libmultilabel 0.7.2__tar.gz → 0.7.3__tar.gz

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: libmultilabel
-Version: 0.7.2
+Version: 0.7.3
 Summary: A library for multi-class and multi-label classification
 Home-page: https://github.com/ASUS-AICS/LibMultiLabel
 Author: LibMultiLabel Team
@@ -19,7 +19,7 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.8
 Requires-Python: >=3.8
 License-File: LICENSE
-Requires-Dist: liblinear-multicore
+Requires-Dist: liblinear-multicore>=2.49.0
 Requires-Dist: numba
 Requires-Dist: pandas>1.3.0
 Requires-Dist: PyYAML

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/common_utils.py

@@ -34,10 +34,10 @@ class AttributeDict(dict):
         self._used.discard(key)
 
     def used_items(self) -> dict:
-        """Returns the items that have been used at least once after being set.
+        """Return the items that have been used at least once after being set.
 
         Returns:
-            dict: the used items.
+            dict: The used items.
         """
         return {k: self[k] for k in self._used}
 
@@ -46,10 +46,10 @@ def dump_log(log_path, metrics=None, split=None, config=None):
     """Write log including the used items of config and the evaluation scores.
 
     Args:
-        log_path(str): path to log path
-        metrics (dict): metric and scores in dictionary format, defaults to None
-        split (str): val or test, defaults to None
-        config (dict): config to save, defaults to None
+        log_path(str): Path to log path.
+        metrics (dict): Metric and scores in dictionary format, defaults to None.
+        split (str): One of `val` or `test`, defaults to None.
+        config (dict): Config to save, defaults to None.
     """
     os.makedirs(os.path.dirname(log_path), exist_ok=True)
     if os.path.isfile(log_path):
@@ -82,7 +82,8 @@ def argsort_top_k(vals, k, axis=-1):
         k: Consider only the top k elements for each query
         axis: Axis along which to sort. The default is -1 (the last axis).
 
-    Returns: Array of indices that sort vals along the specified axis.
+    Returns: 
+        Array of indices that sort vals along the specified axis.
     """
     unsorted_top_k_idx = np.argpartition(vals, -k, axis=axis)[:, -k:]
     unsorted_top_k_scores = np.take_along_axis(vals, unsorted_top_k_idx, axis=axis)
@@ -130,7 +131,7 @@ def is_multiclass_dataset(dataset, label="label"):
 
 
 def timer(func):
-    """Log info-level wall time"""
+    """Log info-level wall time."""
 
     @wraps(func)
     def wrapper(*args, **kwargs):

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/linear/linear.py

@@ -5,7 +5,7 @@ import os
 
 import numpy as np
 import scipy.sparse as sparse
-from liblinear.liblinearutil import train
+from liblinear.liblinearutil import train, problem, parameter, solver_names
 from tqdm import tqdm
 
 __all__ = [
@@ -39,7 +39,7 @@ class FlatModel:
         self.multiclass = multiclass
 
     def predict_values(self, x: sparse.csr_matrix) -> np.ndarray:
-        """Calculates the decision values associated with x.
+        """Calculate the decision values associated with x.
 
         Args:
             x (sparse.csr_matrix): A matrix with dimension number of instances * number of features.
@@ -79,7 +79,7 @@ def train_1vsrest(
     options: str = "",
     verbose: bool = True,
 ) -> FlatModel:
-    """Trains a linear model for multi-label data using a one-vs-rest strategy.
+    """Train a linear model for multi-label data using a one-vs-rest strategy.
 
     Args:
         y (sparse.csr_matrix): A 0/1 matrix with dimensions number of instances * number of classes.
@@ -169,9 +169,9 @@ def train_thresholding(
     options: str = "",
     verbose: bool = True,
 ) -> FlatModel:
-    """Trains a linear model for multi-label data using a one-vs-rest strategy
+    """Train a linear model for multi-label data using a one-vs-rest strategy
     and cross-validation to pick decision thresholds optimizing the sum of Macro-F1 and Micro-F1.
-    Outperforms train_1vsrest in most aspects at the cost of higher time complexity
+    Outperform train_1vsrest in most aspects at the cost of higher time complexity
     due to an internal cross-validation.
 
