ENH Cleanup multiview API and enable oblique multiview

doc/api.rst

@@ -66,6 +66,7 @@ how scikit-learn builds trees.
    PatchObliqueRandomForestRegressor
    HonestForestClassifier
    MultiViewRandomForestClassifier
+   MultiViewObliqueRandomForestClassifier
 
 .. currentmodule:: treeple.tree
 .. autosummary::
@@ -77,6 +78,7 @@ how scikit-learn builds trees.
    PatchObliqueDecisionTreeRegressor
    HonestTreeClassifier
    MultiViewDecisionTreeClassifier
+   MultiViewObliqueDecisionTreeClassifier
 
 Unsupervised
 ------------

doc/whats_new/v0.9.rst

@@ -19,6 +19,16 @@ Note that the previous version of the package will still be available under the
 Changelog
 ---------
 
+- |API| :class:`treeple.tree.MultiViewDecisionTreeClassifier` do not have the
+    ``apply_max_features_per_feature_set`` argument anymore. Instead, the
+    ``max_features`` argument is used to control the number of features to
+    consider when looking for the best split within each feature set explicitly.
+    By `Adam Li`_ :pr:`#265`.
+
+- |Feature| :class:`treeple.tree.MultiViewObliqueDecisionTreeClassifier` is implemented
+    along with its forest version :class:`treeple.MultiViewObliqueRandomForestClassifier`.
+    By `Adam Li`_ :pr:`#265`.
+
 - |API| Rename the package to ``treeple``. By `SUKI-O`_ (:pr:`#292`)
 - |Fix| Fixed a bug in the predict_proba function of the :class:`treeple.HonestForestClassifier` where posteriors
     estimated on empty leaf with ``ignore`` prior would result in ``np.nan``

examples/splitters/plot_multiview_axis_aligned_splitter.py

@@ -28,10 +28,10 @@
 from matplotlib.colors import ListedColormap
 
 from treeple._lib.sklearn.tree._criterion import Gini
-from treeple.tree._oblique_splitter import MultiViewSplitterTester
+from treeple.tree._oblique_splitter import MultiViewObliqueSplitterTester, MultiViewSplitterTester
 
 criterion = Gini(1, np.array((0, 1)))
-max_features = 5
+max_features = 6
 min_samples_leaf = 1
 min_weight_leaf = 0.0
 random_state = np.random.RandomState(10)
@@ -40,7 +40,7 @@
 feature_set_ends = np.array([3, 5, 9], dtype=np.intp)
 n_feature_sets = len(feature_set_ends)
 
-max_features_per_set_ = None
+max_features_per_set_ = np.array([2, 2, 2])
 feature_combinations = 1
 monotonic_cst = None
 missing_value_feature_mask = None
@@ -99,7 +99,11 @@
 for iend in feature_set_ends[1:]:
     ax.axvline(iend - 0.5, color="black", linewidth=1)
 
-ax.set(title="Sampled Projection Matrix", xlabel="Feature Index", ylabel="Projection Vector Index")
+ax.set(
+    title="Sampled Projection Matrix: \nMultiview Axis Aligned Split with Equal Max_Features",
+    xlabel="Feature Index",
+    ylabel="Projection Vector Index",
+)
 ax.set_xticks(np.arange(feature_set_ends[-1]))
 ax.set_yticks(np.arange(max_features))
 ax.set_yticklabels(np.arange(max_features, dtype=int) + 1)
@@ -115,6 +119,7 @@
 colorbar.set_label("Projection Weight (I.e. Sampled Feature From a Feature Set)")
 colorbar.ax.set_yticklabels(["0", "1"])
 
+fig.tight_layout()
 plt.show()
 
 # %%
@@ -127,9 +132,6 @@
 # more than the second feature set, we can specify ``max_features_per_set`` as follows:
 # ``max_features_per_set = [3, 1]``. This will sample from the first feature set three times
 # and the second feature set once.
-#
-# .. note:: In practice, this is controlled by the ``apply_max_features_per_feature_set`` parameter
-#   in :class:`treeple.tree.MultiViewDecisionTreeClassifier`.
 
 max_features_per_set_ = np.array([1, 2, 3], dtype=int)
 max_features = np.sum(max_features_per_set_)
@@ -163,7 +165,11 @@
 for iend in feature_set_ends[1:]:
     ax.axvline(iend - 0.5, color="black", linewidth=1)
 
-ax.set(title="Sampled Projection Matrix", xlabel="Feature Index", ylabel="Projection Vector Index")
+ax.set(
+    title="Sampled Projection Matrix:\n Multiview Axis-aligned Splitter",
+    xlabel="Feature Index",
+    ylabel="Projection Vector Index",
+)
 ax.set_xticks(np.arange(feature_set_ends[-1]))
 ax.set_yticks(np.arange(max_features))
 ax.set_yticklabels(np.arange(max_features, dtype=int) + 1)
@@ -179,6 +185,129 @@
 colorbar.set_label("Projection Weight (I.e. Sampled Feature From a Feature Set)")
 colorbar.ax.set_yticklabels(["0", "1"])
 
