Add LOCI

Author: lionelkusch

docs/src/api.rst

@@ -40,3 +40,13 @@ Classes
    CFI
    PFI
    D0CRT
+
+Marginal Importance
+===================
+
+.. autosummary::
+   :toctree: ./generated/api/marginal
+   :template: class.rst
+
+   LOCI
+   LeaveOneCovariateIn

docs/tools/references.bib

@@ -144,6 +144,15 @@ @article{eshel2003yule
   year    = {2003}
 }
 
+@inproceedings{ewald2024guide,
+  title        = {A guide to feature importance methods for scientific inference},
+  author       = {Ewald, Fiona Katharina and Bothmann, Ludwig and Wright, Marvin N and Bischl, Bernd and Casalicchio, Giuseppe and K{\"o}nig, Gunnar},
+  booktitle    = {World Conference on Explainable Artificial Intelligence},
+  pages        = {440--464},
+  year         = {2024},
+  organization = {Springer}
+}
+
 @article{fan2012variance,
   author    = {Fan, Jianqing and Guo, Shaojun and Hao, Ning},
   journal   = {Journal of the Royal Statistical Society Series B: Statistical Methodology},

examples/plot_conditional_vs_marginal_xor_data.py

@@ -12,11 +12,11 @@
 import seaborn as sns
 from sklearn.base import clone
 from sklearn.linear_model import RidgeCV
-from sklearn.metrics import hinge_loss
+from sklearn.metrics import hinge_loss, accuracy_score
 from sklearn.model_selection import KFold, train_test_split
 from sklearn.svm import SVC
 
-from hidimstat import CFI
+from hidimstat import CFI, LOCI
 
 #############################################################################
 # To solve the XOR problem, we will use a Support Vector Classier (SVC) with Radial Basis Function (RBF) kernel. The decision function of
@@ -82,21 +82,9 @@
 cv = KFold(n_splits=5, shuffle=True, random_state=0)
 clf = SVC(kernel="rbf", random_state=0)
 # Compute marginal importance using univariate models
-marginal_scores = []
-for i in range(X.shape[1]):
-    feat_scores = []
-    for train_index, test_index in cv.split(X):
-        X_train, X_test = X[train_index], X[test_index]
-        y_train, y_test = Y[train_index], Y[test_index]
-
-        X_train_univariate = X_train[:, i].reshape(-1, 1)
-        X_test_univariate = X_test[:, i].reshape(-1, 1)
-
-        univariate_model = clone(clf)
-        univariate_model.fit(X_train_univariate, y_train)
-
-        feat_scores.append(univariate_model.score(X_test_univariate, y_test))
-    marginal_scores.append(feat_scores)
+loci = LOCI(estimator=clone(clf).fit(X, Y), method="decision_function", loss=hinge_loss)
+mean_importances = loci.fit_importance(X, Y, cv=cv)
+marginal_importances = np.array(loci.importances_)
 
 ###########################################################################
 
@@ -129,7 +117,7 @@
 fig, axes = plt.subplots(1, 2, sharey=True, figsize=(6, 2.5))
 # Marginal scores boxplot
 sns.boxplot(
-    data=np.array(marginal_scores).T,
+    data=marginal_importances,
     orient="h",
     ax=axes[0],
     fill=False,

src/hidimstat/__init__.py

@@ -28,6 +28,10 @@
 from .noise_std import reid
 from .permutation_feature_importance import PFI
 
+# marginal methods
+from .marginal import LeaveOneCovariateIn  # for having documentation
+from .marginal import LeaveOneCovariateIn as LOCI
+
 from .statistical_tools.aggregation import quantile_aggregation
 
 try:
@@ -54,4 +58,6 @@
     "CFI",
     "LOCO",
     "PFI",
+    # marginal methods
+    "LOCI",
 ]