pelican-nlp 0.2.4__py3-none-any.whl → 0.2.6__py3-none-any.whl

pelican_nlp/_version.py

@@ -1 +1 @@
-__version__ = "0.2.4"
+__version__ = "0.2.6"

pelican_nlp/cli.py

@@ -7,6 +7,10 @@ def main():
         print("No .yml configuration file found in the current directory.")
         return
 
+    if len(config_files) > 1:
+        print("More than one configuration file found - remove unneeded files from project directory")
+        return
+
     config_file = config_files[0]  # You could also add logic to choose or validate
     print(f"Using configuration file: {config_file}")
 

pelican_nlp/configuration_files/config_audio.yml

@@ -4,7 +4,6 @@
 # Basic Settings
 # -------------
 input_file: "audio"  # Options: 'text' or 'audio'
-PATH_TO_PROJECT_FOLDER: "/home/yvespauli/PycharmProjects/Silvia"
 language: "dutch"  # Options: 'german', 'english'
 recompute_everything: true  # If false, reuses previously computed results
 output_document_information: true

pelican_nlp/configuration_files/config_discourse.yml

@@ -5,7 +5,6 @@ discourse: &discourse_flag true
 #=====================================
 
 #general configurations; always adapt
-PATH_TO_PROJECT_FOLDER: "/home/yvespauli/PycharmProjects/Morteza/"
 language: "german" # Possibly add options for German and English
 
 task_name: "interview" # Give name of task used for creation of the input file (e.g., ['fluency', 'interview'])

pelican_nlp/configuration_files/config_fluency.yml

@@ -5,7 +5,6 @@ fluency_task: &fluency_flag true
 #========================================
 
 #general configurations; always adapt
-PATH_TO_PROJECT_FOLDER: "/home/yvespauli/PycharmProjects/FluencyTest"
 language: "german"
 multiple_sessions: &session_flag false
 

pelican_nlp/configuration_files/config_general.yml

@@ -4,7 +4,6 @@
 # Basic Settings
 # -------------
 input_file: "text"  # Options: 'text' or 'audio'
-PATH_TO_PROJECT_FOLDER: "/home/yvespauli/PycharmProjects/FluencyTest"
 language: "german"  # Options: 'german', 'english'
 recompute_everything: true  # If false, reuses previously computed results
 

pelican_nlp/configuration_files/config_morteza.yml

@@ -3,8 +3,6 @@
 input_file: "text" #or 'audio'
 discourse: &discourse_flag true
 
-#PATH_TO_PROJECT_FOLDER: "/home/yvespauli/PycharmProjects/KetamineStudy/KetamineStudy_ProjectFolder/" # Set default to home directory, e.g., '/home/usr/...'
-PATH_TO_PROJECT_FOLDER: "/home/yvespauli/PycharmProjects/Morteza/"
 language: "german" # Possibly add options for German and English
 
 task_name: "interview" # Give name of task used for creation of the input file (e.g., ['fluency', 'interview'])

pelican_nlp/core/corpus.py

@@ -21,7 +21,7 @@ class Corpus:
         self.documents = documents
         self.config = configuration_settings
         self.project_folder = project_folder
-        self.derivative_dir = project_folder + '/derivatives'
+        self.derivative_dir = project_folder / 'derivatives'
         self.pipeline = TextPreprocessingPipeline(self.config)
         self.task = configuration_settings['task_name']
         self.results_path = None

pelican_nlp/main.py

@@ -24,6 +24,8 @@ from pelican_nlp.core import Corpus
 from pelican_nlp.utils.setup_functions import subject_instantiator, load_config, remove_previous_derivative_dir
 from pelican_nlp.preprocessing import LPDS
 
+project_path = '/home/yvespauli/PycharmProjects/PyPI_testing_fluency/config_fluency.yml'
+
 class Pelican:
 
     """Main class for the Pelican project handling document processing and metric extraction."""
@@ -31,7 +33,7 @@ class Pelican:
     def __init__(self, config_path: str = None, dev_mode: bool = True) -> None:
         self.dev_mode = dev_mode
         
