pelican-nlp 0.2.6__py3-none-any.whl → 0.2.7__py3-none-any.whl

pelican_nlp/_version.py

@@ -1 +1 @@
-__version__ = "0.2.6"
+__version__ = "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.dist-info → pelican_nlp-0.2.7.dist-info}/METADATA

@@ -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.dist-info → pelican_nlp-0.2.7.dist-info}/RECORD

@@ -1,5 +1,5 @@
 pelican_nlp/__init__.py,sha256=TD5xjKeXXAH6nUWG-6igbClgovi5r8RIEqI_ix1QeYo,204
-pelican_nlp/_version.py,sha256=2-ouoBkTVsCtduvfXac3lGkBeSELS7N-9R2Sdu-KxL4,21
+pelican_nlp/_version.py,sha256=LIho7asb0pp1iNbJvXEhRMluyGN4gB4RHIIbAKpROsc,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
@@ -46,7 +46,7 @@ pelican_nlp/extraction/acoustic_feature_extraction.py,sha256=6Csrr6uotarhuAzxYlG
 pelican_nlp/extraction/distance_from_randomness.py,sha256=yikZ3GK2dqpzuNFPVsjuUK0lo6kHOIoIhKPaVrGXRMQ,3365
 pelican_nlp/extraction/extract_embeddings.py,sha256=e5bcNlskd7f-JkWtfd7YutGV5bqcURKrAkETRyTx93Q,2457
 pelican_nlp/extraction/extract_logits.py,sha256=Lc7Es86T8mlSvLMhiDHpFdCc0kCZ9fNr3-VFnOyeybs,3869
-pelican_nlp/extraction/language_model.py,sha256=4tHJZIRCEeHVTwEf2jmOtu-zDGkdXiDjKmlpuxDuLiw,2929
+pelican_nlp/extraction/language_model.py,sha256=npew_4ziTCNE87pjN8LL0eTPujlewVr8pMT7BsmzEjo,4038
 pelican_nlp/extraction/semantic_similarity.py,sha256=QhY5CAOAorxEo3UBWPlMegFvbySF0KH6j4j3m2I3_NY,2552
 pelican_nlp/extraction/test_documents/test_features.csv,sha256=LR_3m4vIm-YWKw5gI5ziswhS-NF9VhKv14c2udLxtJU,488482
 pelican_nlp/extraction/test_documents/wallace_1.15_3.txt,sha256=ShXxOHUZzGPNUqIcOn6-OYkarzNtTC22V05a_Xpvtlw,3731
@@ -69,9 +69,9 @@ pelican_nlp/utils/__init__.py,sha256=q1tGdOOj5UPRC2mGhoMUh8p4cbFCkkbD21bQaOVvFao
 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-0.2.6.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,,
+pelican_nlp-0.2.7.dist-info/licenses/LICENSE,sha256=m3jshBZIXKiBX6qhmhtJcLTVJ1N6BEkQGIflneXvpYg,19336
+pelican_nlp-0.2.7.dist-info/METADATA,sha256=YyZBYza89dtKbvLLHXkxOEZ1BODloXBjh-zZSODLfVI,6155
+pelican_nlp-0.2.7.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+pelican_nlp-0.2.7.dist-info/entry_points.txt,sha256=znlG0paAfju9P10UM3rm5HcCHoj4tarTllNpeaqH_gc,53
+pelican_nlp-0.2.7.dist-info/top_level.txt,sha256=F0qlyqy5FCd3sTS_npUYPeLKN9_BZq6wD4qo9pI0xbg,12
+pelican_nlp-0.2.7.dist-info/RECORD,,