config.py

class config():

    sample_texts_path = 'data/sample_text.csv'

    logo_path = 'images/tum-logo.png'
    main_title = 'Topic Modeling for Summarization'
    lecture_title = 'Machine Learning for Natural Language Processing Applications (IN2106)'

    input_text = 'Enter Some Text:'
    button_text = 'Generate new sample text'
    

    topic_modelling_title = 'Topic Modelling:'
    topic_modelling_answers = ('BERTopic','LDA','CTM','NMF','Top2Vec')

    segmenter_title = 'Segmentizer:'
    segmenter_answers = ('Nltk','Spacy','Stanza')

    summarizer_title = 'Summarizer:'
    summarizer_answers = ('Bart','T5-base','Prophetnet','Pegasus')

    generate_text = 'Generate topic based summaries'

    output_title = 'Select topics you want to see summaries of:'


    warning_len_input_text = 'The length of the input text is not enough to create topic awareness summaries! or change parameters!'
    filter_threshold_summaries = True
    threshold_error = 'X -> not possible to generate a summary due to ''threshold'

    # model parameters
    MIN_NUM_SENTENCES_FOR_SUMMARY_CREATION = 2
    PATH_20_NEWS_CLUSTERID_LABEL_WORDS = 'data/_20news_df_output_clusterId_label_words.csv'

    PATH_20_NEWS_CLUSTERID_LABEL_WORDS_CTM = 'data/_20news_df_output_doc_topic_CTM_LIST.csv'
    PATH_20_NEWS_CLUSTERID_LABEL_WORDS_LDA = 'data/_20news_df_output_doc_topic_LDA_LIST.csv'
    PATH_20_NEWS_CLUSTERID_LABEL_WORDS_NMF = 'data/_20news_df_output_doc_topic_NMF_LIST.csv'
    PATH_20_NEWS_CLUSTERID_LABEL_WORDS_TOP2VEC = 'data/_20news_df_output_doc_topic_Top2Vec_LIST.csv'

    # model paths
    nltk_path = 'models/nltkUtilsObj.pkl'
    sent_trans_path = 'models/sentTransfModelUtilsObj.pkl'

    pegasus_model_path = 'models/pegasus_model'
    bart_model_path = 'models/bart_model'
    t5_model_path = 'models/t5_model'
    prophetnet_model_path = 'models/prophetnet_model'