libmultilabel 0.7.4__tar.gz → 0.8.0__tar.gz

{libmultilabel-0.7.4 → libmultilabel-0.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: libmultilabel
-Version: 0.7.4
+Version: 0.8.0
 Summary: A library for multi-class and multi-label classification
 Home-page: https://github.com/ASUS-AICS/LibMultiLabel
 Author: LibMultiLabel Team
@@ -16,23 +16,25 @@ Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Requires-Python: >=3.8
+Classifier: Programming Language :: Python :: 3.10
+Requires-Python: >=3.10
 License-File: LICENSE
 Requires-Dist: liblinear-multicore>=2.49.0
 Requires-Dist: numba
 Requires-Dist: pandas>1.3.0
 Requires-Dist: PyYAML
 Requires-Dist: scikit-learn
-Requires-Dist: scipy<1.14.0
+Requires-Dist: scipy
 Requires-Dist: tqdm
 Requires-Dist: psutil
+Requires-Dist: sparsekmeans
 Provides-Extra: nn
-Requires-Dist: lightning==2.0.9; extra == "nn"
+Requires-Dist: lightning; extra == "nn"
 Requires-Dist: nltk; extra == "nn"
 Requires-Dist: torch<=2.3; extra == "nn"
 Requires-Dist: torchmetrics==0.10.3; extra == "nn"
 Requires-Dist: torchtext; extra == "nn"
-Requires-Dist: transformers; extra == "nn"
+Requires-Dist: transformers<=4.51.3; extra == "nn"
+Dynamic: license-file
 
 See documentation here: https://www.csie.ntu.edu.tw/~cjlin/libmultilabel

{libmultilabel-0.7.4 → libmultilabel-0.8.0}/README.md

@@ -9,7 +9,7 @@ LibMultiLabel is a library for binary, multi-class, and multi-label classificati
 This is an on-going development so many improvements are still being made. Comments are very welcome.
 
 ## Environments
-- Python: 3.8+
+- Python: 3.10+
 - CUDA: 11.8, 12.1 (if training neural networks by GPU)
 - Pytorch: 2.0.1+
 

{libmultilabel-0.7.4 → libmultilabel-0.8.0}/libmultilabel/linear/linear.py

@@ -27,7 +27,7 @@ class FlatModel:
     def __init__(
         self,
         name: str,
-        weights: np.matrix,
+        weights: np.matrix | sparse.csr_matrix,
         bias: float,
         thresholds: float | np.ndarray,
         multiclass: bool,
@@ -69,7 +69,21 @@ class FlatModel:
                 "csr",
             )
 
-        return (x * self.weights).A + self.thresholds
+        return self._to_dense_array(x * self.weights) + self.thresholds
+
+    def _to_dense_array(self, matrix: np.matrix | sparse.csr_matrix) -> np.ndarray:
+        """Convert a numpy or scipy matrix to a dense ndarray.
+
+        Args:
+            matrix (np.matrix | sparse.csr_matrix): A numpy or scipy sparse matrix.
+
+        Returns:
+            np.ndarray: A dense ndarray of `matrix`.
+        """
+        if sparse.issparse(matrix):
+            return matrix.toarray()
+        elif isinstance(matrix, np.matrix):
+            return np.asarray(matrix)
 
 
 def train_1vsrest(
@@ -458,7 +472,7 @@ def _cost_sensitive_one_label(y: np.ndarray, x: sparse.csr_matrix, options: str)
 
     param_space = [1, 1.33, 1.8, 2.5, 3.67, 6, 13]
 
-    bestScore = -np.Inf
+    bestScore = -np.inf
     for a in param_space:
         cv_options = f"{options} -w1 {a}"
         pred = _cross_validate(y, x, cv_options, perm)
@@ -532,7 +546,7 @@ def train_cost_sensitive_micro(
     l = y.shape[0]
     perm = np.random.permutation(l)
     param_space = [1, 1.33, 1.8, 2.5, 3.67, 6, 13]
-    bestScore = -np.Inf
+    bestScore = -np.inf
 
     if verbose:
         logging.info(f"Training cost-sensitive model for Micro-F1 on {num_class} labels")

