tmnt 0.7.44b20240127__py3-none-any.whl → 0.7.46__py3-none-any.whl

tmnt/data_loading.py

@@ -39,7 +39,8 @@ llm_catalog = {
     'openai-gpt' : (AutoTokenizer.from_pretrained, OpenAIGPTModel.from_pretrained), 
     'sentence-transformers/all-mpnet-base-v2' : (AutoTokenizer.from_pretrained, AutoModel.from_pretrained),
     'allenai/scibert_scivocab_uncased': (AutoTokenizer.from_pretrained, AutoModel.from_pretrained),
-    'johngiorgi/declutr-sci-base': (AutoTokenizer.from_pretrained, AutoModel.from_pretrained) 
+    'johngiorgi/declutr-sci-base': (AutoTokenizer.from_pretrained, AutoModel.from_pretrained),
+    'BAAI/bge-base-en-v1.5': (AutoTokenizer.from_pretrained, AutoModel.from_pretrained) 
     ## add more model options here if desired
     }
 

tmnt/estimator.py

@@ -1115,7 +1115,7 @@ class SeqBowEstimator(BaseEstimator):
                  classifier_dropout = 0.0,
                  pure_classifier_objective = False,
                  validate_each_epoch = False,
-                 entropy_loss_coef = 1000.0,
+                 entropy_loss_coef = 0.0,
                  pool_encoder = True,
                  **kwargs):
         super(SeqBowEstimator, self).__init__(*args, **kwargs)
@@ -1527,13 +1527,6 @@ class SeqBowEstimator(BaseEstimator):
         else:
             self._output_status("Epoch [{}]. Objective = {} ==> PPL = {}. NPMI ={}. Redundancy = {}."
                                 .format(epoch_id, sc_obj, v_res['ppl'], v_res['npmi'], v_res['redundancy']))
-        #if self.reporter:
-        #if 'accuracy' in v_res:
-            #session.report({"objective": sc_obj, "coherence": v_res['npmi'], "perplexity": v_res['ppl'],
-            #                "redundancy": v_res['redundancy'], "accuracy": v_res['accuracy']})
-        #else:
-            #session.report({"objective": sc_obj, "coherence": v_res['npmi'], "perplexity": v_res['ppl'],
-            #            "redundancy": v_res['redundancy']})
         return sc_obj, v_res
                 
     
@@ -1610,13 +1603,8 @@ class SeqBowMetricEstimator(SeqBowEstimator):
             bow_batch_b = seqs_b[3].to_dense()
             sums += bow_batch_a.sum(axis=0)
             sums += bow_batch_b.sum(axis=0)
-        return sums.cpu().numpy()                               #def _get_model_bias_initialize(self, train_data):
-    #    model = self._get_model()
-    #    tr_bow_matrix = self._get_bow_matrix(train_data)
-        #model.initialize_bias_terms(tr_bow_matrix.sum(axis=0))
-    #    return model
+        return sums.cpu().numpy()        
         
-
     def _get_bow_matrix(self, dataloader, cache=False):
         bow_matrix = []
         for _, seqs in enumerate(dataloader):
@@ -1670,10 +1658,5 @@ class SeqBowMetricEstimator(SeqBowEstimator):
         v_res = self.validate(model, dev_data, epoch_id)
         self._output_status("Epoch [{}]. ==> elbo loss = {}; kldiv loss = {}"
                             .format(epoch_id, v_res['elbo_ls'], v_res['kl_ls']))
-        #session.report({"objective": sc_obj, "coherence": v_res['npmi'], "perplexity": v_res['ppl'],
-        #                "redundancy": v_res['redundancy']})
-        #if self.reporter:
-        #    self.reporter(epoch=epoch_id+1, objective=v_res['avg_prec'], time_step=time.time(), coherence=0.0,
-        #                  perplexity=0.0, redundancy=0.0)
         return v_res['kl_ls'], v_res
 

tmnt/modeling.py

@@ -595,11 +595,11 @@ class MetricSeqBowVED(BaseSeqBowVED):
         elbo = elbo1 + elbo2
         rec_loss = rec_loss1 + rec_loss2
         KL_loss = KL_loss1 + KL_loss2
-        z_mu1 = self.latent_distribution.get_mu_encoding(enc2)
-        z_mu2 = self.latent_distribution.get_mu_encoding(enc2)
+        #z_mu1 = self.latent_distribution.get_mu_encoding(enc2)
+        #z_mu2 = self.latent_distribution.get_mu_encoding(enc2)
         redundancy_loss = entropy_loss1 + entropy_loss2 #self.get_redundancy_penalty()
-        return elbo, rec_loss, KL_loss, redundancy_loss, z_mu1, z_mu2
-        #return elbo, rec_loss, KL_loss, redundancy_loss, enc1, enc2
+        #return elbo, rec_loss, KL_loss, redundancy_loss, z_mu1, z_mu2
+        return elbo, rec_loss, KL_loss, redundancy_loss, enc1, enc2
 
 
 class GeneralizedSDMLLoss(_Loss):

{tmnt-0.7.44b20240127.dist-info → tmnt-0.7.46.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tmnt
-Version: 0.7.44b20240127
+Version: 0.7.46
 Summary: Topic modeling neural toolkit
 Home-page: https://github.com/mitre/tmnt.git
 Author: The MITRE Corporation
@@ -9,7 +9,7 @@ License: Apache
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.8
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 License-File: NOTICE
@@ -27,7 +27,9 @@ Requires-Dist: pyOpenSSL ==18.0.0
 Requires-Dist: PySocks ==1.6.8
 Requires-Dist: sacremoses >=0.0.38
 Requires-Dist: sentence-splitter ==1.4
-Requires-Dist: umap-learn ==0.4.6
+Requires-Dist: umap-learn[plot] >=0.5.5
+Requires-Dist: numba
+Requires-Dist: scipy
 Requires-Dist: tabulate >=0.8.7
 Requires-Dist: torch >=2.1.2
 Requires-Dist: torchtext >=0.13.0
@@ -35,7 +37,7 @@ Requires-Dist: torchtext >=0.13.0
 The Topic Modeling Neural Toolkit (TMNT) is a software library that enables training
 topic models as neural network-based variational auto-encoders.
 
