pyseismic-lsr 0.1.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (59) hide show
  1. pyseismic_lsr-0.1.0/.gitignore +42 -0
  2. pyseismic_lsr-0.1.0/.pre-commit-config.yaml +28 -0
  3. pyseismic_lsr-0.1.0/Cargo.lock +1239 -0
  4. pyseismic_lsr-0.1.0/Cargo.toml +58 -0
  5. pyseismic_lsr-0.1.0/LICENSE.md +21 -0
  6. pyseismic_lsr-0.1.0/PKG-INFO +179 -0
  7. pyseismic_lsr-0.1.0/README.md +153 -0
  8. pyseismic_lsr-0.1.0/docs/Installation.md +85 -0
  9. pyseismic_lsr-0.1.0/docs/PythonUsage.md +69 -0
  10. pyseismic_lsr-0.1.0/docs/ReplicateResults.md +12 -0
  11. pyseismic_lsr-0.1.0/docs/RustUsage.md +197 -0
  12. pyseismic_lsr-0.1.0/experiments/cikm2024/cocondenser_no_knn_mem_budget_1.5.toml +67 -0
  13. pyseismic_lsr-0.1.0/experiments/cikm2024/cocondenser_no_knn_mem_budget_2.0.toml +77 -0
  14. pyseismic_lsr-0.1.0/experiments/cikm2024/cocondenser_with_knn_mem_budget_1.5.toml +87 -0
  15. pyseismic_lsr-0.1.0/experiments/cikm2024/cocondenser_with_knn_mem_budget_2.0.toml +105 -0
  16. pyseismic_lsr-0.1.0/experiments/cikm2024/spladev3_no_knn_mem_budget_1.5.toml +71 -0
  17. pyseismic_lsr-0.1.0/experiments/cikm2024/spladev3_no_knn_mem_budget_2.0.toml +79 -0
  18. pyseismic_lsr-0.1.0/experiments/cikm2024/spladev3_with_knn_mem_budget_1.5.toml +94 -0
  19. pyseismic_lsr-0.1.0/experiments/cikm2024/spladev3_with_knn_mem_budget_2.0.toml +100 -0
  20. pyseismic_lsr-0.1.0/experiments/grid_searches/example_grid_search.toml +44 -0
  21. pyseismic_lsr-0.1.0/experiments/sigir2024/efficient-splade.toml +71 -0
  22. pyseismic_lsr-0.1.0/experiments/sigir2024/nq.toml +71 -0
  23. pyseismic_lsr-0.1.0/experiments/sigir2024/splade.toml +71 -0
  24. pyseismic_lsr-0.1.0/experiments/sigir2024/unicoil-t5.toml +71 -0
  25. pyseismic_lsr-0.1.0/imgs/feature_branches.png +0 -0
  26. pyseismic_lsr-0.1.0/imgs/index.png +0 -0
  27. pyseismic_lsr-0.1.0/imgs/logo.jpg +0 -0
  28. pyseismic_lsr-0.1.0/imgs/main_branches.png +0 -0
  29. pyseismic_lsr-0.1.0/imgs/new_logo_seismic.webp +0 -0
  30. pyseismic_lsr-0.1.0/imgs/seismic_table.png +0 -0
  31. pyseismic_lsr-0.1.0/pyproject.toml +40 -0
  32. pyseismic_lsr-0.1.0/rust-toolchain.toml +2 -0
  33. pyseismic_lsr-0.1.0/scripts/GetResultsFromGridSearch.ipynb +122 -0
  34. pyseismic_lsr-0.1.0/scripts/HandsOnSeismic.ipynb +203 -0
  35. pyseismic_lsr-0.1.0/scripts/SeismicGuide.ipynb +613 -0
  36. pyseismic_lsr-0.1.0/scripts/convert_json_to_inner_format.py +367 -0
  37. pyseismic_lsr-0.1.0/scripts/requirements.txt +8 -0
  38. pyseismic_lsr-0.1.0/scripts/run_experiments.py +443 -0
  39. pyseismic_lsr-0.1.0/scripts/run_grid_search.py +115 -0
  40. pyseismic_lsr-0.1.0/scripts/search_python.py +45 -0
  41. pyseismic_lsr-0.1.0/src/bin/build_enhanced_inverted_index.rs +135 -0
  42. pyseismic_lsr-0.1.0/src/bin/build_inverted_index.rs +144 -0