     This method is the micromacro-freq approach from this CIKM 2023 paper:
@@ -235,7 +235,7 @@ def _micromacro_one_label(
             negatives, and the number of labels processed.
 
     Returns:
-        tuple[np.ndarray, float, dict]: the weights, threshold, and the updated stats for calculating
+        tuple[np.ndarray, float, dict]: The weights, threshold, and the updated stats for calculating
         Micro-F1.
     """
 
@@ -319,7 +319,7 @@ def _micromacro_one_label(
 
 
 def _do_train(y: np.ndarray, x: sparse.csr_matrix, options: str) -> np.matrix:
-    """Wrapper around liblinear.liblinearutil.train.
+    """Wrap around liblinear.liblinearutil.train.
     Forcibly suppresses all IO regardless of options.
 
     Args:
@@ -328,13 +328,17 @@ def _do_train(y: np.ndarray, x: sparse.csr_matrix, options: str) -> np.matrix:
         options (str): The option string passed to liblinear.
 
     Returns:
-        np.matrix: the weights.
+        np.matrix: The weights.
     """
     if y.shape[0] == 0:
         return np.matrix(np.zeros((x.shape[1], 1)))
 
+    prob = problem(y, x)
+    param = parameter(options)
+    if param.solver_type in [solver_names.L2R_L1LOSS_SVC_DUAL, solver_names.L2R_L2LOSS_SVC_DUAL]:
+        param.w_recalc = True  # only works for solving L1/L2-SVM dual
     with silent_stderr():
-        model = train(y, x, options)
+        model = train(prob, param)
 
     w = np.ctypeslib.as_array(model.w, (x.shape[1], 1))
     w = np.asmatrix(w)
@@ -373,11 +377,11 @@ def _fmeasure(y_true: np.ndarray, y_pred: np.ndarray) -> float:
     """Calculate F1 score.
 
     Args:
-        y_true (np.ndarray): array of +1/-1.
-        y_pred (np.ndarray): array of +1/-1.
+        y_true (np.ndarray): Array of +1/-1.
+        y_pred (np.ndarray): Array of +1/-1.
 
     Returns:
-        float: the F1 score.
+        float: The F1 score.
     """
     tp = np.sum(np.logical_and(y_true == 1, y_pred == 1))
     fn = np.sum(np.logical_and(y_true == 1, y_pred == -1))
@@ -396,10 +400,10 @@ def train_cost_sensitive(
     options: str = "",
     verbose: bool = True,
 ) -> FlatModel:
-    """Trains a linear model for multi-label data using a one-vs-rest strategy
+    """Train a linear model for multi-label data using a one-vs-rest strategy
     and cross-validation to pick an optimal asymmetric misclassification cost
     for Macro-F1.
-    Outperforms train_1vsrest in most aspects at the cost of higher
+    Outperform train_1vsrest in most aspects at the cost of higher
     time complexity.
     See user guide for more details.
 
@@ -413,7 +417,7 @@ def train_cost_sensitive(
     Returns:
         A model which can be used in predict_values.
     """
-    # Follows the MATLAB implementation at https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/multilabel/
+    # Follow the MATLAB implementation at https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/multilabel/
     x, options, bias = _prepare_options(x, options)
 
     y = y.tocsc()
@@ -446,7 +450,7 @@ def _cost_sensitive_one_label(y: np.ndarray, x: sparse.csr_matrix, options: str)
         options (str): The option string passed to liblinear.
 
     Returns:
-        np.ndarray: the weights.
+        np.ndarray: The weights.
     """
 
     l = y.shape[0]
@@ -500,10 +504,10 @@ def train_cost_sensitive_micro(
     options: str = "",
     verbose: bool = True,
 ) -> FlatModel:
-    """Trains a linear model for multi-label data using a one-vs-rest strategy
+    """Train a linear model for multi-label data using a one-vs-rest strategy
     and cross-validation to pick an optimal asymmetric misclassification cost
     for Micro-F1.
-    Outperforms train_1vsrest in most aspects at the cost of higher
+    Outperform train_1vsrest in most aspects at the cost of higher
     time complexity.
     See user guide for more details.
 
