OntoLearner 1.4.9__py3-none-any.whl → 1.4.11__py3-none-any.whl

ontolearner/text2onto/splitter.py

@@ -200,10 +200,73 @@ class SyntheticDataSplitter:
 
         return terms_splits, types_splits, docs_split, types2docs_splits
 
-    def split(self, train: float = 0.8, val: float = 0.1, test: float = 0.1):
-        split_targets, split_docs_targets = self.set_train_val_test_sizes(train_percentage=train,
-                                                                          val_percentage=val,
-                                                                          test_percentage=test)
+    def split_fine_grained(self, doc_ids):
+        """
+        Build a single split bundle containing only:
+        - docs
+        - terms
+        - types
+        - terms2docs
+        - terms2types
+        """
+        # normalize to string ids (constructor uses str(row.id))
+        doc_ids = {str(d) for d in (doc_ids or [])}
+
+        # docs + collect terms/types from docs
+        docs = []
+        terms_set = set()
+        types_set = set()
+
+        for doc_id in doc_ids:
+            doc = self.doc_id_to_doc[doc_id]
+            docs.append({"id": str(doc.id), "title": doc.title, "text": doc.text})
+
+            terms_set.update(self.doc_id_to_terms[doc_id])
+            types_set.update(self.doc_id_to_types[doc_id])
+
+        terms = sorted(terms_set)
+        types = sorted(types_set)
+
+        # terms2docs: use the constructor-built mapping and restrict to this split's doc_ids
+        terms2docs = {
+            term: sorted(list(self.term_to_doc_id.get(term, set()) & doc_ids))
+            for term in terms
+        }
+
+        # terms2types: ontology lookup (term -> parent types)
+        terms2types = {term: self.child_to_parent.get(term, []) for term in terms}
+
+        return {
+            "documents": docs,
+            "terms": terms,
+            "types": types,
+            "terms2docs": terms2docs,
+            "terms2types": terms2types,
+        }
+
+    def train_test_val_split(self, train: float = 0.8, val: float = 0.1, test: float = 0.1):
+        """
+        Returns:
+            train_split, val_split, test_split
+
+        Each split is a dict with keys:
+        - "docs"
+        - "terms"
+        - "types"
+        - "terms2docs"
+        - "terms2types"
+        """
+        # compute which docs go to which split
+        split_targets, split_docs_targets = self.set_train_val_test_sizes(
+            train_percentage=train,
+            val_percentage=val,
+            test_percentage=test,
+        )
         split_docs = self.create_train_val_test_splits(split_targets, split_docs_targets)
-        terms, types, docs, types2docs = self.generate_split_artefacts(split_docs)
-        return terms, types, docs, types2docs
+        # split_docs: {"train": set(doc_ids), "val": set(doc_ids), "test": set(doc_ids)}
+
+        train_split = self.split_fine_grained(split_docs.get("train", set()))
+        val_split   = self.split_fine_grained(split_docs.get("val", set()))
+        test_split  = self.split_fine_grained(split_docs.get("test", set()))
+
+        return train_split, val_split, test_split

ontolearner/tools/analyzer.py

@@ -14,6 +14,7 @@
 
 import logging
 import time
+import numpy as np
 from abc import ABC
 from rdflib import RDF, RDFS, OWL
 from collections import defaultdict
@@ -186,6 +187,56 @@ class Analyzer(ABC):
 
