Skip to content

Update Python BCF to work without propensities #241

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
Nov 21, 2025
Merged

Update Python BCF to work without propensities #241

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
e48fd7b
Update Python BCF to work without propensities
andrewherren Nov 20, 2025
0a4d8c8
Added unit test to make sure BCF runs without propensity scores
andrewherren Nov 20, 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
35 changes: 13 additions & 22 deletions stochtree/bcf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -932,16 +932,15 @@ def sample(
if sample_sigma2_leaf_tau is not None:
if not isinstance(sample_sigma2_leaf_tau, bool):
raise ValueError("sample_sigma2_leaf_tau must be a bool")
if propensity_covariate is not None:
if propensity_covariate not in [
"prognostic",
"treatment_effect",
"both",
"none",
]:
raise ValueError(
"propensity_covariate must be one of 'prognostic', 'treatment_effect', 'both', or 'none'"
)
if propensity_covariate not in [
"prognostic",
"treatment_effect",
"both",
"none",
]:
raise ValueError(
"propensity_covariate must be one of 'prognostic', 'treatment_effect', 'both', or 'none'"
)
if b_0 is not None:
b_0 = check_scalar(
x=b_0,
Expand Down Expand Up @@ -1663,15 +1662,6 @@ def sample(
] = 0

# Update covariates to include propensities if requested
if propensity_covariate not in [
"none",
"prognostic",
"treatment_effect",
"both",
]:
raise ValueError(
"propensity_covariate must equal one of 'none', 'prognostic', 'treatment_effect', or 'both'"
)
if propensity_covariate != "none":
feature_types = np.append(
feature_types, np.repeat(0, propensity_train.shape[1])
Expand Down Expand Up @@ -1700,9 +1690,10 @@ def sample(
variable_weights_tau = np.append(
variable_weights_tau, np.repeat(1 / num_cov_orig, propensity_train.shape[1])
)
variable_weights_variance = np.append(
variable_weights_variance, np.repeat(0.0, propensity_train.shape[1])
)
# For now, propensities are not included in the variance forest
variable_weights_variance = np.append(
variable_weights_variance, np.repeat(0.0, propensity_train.shape[1])
)

# Renormalize variable weights
variable_weights_mu = variable_weights_mu / np.sum(variable_weights_mu)
Expand Down
13 changes: 13 additions & 0 deletions test/python/test_bcf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -194,6 +194,19 @@ def test_binary_bcf(self):
# Check treatment effect prediction method
tau_hat = bcf_model.predict(X=X_test, Z=Z_test, terms="cate")

# Check that we can run BCF without propensities
bcf_model = BCFModel()
general_params = {"propensity_covariate": "none"}
bcf_model.sample(
X_train=X_train,
Z_train=Z_train,
y_train=y_train,
num_gfr=num_gfr,
num_burnin=num_burnin,
num_mcmc=num_mcmc,
general_params=general_params,
)

def test_continuous_univariate_bcf(self):
# RNG
random_seed = 101
Expand Down
Loading