@@ -571,7 +575,7 @@ def train_binary_and_multiclass(
     options: str = "",
     verbose: bool = True,
 ) -> FlatModel:
-    """Trains a linear model for binary and multi-class data.
+    """Train a linear model for binary and multi-class data.
 
     Args:
         y (sparse.csr_matrix): A 0/1 matrix with dimensions number of instances * number of classes.
@@ -592,8 +596,12 @@ def train_binary_and_multiclass(
         Invalid dataset. Only multi-class dataset is allowed."""
     y = np.squeeze(nonzero_label_ids)
 
+    prob = problem(y, x)
+    param = parameter(options)
+    if param.solver_type in [solver_names.L2R_L1LOSS_SVC_DUAL, solver_names.L2R_L2LOSS_SVC_DUAL]:
+        param.w_recalc = True
     with silent_stderr():
-        model = train(y, x, options)
+        model = train(prob, param)
 
     # Labels appeared in training set; length may be smaller than num_labels
     train_labels = np.array(model.get_labels(), dtype="int")
@@ -622,7 +630,7 @@ def train_binary_and_multiclass(
 
 
 def predict_values(model, x: sparse.csr_matrix) -> np.ndarray:
-    """Calculates the decision values associated with x, equivalent to model.predict_values(x).
+    """Calculate the decision values associated with x, equivalent to model.predict_values(x).
 
     Args:
         model: A model returned from a training function.

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/linear/metrics.py

@@ -8,7 +8,7 @@ __all__ = ["get_metrics", "compute_metrics", "tabulate_metrics", "MetricCollecti
 
 
 def _argsort_top_k(preds: np.ndarray, top_k: int) -> np.ndarray:
-    """Sorts the top k indices in O(n + k log k) time.
+    """Sort the top k indices in O(n + k log k) time.
     The sorting order is ascending to be consistent with np.sort.
     This means the last element is the largest, the first element is the kth largest.
     """
@@ -18,7 +18,7 @@ def _argsort_top_k(preds: np.ndarray, top_k: int) -> np.ndarray:
 
 
 def _dcg_argsort(argsort_preds: np.ndarray, target: np.ndarray, top_k: int) -> np.ndarray:
-    """Computes DCG@k with a sorted preds array and a target array."""
+    """Compute DCG@k with a sorted preds array and a target array."""
     top_k_idx = argsort_preds[:, -top_k:][:, ::-1]
     gains = np.take_along_axis(target, top_k_idx, axis=-1)
     discount = 1 / (np.log2(np.arange(top_k) + 2))
@@ -28,7 +28,7 @@ def _dcg_argsort(argsort_preds: np.ndarray, target: np.ndarray, top_k: int) -> n
 
 
 def _idcg(target: np.ndarray, top_k: int) -> np.ndarray:
-    """Computes IDCG@k for a 0/1 target array. A 0/1 target is a special case that
+    """Compute IDCG@k for a 0/1 target array. A 0/1 target is a special case that
     doesn't require sorting. If IDCG is computed with DCG,
     then target will need to be sorted, which incurs a large overhead.
     """
@@ -247,7 +247,7 @@ class MetricCollection(dict):
         self.max_k = max(getattr(metric, "top_k", 0) for metric in self.metrics.values())
 
     def update(self, preds: np.ndarray, target: np.ndarray):
-        """Adds a batch of decision values and labels.
+        """Add a batch of decision values and labels.
 
         Args:
             preds (np.ndarray): A matrix of decision values with dimensions number of instances * number of classes.
@@ -268,7 +268,7 @@ class MetricCollection(dict):
                 metric.update(preds, target)
 
     def compute(self) -> dict[str, float]:
-        """Computes the metrics from the accumulated batches of decision values and labels.
+        """Compute the metrics from the accumulated batches of decision values and labels.
 
