pelican-nlp 0.2.1__py3-none-any.whl → 0.2.3__py3-none-any.whl

pelican_nlp/_version.py

@@ -1 +1 @@
-__version__ = "0.2.1"
+__version__ = "0.2.3"

pelican_nlp/core/corpus.py

@@ -16,11 +16,12 @@ import pandas as pd
 import re
 
 class Corpus:
-    def __init__(self, corpus_name, documents, configuration_settings):
+    def __init__(self, corpus_name, documents, configuration_settings, project_folder):
         self.name = corpus_name
         self.documents = documents
         self.config = configuration_settings
-        self.derivative_dir = self.config['PATH_TO_PROJECT_FOLDER']+'/derivatives'
+        self.project_folder = project_folder
+        self.derivative_dir = project_folder + '/derivatives'
         self.pipeline = TextPreprocessingPipeline(self.config)
         self.task = configuration_settings['task_name']
         self.results_path = None
@@ -112,14 +113,13 @@ class Corpus:
         from pelican_nlp.extraction.extract_logits import LogitsExtractor
         from pelican_nlp.preprocessing.text_tokenizer import TextTokenizer
         logits_options = self.config['options_logits']
-        project_path = self.config['PATH_TO_PROJECT_FOLDER']
 
         print('logits extraction in progress')
         model_name = logits_options['model_name']
         logitsExtractor = LogitsExtractor(logits_options,
                                           self.pipeline,
-                                          project_path)
-        model = Model(model_name, project_path)
+                                          self.project_folder)
+        model = Model(model_name, self.project_folder)
         model.load_model()
         model_instance = model.model_instance
         tokenizer = TextTokenizer(logits_options['tokenization_method'], model_name=logits_options['model_name'])
@@ -153,7 +153,7 @@ class Corpus:
 
         embedding_options = self.config['options_embeddings']
         print('Embeddings extraction in progress...')
-        embeddingsExtractor = EmbeddingsExtractor(embedding_options, self.config['PATH_TO_PROJECT_FOLDER'])
+        embeddingsExtractor = EmbeddingsExtractor(embedding_options, self.project_folder)
         for i in range(len(self.documents)):
             for key, section in self.documents[i].cleaned_sections.items():
                 print(f'Processing section {key}')

pelican_nlp/main.py

@@ -78,7 +78,7 @@ class Pelican:
         self._LPDS()
         
         # Instantiate all subjects
-        subjects = subject_instantiator(self.config)
+        subjects = subject_instantiator(self.config, self.project_path)
         
         # Process each corpus
         for corpus_name in self.config['corpus_names']:

pelican_nlp/utils/setup_functions.py

@@ -4,8 +4,7 @@ import shutil
 import yaml
 import sys
 
-def subject_instantiator(config):
-    project_folder = config['PATH_TO_PROJECT_FOLDER']
+def subject_instantiator(config, project_folder):
     path_to_subjects = os.path.join(project_folder, 'subjects')
     print('Instantiating Subjects...')
     subjects = [Subject(subject) for subject in os.listdir(path_to_subjects)]

{pelican_nlp-0.2.1.dist-info → pelican_nlp-0.2.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pelican_nlp
-Version: 0.2.1
+Version: 0.2.3
 Summary: Preprocessing and Extraction of Linguistic Information for Computational Analysis
 Author-email: Yves Pauli <yves.pauli@gmail.com>
 License-Expression: CC-BY-NC-4.0

