path # lines of code app.py 156 widgets/duplicates.py 39 widgets/label_distribution.py 39 widgets/text_lengths.py 74 widgets/npmi.py 127 widgets/__init__.py 8 widgets/zipf.py 82 widgets/dataset_description.py 28 widgets/general_stats.py 44 widgets/widget_base.py 17 utils/dataset_utils.py 269 utils/gradio_utils.py 363 utils/__init__.py 24 data_measurements/embeddings/__init__.py 1 data_measurements/embeddings/embeddings.py 410 data_measurements/text_duplicates/text_duplicates.py 57 data_measurements/text_duplicates/__init__.py 1 data_measurements/labels/labels.py 167 data_measurements/labels/__init__.py 1 data_measurements/dataset_statistics.py 380 data_measurements/perplexity/perplexity.py 36 data_measurements/perplexity/__init__.py 1 data_measurements/tokenize.py 38 data_measurements/zipf/__init__.py 1 data_measurements/zipf/zipf.py 165 data_measurements/__init__.py 1 data_measurements/lengths/lengths.py 119 data_measurements/lengths/__init__.py 1 data_measurements/npmi/npmi.py 311 data_measurements/npmi/__init__.py 1 run_data_measurements.py 275 lengths/__init__.py 1 npmi/app.py 4 npmi/npmi.py 125