OntoLearner 1.4.7__py3-none-any.whl → 1.4.9__py3-none-any.whl

{ontolearner-1.4.7.dist-info → ontolearner-1.4.9.dist-info}/RECORD

@@ -1,9 +1,9 @@
-ontolearner/VERSION,sha256=eU2b_S0GS-IEHLoICSOz45ujvshMNXlHgEgoUrX0AH4,6
+ontolearner/VERSION,sha256=x-xbkXEIv48hifmVFcVtJDdZj6d_bmXwy3Lp4d5pPVY,6
 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=G2NP8XMMbCPllW35bLXxH9-hQRcVoRto5aNWT5PZsYY,18684
+ontolearner/base/learner.py,sha256=latiGv8p3nyPrxMp7g5B2MSF-JEInRwIlbOn09uh7io,18899
 ontolearner/base/ontology.py,sha256=JbMJ1-WUyHWQiNJL-DeaqcriUimLdqN3_ESROgqOPTQ,24772
 ontolearner/base/text2onto.py,sha256=iUXYZoqnwgebQuQzM-XSGTVRfHLlhjUK_z5XUvhRICc,5388
 ontolearner/data_structure/__init__.py,sha256=1HiKvk8FKjhYeI92RHnJXxyQbUJBi3JFytjQjthsY_s,599
@@ -12,12 +12,29 @@ ontolearner/data_structure/metric.py,sha256=4QKkZ5L1YK6hDTU-N5Z9I9Ha99DVHmGfYxK7
 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=L54a3uvOeS6hbID6-BFd6fo9rH4WK2Q1XecpXMkEru0,768
-ontolearner/learner/label_mapper.py,sha256=-XW8MHafm4ix3e9u-RRwDePJ71D804DNuKzdf1zudtk,3789
+ontolearner/learner/__init__.py,sha256=RKREPrrjzQ5KYvcOwC_2l7yFKwFBd6HoCwhX2H6Spg8,798
+ontolearner/learner/label_mapper.py,sha256=YMPeFKzJxoCYNU5z7QRYPbB88sWdu1iT6iBDpPsjn-4,3792
 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.py,sha256=GDXr6l0m_prxnctxQzBpm75xL4jW2Q4b91iyePFcDAs,4988
+ontolearner/learner/retriever/__init__.py,sha256=G5XuJcTblqXVWboVW9StJ2Vo2xACp_kG5_w2nrueqlc,854
+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/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
+ontolearner/learner/taxonomy_discovery/rwthdbis.py,sha256=698Gze2cR-QIhpTbuaOFm7Q4p0lCbdWz3rO6rewJZ1s,41644
+ontolearner/learner/taxonomy_discovery/sbunlp.py,sha256=hyTxPMCdS2BIb9R61OQgT9ibZYmPd-vaj7KBCRCAggk,14987
+ontolearner/learner/taxonomy_discovery/skhnlp.py,sha256=nEsA1MJueEs25IC5B-4OAOn5R6mOfz_7C4xIUC6hNN4,45516
+ontolearner/learner/term_typing/__init__.py,sha256=2rBbgp8683GNVgB58T4xe76l4m-NTqL7MwpAnux0IDY,691
+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/ontology/__init__.py,sha256=F9Ta1qCX9mOxIK5CPRypEoglQNkpJ6SJpqziz73xKQE,1328
 ontolearner/ontology/agriculture.py,sha256=ZaXHNEFjbtsMH8M7HQ8ypnfJS4TUQy_as16fwv-kOKA,5903
 ontolearner/ontology/arts_humanities.py,sha256=K4ceDJL6PfIfSJZ86uQUkUXOVoiERG6ItgvVE2lhLKk,3996
@@ -53,7 +70,7 @@ ontolearner/tools/visualizer.py,sha256=cwijl4yYaS1SCLM5wbvRTEcbQj9Bjo4fHzZR6q6o8
 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-1.4.7.dist-info/METADATA,sha256=2oMe5F7YGUl3TiOrhgCTAJyVFQ2LRbUu1WPPEcXvHX4,14083
-ontolearner-1.4.7.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-ontolearner-1.4.7.dist-info/licenses/LICENSE,sha256=krXMLuMKgzX-UgaufgfJdm9ojIloZot7ZdvJUnNxl4I,1067
-ontolearner-1.4.7.dist-info/RECORD,,
+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/learner/retriever.py

