cancel
Showing results for 
Search instead for 
Did you mean: 
Machine Learning
Dive into the world of machine learning on the Databricks platform. Explore discussions on algorithms, model training, deployment, and more. Connect with ML enthusiasts and experts.
cancel
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

Evan_MCK
by Contributor
  • 8416 Views
  • 4 replies
  • 1 kudos

Resolved! Shap Values for predictions from registered model

I have saved a model in the model registry using MLFlow. How can I find the shap values for this model once I have generated predictions in batch mode? Shap tree explainer does not support the mlflow pyfunc model type. When I use mlflow.shap.log_exp...

  • 8416 Views
  • 4 replies
  • 1 kudos
Latest Reply
peacocktv
New Contributor II
  • 1 kudos

Thank you so much for this kind of valuable post its amazing post it may helpful for each visitors. For more information go through my websites here:peacocktv.com/tv | peacocktv.com/tv/xbox

  • 1 kudos
3 More Replies
BeadsPlayer
by New Contributor II
  • 728 Views
  • 0 replies
  • 0 kudos

Streaming inference with Delta Live Tables for a model registered in Unity Catalog

Hi there, I'm trying to run a streaming inference with Delta Live Tables with tables and a model registered in Unity Catalog, but it fails for unclear reasons. The DLT pipeline is based on a notebook, the channel is set to 'Preview', presumably runni...

Machine Learning
Delta Live Tables
streaming
Unity Catalog
  • 728 Views
  • 0 replies
  • 0 kudos
DavidKxx
by Contributor
  • 1866 Views
  • 1 replies
  • 0 kudos

Resolved! Visualizations not displaying

With a copy of notebook https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/open-source-nlp/03.0.SparkNLP_Pretrained_Models.ipynb imported into Databricks, there's a lovely visualization created by the cell that you can locate by searching...

DavidKxx_0-1701107229407.png DavidKxx_1-1701107287817.png
Machine Learning
NER
Visualization
  • 1866 Views
  • 1 replies
  • 0 kudos
Latest Reply
DavidKxx
Contributor
  • 0 kudos

Here's a solution:  use a parameter (here, `return_html = True`) to get an HTML object back, and then call `displayHTML` to actually display the object.from sparknlp_display import NerVisualizer visualiser = NerVisualizer() for i in text_list: ...

  • 0 kudos
brickster_2018
by Databricks Employee
  • 2842 Views
  • 2 replies
  • 0 kudos
  • 2842 Views
  • 2 replies
  • 0 kudos
Latest Reply
N_M
Contributor
  • 0 kudos

How does COPY_INTO work with table restore?I made some tests, and the restore method does NOT restore the key-store values of the target at the specific version, which means that the data that came after the chosen version cannot be inserted (unless ...

  • 0 kudos
1 More Replies
chari
by Contributor
  • 4647 Views
  • 0 replies
  • 0 kudos

workflow job

Hi ,When I create a job of a machine learning model and run the job I see that the cell outputs do not get updated. The model variables would have updated, however.  I also need to keep the notebook updated with cell outputs always when I run the job...

  • 4647 Views
  • 0 replies
  • 0 kudos
Supreme_Auto_Ci
by New Contributor II
  • 3100 Views
  • 4 replies
  • 4 kudos
  • 3100 Views
  • 4 replies
  • 4 kudos
Latest Reply
rahulroy
New Contributor II
  • 4 kudos

Data science is a multidisciplinary field that uses scientific methods, processes, algorithms, and systems to extract knowledge and insights from data. It encompasses the entire data lifecycle, from data acquisition to data exploration, modeling, and...

  • 4 kudos
3 More Replies
choi_2
by New Contributor II
  • 8146 Views
  • 0 replies
  • 0 kudos

Runtime issue

Hello,I am working on a machine learning project. The dataset I am using has more than 5000000 rows. I am using PySpark, and the attached screenshot is the block I used RandomForestRegressor to train the model.It worked even though it took a pretty l...

  • 8146 Views
  • 0 replies
  • 0 kudos
tjkentSI
by New Contributor
  • 1842 Views
  • 1 replies
  • 0 kudos

Bootstrap timeout on instance creation

I am getting the following error...{ "reason": { "code": "BOOTSTRAP_TIMEOUT", "parameters": { "databricks_error_message": "[id: InstanceId(i-0e552e85c37c9da2d), status: INSTANCE_INITIALIZING, workerEnvId:WorkerEnvId(workerenv-12661843...

  • 1842 Views
  • 1 replies
  • 0 kudos
Latest Reply
User16539034020
Databricks Employee
  • 0 kudos

Hello,  Thanks for contacting Databricks Support.  From the error message: [Bootstrap Event] Can reach databricks-prod-artifacts-us-east-1.s3.amazonaws.com: [FAILED]. It suggests an issue with reaching a Databricks-related AWS S3 bucket from your env...

  • 0 kudos
Robbie
by New Contributor III
  • 10152 Views
  • 3 replies
  • 5 kudos

Why are my MLflow results not showing up in the Experiment UI view?

The issue:None of my MLflow experiment results show up in the Experiment UI. Context:I encountered this issue recently, despite having successfully used the MLFlow UI for the past few weeks.Note: I can still access the experiment runs in a notebook, ...

MLflow Experiment UI view (no results showing up) Accessing via `mlflow.get_runs(...)`
  • 10152 Views
  • 3 replies
  • 5 kudos
Latest Reply
Kumaran
Databricks Employee
  • 5 kudos

Hi @Robbie, Thank you for posting your question in the Databricks community. Ensure that you are logging runs correctly using mlflow.start_run(), and that all relevant metrics and artifacts are being logged with the correct parameters. Please check.

  • 5 kudos
2 More Replies
camazg
by New Contributor
  • 1035 Views
  • 0 replies
  • 0 kudos

Copying Models Between Metastores

Hello,We need to promote models to different environments in different regions, they exist in Unity Catalog.We are setting up DataBricks metastores across different regions.We wanted to follow this approach to copy models via UC https://docs.gcp.data...

  • 1035 Views
  • 0 replies
  • 0 kudos
VincentP
by New Contributor III
  • 5668 Views
  • 1 replies
  • 0 kudos

Resolved! FeatureEngineeringClient loses timestamp_keys after write_table

I am trying to use the FeatureEngineeringClient to setup a feature store table with a time series component. However, after initiating the table with a time series column, the key exists, but the key is removed after adding data to the table. Therefo...

  • 5668 Views
  • 1 replies
  • 0 kudos
Latest Reply
VincentP
New Contributor III
  • 0 kudos

Needed to update to runtime 13.3 ...

  • 0 kudos
mykola14
by New Contributor
  • 695 Views
  • 0 replies
  • 0 kudos

Buy monzo account

Buy monzo accountDo you want to buy monzo account? Our store is the best place where you can buy monzo accounts. Only fully verified monzo accounts on our store.Buy monzo account 

monzo.jpg
  • 695 Views
  • 0 replies
  • 0 kudos
mykola12
by New Contributor
  • 1219 Views
  • 0 replies
  • 0 kudos

Buy Advcash account

Buy Advcash accountDo you want to buy advcash account? Our store is the best place where you can buy advcash accounts. Only fully verified advcash accounts on our store.Buy Advcash account

Advcash.jpg
  • 1219 Views
  • 0 replies
  • 0 kudos

Connect with Databricks Users in Your Area

Join a Regional User Group to connect with local Databricks users. Events will be happening in your city, and you won’t want to miss the chance to attend and share knowledge.

If there isn’t a group near you, start one and help create a community that brings people together.

Request a New Group
Labels