{libmultilabel-0.7.4 → libmultilabel-0.8.0}/libmultilabel/linear/tree.py

@@ -4,7 +4,7 @@ from typing import Callable
 
 import numpy as np
 import scipy.sparse as sparse
-import sklearn.cluster
+from sparsekmeans import LloydKmeans, ElkanKmeans
 import sklearn.preprocessing
 from tqdm import tqdm
 import psutil
@@ -101,7 +101,7 @@ class TreeModel:
         self.subtree_models = []
         for i in range(len(self.root.children)):
             subtree_weights_start = self.node_ptr[self.root.children[i].index]
-            subtree_weights_end = self.node_ptr[self.root.children[i+1].index] if i+1 < len(self.root.children) else -1
+            subtree_weights_end = self.node_ptr[self.root.children[i+1].index] if i+1 < len(self.root.children) else self.node_ptr[-1]
             slice = np.s_[:, subtree_weights_start:subtree_weights_end]
             subtree_flatmodel = linear.FlatModel(
                 name="subtree-flattened-tree",
@@ -274,28 +274,29 @@ def _build_tree(label_representation: sparse.csr_matrix, label_map: np.ndarray,
     Returns:
         Node: Root of the (sub)tree built from label_representation.
     """
-    if d >= dmax or label_representation.shape[0] <= K:
-        return Node(label_map=label_map, children=[])
-
-    metalabels = (
-        sklearn.cluster.KMeans(
-            K,
-            random_state=np.random.randint(2**31 - 1),
-            n_init=1,
-            max_iter=300,
-            tol=0.0001,
-            algorithm="elkan",
+    children = []
+    if d < dmax and label_representation.shape[0] > K:
+        if label_representation.shape[0] > 10000:
+            kmeans_algo = ElkanKmeans
+        else:
+            kmeans_algo = LloydKmeans
+
+        kmeans = kmeans_algo(
+            n_clusters=K, max_iter=300, tol=0.0001, random_state=np.random.randint(2**31 - 1), verbose=True
         )
-        .fit(label_representation)
-        .labels_
-    )
+        metalabels = kmeans.fit(label_representation)
 
-    children = []
-    for i in range(K):
-        child_representation = label_representation[metalabels == i]
-        child_map = label_map[metalabels == i]
-        child = _build_tree(child_representation, child_map, d + 1, K, dmax)
-        children.append(child)
+        unique_labels = np.unique(metalabels)
+        if len(unique_labels) == K:
+            create_child_node = lambda i: _build_tree(
+                label_representation[metalabels == i], label_map[metalabels == i], d + 1, K, dmax
+            )
+        else:
+            create_child_node = lambda i: Node(label_map=label_map[metalabels == i], children=[])
+
+        for i in range(K):
+            child = create_child_node(i)
+            children.append(child)
 
     return Node(label_map=label_map, children=children)
 

{libmultilabel-0.7.4 → libmultilabel-0.8.0}/libmultilabel.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: libmultilabel
-Version: 0.7.4
+Version: 0.8.0
 Summary: A library for multi-class and multi-label classification
 Home-page: https://github.com/ASUS-AICS/LibMultiLabel
 Author: LibMultiLabel Team
@@ -16,23 +16,25 @@ Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Requires-Python: >=3.8
+Classifier: Programming Language :: Python :: 3.10
+Requires-Python: >=3.10
 License-File: LICENSE
 Requires-Dist: liblinear-multicore>=2.49.0
 Requires-Dist: numba
 Requires-Dist: pandas>1.3.0
 Requires-Dist: PyYAML
 Requires-Dist: scikit-learn
-Requires-Dist: scipy<1.14.0
+Requires-Dist: scipy
 Requires-Dist: tqdm
 Requires-Dist: psutil
+Requires-Dist: sparsekmeans
 Provides-Extra: nn
-Requires-Dist: lightning==2.0.9; extra == "nn"
+Requires-Dist: lightning; extra == "nn"
 Requires-Dist: nltk; extra == "nn"
 Requires-Dist: torch<=2.3; extra == "nn"
 Requires-Dist: torchmetrics==0.10.3; extra == "nn"
 Requires-Dist: torchtext; extra == "nn"
-Requires-Dist: transformers; extra == "nn"
+Requires-Dist: transformers<=4.51.3; extra == "nn"
+Dynamic: license-file
 
 See documentation here: https://www.csie.ntu.edu.tw/~cjlin/libmultilabel

{libmultilabel-0.7.4 → libmultilabel-0.8.0}/libmultilabel.egg-info/requires.txt

@@ -3,14 +3,15 @@ numba
 pandas>1.3.0
 PyYAML
 scikit-learn
-scipy<1.14.0
+scipy
 tqdm
 psutil
+sparsekmeans
 
 [nn]
-lightning==2.0.9
+lightning
 nltk
 torch<=2.3
 torchmetrics==0.10.3
 torchtext
-transformers
+transformers<=4.51.3

{libmultilabel-0.7.4 → libmultilabel-0.8.0}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = libmultilabel
-version = 0.7.4
+version = 0.8.0
 author = LibMultiLabel Team
 license = MIT License
 license_file = LICENSE
@@ -20,7 +20,7 @@ classifiers =
 	License :: OSI Approved :: MIT License
 	Operating System :: OS Independent
 	Programming Language :: Python :: 3
-	Programming Language :: Python :: 3.8
+	Programming Language :: Python :: 3.10
 
 [options]
 packages = find:
@@ -30,19 +30,20 @@ install_requires =
 	pandas>1.3.0
 	PyYAML
 	scikit-learn
-	scipy<1.14.0
+	scipy
 	tqdm
 	psutil
-python_requires = >=3.8
+	sparsekmeans
+python_requires = >=3.10
 
 [options.extras_require]
 nn = 
-	lightning==2.0.9
+	lightning
 	nltk
 	torch<=2.3
 	torchmetrics==0.10.3
 	torchtext
-	transformers
+	transformers<=4.51.3
 
 [options.packages.find]
 exclude =