h2o | h2o template engine in ruby | GraphQL library

I use targets as a pipelining tool for an ML project with H2O. The main uniqueness of using H2O here is that it creates a new "cluster" (basically a new local process/server which communicates via Rest APIs as far as I understand).

The issue I am having is two-fold.

1. How can I stop/operate the cluster within the targets framework in a smart way
2. How can I save & load the data/models within the targets framework

A minimum working example I came up with looks like this (being the _targets.R file):

As the title says. I cannot run h20.init.

I have already downloaded the 64 bit version of the Java SE Development Kit 8u291. I also downloaded the xgboost library in R (install.packages("xgboost") ). Finally, I have updated all my NVIDIA drivers and downloaded the latest CUDA (although, tbh I don't even know what that does). I followed the steps described in the NVIDIA forums to avoid the crash I had when installing (i.e. remove integration with visual studio). FWIW I'm using a DELL Inspiron 15 Gaming and it has a NVIDIA GTX 1050 with 4GB.

Here's the full code I'm using (straight from the h2o download instructions except for the first line):

I'd like to create a randomized data frame in R where the values of the 2nd column = 1st column + number and the next value of the 1st column = 2nd column + number

It would look something like this:

I've tried doing this:

I have a H2OFrame with two columns and I want to create new column, which is calculated from existing columns (sum of existing columns). How can I create new column in H2OFrame (like mutate() in dplyr) without converting H2OFrame to another frame? Is there any H2O R function doing this?

I have a measurement in every 10-second interval with a date and I need to put a continuous number in one column for the time. Could you please help me to create a loop in R. example data:

I created the following environment.yml file from my local Anaconda that contains an openjdk package.

I want to use H2O's Sparkling Water on multi-node clusters in Azure Databricks, interactively and in jobs through RStudio and R notebooks, respectively. I can start an H2O cluster and a Sparkling Water context on a rocker/verse:4.0.3 and a databricksruntime/rbase:latest (as well as databricksruntime/standard) Docker container on my local machine but currently not on a Databricks cluster. There seems to be a classic classpath problem.

I'm using a generalized low-rank estimator to infer missing values in a data set regarding sensor readings. I'm using H2O to create and train the model:

I need to know which loss functions are used in the h2o gbm and xgboost functions for the gaussian, binomial and multinomial distributions. Unfortunately, my knowledge of Java is very limited and I can't really decipher the source code, and there doesn't seem to be any document clarifying which distribution is associated with which function. I think I gather from here that it's logloss for binomial and MSE for gaussian, but I can't find anything for multinomial. Does anybody here maybe know the answer?