{pelican_nlp-0.2.1.dist-info → pelican_nlp-0.2.3.dist-info}/RECORD

@@ -1,7 +1,7 @@
 pelican_nlp/__init__.py,sha256=TD5xjKeXXAH6nUWG-6igbClgovi5r8RIEqI_ix1QeYo,204
-pelican_nlp/_version.py,sha256=tC9CwL4Nm8brVXJnZNGk_eoZaJj6eOtLKtOrdJMrpoI,21
+pelican_nlp/_version.py,sha256=X0PliCRFAeVnSTceUeHX1eM0j1HFhGFDWCRxLdde2Bs,21
 pelican_nlp/cli.py,sha256=uXouL67mTjBynFMWpBTaGvGtEBWDnbS1BI7aRdxV-0M,439
-pelican_nlp/main.py,sha256=WKiDHXVFKtkD6AkTZSGlT824hKbpp5PAu2-HlcKsi-Q,7501
+pelican_nlp/main.py,sha256=4Lmy87B3x0bDZbKa38Y9ig3DFYYvWhtK4WJpZwBsQB0,7520
 pelican_nlp/Nils_backup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pelican_nlp/Nils_backup/extract_acoustic_features.py,sha256=eSP8lXxbZ15YE1HqxGtma9uWOcSN-fI-ig-NwQ9eOA8,10771
 pelican_nlp/Nils_backup/speaker_diarization_Nils.py,sha256=3RIhjKihu4Z1rruMt9KESFE2lqesfzIpRr7rLummUEo,10219
@@ -38,7 +38,7 @@ pelican_nlp/configuration_files/config_general.yml,sha256=dOBiqOhw0VgV0LZ1boYJhh
 pelican_nlp/configuration_files/config_morteza.yml,sha256=T378fxvBY9hERVGsnXroDFCy8Zh5PIq4dyer2b5AiDY,3376
 pelican_nlp/core/__init__.py,sha256=whJc5dWsGsKn2IAw-D4BvCvUKW1sVtWYE1WJIuUr5uI,165
 pelican_nlp/core/audio_document.py,sha256=hhSJNgeqSYa6_uws2ho66agHhAdHuKN3EIEdIsIcXKg,586
-pelican_nlp/core/corpus.py,sha256=6pDRmeO0XoHylhjLE4Fi5Tc3HCMQJ-Xk0YRzEfz5Z1Y,15168
+pelican_nlp/core/corpus.py,sha256=j_p4hWwLnHuGu4jQakG9oVeizDD9mvWVWVJKTu_lMB4,15143
 pelican_nlp/core/document.py,sha256=j2HP5FX6cfmXHo7OWVFCX6cMsDyqsOmNlnGNNNfCm2c,8467
 pelican_nlp/core/subject.py,sha256=-pi3jDzb2zLiG8JNAi9i-9Jd-VtsPxDO4ShQci2QSMg,1059
 pelican_nlp/extraction/__init__.py,sha256=hfqFiaKpQBS6cwRm9Yd7MpOcV60_xJmwuQ2Kegary5k,84
@@ -68,10 +68,10 @@ pelican_nlp/sample_configuration_files/config_general.yml,sha256=UuGnZUa-SVmioE9
 pelican_nlp/utils/__init__.py,sha256=q1tGdOOj5UPRC2mGhoMUh8p4cbFCkkbD21bQaOVvFao,189
 pelican_nlp/utils/csv_functions.py,sha256=hsG73gm3Up9sAerp6gIxuNHaeP1vJj6HSh7ggVm1SSo,7272
 pelican_nlp/utils/sample_usage.py,sha256=W__OVMjWND-ZtxxRhfGJDHwbVpGlB-anXDxyA5P4cME,353
-pelican_nlp/utils/setup_functions.py,sha256=s0QcarswU8qeFBcEQNIYC1ooaD-xwRiTJn--yPEId8E,3612
-pelican_nlp-0.2.1.dist-info/licenses/LICENSE,sha256=m3jshBZIXKiBX6qhmhtJcLTVJ1N6BEkQGIflneXvpYg,19336
-pelican_nlp-0.2.1.dist-info/METADATA,sha256=VvSKygkPyQ_RzTM9-HvKRdP-m0TtQThAC8pLoJJPikE,5562
-pelican_nlp-0.2.1.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-pelican_nlp-0.2.1.dist-info/entry_points.txt,sha256=znlG0paAfju9P10UM3rm5HcCHoj4tarTllNpeaqH_gc,53
-pelican_nlp-0.2.1.dist-info/top_level.txt,sha256=F0qlyqy5FCd3sTS_npUYPeLKN9_BZq6wD4qo9pI0xbg,12
-pelican_nlp-0.2.1.dist-info/RECORD,,
+pelican_nlp/utils/setup_functions.py,sha256=t4WG5qd5iYpNNBGklje_8ukwmJp_C9RMLLi7veDgNeA,3574
+pelican_nlp-0.2.3.dist-info/licenses/LICENSE,sha256=m3jshBZIXKiBX6qhmhtJcLTVJ1N6BEkQGIflneXvpYg,19336
+pelican_nlp-0.2.3.dist-info/METADATA,sha256=3GFutxyfVQ-AfzbVYiew-AFmj_6NyoLIuF6y0bqRLqw,5562
+pelican_nlp-0.2.3.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+pelican_nlp-0.2.3.dist-info/entry_points.txt,sha256=znlG0paAfju9P10UM3rm5HcCHoj4tarTllNpeaqH_gc,53
+pelican_nlp-0.2.3.dist-info/top_level.txt,sha256=F0qlyqy5FCd3sTS_npUYPeLKN9_BZq6wD4qo9pI0xbg,12
+pelican_nlp-0.2.3.dist-info/RECORD,,