id: 1
unit: def run()
file: misc/reference_datasets/multilingual/download_cc-100.py
start line: 0
end line: 0
size: 147 LOC
McCabe index: 6
number of parameters: 4

id: 2
unit: def run()
file: misc/precision_filtering/slurm_count_word.py
start line: 0
end line: 0
size: 37 LOC
McCabe index: 14
number of parameters: 4

id: 3
unit: def __init__()
file: misc/reference_datasets/multilingual/copy_raw_data.py
start line: 0
end line: 0
size: 32 LOC
McCabe index: 1
number of parameters: 15

id: 4
unit: def __init__()
file: misc/precision_filtering/run_precision_filtering.py
start line: 0
end line: 0
size: 31 LOC
McCabe index: 8
number of parameters: 5

id: 5
unit: def read_files_shard()
file: misc/reference_datasets/monolingual/zh/download_mapcc.py
start line: 0
end line: 0
size: 29 LOC
McCabe index: 9
number of parameters: 2

id: 6
unit: def read_files_shard()
file: misc/reference_datasets/multilingual/part jsons.py
start line: 0
end line: 0
size: 29 LOC
McCabe index: 9
number of parameters: 2

id: 7
unit: def get_checkpoints_to_run()
file: ablations/evaluation/launch_evals.py
start line: 0
end line: 0
size: 24 LOC
McCabe index: 12
number of parameters: 6

id: 8
unit: def run()
file: misc/reference_datasets/monolingual/zh/download_mapcc.py
start line: 0
end line: 0
size: 23 LOC
McCabe index: 4
number of parameters: 4

id: 9
unit: def read_file()
file: misc/reference_datasets/multilingual/copy_raw_data.py
start line: 0
end line: 0
size: 23 LOC
McCabe index: 7
number of parameters: 2

id: 10
unit: def run()
file: misc/reference_datasets/multilingual/copy_raw_data.py
start line: 0
end line: 0
size: 20 LOC
McCabe index: 8
number of parameters: 4

id: 11
unit: def url_filter()
file: misc/precision_filtering/run_precision_filtering.py
start line: 0
end line: 0
size: 19 LOC
McCabe index: 8
number of parameters: 2

id: 12
unit: def run()
file: misc/reference_datasets/multilingual/download_hplt.py
start line: 0
end line: 0
size: 18 LOC
McCabe index: 7
number of parameters: 4

id: 13
unit: def __init__()
file: misc/reference_datasets/monolingual/ar/download_arabicweb24.py
start line: 0
end line: 0
size: 17 LOC
McCabe index: 1
number of parameters: 0

id: 14
unit: def __init__()
file: misc/reference_datasets/monolingual/fr/download_croissant.py
start line: 0
end line: 0
size: 17 LOC
McCabe index: 1
number of parameters: 0

id: 15
unit: def read_file()
file: misc/reference_datasets/multilingual/part jsons.py
start line: 0
end line: 0
size: 17 LOC
McCabe index: 5
number of parameters: 2

id: 16
unit: def read_file()
file: misc/reference_datasets/monolingual/ar/download_arabicweb24.py
start line: 0
end line: 0
size: 16 LOC
McCabe index: 4
number of parameters: 2

id: 17
unit: def read_file()
file: misc/reference_datasets/monolingual/fr/download_croissant.py
start line: 0
end line: 0
size: 16 LOC
McCabe index: 4
number of parameters: 2

id: 18
unit: def load_and_save_tokenizer_freq()
file: misc/precision_filtering/count_common.py
start line: 0
end line: 0
size: 16 LOC
McCabe index: 5
number of parameters: 2

id: 19
unit: def print_differences()
file: ablations/training/launch_exp.py
start line: 0
end line: 0
size: 14 LOC
McCabe index: 8
number of parameters: 2

id: 20
unit: def save()
file: misc/precision_filtering/wordlist_gen.py
start line: 0
end line: 0
size: 14 LOC
McCabe index: 2
number of parameters: 2

id: 21
unit: def checkpoint_exists()
file: ablations/evaluation/launch_evals.py
start line: 0
end line: 0
size: 13 LOC
McCabe index: 6
number of parameters: 4

id: 22
unit: def read()
file: misc/reference_datasets/monolingual/zh/download_mapcc.py
start line: 0
end line: 0
size: 13 LOC
McCabe index: 5
number of parameters: 2

id: 23
unit: def read()
file: misc/reference_datasets/multilingual/part jsons.py
start line: 0
end line: 0
size: 13 LOC
McCabe index: 5
number of parameters: 2

id: 24
unit: def load_words_from_txt()
file: misc/precision_filtering/wordlist_score.py
start line: 0
end line: 0
size: 13 LOC
McCabe index: 8
number of parameters: 1

