API 2: EnCluDl

docs/src/api.rst

@@ -30,6 +30,7 @@ Feature Importance Classes
    D0CRT
    ModelXKnockoff
    DesparsifiedLasso
+   EnsembleClusteredInference
 
 Feature Importance functions
 ============================

examples/plot_2D_simulation_example.py

@@ -211,6 +211,7 @@ def weight_map_2D_extended(shape, roi_size, delta):
 from sklearn.preprocessing import StandardScaler
 
 from hidimstat.ensemble_clustered_inference import (
+    EnsembleClusteredInference,
     clustered_inference,
     clustered_inference_pvalue,
 )
@@ -221,21 +222,16 @@ def weight_map_2D_extended(shape, roi_size, delta):
 )
 
 # clustered desparsified lasso (CluDL)
-ward_, desparsified_lasso_ = clustered_inference(
-    X_init, y, ward, scaler_sampling=StandardScaler(), random_state=0
-)
-beta_hat, pval, pval_corr, one_minus_pval, one_minus_pval_corr = (
-    clustered_inference_pvalue(n_samples, False, ward_, desparsified_lasso_)
+clustered_inference = EnsembleClusteredInference(
+    ward=ward, scaler_sampling=StandardScaler(), n_bootstraps=1
 )
+clustered_inference.fit_importance(X_init, y)
 
 # compute estimated support (first method)
-zscore = zscore_from_pval(pval, one_minus_pval)
-selected_cdl = zscore > thr_c  # use the "clustering threshold"
-
-# compute estimated support (second method)
-selected_cdl = np.logical_or(
-    pval_corr < fwer_target / 2, one_minus_pval_corr < fwer_target / 2
+zscore = zscore_from_pval(
+    clustered_inference.pvalues_, 1 - clustered_inference.pvalues_
 )
+selected_cdl = zscore > thr_c  # use the "clustering threshold"
 
 
 # %%
@@ -251,20 +247,12 @@ def weight_map_2D_extended(shape, roi_size, delta):
 )
 
 # ensemble of clustered desparsified lasso (EnCluDL)
-list_ward, list_desparsified_lasso = ensemble_clustered_inference(
-    X_init,
-    y,
-    ward,
-    scaler_sampling=StandardScaler(),
-    random_state=0,
-    n_jobs=n_jobs,
+ensemble_clustered_inference = EnsembleClusteredInference(
+    ward=ward, scaler_sampling=StandardScaler(), n_bootstraps=5
 )
-beta_hat, selected_ecdl = ensemble_clustered_inference_pvalue(
-    n_samples,
-    False,
-    list_ward,
-    list_desparsified_lasso,
-    fdr=fwer_target,
+ensemble_clustered_inference.fit_importance(X_init, y)
+selected_ecdl = ensemble_clustered_inference.fdr_selection(
+    fdr=fwer_target, alternative_hypothesis=None
 )
 
 

examples/plot_fmri_data_example.py

@@ -47,12 +47,7 @@
 from sklearn.utils import Bunch
 
 from hidimstat.desparsified_lasso import DesparsifiedLasso
-from hidimstat.ensemble_clustered_inference import (
-    clustered_inference,
-    clustered_inference_pvalue,
-    ensemble_clustered_inference,
-    ensemble_clustered_inference_pvalue,
-)
+from hidimstat.ensemble_clustered_inference import EnsembleClusteredInference
 from hidimstat.statistical_tools.p_values import zscore_from_pval
 
 # Remove warnings during loading data
@@ -183,19 +178,22 @@ def preprocess_haxby(subject=2, memory=None):
 # %%
 # Now, the clustered inference algorithm which combines parcellation
 # and high-dimensional inference (c.f. References).
-ward_, cl_desparsified_lasso = clustered_inference(
-    X,
-    y,
-    ward,
+clustered_inference = EnsembleClusteredInference(
+    variable_importance=DesparsifiedLasso(
+        noise_method="median",
+        estimator=clone(estimator),
+        tolerance_reid=1e-2,
+        n_jobs=1,
+    ),
+    ward=ward,
     scaler_sampling=StandardScaler(),
-    estimator=clone(estimator),
-    tolerance_reid=1e-2,
-    random_state=1,
-    n_jobs=n_jobs,
-)
-beta_hat, pval_cdl, _, one_minus_pval_cdl, _ = clustered_inference_pvalue(
-    X.shape[0], None, ward_, cl_desparsified_lasso
+    n_bootstraps=1,
+    n_jobs=1,
+    random_state=0,
 )
+beta_hat = clustered_inference.fit_importance(X, y)
+pval_cdl = clustered_inference.pvalues_
+one_minus_pval_cdl = 1 - clustered_inference.pvalues_
 
 # %%
 # Below, we run the ensemble clustered inference algorithm which adds a
@@ -205,24 +203,23 @@ def preprocess_haxby(subject=2, memory=None):
 # then 5 statistical maps are produced and aggregated into one.
 # However you might benefit from clustering randomization taking
 # `n_bootstraps=25` or `n_bootstraps=100`, also we set `n_jobs=n_jobs`.
-list_ward, list_cl_desparsified_lasso = ensemble_clustered_inference(
-    X,
-    y,
-    ward,
-    groups=groups,
+ensemble_clustered_inference = EnsembleClusteredInference(
+    variable_importance=DesparsifiedLasso(
+        noise_method="median",
+        estimator=clone(estimator),
+        tolerance_reid=1e-2,
+        n_jobs=1,
+    ),
+    ward=ward,
     scaler_sampling=StandardScaler(),
     n_bootstraps=5,
-    estimator=clone(estimator),
-    tolerance_reid=1e-2,
-    random_state=2,
-    n_jobs=n_jobs,
+    n_jobs=1,
+    random_state=0,
 )
-beta_hat, selected = ensemble_clustered_inference_pvalue(
-    X.shape[0],
-    False,
-    list_ward,
-    list_cl_desparsified_lasso,
-    fdr=0.1,
+beta_hat = ensemble_clustered_inference.fit_importance(X, y)
+pval_cdl = ensemble_clustered_inference.pvalues_
+selected = ensemble_clustered_inference.fdr_selection(
+    fdr=0.1, alternative_hypothesis=None
 )
 
 # %%

src/hidimstat/__init__.py

@@ -2,6 +2,7 @@
 from .desparsified_lasso import DesparsifiedLasso, desparsified_lasso, reid
 from .distilled_conditional_randomization_test import D0CRT, d0crt
 from .ensemble_clustered_inference import (
+    EnsembleClusteredInference,
     clustered_inference,
     clustered_inference_pvalue,
     ensemble_clustered_inference,
@@ -25,6 +26,7 @@
     "DesparsifiedLasso",
     "d0crt",
     "D0CRT",
+    "EnsembleClusteredInference",
     "ensemble_clustered_inference",
     "ensemble_clustered_inference_pvalue",
     "reid",