         return metrics
 
+    @staticmethod
+    def compute_complexity_score(
+            topology_metrics: TopologyMetrics,
+            dataset_metrics: DatasetMetrics,
+            a: float = 0.4,
+            b: float = 6.0,
+            eps: float = 1e-12
+        ) -> float:
+        """
+        Compute a single normalized complexity score for an ontology.
+
+        This function combines structural topology metrics and dataset quality metrics
+        into a weighted aggregate score, then applies a logistic transformation to
+        normalize it to the range [0, 1]. The score reflects overall ontology complexity,
+        considering graph structure, hierarchy, breadth, coverage, and dataset richness.
+
+        Args:
+            topology_metrics (TopologyMetrics): Precomputed structural metrics of the ontology graph.
+            dataset_metrics (DatasetMetrics): Precomputed metrics of extracted learning datasets.
+            a (float, optional): Steepness parameter for the logistic normalization function. Default is 0.4.
+            b (float, optional): Centering parameter for the logistic function, should be tuned to match the scale of aggregated metrics. Default is 6.0.
+            eps (float, optional): Small epsilon to prevent numerical issues in logistic computation. Default is 1e-12.
+
+        Returns:
+            float: Normalized complexity score in [0, 1], where higher values indicate more complex ontologies.
+
+        Notes:
+            - Weights are assigned to different metric categories: graph metrics, coverage metrics, hierarchy metrics,
+              breadth metrics, and dataset metrics (term-types, taxonomic, non-taxonomic relations).
+            - Metrics are log-normalized before weighting to reduce scale differences.
+            - The logistic transformation ensures the final score is bounded and interpretable.
+        """
+        # Define metric categories with their weights
+        metric_categories = {
+            0.3: ["total_nodes", "total_edges", "num_root_nodes", "num_leaf_nodes"],
+            0.25: ["num_classes", "num_properties", "num_individuals"],
+            0.10: ["max_depth", "min_depth", "avg_depth", "depth_variance"],
+            0.20: ["max_breadth", "min_breadth", "avg_breadth", "breadth_variance"],
+            0.15: ["num_term_types", "num_taxonomic_relations", "num_non_taxonomic_relations", "avg_terms"]
+        }
+        weights = {metric: weight for weight, metrics in metric_categories.items() for metric in metrics}
+        metrics = [metric for _, metric_list in metric_categories.items() for metric in metric_list]
+        onto_metrics = {**topology_metrics.__dict__, **dataset_metrics.__dict__}
+        norm_weighted_values = [np.log1p(onto_metrics[m]) * weights[m] for m in metrics if m in onto_metrics]
+        total_weight = sum(weights[m] for m in metrics if m in onto_metrics)
+        weighted_sum = sum(norm_weighted_values) / total_weight if total_weight > 0 else 0.0
+        complexity_score = 1.0 / (1.0 + np.exp(-a * (weighted_sum - b) + eps))
+        return complexity_score
+
+
     @staticmethod
     def compute_dataset_metrics(ontology: BaseOntology) -> DatasetMetrics:
         """

{ontolearner-1.4.9.dist-info → ontolearner-1.4.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: OntoLearner
-Version: 1.4.9
+Version: 1.4.11
 Summary: OntoLearner: A Modular Python Library for Ontology Learning with LLMs.
 License: MIT
 License-File: LICENSE
@@ -14,7 +14,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: Levenshtein
-Requires-Dist: bitsandbytes (>=0.45.1,<0.46.0)
+Requires-Dist: bitsandbytes (>=0.45.1,<1.0.0) ; platform_system == "Linux"
 Requires-Dist: dspy (>=2.6.14,<3.0.0)
 Requires-Dist: g4f
 Requires-Dist: gensim

