regression model in a java program. Once I run the pipeline I am able to get a DefaultLeapFrame object with one row Stream(Row(1.3,12,3.6,DenseTensor([D@538613b3,List(2)),1.0), ?). But I am not sure how to…
mathfish
  • 184
  • 1
  • 12
0
votes
1 answer

MLeap broken with Skicit-learn when serialising: object has no attribute 'input_features'

I'm facing an issue with MLeap 0.16 and Python 3 when I try serialising a model. Here is my code: from mleap.sklearn.logistic import LogisticRegression from sklearn.datasets import load_iris X, y = load_iris(return_X_y=True) clf =…
Nastasia
  • 557
  • 3
  • 22
0
votes
1 answer

What could cause an error in sparklyr and mleap ml_write_bundle example?

I'm trying to follow RStudio-MLeap example (https://github.com/rstudio/mleap) but I get an error at `ml_write_bundle()'. Does anyone know how to troubleshoot? # The example code: library(mleap) library(sparklyr) sc <- spark_connect(master =…
KM_83
  • 697
  • 3
  • 9
0
votes
1 answer

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 testALS.zip when calling this curl -XPUT -H…
廉亚红
  • 1
0
votes
3 answers

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 ml.combust.mleap.core.Model import…
Ashwin Padhy
  • 111
  • 1
  • 9
0
votes
1 answer

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 numbers with out any input fields. So can we generate a…
Ashwin Padhy
  • 111
  • 1
  • 9
0
votes
1 answer

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 { bundleFile.loadMleapBundle().get }).opt.get The error…
rmilbu
  • 1
0
votes
1 answer

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 saved using MLeap into my Java code, into my own…
dmitrievanthony
  • 1,501
  • 1
  • 15
  • 41
1
2
3