-        # If no config path is provided, use the default config from package
+        # If no config path is provided, use the default config from package; used for dev-mode
         if config_path is None:
             package_dir = Path(__file__).parent
             default_config = package_dir / 'configuration_files' / 'config_fluency.yml'
@@ -205,4 +207,4 @@ class Pelican:
 
 
 if __name__ == '__main__':
-    Pelican().run()
+    Pelican(project_path).run()

pelican_nlp/sample_configuration_files/config_discourse.yml

@@ -5,7 +5,6 @@ discourse: &discourse_flag true
 #=====================================
 
 #general configurations; always adapt
-PATH_TO_PROJECT_FOLDER: "/path/to/your/project"
 language: "german" # Possibly add options for German and English
 
 task_name: "interview" # Give name of task used for creation of the input file (e.g., ['fluency', 'interview'])

pelican_nlp/sample_configuration_files/config_fluency.yml

@@ -5,7 +5,6 @@ fluency_task: &fluency_flag true
 #========================================
 
 #general configurations; always adapt
-PATH_TO_PROJECT_FOLDER: "/path/to/your/project"
 language: "german"
 multiple_sessions: &session_flag false
 

pelican_nlp/sample_configuration_files/config_general.yml

@@ -4,9 +4,8 @@
 # Basic Settings
 # -------------
 input_file: "text"  # Options: 'text' or 'audio'
-PATH_TO_PROJECT_FOLDER: "/path/to/your/project"
 language: "german"
-recompute_everything: true  # If false, reuses previously computed results
+recompute_everything: true #If false will give warning if output folder already exists
 
 # Task Configuration
 # -----------------
@@ -21,7 +20,7 @@ corpus_names:  # List of task corpora
 multiple_sessions: false
 number_of_subjects: null  # If null, auto-detected
 number_of_speakers: 1
-subject_speakertag: null  # Speaker tag for subject (e.g., "B")
+subject_speakertag: null  # Speaker tag for subject (e.g., "B"), only for discourse
 
 # Document Structure
 # ----------------

{pelican_nlp-0.2.4.dist-info → pelican_nlp-0.2.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pelican_nlp
-Version: 0.2.4
+Version: 0.2.6
 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
@@ -65,6 +65,18 @@ pelican_nlp stands for "Preprocessing and Extraction of Linguistic Information f
 Installation
 ============
 
+Create conda environment
+
+.. code-block:: bash
+
+    conda create -n pelican-nlp python=3.10
+
+Activate environment
+
+.. code-block:: bash
+
+    conda activate pelican-nlp
+
 Install the package using pip:
 
 .. code-block:: bash
@@ -80,12 +92,12 @@ For the latest development version:
 Usage
 =====
 
-To use the pelican_nlp package:
+To run pelican_nlp you need a configuration.yml file in your project directory, which specifies the configurations used for your project.
+Sample configuration files can be found on the pelican_nlp github repository: https://github.com/ypauli/pelican_nlp/tree/main/sample_configuration_files
 
-Adapt your configuration file to your needs.
-ALWAYS change the specified project folder location.
+Adapt your configuration file to your needs and save your personal configuration.yml file to your main project directory.
 
-Save configuration file to main project directory.
+Running pelican_nlp with your configurations can be done directly from the command line interface or via Python script.
 
 Run from command line:
 
@@ -93,13 +105,16 @@ Navigate to main project directory in command line and enter the following comma
 
 .. code-block:: bash
 
+    conda activate pelican-nlp
     pelican-run
 
 
 Run with python script:
 
 Create python file with IDE of your choice (e.g. Visual Studio Code, Pycharm, etc.) and copy the following code into the file:
+Make sure to use the previously created conda environment 'pelican-nlp' for your project.
 