{ontolearner-1.4.9.dist-info → ontolearner-1.4.11.dist-info}/RECORD

@@ -1,27 +1,28 @@
-ontolearner/VERSION,sha256=x-xbkXEIv48hifmVFcVtJDdZj6d_bmXwy3Lp4d5pPVY,6
+ontolearner/VERSION,sha256=IUVii4YAC88nU9izX_pBt1ZZ3pyLpyv3xOe7B9Tzuzo,7
 ontolearner/__init__.py,sha256=E4yukFv2PV4uyztTPDWljCySY9AVDcDDzabuvxfabYE,1889
 ontolearner/_learner.py,sha256=2CRQvpsz8akIOdxTs2-KLJ-MssULrjpK-QDD3QXUJXI,5297
 ontolearner/_ontology.py,sha256=W1mp195SImqLKwaj4ueEaBWuLJg2jUdx1JT20Ds3fmQ,6950
 ontolearner/base/__init__.py,sha256=5pf-ltxzGp32xhEcPdbtm11wXJrYJMUeWG-mbcAYD8Q,705
-ontolearner/base/learner.py,sha256=latiGv8p3nyPrxMp7g5B2MSF-JEInRwIlbOn09uh7io,18899
-ontolearner/base/ontology.py,sha256=JbMJ1-WUyHWQiNJL-DeaqcriUimLdqN3_ESROgqOPTQ,24772
+ontolearner/base/learner.py,sha256=dWMiIBhdvxZLxIWrTq4d4LbyCqDuAmTwfmxwa7UkjfQ,20075
+ontolearner/base/ontology.py,sha256=t7n81Vk8Y5BCK88AYIyNKd7d1LjJnoTlXigyPvrLxR4,24784
 ontolearner/base/text2onto.py,sha256=iUXYZoqnwgebQuQzM-XSGTVRfHLlhjUK_z5XUvhRICc,5388
 ontolearner/data_structure/__init__.py,sha256=1HiKvk8FKjhYeI92RHnJXxyQbUJBi3JFytjQjthsY_s,599
 ontolearner/data_structure/data.py,sha256=jUUDfqsOZcEqIR83SRboiKibPdA_JquI1uOEiQQ_lqY,11273
 ontolearner/data_structure/metric.py,sha256=4QKkZ5L1YK6hDTU-N5Z9I9Ha99DVHmGfYxK7N2qdhfc,7589
 ontolearner/evaluation/__init__.py,sha256=4BZr3BUXjQDTj4Aqlqy4THa80lZPsMuh1EBTCyi9Wig,842
 ontolearner/evaluation/evaluate.py,sha256=NYCVcmPqpyIxYZrMAim37gL-erdh698RD3t3eNTTgZc,1163
-ontolearner/evaluation/metrics.py,sha256=3Aw6ycJ3_Q6xfj4tMBJP6QcexUei0G16H0ZQWt87aRU,6286
-ontolearner/learner/__init__.py,sha256=RKREPrrjzQ5KYvcOwC_2l7yFKwFBd6HoCwhX2H6Spg8,798
-ontolearner/learner/label_mapper.py,sha256=YMPeFKzJxoCYNU5z7QRYPbB88sWdu1iT6iBDpPsjn-4,3792
+ontolearner/evaluation/metrics.py,sha256=rgEHwkvtWIZ8BB8dNN5bjwptV70F4Y9RRLp9j2xeAuE,7914
+ontolearner/learner/__init__.py,sha256=8NOPB8IaU04Ae5aWnIm6B0rcijSYN6z3xJElzzKD34I,822
+ontolearner/learner/label_mapper.py,sha256=SiceknqOW2ORX7K4-ljLJYay8DQrKF6Dwv-wUg7uQ78,3793
 ontolearner/learner/llm.py,sha256=3kq_IrwEPTFgeNVKZH9Er_OydJuDpRBtM3YXNNa8_KA,10343
-ontolearner/learner/prompt.py,sha256=0ckH7xphIDKczPe7G-rwiOxFGZ7RsLnpPlNW92b-31U,1574
-ontolearner/learner/rag.py,sha256=eysB2RvcWkVo53s8-kSbZtJv904YVTmdtxplM4ukUKM,4283
-ontolearner/learner/retriever/__init__.py,sha256=G5XuJcTblqXVWboVW9StJ2Vo2xACp_kG5_w2nrueqlc,854
+ontolearner/learner/prompt.py,sha256=1z8KRLrvRBS8QFoJYGlaajwHi4P4CZezhNQv3WcIfNA,2464
+ontolearner/learner/rag/__init__.py,sha256=NpnBBw5wqZ1MNtpIJ7zT-LWm5IL9aDEzwlbKPo_kCis,612
+ontolearner/learner/rag/rag.py,sha256=apnjK4KvVzFmzF6CmxtZoYoE9NAscRVULTt8Nj5wcWk,4430
+ontolearner/learner/retriever/__init__.py,sha256=ECMEEtwacnugiJ-sADVGidS88pC57nVi299vKb5R16U,860
+ontolearner/learner/retriever/augmented_retriever.py,sha256=tI4z7IbbaShOY-BxOreEGe7fhemz7l48diB2Erri3ek,14004
 ontolearner/learner/retriever/crossencoder.py,sha256=yurzGE4zydlBSwUefi1CugsWv34HEZ61qADG_-nILbo,4996
 ontolearner/learner/retriever/embedding.py,sha256=Lp9oA7LiOYaSWDvzG779KMv5keNl6Xv7hw0WpeaepDE,7875
-ontolearner/learner/retriever/learner.py,sha256=VcarTwwR8HNddJCh0loCQejDzZ_GO4NkdQUjEhLVy48,11181
-ontolearner/learner/retriever/llm_retriever.py,sha256=goInWYxrD9PSo_EsSKbNV8wEaSPvWY3LEC8XM7jlH64,12917
+ontolearner/learner/retriever/learner.py,sha256=bMkXj_MnzBRQDjPloqnOYEj400fsO6CFBfUql7gHIxw,11184
 ontolearner/learner/retriever/ngram.py,sha256=XgS1OeheKEIi7wfJHZgS8mWxKv9MQrP0apOJD_XSOnM,4575