  43. pyseismic_lsr-0.1.0/src/bin/generate_groundtrouth.rs +58 -0
  44. pyseismic_lsr-0.1.0/src/bin/perf_enhanced_inverted_index.rs +156 -0
  45. pyseismic_lsr-0.1.0/src/bin/perf_inverted_index.rs +144 -0
  46. pyseismic_lsr-0.1.0/src/distances.rs +186 -0
  47. pyseismic_lsr-0.1.0/src/elias_fano/tests.rs +11 -0
  48. pyseismic_lsr-0.1.0/src/elias_fano.rs +283 -0
  49. pyseismic_lsr-0.1.0/src/inverted_index.rs +1069 -0
  50. pyseismic_lsr-0.1.0/src/inverted_index_wrapper.rs +315 -0
  51. pyseismic_lsr-0.1.0/src/json_utils.rs +65 -0
  52. pyseismic_lsr-0.1.0/src/lib.rs +66 -0
  53. pyseismic_lsr-0.1.0/src/pylib/mod.rs +419 -0
  54. pyseismic_lsr-0.1.0/src/quantized_summary.rs +177 -0
  55. pyseismic_lsr-0.1.0/src/space_usage.rs +68 -0
  56. pyseismic_lsr-0.1.0/src/sparse_dataset.rs +1591 -0
  57. pyseismic_lsr-0.1.0/src/topk_selectors/heap_faiss.rs +846 -0
  58. pyseismic_lsr-0.1.0/src/topk_selectors.rs +54 -0
  59. pyseismic_lsr-0.1.0/src/utils.rs +467 -0
pyseismic_lsr-0.1.0/.gitignore ADDED
@@ -0,0 +1,42 @@
1
+ # Generated by Cargo
2
+ # will have compiled files and executables
3
+ debug/
4
+ target/
5
+
6
+ # Remove Cargo.lock from gitignore if creating an executable, leave it for libraries
7
+ # More information here https://doc.rust-lang.org/cargo/guide/cargo-toml-vs-cargo-lock.html
8
+ Cargo.lock
9
+
10
+ # These are backup files generated by rustfmt
11
+ **/*.rs.bk
12
+
13
+ # MSVC Windows builds of rustc generate these, which store debugging information
14
+ *.pdb
15
+
16
+
17
+ # Output/groundtruth files
18
+ *.tsv
19
+
20
+
21
+ # Virtual environment
22
+ .venv/
23
+ venv/
24
+ env/
25
+
26
+ # Python cache files
27
+ __pycache__/
28
+ *.pyc
29
+ *.pyo
30
+ *.pyd
31
+
32
+
33
+ # Maturin build output
34
+ dist/
35
+ build/
36
+ *.egg-info/
37
+
38
+ # macOS
39
+ .DS_Store
40
+
41
+ # Windows
42
+ Thumbs.db
pyseismic_lsr-0.1.0/.pre-commit-config.yaml ADDED
@@ -0,0 +1,28 @@
1
+ #
2
+ # Precommit file
3
+ #
4
+ exclude: "^scripts"
5
+
6
+ default_stages: [commit]
7
+
8
+ repos:
9
+ - repo: https://github.com/doublify/pre-commit-rust
10
+ rev: v1.0
11
+ hooks:
12
+ - id: fmt
13
+ - id: cargo-check
14
+ - id: clippy
15
+ - id: test
16
+ - repo: https://github.com/pre-commit/pre-commit-hooks
17
+ rev: v4.6.0
18
+ hooks:
19
+ - id: check-added-large-files # prevents giant files from being committed.
20
+ - id: check-case-conflict # checks for files that would conflict in case-insensitive filesystems.
21
+ - id: check-merge-conflict # checks for files that contain merge conflict strings.
22
+ - id: end-of-file-fixer # ensures that a file is either empty, or ends with one newline.
23
+ - id: trailing-whitespace # trims trailing whitespace.
24
+ - repo: https://github.com/pre-commit/mirrors-prettier
25
+ rev: v4.0.0-alpha.8
26
+ hooks:
27
+ - id: prettier
28
+ files: \.(json|markdown|md|yaml|yml)$