+Run the following Python code:
 .. code-block:: python
 
     from pelican_nlp.main import Pelican
@@ -142,8 +157,7 @@ Features
 Examples
 ========
 
-You can find example setups in the [`examples/`](https://github.com/ypauli/pelican_nlp/tree/main/examples) folder.
-ALWAYS change the path to the project folder specified in the configuration file to your specific project location.
+You can find example setups on the github repository in the 'examples` folder: https://github.com/ypauli/pelican_nlp/tree/main/examples
 
 Contributing
 ============

{pelican_nlp-0.2.4.dist-info → pelican_nlp-0.2.6.dist-info}/RECORD

@@ -1,7 +1,7 @@
 pelican_nlp/__init__.py,sha256=TD5xjKeXXAH6nUWG-6igbClgovi5r8RIEqI_ix1QeYo,204
-pelican_nlp/_version.py,sha256=k2uKAAzDEmm1BIVWeztFlHrCh9fq64H6szFcsXW7tvs,21
-pelican_nlp/cli.py,sha256=uXouL67mTjBynFMWpBTaGvGtEBWDnbS1BI7aRdxV-0M,439
-pelican_nlp/main.py,sha256=iTaV0xuftFijsn1QLk_6iZ2AQDs-r6Z9l0sACOXFwGo,7539
+pelican_nlp/_version.py,sha256=2-ouoBkTVsCtduvfXac3lGkBeSELS7N-9R2Sdu-KxL4,21
+pelican_nlp/cli.py,sha256=mPz-ASIMUme69G6YGVpTnHr5VfM3XA4h29WFd7DXpa4,588
+pelican_nlp/main.py,sha256=HX2Rbl4j7RXaMXlGCtggBBqcg3gRh-ey1PdLsQcDX30,7660
 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
@@ -31,14 +31,14 @@ pelican_nlp/Nils_backup/transcription/word_boundaries.py,sha256=n6erYFVgDWLkgMnS
 pelican_nlp/Nils_backup/transcription/output/holmes_control_nova_all_outputs.json,sha256=Eo2pseyXGWSRLs44fDBIAUU7d57gXFXcq4A58iuLoVo,212326
 pelican_nlp/Silvia_files/Opensmile/opensmile_feature_extraction.py,sha256=sJsthRqJI8bfH38H-OwyQdxXCBIrXEdFm3qSARamYIw,2093
 pelican_nlp/Silvia_files/prosogram/prosogram.py,sha256=ndjtTSgVzEchPEcRNb9jAHuiKRJYXI2C3Y__Deyc1rU,3324
-pelican_nlp/configuration_files/config_audio.yml,sha256=aUneGp32RkBQD2xxgYw7J4djWatfWEjTm7Z8UeO49ec,3868
-pelican_nlp/configuration_files/config_discourse.yml,sha256=WrZk5J2xWMQQPOu25BsqIOM5CrYcAhxCxoMcQVKbDIU,3661
-pelican_nlp/configuration_files/config_fluency.yml,sha256=nBTGJXnbj8IhWsJGwP4ZutZCeIu2ybHUepG7RAWA1y0,3060
-pelican_nlp/configuration_files/config_general.yml,sha256=dOBiqOhw0VgV0LZ1boYJhhjCsnTaYBk6qoCTai-fk-o,3474
-pelican_nlp/configuration_files/config_morteza.yml,sha256=T378fxvBY9hERVGsnXroDFCy8Zh5PIq4dyer2b5AiDY,3376
+pelican_nlp/configuration_files/config_audio.yml,sha256=E9PTI9-DGj-jCMU-teRLqbbtdBOuxEqeu7p48nr0LEg,3803
+pelican_nlp/configuration_files/config_discourse.yml,sha256=wUWjqiwjyBi7-pxP66h_EGPA5XVw6lbIAj71S3tdlqU,3594
+pelican_nlp/configuration_files/config_fluency.yml,sha256=JYpq90K4AF5TslzESJK6Nidw6-D1IiqD_6cdmlCd5-w,2990