         Returns:
             dict[str, float]: A dictionary of metric values.
@@ -279,7 +279,7 @@ class MetricCollection(dict):
         return ret
 
     def reset(self):
-        """Clears the accumulated batches of decision values and labels."""
+        """Clear the accumulated batches of decision values and labels."""
         for metric in self.metrics.values():
             metric.reset()
 

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/linear/tree.py

@@ -59,7 +59,7 @@ class TreeModel:
         x: sparse.csr_matrix,
         beam_width: int = 10,
     ) -> np.ndarray:
-        """Calculates the probability estimates associated with x.
+        """Calculate the probability estimates associated with x.
 
         Args:
             x (sparse.csr_matrix): A matrix with dimension number of instances * number of features.
@@ -118,7 +118,7 @@ def train_tree(
     dmax=10,
     verbose: bool = True,
 ) -> TreeModel:
-    """Trains a linear model for multi-label data using a divide-and-conquer strategy.
+    """Train a linear model for multi-label data using a divide-and-conquer strategy.
     The algorithm used is based on https://github.com/xmc-aalto/bonsai.
 
     Args:
@@ -178,7 +178,7 @@ def train_tree(
 
 
 def _build_tree(label_representation: sparse.csr_matrix, label_map: np.ndarray, d: int, K: int, dmax: int) -> Node:
-    """Builds the tree recursively by kmeans clustering.
+    """Build the tree recursively by kmeans clustering.
 
     Args:
         label_representation (sparse.csr_matrix): A matrix with dimensions number of classes under this node * number of features.
@@ -235,7 +235,7 @@ def get_estimated_model_size(root):
 
 
 def _train_node(y: sparse.csr_matrix, x: sparse.csr_matrix, options: str, node: Node):
-    """If node is internal, computes the metalabels representing each child and trains
+    """If node is internal, compute the metalabels representing each child and train
     on the metalabels. Otherwise, train on y.
 
     Args:
@@ -258,7 +258,7 @@ def _train_node(y: sparse.csr_matrix, x: sparse.csr_matrix, options: str, node:
 
 
 def _flatten_model(root: Node) -> tuple[linear.FlatModel, np.ndarray]:
-    """Flattens tree weight matrices into a single weight matrix. The flattened weight
+    """Flatten tree weight matrices into a single weight matrix. The flattened weight
     matrix is used to predict all possible values, which is cached for beam search.
     This pessimizes complexity but is faster in practice.
     Consecutive values of the returned map denotes the start and end indices of the
@@ -289,7 +289,7 @@ def _flatten_model(root: Node) -> tuple[linear.FlatModel, np.ndarray]:
 
     model = linear.FlatModel(
         name="flattened-tree",
-        weights=sparse.hstack(weights, "csr"),
+        weights=sparse.hstack(weights, "csc"),
         bias=bias,
         thresholds=0,
         multiclass=False,

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/linear/utils.py

@@ -31,7 +31,7 @@ LINEAR_TECHNIQUES = {
 
 
 def save_pipeline(checkpoint_dir: str, preprocessor: Preprocessor, model):
-    """Saves preprocessor and model to checkpoint_dir/linear_pipline.pickle.
+    """Save preprocessor and model to checkpoint_dir/linear_pipline.pickle.
 
     Args:
         checkpoint_dir (str): The directory to save to.
@@ -53,7 +53,7 @@ def save_pipeline(checkpoint_dir: str, preprocessor: Preprocessor, model):
 
 
 def load_pipeline(checkpoint_path: str) -> tuple[Preprocessor, Any]:
-    """Loads preprocessor and model from checkpoint_path.
+    """Load preprocessor and model from checkpoint_path.
 
     Args:
         checkpoint_path (str): The path to a previously saved pipeline.

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/nn/attentionxml.py

@@ -47,7 +47,7 @@ class PLTTrainer:
             raise ValueError(
                 "The label space of multi-class datasets is usually not large, so PLT training is unnecessary."
                 "Please consider other methods."
-                "If you have a multi-class set with numerous labels, please let us know"
+                "If you have a multi-class set with numerous labels, please let us know."
             )
 
         # cluster
@@ -137,11 +137,11 @@ class PLTTrainer:
         Given the ground-truth labels, [0, 1, 4], the resulting clusters are [0, 2].
 
