A temporal dependency occurs when developers change two or more files at the same time (i.e. they are a part of the same commit).
No file pairs changed together.
No temporal dependencies found.
No temporal dependencies found.
Pairs | # same commits | # commits 1 | # commits 2 | latest commit |
---|---|---|---|---|
src/datatrove/utils/tokenization.py src/datatrove/pipeline/tokens/merger.py |
1 | 8 (12%) | 24 (4%) | 2025-04-29 |
src/datatrove/pipeline/dedup/exact_substrings.py src/datatrove/pipeline/dedup/minhash.py |
1 | 27 (3%) | 50 (2%) | 2025-04-29 |
src/datatrove/pipeline/dedup/exact_substrings.py src/datatrove/executor/local.py |
1 | 27 (3%) | 35 (2%) | 2025-04-29 |
src/datatrove/pipeline/readers/base.py src/datatrove/executor/slurm.py |
1 | 40 (2%) | 69 (1%) | 2025-04-29 |
src/datatrove/executor/slurm.py src/datatrove/pipeline/dedup/minhash.py |
1 | 69 (1%) | 50 (2%) | 2025-04-29 |
src/datatrove/pipeline/dedup/exact_substrings.py src/datatrove/executor/slurm.py |
1 | 27 (3%) | 69 (1%) | 2025-04-29 |
src/datatrove/tools/jobs_status.py src/datatrove/tools/failed_logs.py |
1 | 6 (16%) | 8 (12%) | 2025-04-29 |
src/datatrove/tools/check_dataset.py src/datatrove/pipeline/dedup/minhash.py |
1 | 11 (9%) | 50 (2%) | 2025-04-29 |
src/datatrove/tools/failed_logs.py src/datatrove/executor/ray.py |
1 | 8 (12%) | 2 (50%) | 2025-04-29 |
src/datatrove/tools/jobs_status.py src/datatrove/pipeline/readers/base.py |
1 | 6 (16%) | 40 (2%) | 2025-04-29 |
src/datatrove/utils/perplexity.py src/datatrove/executor/slurm.py |
1 | 2 (50%) | 69 (1%) | 2025-04-29 |
src/datatrove/tools/failed_logs.py src/datatrove/executor/slurm.py |
1 | 8 (12%) | 69 (1%) | 2025-04-29 |
src/datatrove/tools/check_dataset.py src/datatrove/executor/local.py |
1 | 11 (9%) | 35 (2%) | 2025-04-29 |
src/datatrove/pipeline/dedup/url_dedup.py src/datatrove/executor/local.py |
1 | 7 (14%) | 35 (2%) | 2025-04-29 |
src/datatrove/tools/check_dataset.py src/datatrove/pipeline/tokens/tokenizer.py |
1 | 11 (9%) | 42 (2%) | 2025-04-29 |
src/datatrove/pipeline/dedup/url_dedup.py src/datatrove/pipeline/dedup/minhash.py |
1 | 7 (14%) | 50 (2%) | 2025-04-29 |
src/datatrove/pipeline/readers/base.py src/datatrove/pipeline/decont/n_grams.py |
1 | 40 (2%) | 8 (12%) | 2025-04-29 |
src/datatrove/utils/dataset.py src/datatrove/utils/_import_utils.py |
1 | 4 (25%) | 6 (16%) | 2025-04-30 |
src/datatrove/utils/dataset.py src/datatrove/io.py |
1 | 4 (25%) | 23 (4%) | 2025-04-30 |
src/datatrove/executor/__init__.py src/datatrove/executor/ray.py |
1 | 2 (50%) | 2 (50%) | 2025-04-29 |
src/datatrove/tools/jobs_status.py src/datatrove/executor/slurm.py |
1 | 6 (16%) | 69 (1%) | 2025-04-29 |
src/datatrove/utils/tokenization.py src/datatrove/pipeline/tokens/tokenizer.py |
1 | 8 (12%) | 42 (2%) | 2025-04-29 |
src/datatrove/executor/ray.py pyproject.toml |