 ontolearner/learner/taxonomy_discovery/__init__.py,sha256=-Hb5Dl6_6c4l1uIT2zWtyBWMq5cjVD4PNjxt5qJePl4,747
 ontolearner/learner/taxonomy_discovery/alexbek.py,sha256=kFEDvoKxLf-sB7-d5REkcC0DqXZpcA6ZSJ2QHrNoC5E,19010
@@ -32,9 +33,9 @@ ontolearner/learner/term_typing/__init__.py,sha256=2rBbgp8683GNVgB58T4xe76l4m-NT
 ontolearner/learner/term_typing/alexbek.py,sha256=SzWQbndkhAjxETVbrJ4uyH7ykL_TMIwHozSS08zwjoM,46684
 ontolearner/learner/term_typing/rwthdbis.py,sha256=F6Jr1SrsbDOIe0Ee_FkDVGTG4wRWpM-R2YqrqEQiex0,14576
 ontolearner/learner/term_typing/sbunlp.py,sha256=Xd3UqMO3m_Skn_2geTN22MGQmSD6R8bYfPgubZre3IE,19820
-ontolearner/learner/text2onto/__init__.py,sha256=4-G6iel0Nxcj4nzPxUDqtFf9CMCzi8LghooOSAnbNfc,641
-ontolearner/learner/text2onto/alexbek.py,sha256=MySzxJUR0F3UyeS5rPIN988xxtPaoAxDFkBc-Q0vFTE,45494
-ontolearner/learner/text2onto/sbunlp.py,sha256=5p-s2Ixtntws5eO3gOUyYLpfZpCbOE0hG5gEcCwKHz4,24177
+ontolearner/learner/text2onto/__init__.py,sha256=bLv25lJmgQymgMfhr6JTezMndpDMk9ihheY-VLE-nRI,644
+ontolearner/learner/text2onto/alexbek.py,sha256=0CE5KHgB47tXASgscYH-W3X17XtI2QBtTuhDNpGGaUI,23347
+ontolearner/learner/text2onto/sbunlp.py,sha256=-ULysm_iFUMqEsxNRwgZVcq-70nBzlXMR5BeMezUjjw,23786
 ontolearner/ontology/__init__.py,sha256=F9Ta1qCX9mOxIK5CPRypEoglQNkpJ6SJpqziz73xKQE,1328
 ontolearner/ontology/agriculture.py,sha256=ZaXHNEFjbtsMH8M7HQ8ypnfJS4TUQy_as16fwv-kOKA,5903
 ontolearner/ontology/arts_humanities.py,sha256=K4ceDJL6PfIfSJZ86uQUkUXOVoiERG6ItgvVE2lhLKk,3996
@@ -62,15 +63,15 @@ ontolearner/processor.py,sha256=LaPUr4BSmPZDINo5t55q9U0i9lLXa77u4pN38usQMBc,4817
 ontolearner/text2onto/__init__.py,sha256=YbbDYpHYSMA4dof-7y40PKYsiRO7wvoXZ2LbsRwpPJE,645
 ontolearner/text2onto/batchifier.py,sha256=2CljvcZo0EDW3sHHcG9d5w26RcRwbMsQdFB1j-vCam4,6646
 ontolearner/text2onto/general.py,sha256=2RUFMbWm7qLq3MJHsyNb3rgYkGcicnkbiH2wdPBsBps,1099
-ontolearner/text2onto/splitter.py,sha256=7SrFeUM5GZTTvbrve9RRKtBjELlkpnMkyPluO614PYM,10941
+ontolearner/text2onto/splitter.py,sha256=PeiVbw5zuNlX3dhtcIJRVCghNizWE8ugIGV7OigR5Ac,12743
 ontolearner/text2onto/synthesizer.py,sha256=tSJgPTFWVKBQi2RqLQfMhX_noXeNLh2Wq2Ezbqyv-OA,5486
 ontolearner/tools/__init__.py,sha256=IB5ycAW5vUDKeq-NAMMbwjSFzwSzC-5j0UobIzO3ZmI,623
-ontolearner/tools/analyzer.py,sha256=8iL9wY1ESh4RumSW-s28EtXjtjPj71IKp0MBK0ograg,9925
+ontolearner/tools/analyzer.py,sha256=1SooAT7qYqDIrHyvHXnrBRmuPwZhLK1uj26OiKRECc0,12989
 ontolearner/tools/visualizer.py,sha256=cwijl4yYaS1SCLM5wbvRTEcbQj9Bjo4fHzZR6q6o8qo,6267
 ontolearner/utils/__init__.py,sha256=pSEyU3dlPMADBqygqaaid44RdWf0Lo3Fvz-K_rQ7_Bw,733
 ontolearner/utils/io.py,sha256=3DqGK2p7c0onKi0Xxs16WB08uHfHUId3bW0dDKwyS0g,2110
 ontolearner/utils/train_test_split.py,sha256=Zlm42eT6QGWwlySyomCPIiTGmGqeN_h4z4xBY2EAOR8,11530
-ontolearner-1.4.9.dist-info/METADATA,sha256=c_V_1mUkxAhzJz04u1wRYU7xodpZQdiJXBVFzUCIMK8,11444
-ontolearner-1.4.9.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-ontolearner-1.4.9.dist-info/licenses/LICENSE,sha256=krXMLuMKgzX-UgaufgfJdm9ojIloZot7ZdvJUnNxl4I,1067
-ontolearner-1.4.9.dist-info/RECORD,,
+ontolearner-1.4.11.dist-info/METADATA,sha256=YDJySz7VAXa80XACaj-WDyuHtFhticcNqEmQVaR8Jsg,11473
+ontolearner-1.4.11.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+ontolearner-1.4.11.dist-info/licenses/LICENSE,sha256=krXMLuMKgzX-UgaufgfJdm9ojIloZot7ZdvJUnNxl4I,1067
+ontolearner-1.4.11.dist-info/RECORD,,