Stack Overflow
Stack Overflow

Questions tagged [automl]

Automated Machine Learning (AutoML) is to make machine learning more accessible by automatically generating a data analysis pipeline that can include data pre-processing, feature selection, and feature engineering methods along with machine learning methods and parameter settings

The goal of Automated Machine Learning (AutoML) is to make machine learning more accessible by automatically generating a data analysis pipeline that can include data pre-processing, feature selection, and feature engineering methods along with machine learning methods and parameter settings that are optimized for your data

More and more research and libraries are available on the topic, examples include auto-sklearn, H2O AutoML and Cloud AutoML.

434 questions
4
votes
2 answers

Auto-sklearn: How to load pickle file and run predict()

I have fitted a classification model using auto-sklearn, and managed to save it to a file with pickle. x = automl.show_models() results = {"ensemble": x} pickle.dump(results, open('file.pickle','wb')) I also have managed to reload the model. automl…
Joao
  • 41
  • 1
  • 2
4
votes
1 answer

How to extract more than label text items in a single annotation using Google NLP

I have created dataset using Google NLP Entity extraction and I uploaded input data's(train, test, validation jsonl files) like NLP format that will be stored in google storage bucket. Sample Annotation: { "annotations": [{ …
dwayneJohn
  • 919
  • 1
  • 12
  • 30
4
votes
0 answers

Tensorflow.js pretrained Google AutoML model not working

I've trained a model on Google Cloud AutoML. And I've used it on this code:
sundowatch
  • 3,012
  • 3
  • 38
  • 66
4
votes
1 answer

Using service accounts and oauth2 to call autoML Google API

I've trained an image classification model using autoML API and now I would like to create a JAVA program that makes predictions of given images using that model. As mentioned in the docs, this API requires the OAuth scope:…
Mouna Ben Chamekh
  • 353
  • 1
  • 13
4
votes
2 answers

How to use Google AutoML on web app?

I have a Google Cloud AutoML NL model ready to use. I wish to link this with my web app with Firebase backend. Following is my code to call. There is authorization issue. I want to understand how to authorize the app to help the client apps get…
Disu
  • 175
  • 1
  • 10
4
votes
2 answers

Unable to load non-winning models in automl() use case

I'm using automl function with code snippet shown below h2o.init() h2o_train = as.h2o(train) h2o_test = as.h2o(test) aml <- h2o.automl(x=x, y=y, training_frame=h2o_train, leaderboard_frame=h2o_test) print(aml@leaderboard) # view top…
Paul Lo
  • 6,032
  • 6
  • 31
  • 36
3
votes
0 answers

Azure AutoMl error : A field of the entity is over the size limit

I am trying to run an automl code on Azure using the azureml SDK (class AutoMLStep). But it is throwing an error saying A field of the entity is over the size limit. FieldName=RunDto.Properties.Value/Length, Limit=550000, Size=697351 ERROR - AutoML…
colab123
  • 81
  • 1
  • 6
3
votes
2 answers

Is Auto-sklearn available for apple silicon?

I have my laptop to be the latest MBP with M1 chip. Weird errors popped out while I was trying to install the auto-sklearn package for my machine. I wonder is that package compatible with M1 chip or is there any method that I am able to get it…
weiyang wang
  • 87
  • 1
  • 3
3
votes
1 answer

H2O local server has died unexpectedly

I am having a problem reproducing the AutoML tutorial in H2O documentation. After initatiing my h2o local server (h2o.init()) I get the following output, which sounds correct: Checking whether there is an H2O instance running at…
Lucas Bali
  • 71
  • 5
3
votes
2 answers

Retrieve cross validation performance (AUC) on h2o AutoML for holdout dataset

I am training a binary classification model with h2o AutoML using the default cross-validation (nfolds=5). I need to obtain the AUC score for each holdout fold in order to compute the variability. This is the code I am using: h2o.init() prostate =…
A1010
  • 360
  • 5
  • 18
3
votes
1 answer

Is there a page limit for predicting using GCP AutoML for Custom Entity Extraction

I am trying to explore the custom entity extraction using GCP AutoML, I have a 10 page documents used for training the model, where my entities are trained those were 7 & 8 page as well. While Testing from GCP AutoML UI, I used one of the trained…
Sheetal Lomate
  • 53
  • 9
3
votes
0 answers

H2O Sparkling Water AutoML not working properly in Spark Scala. Exception: Ease restrictions on setMaxModels or setMaxRuntimeSecs

I'm looking into H2O sparkling water AutoML using scala. I'm running it on my laptop on localhost. Even though I'm not adding any restrictions on H2OAutoML() class using setMaxModels or setMaxRuntimeSecs method. The model.fit method fails with an…
Bhushan Gosavi
  • 55
  • 5
3
votes
1 answer

Invalid resource ID when calling auto ml api from cloud function

I'm calling the auto ml api to get a prediction but I have the following error : AutoML API Error: { Error: 5 NOT_FOUND: Invalid resource ID at Object.exports.createStatusError (/srv/node_modules/grpc/src/common.js:91:15) at Object.onReceiveStatus…
Florian Hirson
  • 47
  • 6
3
votes
1 answer

Extracting models from H2O AutoML leaderboard

When I train a model in R using autoML, I can view the leaderboard of the models via automl_model@leaderboard and I can get access to the best model via automl_model@leader However, I want also make experiments with the 2nd best model, 3rd best…
Babypopo
  • 131
  • 1
  • 7
3
votes
0 answers

Error: File b'tpu_train/metadata/results.csv' does not exist: b'tpu_train/metadata/results.csv' when running automl_gs on Colab

I came across this interesting automl library, and was following this guide to run the module on Colab. In my Colab instance, I have this code: !pip install automl_gs import os from automl_gs import automl_grid_search from google.colab import…
user1330974
  • 2,500
  • 5
  • 32
  • 60
1
2
3
…
28 29