         Args:
-            cluster_mapping (np.ndarray): mapping from clusters generated by build_label_tree to labels .
-            *labels (csr_matrix): labels in CSR sparse format.
+            cluster_mapping (np.ndarray): Mapping from clusters generated by build_label_tree to labels.
+            *labels (csr_matrix): Labels in CSR sparse format.
 
         Returns:
-            Generator[csr_matrix]: resulting clusters converted from labels in CSR sparse format
+            Generator[csr_matrix]: Resulting clusters converted from labels in CSR sparse format.
         """
         mapping = np.empty(self.num_classes, dtype=np.uint32)
         for idx, clusters in enumerate(cluster_mapping):
@@ -169,12 +169,12 @@ class PLTTrainer:
         Also notice that this function deals with DENSE matrix.
 
         Args:
-            cluster_mapping (np.ndarray): mapping from clusters generated by build_label_tree to labels .
-            clusters (np.ndarray): predicted clusters from model 0.
-            cluster_scores (Optional: np.ndarray): predicted scores of each cluster from model 0.
+            cluster_mapping (np.ndarray): Mapping from clusters generated by build_label_tree to labels.
+            clusters (np.ndarray): Predicted clusters from model 0.
+            cluster_scores (Optional: np.ndarray): Predicted scores of each cluster from model 0.
 
         Returns:
-            Generator[np.ndarray]: resulting labels expanded from clusters
+            Generator[np.ndarray]: Resulting labels expanded from clusters.
         """
 
         labels_selected = []
@@ -192,10 +192,10 @@ class PLTTrainer:
             return labels_selected
 
     def fit(self, datasets):
-        """fit model to the training dataset
+        """Fit model to the training dataset.
 
         Args:
-            datasets: dict containing training, validation, and/or test datasets
+            datasets: Dict containing training, validation, and/or test datasets.
         """
         if self.get_best_model_path(level=1).exists():
             return
@@ -596,8 +596,8 @@ class PlainDataset(Dataset):
     this while generating clusters. There is no need to do multilabel binarization again.
 
     Args:
-        x (list | ndarray | Tensor): texts.
-        y (Optional: csr_matrix | ndarray | Tensor): labels.
+        x (list | ndarray | Tensor): Texts.
+        y (Optional: csr_matrix | ndarray | Tensor): Labels.
     """
 
     def __init__(self, x, y=None):
@@ -633,12 +633,12 @@ class PLTDataset(PlainDataset):
     """Dataset for model_1 of AttentionXML.
 
     Args:
-        x: texts.
-        y: labels.
+        x: Texts.
+        y: Labels.
         num_classes: number of classes.
-        num_labels_selected: the number of selected labels.
-        labels_selected: sampled predicted labels from model_0. Shape: (len(x), predict_top_k).
-        label_scores: scores for each label. Shape: (len(x), predict_top_k).
+        num_labels_selected: The number of selected labels.
+        labels_selected: Sampled predicted labels from model_0. Shape: (len(x), predict_top_k).
+        label_scores: Scores for each label. Shape: (len(x), predict_top_k).
     """
 
     def __init__(
@@ -709,10 +709,10 @@ def build_label_tree(sparse_x: csr_matrix, sparse_y: csr_matrix, cluster_size: i
     ((0, 2), (1, 3), (4, 5)).
 
     Args:
-        sparse_x: features extracted from texts in CSR sparse format
-        sparse_y: binarized labels in CSR sparse format
-        cluster_size: the maximum number of labels within each cluster
-        output_dir: directory to store the clustering file
+        sparse_x: Features extracted from texts in CSR sparse format.
+        sparse_y: Binarized labels in CSR sparse format.
+        cluster_size: The maximum number of labels within each cluster.
+        output_dir: Directory to store the clustering file.
     """
     # skip constructing label tree if the output file already exists
     output_dir = output_dir if isinstance(output_dir, Path) else Path(output_dir)
@@ -755,8 +755,8 @@ def _split_cluster(cluster: ndarray, label_repr: csr_matrix) -> tuple[ndarray, n
     2. the end-of-loop criterion is the difference between the new and old average in-cluster distances to centroids.
 
