pelican-nlp 0.2.6__tar.gz → 0.2.7__tar.gz

{pelican_nlp-0.2.6/pelican_nlp.egg-info → pelican_nlp-0.2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pelican_nlp
-Version: 0.2.6
+Version: 0.2.7
 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
@@ -69,7 +69,7 @@ Create conda environment
 
 .. code-block:: bash
 
-    conda create -n pelican-nlp python=3.10
+    conda create -n pelican-nlp -c defaults python=3.10
 
 Activate environment
 
@@ -157,7 +157,7 @@ Features
 Examples
 ========
 
-You can find example setups on the github repository in the 'examples` folder: https://github.com/ypauli/pelican_nlp/tree/main/examples
+You can find example setups on the github repository in the `examples <https://github.com/ypauli/pelican_nlp/tree/main/examples>`_ folder:
 
 Contributing
 ============

{pelican_nlp-0.2.6 → pelican_nlp-0.2.7}/README.rst

@@ -23,7 +23,7 @@ Create conda environment
 
 .. code-block:: bash
 
-    conda create -n pelican-nlp python=3.10
+    conda create -n pelican-nlp -c defaults python=3.10
 
 Activate environment
 
@@ -111,7 +111,7 @@ Features
 Examples
 ========
 
-You can find example setups on the github repository in the 'examples` folder: https://github.com/ypauli/pelican_nlp/tree/main/examples
+You can find example setups on the github repository in the `examples <https://github.com/ypauli/pelican_nlp/tree/main/examples>`_ folder:
 
 Contributing
 ============

{pelican_nlp-0.2.6 → pelican_nlp-0.2.7}/examples/PyPI_testing_discourse/config_discourse.yml

@@ -5,7 +5,6 @@ discourse: &discourse_flag true
 #=====================================
 
 #general configurations; always adapt
-PATH_TO_PROJECT_FOLDER: "/home/yvespauli/PycharmProjects/PyPI_testing_discourse"
 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-0.2.6 → pelican_nlp-0.2.7}/examples/PyPI_testing_image-descriptions/config_image-descriptions.yml

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

pelican_nlp-0.2.7/pelican_nlp/_version.py

@@ -0,0 +1 @@
+__version__ = "0.2.7"

{pelican_nlp-0.2.6 → pelican_nlp-0.2.7}/pelican_nlp/extraction/language_model.py

@@ -1,5 +1,6 @@
 import torch
 import psutil
+import os
 
 from accelerate import init_empty_weights, infer_auto_device_map, dispatch_model
 from transformers import AutoModelForCausalLM
@@ -17,8 +18,31 @@ class Model:
         if self.model_name == 'fastText':
             import fasttext
             import fasttext.util
-            fasttext.util.download_model('de', if_exists='ignore')
-            self.model_instance = fasttext.load_model('cc.de.300.bin')
+            
+            # Create a model directory if it doesn't exist
+            model_dir = os.path.join(os.path.expanduser('~'), '.fasttext')
+            os.makedirs(model_dir, exist_ok=True)
+            
+            # Set the model path using proper OS path joining
+            model_path = os.path.join(model_dir, 'cc.de.300.bin')
+            
+            # Download only if model doesn't exist
+            if not os.path.exists(model_path):
+                try:
+                    fasttext.util.download_model('de', if_exists='ignore')
+                except OSError:
+                    # Direct download fallback for Windows
+                    import urllib.request
+                    url = 'https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.de.300.bin.gz'
+                    urllib.request.urlretrieve(url, model_path + '.gz')
+                    # Decompress the file
+                    import gzip
+                    with gzip.open(model_path + '.gz', 'rb') as f_in:
+                        with open(model_path, 'wb') as f_out:
+                            f_out.write(f_in.read())
+                    os.remove(model_path + '.gz')
+            
+            self.model_instance = fasttext.load_model(model_path)
             print('FastText model loaded.')
         elif self.model_name == 'xlm-roberta-base':
             from transformers import AutoModel

{pelican_nlp-0.2.6/examples/PyPI_testing_fluency → pelican_nlp-0.2.7/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: "/home/yvespauli/PycharmProjects/pelican_testing"
 language: "german"
 multiple_sessions: &session_flag false
 

{pelican_nlp-0.2.6 → pelican_nlp-0.2.7/pelican_nlp.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pelican_nlp
-Version: 0.2.6
+Version: 0.2.7
 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
@@ -69,7 +69,7 @@ Create conda environment
 
 .. code-block:: bash
 
-    conda create -n pelican-nlp python=3.10
+    conda create -n pelican-nlp -c defaults python=3.10
 
 Activate environment
 
@@ -157,7 +157,7 @@ Features
 Examples
 ========
 
-You can find example setups on the github repository in the 'examples` folder: https://github.com/ypauli/pelican_nlp/tree/main/examples
+You can find example setups on the github repository in the `examples <https://github.com/ypauli/pelican_nlp/tree/main/examples>`_ folder:
 
 Contributing
 ============

pelican_nlp-0.2.6/pelican_nlp/_version.py

@@ -1 +0,0 @@
-__version__ = "0.2.6"