1 | 2 (50%) | 32 (3%) | 2025-04-29 |
src/datatrove/executor/slurm.py src/datatrove/executor/local.py |
1 | 69 (1%) | 35 (2%) | 2025-04-29 |
src/datatrove/tools/check_dataset.py src/datatrove/pipeline/dedup/exact_substrings.py |
1 | 11 (9%) | 27 (3%) | 2025-04-29 |
src/datatrove/pipeline/readers/base.py src/datatrove/executor/ray.py |
1 | 40 (2%) | 2 (50%) | 2025-04-29 |
src/datatrove/executor/ray.py src/datatrove/executor/slurm.py |
1 | 2 (50%) | 69 (1%) | 2025-04-29 |
src/datatrove/tools/failed_logs.py src/datatrove/pipeline/readers/base.py |
1 | 8 (12%) | 40 (2%) | 2025-04-29 |
src/datatrove/utils/perplexity.py src/datatrove/executor/ray.py |
1 | 2 (50%) | 2 (50%) | 2025-04-29 |
src/datatrove/tools/jobs_status.py src/datatrove/executor/ray.py |
1 | 6 (16%) | 2 (50%) | 2025-04-29 |
src/datatrove/tools/jobs_status.py src/datatrove/pipeline/decont/n_grams.py |
1 | 6 (16%) | 8 (12%) | 2025-04-29 |
src/datatrove/pipeline/tokens/merger.py src/datatrove/pipeline/tokens/tokenizer.py |
1 | 24 (4%) | 42 (2%) | 2025-04-29 |
src/datatrove/pipeline/decont/n_grams.py src/datatrove/executor/slurm.py |
1 | 8 (12%) | 69 (1%) | 2025-04-29 |
src/datatrove/utils/perplexity.py src/datatrove/pipeline/decont/n_grams.py |
1 | 2 (50%) | 8 (12%) | 2025-04-29 |
src/datatrove/executor/__init__.py pyproject.toml |
1 | 2 (50%) | 32 (3%) | 2025-04-29 |
src/datatrove/utils/_import_utils.py src/datatrove/io.py |
1 | 6 (16%) | 23 (4%) | 2025-04-30 |
src/datatrove/executor/local.py src/datatrove/pipeline/dedup/minhash.py |
1 | 35 (2%) | 50 (2%) | 2025-04-29 |
src/datatrove/pipeline/decont/n_grams.py src/datatrove/executor/ray.py |
1 | 8 (12%) | 2 (50%) | 2025-04-29 |
src/datatrove/utils/perplexity.py src/datatrove/tools/failed_logs.py |
1 | 2 (50%) | 8 (12%) | 2025-04-29 |
src/datatrove/pipeline/dedup/url_dedup.py src/datatrove/pipeline/dedup/exact_substrings.py |
1 | 7 (14%) | 27 (3%) | 2025-04-29 |
src/datatrove/tools/failed_logs.py src/datatrove/pipeline/decont/n_grams.py |
1 | 8 (12%) | 8 (12%) | 2025-04-29 |
src/datatrove/utils/perplexity.py src/datatrove/pipeline/readers/base.py |
1 | 2 (50%) | 40 (2%) | 2025-04-29 |
src/datatrove/pipeline/dedup/url_dedup.py src/datatrove/executor/slurm.py |
1 | 7 (14%) | 69 (1%) | 2025-04-29 |
src/datatrove/tools/check_dataset.py src/datatrove/executor/slurm.py |
1 | 11 (9%) | 69 (1%) | 2025-04-29 |
src/datatrove/utils/perplexity.py src/datatrove/tools/jobs_status.py |
1 | 2 (50%) | 6 (16%) | 2025-04-29 |
src/datatrove/tools/check_dataset.py src/datatrove/pipeline/dedup/url_dedup.py |
1 | 11 (9%) | 7 (14%) | 2025-04-29 |
Pairs | # same commits | # commits 1 | # commits 2 | latest commit |
---|---|---|---|---|
src/datatrove/utils/tokenization.py src/datatrove/pipeline/tokens/tokenizer.py |
2 | 8 (25%) | 42 (4%) | 2025-04-29 |
src/datatrove/pipeline/tokens/counter.py src/datatrove/pipeline/tokens/tokenizer.py |