     Args:
-        cluster: a subset of labels
-        label_repr: the normalized representations of the relationship between labels and texts of the given cluster
+        cluster: A subset of labels.
+        label_repr: The normalized representations of the relationship between labels and texts of the given cluster.
     """
     # Randomly choose two points as initial centroids and obtain their label representations
     centroids = label_repr[np.random.choice(len(cluster), size=2, replace=False)].toarray()

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/nn/data_utils.py

@@ -355,7 +355,7 @@ def get_embedding_weights_from_file(word_dict, embed_file, silent=False, cache=N
         cache (str, optional): Path to a directory for storing cached embeddings. Defaults to None.
 
     Returns:
-        torch.Tensor: Embedding weights (vocab_size, embed_size)
+        torch.Tensor: Embedding weights (vocab_size, embed_size).
     """
     # Load pretrained word embedding
     load_embedding_from_file = embed_file not in pretrained_aliases

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/nn/metrics.py

@@ -13,7 +13,7 @@ class _PrecisonRecallWrapperMetric(Metric):
     """Encapsulate common functions of RPrecision, PrecisionAtK, and RecallAtK.
 
     Args:
-        top_k (int): the top k relevant labels to evaluate.
+        top_k (int): The top k relevant labels to evaluate.
     """
 
     # If the metric state of one batch is independent of the state of other batches,
@@ -133,7 +133,7 @@ class NDCGAtK(Metric):
     As a result, we implement our own batch-wise NDCG.
 
     Args:
-        top_k (int): the top k relevant labels to evaluate.
+        top_k (int): The top k relevant labels to evaluate.
     """
 
     # If the metric state of one batch is independent of the state of other batches,
@@ -170,7 +170,7 @@ class NDCGAtK(Metric):
         return (gains * discount).sum(dim=1)
 
     def _idcg(self, target, discount):
-        """Computes IDCG@k for a 0/1 target tensor.
+        """Compute IDCG@k for a 0/1 target tensor.
         A 0/1 target is a special case that doesn't require sorting.
         """
         cum_discount = discount.cumsum(dim=0)

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/nn/model.py

@@ -11,7 +11,7 @@ from ..nn.metrics import get_metrics, tabulate_metrics
 
 
 class MultiLabelModel(L.LightningModule):
-    """Abstract class handling Pytorch Lightning training flow
+    """Abstract class handling Pytorch Lightning training flow.
 
     Args:
         num_classes (int): Total number of classes.
@@ -70,7 +70,7 @@ class MultiLabelModel(L.LightningModule):
 
     @abstractmethod
     def shared_step(self, batch):
-        """Return loss and predicted logits"""
+        """Return loss and predicted logits."""
         return NotImplemented
 
     def configure_optimizers(self):
@@ -164,11 +164,11 @@ class MultiLabelModel(L.LightningModule):
         return {"top_k_pred": top_k_idx, "top_k_pred_scores": top_k_scores}
 
     def forward(self, batch):
-        """compute predicted logits"""
+        """Compute predicted logits."""
         return self.network(batch)["logits"]
 
     def print(self, *args, **kwargs):
-        """Prints only from process 0 and not in silent mode. Use this in any
+        """Print only from process 0 and not in silent mode. Use this in any
         distributed mode to log only once."""
 
         if not self.silent:

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/nn/networks/bert.py

@@ -3,7 +3,7 @@ from transformers import AutoModelForSequenceClassification
 
 
 class BERT(nn.Module):
-    """BERT
+    """BERT.
 
     Args:
         num_classes (int): Total number of classes.

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/nn/networks/bert_attention.py

@@ -6,7 +6,7 @@ from .modules import LabelwiseAttention, LabelwiseLinearOutput, LabelwiseMultiHe
 
 
 class BERTAttention(nn.Module):
-    """BERT + Label-wise Document Attention or Multi-Head Attention
+    """BERT + Label-wise Document Attention or Multi-Head Attention.
 
     Args:
         num_classes (int): Total number of classes.

