SinaTools 0.1.32__tar.gz → 0.1.34__tar.gz

{SinaTools-0.1.32 → SinaTools-0.1.34}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: SinaTools
-Version: 0.1.32
+Version: 0.1.34
 Summary: Open-source Python toolkit for Arabic Natural Understanding, allowing people to integrate it in their system workflow.
 Home-page: https://github.com/SinaLab/sinatools
 License: MIT license

{SinaTools-0.1.32 → SinaTools-0.1.34}/SinaTools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: SinaTools
-Version: 0.1.32
+Version: 0.1.34
 Summary: Open-source Python toolkit for Arabic Natural Understanding, allowing people to integrate it in their system workflow.
 Home-page: https://github.com/SinaLab/sinatools
 License: MIT license

{SinaTools-0.1.32 → SinaTools-0.1.34}/SinaTools.egg-info/entry_points.txt

@@ -12,6 +12,7 @@ implication = sinatools.CLI.utils.implication:main
 install_env = sinatools.install_env:main
 jaccard_similarity = sinatools.CLI.utils.jaccard:main
 morphology_analyzer = sinatools.CLI.morphology.morph_analyzer:main
+relation_extractor = sinatools.CLI.relations.relation_extractor:main
 remove_latin = sinatools.CLI.utils.remove_latin:main
 remove_punctuation = sinatools.CLI.utils.remove_punctuation:main
 semantic_relatedness = sinatools.CLI.semantic_relatedness.compute_relatedness:main

{SinaTools-0.1.32 → SinaTools-0.1.34}/setup.py

@@ -78,7 +78,9 @@ setup(
             ('extend_synonyms='
                 'sinatools.CLI.synonyms.extend_synonyms:main'),                    
             ('semantic_relatedness='
-                'sinatools.CLI.semantic_relatedness.compute_relatedness:main'),                                 
+                'sinatools.CLI.semantic_relatedness.compute_relatedness:main'),
+            ('relation_extractor='
+                'sinatools.CLI.relations.relation_extractor:main'),
         ],
     },
     data_files=[('sinatools', ['sinatools/environment.yml'])],

{SinaTools-0.1.32 → SinaTools-0.1.34}/sinatools/CLI/DataDownload/download_files.py

@@ -34,6 +34,7 @@ import argparse
 from sinatools.DataDownload.downloader import download_file
 from sinatools.DataDownload.downloader import download_files
 from sinatools.DataDownload.downloader import get_appdatadir
+from sinatools.DataDownload.downloader import download_folder_from_hf
 from sinatools.DataDownload.downloader import urls
 
 
@@ -53,8 +54,10 @@ def main():
             if file == "wsd":
                 download_file(urls["morph"])
                 download_file(urls["ner"])
-                download_file(urls["wsd_model"])
-                download_file(urls["wsd_tokenizer"])
+                #download_file(urls["wsd_model"])
+                #download_file(urls["wsd_tokenizer"])
+                download_folder_from_hf("SinaLab/ArabGlossBERT", "bert-base-arabertv02_22_May_2021_00h_allglosses_unused01")
+                download_folder_from_hf("SinaLab/ArabGlossBERT", "bert-base-arabertv02")
                 download_file(urls["one_gram"])
                 download_file(urls["five_grams"])
                 download_file(urls["four_grams"])

{SinaTools-0.1.32 → SinaTools-0.1.34}/sinatools/DataDownload/downloader.py

@@ -8,8 +8,8 @@ import tarfile
 urls = {
     'morph': 'https://sina.birzeit.edu/lemmas_dic.pickle',
     'ner': 'https://sina.birzeit.edu/Wj27012000.tar.gz',
-    'wsd_model': 'https://sina.birzeit.edu/bert-base-arabertv02_22_May_2021_00h_allglosses_unused01.zip',
-    'wsd_tokenizer': 'https://sina.birzeit.edu/bert-base-arabertv02.zip',
+    # 'wsd_model': 'https://sina.birzeit.edu/bert-base-arabertv02_22_May_2021_00h_allglosses_unused01.zip',
+    # 'wsd_tokenizer': 'https://sina.birzeit.edu/bert-base-arabertv02.zip',
     'one_gram': 'https://sina.birzeit.edu/one_gram.pickle',
     'five_grams': 'https://sina.birzeit.edu/five_grams.pickle',
     'four_grams':'https://sina.birzeit.edu/four_grams.pickle',
@@ -184,4 +184,35 @@ def download_files():
         None
     """
     for url in urls.values():
-        download_file(url)
+        download_file(url)
+
+
+def download_folder_from_hf(repo_url, folder_name):
+    
+    # Hugging Face API to fetch files from the repository
+    api_url = f"https://huggingface.co/api/models/{repo_url}/tree/main/{folder_name}"
+
+    # Make the request to get the folder structure
+    response = requests.get(api_url)
+    if response.status_code != 200:
+        print(f"Failed to fetch folder contents. Status code: {response.status_code}")
+        return
+    
+    folder_content = response.json()
+    
+    # Download each file in the folder
+    for file_info in folder_content:
+        file_name = file_info["path"]
+        file_url = f"https://huggingface.co/{repo_url}/resolve/main/{file_name}"
+        
+        # Download the file and save it to the output directory
+        file_response = requests.get(file_url)
+        if file_response.status_code == 200:
+            # Create any necessary directories
+            output_file_path = os.path.join(get_appdatadir(), file_name)
+            os.makedirs(os.path.dirname(output_file_path), exist_ok=True)
+            with open(output_file_path, 'wb') as f:
+                f.write(file_response.content)
+            print(f"Downloaded: {file_name}")
+        else:
+            print(f"Failed to download {file_name}. Status code: {file_response.status_code}")

SinaTools-0.1.34/sinatools/VERSION

@@ -0,0 +1 @@
+0.1.34

{SinaTools-0.1.32 → SinaTools-0.1.34}/sinatools/morphology/morph_analyzer.py

@@ -16,7 +16,7 @@ def find_solution(token, language, flag):
            solutions = [solutions[0]]
         for solution in solutions:
             # token, freq, lemma, lemma_id, root, pos
-            resulted_solutions.append([token, solution[0], solution[1], solution[2], solution[3], solution[4]])
+            resulted_solutions.append([token, solution[1], solution[2], solution[3], solution[4], solution[5]])
         return resulted_solutions
     else:
         return []

{SinaTools-0.1.32 → SinaTools-0.1.34}/sinatools/relations/relation_extractor.py

@@ -193,7 +193,7 @@ def event_argument_relation_extraction(documnet):
                     score = predicted_relation[0][0]['score']  
                     if score > 0.50:
                         triple_id+=1
-                        relation={"TripleID":triple_id,"Subject":{"ID":entity_identifier[event_entity],"Type": entities[event_entity], "Label":event_entity}, "Relation": category, "Object":{"ID":entity_identifier[arg_name],"Type": entities[arg_name], "Label":arg_name,}}
+                        relation={"TripleID":triple_id,"Subject":{"ID":entity_identifier[event_entity],"Type": entities[event_entity], "Label":event_entity}, "Relation": category, "Object":{"ID":entity_identifier[arg_name],"Type": entities[arg_name], "Label":arg_name,},"confidence": f"{score: .2f}"}
                         output_list.append(relation)
     
-    return output_list
+    return output_list

SinaTools-0.1.32/sinatools/VERSION

@@ -1 +0,0 @@
-0.1.32