1 | 14 (7%) | 42 (2%) | 2025-01-09 |
src/datatrove/tools/jobs_status.py src/datatrove/pipeline/decont/n_grams.py |
1 | 6 (16%) | 8 (12%) | 2025-04-29 |
src/datatrove/pipeline/dedup/url_dedup.py src/datatrove/pipeline/dedup/exact_substrings.py |
1 | 7 (14%) | 27 (3%) | 2025-04-29 |
src/datatrove/pipeline/dedup/url_dedup.py src/datatrove/pipeline/dedup/minhash.py |
1 | 7 (14%) | 50 (2%) | 2025-04-29 |
src/datatrove/executor/slurm.py src/datatrove/executor/local.py |
1 | 69 (1%) | 35 (2%) | 2025-04-29 |
src/datatrove/tools/jobs_status.py src/datatrove/executor/slurm.py |
1 | 6 (16%) | 69 (1%) | 2025-04-29 |
src/datatrove/utils/perplexity.py src/datatrove/tools/jobs_status.py |
1 | 2 (50%) | 6 (16%) | 2025-04-29 |
src/datatrove/pipeline/filters/language_filter.py src/datatrove/pipeline/filters/fasttext_filter.py |
1 | 23 (4%) | 7 (14%) | 2025-01-09 |
src/datatrove/pipeline/decont/n_grams.py src/datatrove/executor/slurm.py |
1 | 8 (12%) | 69 (1%) | 2025-04-29 |
src/datatrove/tools/failed_logs.py src/datatrove/executor/ray.py |
1 | 8 (12%) | 2 (50%) | 2025-04-29 |
src/datatrove/tools/check_dataset.py src/datatrove/pipeline/tokens/tokenizer.py |
1 | 11 (9%) | 42 (2%) | 2025-04-29 |
src/datatrove/pipeline/filters/fasttext_filter.py src/datatrove/utils/_import_utils.py |
1 | 7 (14%) | 6 (16%) | 2025-01-09 |
src/datatrove/pipeline/dedup/exact_substrings.py src/datatrove/executor/local.py |
1 | 27 (3%) | 35 (2%) | 2025-04-29 |
src/datatrove/executor/ray.py pyproject.toml |
1 | 2 (50%) | 32 (3%) | 2025-04-29 |
src/datatrove/pipeline/dedup/sentence_dedup.py src/datatrove/pipeline/dedup/url_dedup.py |
1 | 38 (2%) | 7 (14%) | 2025-01-24 |
src/datatrove/pipeline/dedup/exact_substrings.py src/datatrove/executor/slurm.py |
1 | 27 (3%) | 69 (1%) | 2025-04-29 |
src/datatrove/pipeline/tokens/__init__.py src/datatrove/pipeline/tokens/megatron_tokenizer.py |
1 | 7 (14%) | 3 (33%) | 2025-01-09 |
src/datatrove/pipeline/dedup/exact_substrings.py src/datatrove/utils/tokenization.py |
1 | 27 (3%) | 8 (12%) | 2025-01-09 |
src/datatrove/tools/check_dataset.py src/datatrove/executor/local.py |
1 | 11 (9%) | 35 (2%) | 2025-04-29 |
src/datatrove/pipeline/dedup/exact_substrings.py src/datatrove/pipeline/dedup/minhash.py |
1 | 27 (3%) | 50 (2%) | 2025-04-29 |
src/datatrove/executor/ray.py src/datatrove/executor/slurm.py |
1 | 2 (50%) | 69 (1%) | 2025-04-29 |
src/datatrove/pipeline/decont/n_grams.py src/datatrove/executor/ray.py |
1 | 8 (12%) | 2 (50%) | 2025-04-29 |
src/datatrove/pipeline/tokens/counter.py src/datatrove/pipeline/dedup/exact_substrings.py |
1 | 14 (7%) | 27 (3%) | 2025-01-09 |
src/datatrove/pipeline/extractors/trafilatura.py src/datatrove/pipeline/extractors/base.py |
1 | 16 (6%) | 20 (5%) | 2025-01-02 |
src/datatrove/utils/_import_utils.py src/datatrove/io.py |