+pelican_nlp/configuration_files/config_general.yml,sha256=Dx06lK77yHSiH5U8vxrfm5U5Xc0O6rft6i6PuwcqNuU,3404
+pelican_nlp/configuration_files/config_morteza.yml,sha256=ZUcEIHrXWH9H3r42kTWIFEfgtqZBpyYUMOErVC7X3z8,3152
 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=j_p4hWwLnHuGu4jQakG9oVeizDD9mvWVWVJKTu_lMB4,15143
+pelican_nlp/core/corpus.py,sha256=EIt-3giRaFe0vcJoKla_J8uVF_zR6oGmbQnNbllO9C0,15142
 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
@@ -62,16 +62,16 @@ pelican_nlp/preprocessing/text_cleaner.py,sha256=QKqxwoRR8dnuBYiY-PXK1kB7744TVUc
 pelican_nlp/preprocessing/text_importer.py,sha256=FtSyJjFXDxVle7Jpyw6EqCLDbLTCRxqVQi9ymWWtPB4,1356
 pelican_nlp/preprocessing/text_normalizer.py,sha256=huo5VFqJ0p2jq-ud1047XvMu1qNeaiuG879SF3zkJoM,894
 pelican_nlp/preprocessing/text_tokenizer.py,sha256=h875bXr0YuMrLh4HtQUvpHmASScddtkQXGaF9mm7uwU,1642
-pelican_nlp/sample_configuration_files/config_discourse.yml,sha256=xVHIUpSORV6iR0nEvuess6rfiAvuGEkqmaMWD_6kyFE,3618
-pelican_nlp/sample_configuration_files/config_fluency.yml,sha256=oQ6Y2BhRLExEMpS3VRH2pFrGHi788L66aSYUm05nV_A,3038
-pelican_nlp/sample_configuration_files/config_general.yml,sha256=UuGnZUa-SVmioE9NmXWOMKuv3uG5mNjIuXgA6-Y0JS0,3440
+pelican_nlp/sample_configuration_files/config_discourse.yml,sha256=OaTCoMwhDjrOIBpw1nKXWIoSWRUUFNjGQdgQZHVrJn0,3570
+pelican_nlp/sample_configuration_files/config_fluency.yml,sha256=JYpq90K4AF5TslzESJK6Nidw6-D1IiqD_6cdmlCd5-w,2990
+pelican_nlp/sample_configuration_files/config_general.yml,sha256=-GAVATlqXuQq4ANSW0JauwIGhr7ET_oZiBiM7I40AkA,3424
 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=t4WG5qd5iYpNNBGklje_8ukwmJp_C9RMLLi7veDgNeA,3574
-pelican_nlp-0.2.4.dist-info/licenses/LICENSE,sha256=m3jshBZIXKiBX6qhmhtJcLTVJ1N6BEkQGIflneXvpYg,19336
-pelican_nlp-0.2.4.dist-info/METADATA,sha256=tiN6ZrLCIm6zJOlE-6YQjyzuFVyjAJBLYpmnd7ytX8A,5562
-pelican_nlp-0.2.4.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-pelican_nlp-0.2.4.dist-info/entry_points.txt,sha256=znlG0paAfju9P10UM3rm5HcCHoj4tarTllNpeaqH_gc,53
-pelican_nlp-0.2.4.dist-info/top_level.txt,sha256=F0qlyqy5FCd3sTS_npUYPeLKN9_BZq6wD4qo9pI0xbg,12
-pelican_nlp-0.2.4.dist-info/RECORD,,
+pelican_nlp-0.2.6.dist-info/licenses/LICENSE,sha256=m3jshBZIXKiBX6qhmhtJcLTVJ1N6BEkQGIflneXvpYg,19336
+pelican_nlp-0.2.6.dist-info/METADATA,sha256=DYwHgLjafHAMgzDy0ADYPm_FBvLdRxW98jBAxTH70vU,6140
+pelican_nlp-0.2.6.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+pelican_nlp-0.2.6.dist-info/entry_points.txt,sha256=znlG0paAfju9P10UM3rm5HcCHoj4tarTllNpeaqH_gc,53
+pelican_nlp-0.2.6.dist-info/top_level.txt,sha256=F0qlyqy5FCd3sTS_npUYPeLKN9_BZq6wD4qo9pI0xbg,12
+pelican_nlp-0.2.6.dist-info/RECORD,,