-
Training XGBoost in a distributed environment
I've read in the docs that XGBoost supports multiprocessing. I have successfully run it in a single node environment, where I verified that it was using all the cores. However, when I try it in a distributed setting, it does not give an error, it just gets stuck at 0%. I'm not sure if it currently does not support…
-
Is it possible to turn off checking for 401 error?
We have been getting the 401 unauthorized error (see below) spontaneously (could be within minutes or hours) while running makeGLMModel within a long for loop. Since we are not using FLOW, it is possible to turn off the checking that gives the error? We are running H2O 3.36.1.2 from Jupyterlab in linux with python 3.9.…
-
Does the column order in scoring dataframes matter to H2O models using mojo format?
My ML Ops team is suggesting that perhaps the reason why I'm getting different scores than they are (even though the scoring process flow in R and the mojo model is supposedly the same) is that perhaps the difference in the order of the columns in the dataframes we are each scoring having an impact. I can't actually verify…
-
How does one save and re-open a flow.
This is certainly a newbie question, but I cannot figure out how to save and restore a flow. I am using h2o flow on my local computer, both server and browser. v3.38.0.3. Windows 10, Chrome browser. I can save a flow, and certainly something is being saved since if I try to save again with the same name, I get prompted to…
-
Does H2O in clustered formation support a configurable number of concurrent HTTP connections?
I have followed the H2O documentation to create an H2O cluster in Kubernetes using the Docker h2oai/h2o-open-source-k8s:3.38.0.2 image. When I load test the cluster it can support about 80 concurrent HTTP connections that are opened with this Python code: import h2o h2o.connect(url='http://' + "clusterhostname" +':0') My…
-
How long does the H2O Clustering command run?
I ran H2O clustering yesterday to try it out - as it was taking a very long time and I did not receive any feedback in regards to elapsed time, I wanted to ask how long one H2O clustering run can take. Is it a matter of hours or days? my dataset is reasonably-sized (40 patients, 20 variables)
-
Can't connect to http://localhost:54321
Hello, i want to run the lilikoi example code with the mock data provided by the lilikoi R package, however, I am stuck at the lilikoi.machine_learning() command due to a connection error with H2O. I downloaded the H2O file and unzipped it in the R Terminal, but now I cannot connect to http://localhost:54321 as indicated…
-
Feature request properly made?
Hi, Following a discussion (https://groups.google.com/g/h2ostream/c/BEwC2iVZvgY) over on h2ostream, I opened a feature request ticket, namely https://h2oai.atlassian.net/browse/PUBDEV-8891. I suspect this issue has remained unassigned due to there being more pressing priorities, but if I logged it incorrectly, or if it…
-
h2oai.awesome-h2o on GitHub
I want to share a good resource - H2O.ai Awesome on GitHub where we're been adding to a curated list of all the awesome projects, applications, research, tutorials, courses and books that use H2O-3, our open source, distributed machine learning platform. H2O offers parallelized implementations of many supervised and…