-
There's a corner case where R crashes when num.trees is less than 8 on my computer:
library(grf)
# Generate data.
n = 2000; p = 10
X = matrix(rnorm(n*p), n, p)
X.test = matrix(0, 101, p)
X.t…
-
I have been applying causal forest to datas that have tens millions of observations, and I've been encountering memory issues. When building a forest with only 1000 trees (lower than the recommended a…
-
Referencing #120 it appears from my reading that the use of this package with binary outcomes is considered acceptable and that the inference is valid. Is this correct? Should one consider any methods…
-
Hi, thanks for the great package.
I have a dataset which has 200000 rows and 15 columns. I tried to apply UMAP as following
`embedding = umap.UMAP(n_neighbors=5,
min_dist…
-
Hello,
I trying to understand the output information of one tree from a causal forest.
In this example, the number of training samples is 772.
> tau.forest = causal_forest(x, y, z, num.trees =…
-
Hello:
I am working on a project with a large number of observations (around 300,000 or so). In this project, there are approximately 20 explanatory variables that are useful in determining the tre…
-
Hello @jtibshirani
Quick question: For a given final node "i" of a tree (i.e. a leaf),
does the output tree$nodes[[i]]$samples correspond to the observations of the training sub sample used to build…
predt updated
6 years ago
-
I think there could be added some disadvantages in the feature importance chapter.
There is this paper: https://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-8-25
Moreover ther…
-
Right now GRF is based on an IID assumption. It would be nice to be able to use GRF on data with a hierarchical structure. This is especially relevant in RCTs where studies occur across administrative…
-
Thanks for writing this library! The bagged causalMARS model has a greater uplift than the causal forests from the `grf` library. I know this is in beta, but thought I would throw up an issue anyways.…