@@ -1,101 +0,0 @@
-# Copyright (c) 2025 SciKnowOrg
-#
-# Licensed under the MIT License (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#      https://opensource.org/licenses/MIT
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-from ..base import AutoRetriever, AutoLearner
-from typing import Any, Optional
-import warnings
-
-class AutoRetrieverLearner(AutoLearner):
-    def __init__(self, base_retriever: Any = AutoRetriever(), top_k: int = 5, batch_size: int = -1):
-        super().__init__()
-        self.retriever = base_retriever
-        self.top_k = top_k
-        self._is_term_typing_fit = False
-        self._batch_size = batch_size
-
-    def load(self, model_id: str = "sentence-transformers/all-MiniLM-L6-v2"):
-        self.retriever.load(model_id=model_id)
-
-    def _retriever_fit(self, data: Any):
-        if isinstance(data, list) and all(isinstance(item, str) for item in data):
-            self.retriever.index(inputs=data)
-        else:
-            raise TypeError("Expected a list of strings for retriever at term-typing task.")
-
-    def _retriever_predict(self, data:Any, top_k: int) -> Any:
-        if isinstance(data, list):
-            return self.retriever.retrieve(query=data, top_k=top_k, batch_size=self._batch_size)
-        if isinstance(data, str):
-            return self.retriever.retrieve(query=[data], top_k=top_k)
-        raise TypeError(f"Unsupported data type {type(data)}. You should pass a List[str] or a str.")
-
-    def _term_typing(self, data: Any, test: bool = False) -> Optional[Any]:
-        """
-        during training: data = ["type-1", .... ],
-        during testing: data = ['term-1', ...]
-        """
-        if test:
-            if self._is_term_typing_fit:
-                types = self._retriever_predict(data=data, top_k=self.top_k)
-                return [{"term": term, "types": type} for term, type in zip(data, types)]
-            else:
-                raise RuntimeError("Term typing model must be fit before prediction.")
-        else:
-            self._retriever_fit(data=data)
-            self._is_term_typing_fit = True
-
-    def _taxonomy_discovery(self, data: Any, test: bool = False) -> Optional[Any]:
-        """
-        during training: data = ['type-1', ...],
-        during testing (same data): data= ['type-1', ...]
-        """
-        if test:
-            self._retriever_fit(data=data)
-            candidates_lst =  self._retriever_predict(data=data, top_k=self.top_k + 1)
-            taxonomic_pairs = [{"parent": candidate, "child": query}
-                               for query, candidates in zip(data, candidates_lst)
-                               for candidate in candidates if candidate.lower() != query.lower()]
-            return taxonomic_pairs
-        else:
-            warnings.warn("No requirement for fiting the taxonomy discovery model, the predict module will use the input data to do the fit as well.")
-
-    def _non_taxonomic_re(self, data: Any, test: bool = False) -> Optional[Any]:
-        """
-        during training: data = ['type-1', ...],
-        during testing: {'types': [...], 'relations': [... ]}
-        """
-        if test:
-            # print(data)
-            if 'types' not in data or 'relations' not in data:
-                raise ValueError("The non-taxonomic re predict should take {'types': [...], 'relations': [... ]}")
-            if len(data['types']) == 0:
-                warnings.warn("No `types` avaliable to do the non-taxonomic re-prediction.")
-                return None
-            self._retriever_fit(data=data['types'])
-            candidates_lst = self._retriever_predict(data=data['types'], top_k=self.top_k + 1)
-            taxonomic_pairs = []
-            taxonomic_pairs_query = []
-            for query, candidates in zip(data['types'], candidates_lst):
-                for candidate in candidates:
-                    if candidate != query:
-                        taxonomic_pairs.append((query, candidate))
-                        taxonomic_pairs_query.append(f"Head: {query} \n Tail: {candidate}")
-            self._retriever_fit(data=data['relations'])
-            candidate_relations_lst = self._retriever_predict(data=taxonomic_pairs_query, top_k=self.top_k)
-            non_taxonomic_re = [{"head": head, "tail": tail, "relation": relation}
-                                for (head, tail), candidate_relations in zip(taxonomic_pairs, candidate_relations_lst)
-                                for relation in candidate_relations]
-            return non_taxonomic_re
-        else:
-            warnings.warn("No requirement for fiting the non-taxonomic RE model, the predict module will use the input data to do the fit as well..")