Adding Local Adaptive Streaming Tree (#1610)

* add first last with out-of-date docs * update LAST to detect change in the data distribution + iter_arff none class Docs are also updated * update docs * Update hoeffding_adaptive_tree_classifier.py * changes after tests * solving inheritance and small fixes * tests + current_merit method * Update river/tree/hoeffding_adaptive_tree_classifier.py * update docs * change docs * change last * Update docs/releases/unreleased.md * Update river/tree/hoeffding_adaptive_tree_classifier.py * Update river/tree/last_classifier.py * add disclamer * Update river/tree/last_classifier.py --------- Co-authored-by: Saulo Martiello Mastelini <[email protected]>
online-ml · Sep 6, 2024 · e3b2163 · e3b2163
1 parent 7e3eb19
commit e3b2163
Show file tree

Hide file tree

Showing 12 changed files with 614 additions and 2 deletions.
diff --git a/docs/releases/unreleased.md b/docs/releases/unreleased.md
@@ -17,3 +17,9 @@
 ## tree
 
 - Instead of letting trees grow indefinitely, setting the `max_depth` parameter to `None` will stop the trees from growing when they reach the system recursion limit.
+
+-Added `tree.LASTClassifier` (Local Adaptive Streaming Tree Classifier).
+
+## stream
+
+- `stream.iter_arff` now supports blank values (treated as missing values).
diff --git a/river/stream/iter_arff.py b/river/stream/iter_arff.py
@@ -176,7 +176,7 @@ def iter_arff(
             x = {
                 name: cast(val) if cast else val
                 for name, cast, val in zip(names, casts, r.rstrip().split(","))
-                if val != "?"
+                if val != "?" and val != ""
             }
 
         # Handle target
@@ -185,7 +185,10 @@ def iter_arff(
             if isinstance(target, list):
                 y = {name: x.pop(name, 0) for name in target}
             else:
-                y = x.pop(target) if target else None
+                try:
+                    y = x.pop(target) if target else None
+                except KeyError:
+                    y = None
 
         yield x, y
 

diff --git a/river/tree/__init__.py b/river/tree/__init__.py
@@ -59,6 +59,7 @@
 from .hoeffding_tree_classifier import HoeffdingTreeClassifier
 from .hoeffding_tree_regressor import HoeffdingTreeRegressor
 from .isoup_tree_regressor import iSOUPTreeRegressor
+from .last_classifier import LASTClassifier
 from .stochastic_gradient_tree import SGTClassifier, SGTRegressor
 
 __all__ = [
@@ -70,6 +71,7 @@
     "HoeffdingTreeRegressor",
     "HoeffdingAdaptiveTreeRegressor",
     "iSOUPTreeRegressor",
+    "LASTClassifier",
     "SGTClassifier",
     "SGTRegressor",
 ]