1 | 6 (16%) | 23 (4%) | 2025-04-30 |
src/datatrove/pipeline/stats/token_stats.py src/datatrove/pipeline/tokens/megatron_tokenizer.py |
1 | 2 (50%) | 3 (33%) | 2025-01-09 |
src/datatrove/pipeline/readers/base.py src/datatrove/pipeline/decont/n_grams.py |
1 | 40 (2%) | 8 (12%) | 2025-04-29 |
src/datatrove/utils/perplexity.py src/datatrove/tools/failed_logs.py |
1 | 2 (50%) | 8 (12%) | 2025-04-29 |
src/datatrove/pipeline/writers/parquet.py src/datatrove/pipeline/writers/huggingface.py |
1 | 5 (20%) | 7 (14%) | 2025-01-30 |
src/datatrove/pipeline/tokens/megatron_tokenizer.py src/datatrove/utils/tokenization.py |
1 | 3 (33%) | 8 (12%) | 2025-01-09 |
src/datatrove/utils/dataset.py src/datatrove/io.py |
1 | 4 (25%) | 23 (4%) | 2025-04-30 |
src/datatrove/utils/perplexity.py src/datatrove/pipeline/readers/base.py |
1 | 2 (50%) | 40 (2%) | 2025-04-29 |
src/datatrove/pipeline/tokens/counter.py src/datatrove/utils/tokenization.py |
1 | 14 (7%) | 8 (12%) | 2025-01-09 |
src/datatrove/pipeline/dedup/url_dedup.py src/datatrove/executor/local.py |
1 | 7 (14%) | 35 (2%) | 2025-04-29 |
src/datatrove/pipeline/tokens/megatron_tokenizer.py src/datatrove/pipeline/dedup/exact_substrings.py |
1 | 3 (33%) | 27 (3%) | 2025-01-09 |
src/datatrove/tools/check_dataset.py src/datatrove/pipeline/dedup/exact_substrings.py |
1 | 11 (9%) | 27 (3%) | 2025-04-29 |
src/datatrove/tools/jobs_status.py src/datatrove/executor/ray.py |
1 | 6 (16%) | 2 (50%) | 2025-04-29 |
src/datatrove/pipeline/tokens/merger.py src/datatrove/pipeline/tokens/tokenizer.py |
1 | 24 (4%) | 42 (2%) | 2025-04-29 |
src/datatrove/executor/__init__.py pyproject.toml |
1 | 2 (50%) | 32 (3%) | 2025-04-29 |
src/datatrove/utils/dataset.py src/datatrove/utils/_import_utils.py |
1 | 4 (25%) | 6 (16%) | 2025-04-30 |
src/datatrove/pipeline/stats/token_stats.py src/datatrove/utils/tokenization.py |
1 | 2 (50%) | 8 (12%) | 2025-01-09 |
src/datatrove/pipeline/dedup/exact_substrings.py src/datatrove/pipeline/tokens/tokenizer.py |
1 | 27 (3%) | 42 (2%) | 2025-01-09 |
src/datatrove/pipeline/stats/token_stats.py src/datatrove/pipeline/tokens/tokenizer.py |
1 | 2 (50%) | 42 (2%) | 2025-01-09 |
src/datatrove/tools/failed_logs.py src/datatrove/executor/slurm.py |
1 | 8 (12%) | 69 (1%) | 2025-04-29 |
src/datatrove/utils/perplexity.py src/datatrove/executor/slurm.py |
1 | 2 (50%) | 69 (1%) | 2025-04-29 |
src/datatrove/tools/failed_logs.py src/datatrove/pipeline/readers/base.py |
1 | 8 (12%) | 40 (2%) | 2025-04-29 |
src/datatrove/pipeline/tokens/counter.py src/datatrove/pipeline/stats/token_stats.py |
1 | 14 (7%) | 2 (50%) | 2025-01-09 |
src/datatrove/utils/perplexity.py src/datatrove/pipeline/decont/n_grams.py |
1 | 2 (50%) | 8 (12%) | 2025-04-29 |
src/datatrove/executor/local.py src/datatrove/pipeline/dedup/minhash.py |
1 | 35 (2%) | 50 (2%) | 2025-04-29 |