Nützliche_Befehle.txt

# Zeigt alle Klassen des Datasets an
    pt_dataset = pt.get_dataset('irds:ir-lab-sose-2024/ir-acl-anthology-20240504-training')

    print("Verfügbare Methoden und Eigenschaften des Datasets:")
    print(dir(pt_dataset))
#   '__class__',
    '__delattr__',
    '__dict__',
    '__dir__', 
    '__doc__', 
    '__eq__',
    '__format__',
    '__ge__',
    '__getattribute__',
    '__gt__',
    '__hash__',
    '__init__',
    '__init_subclass__',
    '__le__',
    '__lt__',
    '__module__',
    '__ne__',
    '__new__',
    '__reduce__',
    '__reduce_ex__',
    '__repr__',
    '__setattr__',
    '__sizeof__',
    '__str__',
    '__subclasshook__',
    '__weakref__',
    '_configure',
    '_describe_component',
    '_irds_id',
    '_irds_ref', 
    'get_corpus', 
    'get_corpus_iter',
    'get_corpus_lang',
    'get_index',
    'get_qrels', 
    'get_results',
    'get_topics',
    'get_topics_lang',
    'get_topicsqrels',
    'info_url',
    'irds_ref'    

#Suchen
bm25.search('pagerank')

# #Benötigt um Permission error beim entpacken zu umgehen
# import os
# import shutil

# source = "/root/.tira/extracted_datasets/ir-lab-sose-2024/ir-acl-anthology-20240504-training/ir-acl-anthology-20240504-training"
# destination = "/root/.tira/extracted_datasets/ir-lab-sose-2024/ir-acl-anthology-20240504-training/input-data"

# try:
#     os.rename(source, destination)
# except PermissionError as e:
#     print(f"PermissionError encountered: {e}. Trying to copy instead.")
#     shutil.copytree(source, destination)
#     shutil.rmtree(source)

pt_dataset.get_corpus_iter()
pt_dataset.get_corpus()
pt_dataset.get_topics()
pt_dataset.get_qrels()