Skip to content

Fix post-sampler cleanup issues in BART and BCF for R and Python #155

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Mar 17, 2025
Merged

Fix post-sampler cleanup issues in BART and BCF for R and Python #155

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
06c803a
Override keep_gfr if no MCMC samples
andrewherren Mar 16, 2025
fc24040
Fixed indexing issue in post-sampler cleanup in R and Python
andrewherren Mar 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions R/bart.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -826,13 +826,13 @@ bart <- function(X_train, y_train, leaf_basis_train = NULL, rfx_group_ids_train
if ((!keep_gfr) && (num_gfr > 0)) {
for (i in 1:num_gfr) {
if (include_mean_forest) {
forest_samples_mean$delete_sample(i-1)
forest_samples_mean$delete_sample(0)
}
if (include_variance_forest) {
forest_samples_variance$delete_sample(i-1)
forest_samples_variance$delete_sample(0)
}
if (has_rfx) {
rfx_samples$delete_sample(i-1)
rfx_samples$delete_sample(0)
}
}
if (sample_sigma_global) {
Expand Down
8 changes: 4 additions & 4 deletions R/bcf.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1214,13 +1214,13 @@ bcf <- function(X_train, Z_train, y_train, propensity_train = NULL, rfx_group_id
# Remove GFR samples if they are not to be retained
if ((!keep_gfr) && (num_gfr > 0)) {
for (i in 1:num_gfr) {
forest_samples_mu$delete_sample(i-1)
forest_samples_tau$delete_sample(i-1)
forest_samples_mu$delete_sample(0)
forest_samples_tau$delete_sample(0)
if (include_variance_forest) {
forest_samples_variance$delete_sample(i-1)
forest_samples_variance$delete_sample(0)
}
if (has_rfx) {
rfx_samples$delete_sample(i-1)
rfx_samples$delete_sample(0)
}
}
if (sample_sigma_global) {
Expand Down
8 changes: 6 additions & 2 deletions stochtree/bart.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -226,6 +226,10 @@ def sample(self, X_train: Union[np.array, pd.DataFrame], y_train: np.array, basi
keep_vars_variance = variance_forest_params_updated['keep_vars']
drop_vars_variance = variance_forest_params_updated['drop_vars']

# Override keep_gfr if there are no MCMC samples
if num_mcmc == 0:
keep_gfr = True

# Check that num_chains >= 1
if not isinstance(num_chains, Integral) or num_chains < 1:
raise ValueError("num_chains must be an integer greater than 0")
Expand Down Expand Up @@ -680,9 +684,9 @@ def sample(self, X_train: Union[np.array, pd.DataFrame], y_train: np.array, basi
if not keep_gfr and num_gfr > 0:
for i in range(num_gfr):
if self.include_mean_forest:
self.forest_container_mean.delete_sample(i)
self.forest_container_mean.delete_sample(0)
if self.include_variance_forest:
self.forest_container_variance.delete_sample(i)
self.forest_container_variance.delete_sample(0)
if self.sample_sigma_global:
self.global_var_samples = self.global_var_samples[num_gfr:]
if self.sample_sigma_leaf:
Expand Down
10 changes: 7 additions & 3 deletions stochtree/bcf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -299,6 +299,10 @@ def sample(self, X_train: Union[pd.DataFrame, np.array], Z_train: np.array, y_tr
keep_vars_variance = variance_forest_params_updated['keep_vars']
drop_vars_variance = variance_forest_params_updated['drop_vars']

# Override keep_gfr if there are no MCMC samples
if num_mcmc == 0:
keep_gfr = True

# Variable weight preprocessing (and initialization if necessary)
if variable_weights is None:
if X_train.ndim > 1:
Expand Down Expand Up @@ -1051,10 +1055,10 @@ def sample(self, X_train: Union[pd.DataFrame, np.array], Z_train: np.array, y_tr
# Remove GFR samples if they are not to be retained
if not keep_gfr and num_gfr > 0:
for i in range(num_gfr):
self.forest_container_mu.delete_sample(i)
self.forest_container_tau.delete_sample(i)
self.forest_container_mu.delete_sample(0)
self.forest_container_tau.delete_sample(0)
if self.include_variance_forest:
self.forest_container_variance.delete_sample(i)
self.forest_container_variance.delete_sample(0)
if self.adaptive_coding:
self.b1_samples = self.b1_samples[num_gfr:]
self.b0_samples = self.b0_samples[num_gfr:]
Expand Down
Loading