id: 25
unit: def adapter()
file: misc/reference_datasets/multilingual/download_mc4.py
start line: 0
end line: 0
size: 10 LOC
McCabe index: 2
number of parameters: 4

id: 26
unit: def launch_slurm_job()
file: ablations/evaluation/launch_evals.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 2
number of parameters: 2

id: 27
unit: def launch_slurm_job()
file: ablations/evaluation/launch_random_evals.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 2
number of parameters: 2

id: 28
unit: def _open_next_file()
file: misc/reference_datasets/monolingual/zh/download_mapcc.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 3
number of parameters: 1

id: 29
unit: def __init__()
file: misc/reference_datasets/monolingual/zh/download_mapcc.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 1
number of parameters: 0

id: 30
unit: def _open_next_file()
file: misc/reference_datasets/multilingual/part jsons.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 3
number of parameters: 1

id: 31
unit: def __init__()
file: misc/reference_datasets/multilingual/part jsons.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 1
number of parameters: 0

id: 32
unit: def filter_by_ratio()
file: misc/precision_filtering/wordlist_gen.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 7
number of parameters: 3

id: 33
unit: def filter_top_percentile()
file: misc/precision_filtering/wordlist_gen.py
start line: 0
end line: 0
size: 8 LOC
McCabe index: 4
number of parameters: 2

id: 34
unit: def parse_date()
file: ablations/evaluation/launch_evals.py
start line: 0
end line: 0
size: 7 LOC
McCabe index: 3
number of parameters: 1

id: 35
unit: def adapter()
file: misc/reference_datasets/multilingual/download_culturax.py
start line: 0
end line: 0
size: 7 LOC
McCabe index: 1
number of parameters: 4

id: 36
unit: def adapter()
file: misc/reference_datasets/multilingual/copy_raw_data.py
start line: 0
end line: 0
size: 7 LOC
McCabe index: 1
number of parameters: 4

id: 37
unit: def wordlist_filter()
file: misc/precision_filtering/run_precision_filtering.py
start line: 0
end line: 0
size: 7 LOC
McCabe index: 2
number of parameters: 2

id: 38
unit: def filter_score()
file: misc/precision_filtering/wordlist_score.py
start line: 0
end line: 0
size: 7 LOC
McCabe index: 8
number of parameters: 2

id: 39
unit: def run()
file: misc/reference_datasets/monolingual/zh/download_mapcc.py
start line: 0
end line: 0
size: 6 LOC
McCabe index: 3
number of parameters: 4

id: 40
unit: def wordlist()
file: misc/precision_filtering/run_precision_filtering.py
start line: 0
end line: 0
size: 6 LOC
McCabe index: 4
number of parameters: 1

id: 41
unit: def launch_slurm_job()
file: ablations/training/launch_exp.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 1
number of parameters: 2

id: 42
unit: def __init__()
file: misc/reference_datasets/monolingual/zh/download_mapcc.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 1
number of parameters: 2

id: 43
unit: def __init__()
file: misc/reference_datasets/multilingual/part jsons.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 1
number of parameters: 2

id: 44
unit: def open_concatenated_gzip_files()
file: misc/reference_datasets/monolingual/zh/download_mapcc.py
start line: 0
end line: 0
size: 4 LOC
McCabe index: 1
number of parameters: 1

id: 45
unit: def open_concatenated_gzip_files()
file: misc/reference_datasets/multilingual/part jsons.py
start line: 0
end line: 0
size: 4 LOC
McCabe index: 1
number of parameters: 1

id: 46
unit: def close()
file: misc/reference_datasets/monolingual/zh/download_mapcc.py
start line: 0
end line: 0
size: 3 LOC
McCabe index: 2
number of parameters: 1

id: 47
unit: def close()
file: misc/reference_datasets/multilingual/part jsons.py
start line: 0
end line: 0
size: 3 LOC
McCabe index: 2
number of parameters: 1

id: 48
unit: def __init__()
file: misc/precision_filtering/slurm_count_word.py
start line: 0
end line: 0
size: 3 LOC
McCabe index: 1
number of parameters: 3

id: 49
unit: def above_lang_threshold()
file: fineweb-2-pipeline.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 2

id: 50
unit: def generate_tokenizer_identifier()
file: misc/precision_filtering/slurm_count_word.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 1

id: 51
unit: def filter()
file: misc/precision_filtering/run_precision_filtering.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 2
number of parameters: 2

id: 52
unit: def generate_tokenizer_identifier()
file: misc/precision_filtering/count_common.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 1

id: 53
unit: def generate_tokenizer_identifier()
file: misc/precision_filtering/wordlist_gen.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 1