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/nn/networks/caml.py

@@ -7,8 +7,8 @@ from torch.nn.init import xavier_uniform_
 
 class CAML(nn.Module):
     """CAML (Convolutional Attention for Multi-Label classification)
-    Follows the work of Mullenbach et al. [https://aclanthology.org/N18-1100.pdf]
-    This class is for reproducing the results in the paper.
+    Following Mullenbach et al. [https://aclanthology.org/N18-1100.pdf],
+    this class is for reproducing the results in the paper.
     Use CNNLWAN instead for better modularization.
 
     Args:

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/nn/networks/kim_cnn.py

@@ -5,7 +5,7 @@ from .modules import Embedding, CNNEncoder
 
 
 class KimCNN(nn.Module):
-    """KimCNN
+    """KimCNN.
 
     Args:
         embed_vecs (torch.Tensor): The pre-trained word vectors of shape (vocab_size, embed_dim).

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/nn/networks/labelwise_attention_networks.py

@@ -16,7 +16,7 @@ from .modules import (
 
 
 class LabelwiseAttentionNetwork(ABC, nn.Module):
-    """Base class for Labelwise Attention Network
+    """Base class for Labelwise Attention Network.
 
     Args:
         embed_vecs (torch.Tensor): The pre-trained word vectors of shape (vocab_size, embed_dim).
@@ -48,7 +48,7 @@ class LabelwiseAttentionNetwork(ABC, nn.Module):
 
 
 class RNNLWAN(LabelwiseAttentionNetwork):
-    """Base class for RNN Labelwise Attention Network"""
+    """Base class for RNN Labelwise Attention Network."""
 
     def forward(self, input):
         # (batch_size, sequence_length, embed_dim)
@@ -61,7 +61,7 @@ class RNNLWAN(LabelwiseAttentionNetwork):
 
 
 class BiGRULWAN(RNNLWAN):
-    """BiGRU Labelwise Attention Network
+    """BiGRU Labelwise Attention Network.
 
     Args:
         embed_vecs (torch.Tensor): The pre-trained word vectors of shape (vocab_size, embed_dim).
@@ -111,7 +111,7 @@ class BiGRULWAN(RNNLWAN):
 
 
 class BiLSTMLWAN(RNNLWAN):
-    """BiLSTM Labelwise Attention Network
+    """BiLSTM Labelwise Attention Network.
 
     Args:
         embed_vecs (torch.Tensor): The pre-trained word vectors of shape (vocab_size, embed_dim).
@@ -155,7 +155,7 @@ class BiLSTMLWAN(RNNLWAN):
 
 
 class BiLSTMLWMHAN(LabelwiseAttentionNetwork):
-    """BiLSTM Labelwise Multihead Attention Network
+    """BiLSTM Labelwise Multihead Attention Network.
 
     Args:
         embed_vecs (torch.Tensor): The pre-trained word vectors of shape (vocab_size, embed_dim).
@@ -217,7 +217,7 @@ class BiLSTMLWMHAN(LabelwiseAttentionNetwork):
 
 
 class CNNLWAN(LabelwiseAttentionNetwork):
-    """CNN Labelwise Attention Network
+    """CNN Labelwise Attention Network.
 
     Args:
         embed_vecs (torch.Tensor): The pre-trained word vectors of shape (vocab_size, embed_dim).

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/nn/networks/modules.py

@@ -7,7 +7,7 @@ from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence
 
 
 class Embedding(nn.Module):
-    """Embedding layer with dropout
+    """Embedding layer with dropout.
 
     Args:
         embed_vecs (torch.Tensor): The pre-trained word vectors of shape (vocab_size, embed_dim).
@@ -26,7 +26,7 @@ class Embedding(nn.Module):
 
 
 class RNNEncoder(ABC, nn.Module):
-    """Base class of RNN encoder with dropout
+    """Base class of RNN encoder with dropout.
 
     Args:
         input_size (int): The number of expected features in the input.
@@ -55,7 +55,7 @@ class RNNEncoder(ABC, nn.Module):
 
 
 class GRUEncoder(RNNEncoder):
-    """Bi-directional GRU encoder with dropout
+    """Bi-directional GRU encoder with dropout.
 