-Current stable version is: 0.7.44
+Current stable version is: 0.7.46
 
 Documentation can be found here: https://tmnt.readthedocs.io/en/stable/
 

{tmnt-0.7.44b20240127.dist-info → tmnt-0.7.46.dist-info}/RECORD

@@ -1,11 +1,11 @@
 tmnt/__init__.py,sha256=EPNq1H7UMyMewWT_zTGBaC7ZouvCywX_gMX4G1dtmvw,250
 tmnt/configuration.py,sha256=P8PEhzVPKO5xG0FrdTLRQ60OYWigbzPY-OSx_hzQlrY,10054
-tmnt/data_loading.py,sha256=B47kfq5nrpw2bHYT2qEv2tpCLT7EFwqD7ZDjsoBto_Q,18303
+tmnt/data_loading.py,sha256=IB7qgoeIY6a4i-YDB7kwWUU3LMvlCGF6_PgzlWDjkc8,18392
 tmnt/distribution.py,sha256=Pmyc5gwDd_-jP7vLVb0vdNQaSSvF1EuiTZEWg3KfmI8,10866
-tmnt/estimator.py,sha256=kQZ42MfOBBZuF0TQVdd9vBlw101ZlXk77mlws2ZvAS4,78014
+tmnt/estimator.py,sha256=cRdA3s3_PmbSU36xYc8cfano_rkqEl9j_0FM3eZ8IA8,76953
 tmnt/eval_npmi.py,sha256=ODRDMsBgDM__iCNEX399ck7bAhl7ydvgDqmpfR7Y-q4,5048
 tmnt/inference.py,sha256=Sw7GO7QiWVEtbPJKBjFB7AiKRmUOZbFZn3tCrsStzWw,17845
-tmnt/modeling.py,sha256=-fvmbT-KXr8luhELnCAOyZ-DUbTUd65cKRNRaH49EKI,33016
+tmnt/modeling.py,sha256=372eAVcnI5xcBYRwSO8N0XK_ECWHwRw7KfuIB8uz3RA,33018
 tmnt/preprocess/__init__.py,sha256=gwMejkQrnqKS05i0JVsUru2hDUR5jE1hKC10dL934GU,170
 tmnt/preprocess/tokenizer.py,sha256=-ZgowfbHrM040vbNTktZM_hdl6HDTqxSJ4mDAxq3dUs,14050
 tmnt/preprocess/vectorizer.py,sha256=RkdivqP76qAJDianV09lONad9NbfBVWLZgIbU_P1-zo,15796
@@ -17,9 +17,9 @@ tmnt/utils/ngram_helpers.py,sha256=VrIzou2oQHCLBLSWODDeikN3PYat1NqqvEeYQj_GhbA,1
 tmnt/utils/pubmed_utils.py,sha256=3sHwoun7vxb0GV-arhpXLMUbAZne0huAh9xQNy6H40E,1274
 tmnt/utils/random.py,sha256=qY75WG3peWoMh9pUyCPBEo6q8IvkF6VRjeb5CqJOBF8,327
 tmnt/utils/recalibrate.py,sha256=TmpB8An8bslICZ13UTJfIvr8VoqiSedtpHxec4n8CHk,1439
-tmnt-0.7.44b20240127.dist-info/LICENSE,sha256=qFZJrfJ7Zi4IXDiyiGVrHWic_l1h2tc36tI8Z7rK9bs,11356
-tmnt-0.7.44b20240127.dist-info/METADATA,sha256=RNb_SRd6cyvKGKSJT1NKTDdjjVVUfhDXqRuFIxmy2dE,1403
-tmnt-0.7.44b20240127.dist-info/NOTICE,sha256=p0kYIVAkReTFaGb4C-qPa7h5ztze6hGzOpjCMMbOipU,425
-tmnt-0.7.44b20240127.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-tmnt-0.7.44b20240127.dist-info/top_level.txt,sha256=RpYgUl187sXnqmiwKjZZdcDlHz2AALs6bGdUcukyd_E,5
-tmnt-0.7.44b20240127.dist-info/RECORD,,
+tmnt-0.7.46.dist-info/LICENSE,sha256=qFZJrfJ7Zi4IXDiyiGVrHWic_l1h2tc36tI8Z7rK9bs,11356
+tmnt-0.7.46.dist-info/METADATA,sha256=KLktIuJoTOtPvY1uML9pgNJwRE-Rxact3yLk092gw7I,1443
+tmnt-0.7.46.dist-info/NOTICE,sha256=p0kYIVAkReTFaGb4C-qPa7h5ztze6hGzOpjCMMbOipU,425
+tmnt-0.7.46.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+tmnt-0.7.46.dist-info/top_level.txt,sha256=RpYgUl187sXnqmiwKjZZdcDlHz2AALs6bGdUcukyd_E,5
+tmnt-0.7.46.dist-info/RECORD,,