+fig.tight_layout()
+plt.show()
+
+# %%
+# Sampling multiview oblique splits
+# ---------------------------------
+# The multi-view splitter can also sample oblique splits. The oblique splits are
+# generated by sampling a projection matrix and then transforming the data into the
+# projected space.
+
+feature_combinations = 1.5
+cross_feature_set_sampling = False
+splitter = MultiViewObliqueSplitterTester(
+    criterion,
+    max_features,
+    min_samples_leaf,
+    min_weight_leaf,
+    random_state,
+    monotonic_cst,
+    feature_combinations,
+    feature_set_ends,
+    n_feature_sets,
+    max_features_per_set_,
+    cross_feature_set_sampling,
+)
+splitter.init_test(X, y, sample_weight, missing_value_feature_mask)
+
+# sample the projection matrix
+projection_matrix = splitter.sample_projection_matrix_py()
+print(projection_matrix)
+
+cmap = ListedColormap(["orange", "white", "green"])
+
+# Create a heatmap to visualize the indices
+fig, ax = plt.subplots(figsize=(6, 6))
+
+ax.imshow(
+    projection_matrix, cmap=cmap, aspect=feature_set_ends[-1] / max_features, interpolation="none"
+)
+ax.axvline(feature_set_ends[0] - 0.5, color="black", linewidth=1, label="Feature Sets")
+for iend in feature_set_ends[1:]:
+    ax.axvline(iend - 0.5, color="black", linewidth=1)
+
+ax.set(
+    title="Sampled Projection Matrix:\n Multiview Oblique Splits W/O Cross-Feature Sampling",
+    xlabel="Feature Index",
+    ylabel="Projection Vector Index",
+)
+ax.set_xticks(np.arange(feature_set_ends[-1]))
+ax.set_yticks(np.arange(max_features))
+ax.set_yticklabels(np.arange(max_features, dtype=int) + 1)
+ax.set_xticklabels(np.arange(feature_set_ends[-1], dtype=int) + 1)
+ax.legend()
+
+# Create a mappable object
+sm = ScalarMappable(cmap=cmap)
+sm.set_array([])  # You can set an empty array or values here
+
+# Create a color bar with labels for each feature set
+colorbar = fig.colorbar(sm, ax=ax, ticks=[0, 0.5, 1], format="%d")
+colorbar.set_label("Projection Weight")
+colorbar.ax.set_yticklabels(["-1", "0", "1"])
+
+fig.tight_layout()
+plt.show()
+
+# %%
+# Sampling multiview oblique splits with cross-feature-set sampling.
+# Now, we can also sample across feature sets within each projection vector.
+
+cross_feature_set_sampling = True
+splitter = MultiViewObliqueSplitterTester(
+    criterion,
+    max_features,
+    min_samples_leaf,
+    min_weight_leaf,
+    random_state,
+    monotonic_cst,
+    feature_combinations,
+    feature_set_ends,
+    n_feature_sets,
+    max_features_per_set_,
+    cross_feature_set_sampling,
+)
+splitter.init_test(X, y, sample_weight, missing_value_feature_mask)
+
+# sample the projection matrix
+projection_matrix = splitter.sample_projection_matrix_py()
+print(projection_matrix)
+
+cmap = ListedColormap(["orange", "white", "green"])
+
+# Create a heatmap to visualize the indices
+fig, ax = plt.subplots(figsize=(6, 6))
+
+ax.imshow(
+    projection_matrix, cmap=cmap, aspect=feature_set_ends[-1] / max_features, interpolation="none"
+)
+ax.axvline(feature_set_ends[0] - 0.5, color="black", linewidth=1, label="Feature Sets")
+for iend in feature_set_ends[1:]:
+    ax.axvline(iend - 0.5, color="black", linewidth=1)
+
+ax.set(
+    title="Sampled Projection Matrix:\n Multiview Oblique Splits W/ Cross-Feature Sampling",
+    xlabel="Feature Index",
+    ylabel="Projection Vector Index",
+)
+ax.set_xticks(np.arange(feature_set_ends[-1]))
+ax.set_yticks(np.arange(max_features))
+ax.set_yticklabels(np.arange(max_features, dtype=int) + 1)
+ax.set_xticklabels(np.arange(feature_set_ends[-1], dtype=int) + 1)
+ax.legend()
+
+# Create a mappable object
+sm = ScalarMappable(cmap=cmap)
+sm.set_array([])  # You can set an empty array or values here
+
+# Create a color bar with labels for each feature set
+colorbar = fig.colorbar(sm, ax=ax, ticks=[0, 0.5, 1], format="%d")
+colorbar.set_label("Projection Weight")
+colorbar.ax.set_yticklabels(["-1", "0", "1"])
+
+fig.tight_layout()
 plt.show()
 
 # %%

treeple/__init__.py

@@ -45,7 +45,11 @@
             ExtraTreesRegressor,
         )
         from .neighbors import NearestNeighborsMetaEstimator
-        from .ensemble import ExtendedIsolationForest, MultiViewRandomForestClassifier
+        from .ensemble import (
+            ExtendedIsolationForest,
+            MultiViewRandomForestClassifier,
+            MultiViewObliqueRandomForestClassifier,
+        )
         from .ensemble._unsupervised_forest import (
             UnsupervisedRandomForest,
             UnsupervisedObliqueRandomForest,
@@ -88,4 +92,5 @@
         "ExtraTreesRegressor",
         "ExtendedIsolationForest",
         "MultiViewRandomForestClassifier",
+        "MultiViewObliqueRandomForestClassifier",
     ]

treeple/ensemble/__init__.py

@@ -1,6 +1,6 @@
 from ._eiforest import ExtendedIsolationForest
 from ._honest_forest import HonestForestClassifier
-from ._multiview import MultiViewRandomForestClassifier
+from ._multiview import MultiViewObliqueRandomForestClassifier, MultiViewRandomForestClassifier
 from ._supervised_forest import (
     ExtraObliqueRandomForestClassifier,
     ExtraObliqueRandomForestRegressor,