     Args:
         input_size (int): The number of expected features in the input.
@@ -73,7 +73,7 @@ class GRUEncoder(RNNEncoder):
 
 
 class LSTMEncoder(RNNEncoder):
-    """Bi-directional LSTM encoder with dropout
+    """Bi-directional LSTM encoder with dropout.
 
     Args:
         input_size (int): The number of expected features in the input.
@@ -91,7 +91,7 @@ class LSTMEncoder(RNNEncoder):
 
 
 class CNNEncoder(nn.Module):
-    """Multi-filter-size CNN encoder for text classification with max-pooling
+    """Multi-filter-size CNN encoder for text classification with max-pooling.
 
     Args:
         input_size (int): The number of expected features in the input.
@@ -103,7 +103,7 @@ class CNNEncoder(nn.Module):
                         If num_pool = 0, do nothing.
                         If num_pool = 1, do typical max-pooling.
                         If num_pool > 1, do adaptive max-pooling.
-        channel_last (bool): Whether to transpose the dimension from (batch_size, num_channel, length) to (batch_size, length, num_channel)
+        channel_last (bool): Whether to transpose the dimension from (batch_size, num_channel, length) to (batch_size, length, num_channel).
     """
 
     def __init__(
@@ -149,8 +149,8 @@ class CNNEncoder(nn.Module):
 
 
 class LabelwiseAttention(nn.Module):
-    """Applies attention technique to summarize the sequence for each label
-    See `Explainable Prediction of Medical Codes from Clinical Text <https://aclanthology.org/N18-1100.pdf>`_
+    """Apply attention technique to summarize the sequence for each label.
+    See `Explainable Prediction of Medical Codes from Clinical Text <https://aclanthology.org/N18-1100.pdf>`_.
 
     Args:
         input_size (int): The number of expected features in the input.
@@ -171,7 +171,7 @@ class LabelwiseAttention(nn.Module):
 
 
 class LabelwiseMultiHeadAttention(nn.Module):
-    """Labelwise multi-head attention
+    """Labelwise multi-head attention.
 
     Args:
         input_size (int): The number of expected features in the input.
@@ -197,7 +197,7 @@ class LabelwiseMultiHeadAttention(nn.Module):
 
 
 class LabelwiseLinearOutput(nn.Module):
-    """Applies a linear transformation to the incoming data for each label
+    """Apply a linear transformation to the incoming data for each label.
 
     Args:
         input_size (int): The number of expected features in the input.

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel/nn/networks/xml_cnn.py

@@ -6,7 +6,7 @@ from .modules import Embedding, CNNEncoder
 
 
 class XMLCNN(nn.Module):
-    """XML-CNN
+    """XML-CNN.
 
     Args:
         embed_vecs (torch.Tensor): The pre-trained word vectors of shape (vocab_size, embed_dim).

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: libmultilabel
-Version: 0.7.2
+Version: 0.7.3
 Summary: A library for multi-class and multi-label classification
 Home-page: https://github.com/ASUS-AICS/LibMultiLabel
 Author: LibMultiLabel Team
@@ -19,7 +19,7 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.8
 Requires-Python: >=3.8
 License-File: LICENSE
-Requires-Dist: liblinear-multicore
+Requires-Dist: liblinear-multicore>=2.49.0
 Requires-Dist: numba
 Requires-Dist: pandas>1.3.0
 Requires-Dist: PyYAML

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/libmultilabel.egg-info/requires.txt

@@ -1,4 +1,4 @@
-liblinear-multicore
+liblinear-multicore>=2.49.0
 numba
 pandas>1.3.0
 PyYAML

{libmultilabel-0.7.2 → libmultilabel-0.7.3}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = libmultilabel
-version = 0.7.2
+version = 0.7.3
 author = LibMultiLabel Team
 license = MIT License
 license_file = LICENSE
@@ -25,7 +25,7 @@ classifiers =
 [options]
 packages = find:
 install_requires = 
-	liblinear-multicore
+	liblinear-multicore>=2.49.0
 	numba
 	pandas>1.3.0
 	PyYAML