easylink 0.1.17__py3-none-any.whl → 0.1.19__py3-none-any.whl

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 (56) hide show
  1. easylink/_version.py +1 -1
  2. easylink/cli.py +24 -3
  3. easylink/configuration.py +43 -36
  4. easylink/devtools/implementation_creator.py +71 -22
  5. easylink/implementation.py +88 -11
  6. easylink/implementation_metadata.yaml +177 -29
  7. easylink/pipeline.py +15 -6
  8. easylink/pipeline_schema.py +12 -13
  9. easylink/pipeline_schema_constants/__init__.py +4 -5
  10. easylink/pipeline_schema_constants/main.py +489 -0
  11. easylink/runner.py +11 -7
  12. easylink/step.py +89 -0
  13. easylink/steps/cascading/exclude_clustered.def +22 -0
  14. easylink/steps/cascading/exclude_clustered.py +76 -0
  15. easylink/steps/cascading/exclude_none.def +22 -0
  16. easylink/steps/cascading/exclude_none.py +76 -0
  17. easylink/steps/cascading/update_clusters_by_connected_components.def +22 -0
  18. easylink/steps/cascading/update_clusters_by_connected_components.py +101 -0
  19. easylink/steps/default/default_clusters_to_links.def +22 -0
  20. easylink/steps/default/default_clusters_to_links.py +91 -0
  21. easylink/steps/default/default_determining_exclusions.def +22 -0
  22. easylink/steps/default/default_determining_exclusions.py +81 -0
  23. easylink/steps/default/default_removing_records.def +22 -0
  24. easylink/steps/default/default_removing_records.py +59 -0
  25. easylink/steps/default/default_schema_alignment.def +22 -0
  26. easylink/steps/default/default_schema_alignment.py +53 -0
  27. easylink/steps/default/default_updating_clusters.def +22 -0
  28. easylink/steps/default/default_updating_clusters.py +67 -0
  29. easylink/steps/fastLink/fastLink_evaluating_pairs.R +136 -0
  30. easylink/steps/fastLink/fastLink_evaluating_pairs.def +21 -0
  31. easylink/steps/fastLink/fastLink_links_to_clusters.R +128 -0
  32. easylink/steps/fastLink/fastLink_links_to_clusters.def +21 -0
  33. easylink/steps/rl-dummy/canonicalizing_and_downstream_analysis/dummy_canonicalizing_and_downstream_analysis.def +22 -0
  34. easylink/steps/rl-dummy/canonicalizing_and_downstream_analysis/dummy_canonicalizing_and_downstream_analysis.py +42 -0
  35. easylink/steps/rl-dummy/input_data/create_input_files.ipynb +1433 -0
  36. easylink/steps/rl-dummy/input_data/input_file_1.parquet +0 -0
  37. easylink/steps/rl-dummy/input_data/input_file_2.parquet +0 -0
  38. easylink/steps/rl-dummy/input_data/known_clusters.parquet +0 -0
  39. easylink/steps/rl-dummy/pre-processing/dummy_pre-processing.def +22 -0
  40. easylink/steps/rl-dummy/pre-processing/dummy_pre-processing.py +59 -0
  41. easylink/steps/splink/splink_blocking_and_filtering.def +22 -0
  42. easylink/steps/splink/splink_blocking_and_filtering.py +130 -0
  43. easylink/steps/splink/splink_evaluating_pairs.def +22 -0
  44. easylink/steps/splink/splink_evaluating_pairs.py +164 -0
  45. easylink/steps/splink/splink_links_to_clusters.def +22 -0
  46. easylink/steps/splink/splink_links_to_clusters.py +63 -0
  47. easylink/utilities/data_utils.py +72 -0
  48. easylink/utilities/paths.py +4 -3
  49. easylink/utilities/validation_utils.py +509 -11
  50. {easylink-0.1.17.dist-info → easylink-0.1.19.dist-info}/METADATA +5 -1
  51. easylink-0.1.19.dist-info/RECORD +91 -0
  52. {easylink-0.1.17.dist-info → easylink-0.1.19.dist-info}/WHEEL +1 -1
  53. easylink-0.1.19.dist-info/licenses/LICENSE +28 -0
  54. easylink-0.1.17.dist-info/RECORD +0 -55
  55. {easylink-0.1.17.dist-info → easylink-0.1.19.dist-info}/entry_points.txt +0 -0
  56. {easylink-0.1.17.dist-info → easylink-0.1.19.dist-info}/top_level.txt +0 -0
@@ -1,5 +1,5 @@
1
1
  Wheel-Version: 1.0
2
- Generator: setuptools (80.7.0)
2
+ Generator: setuptools (80.9.0)
3
3
  Root-Is-Purelib: true
4
4
  Tag: py3-none-any
5
5
 
@@ -0,0 +1,28 @@
1
+ BSD 3-Clause License
2
+
3
+ Copyright (c) 2025, Institute for Health Metrics and Evaluation
4
+
5
+ Redistribution and use in source and binary forms, with or without
6
+ modification, are permitted provided that the following conditions are met:
7
+
8
+ 1. Redistributions of source code must retain the above copyright notice, this
9
+ list of conditions and the following disclaimer.
10
+
11
+ 2. Redistributions in binary form must reproduce the above copyright notice,
12
+ this list of conditions and the following disclaimer in the documentation
13
+ and/or other materials provided with the distribution.
14
+
15
+ 3. Neither the name of the copyright holder nor the names of its
16
+ contributors may be used to endorse or promote products derived from
17
+ this software without specific prior written permission.
18
+
19
+ THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
20
+ AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
21
+ IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
22
+ DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
23
+ FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
24
+ DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
25
+ SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
26
+ CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
27
+ OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
28
+ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
@@ -1,55 +0,0 @@
1
- easylink/__about__.py,sha256=2-oxCfu9t9yUJouLDwqYRZ0eii8kN25SxRzsawjWjho,440
2
- easylink/__init__.py,sha256=gGMcIVfiVnHtlDw5mZwhevcDb2wt-kuP6F64gnkFack,159
3
- easylink/_version.py,sha256=BzIjnki8Bz3evNWo6bjGxxpLhy_tN9MRYhtM0MnDiWs,23
4
- easylink/cli.py,sha256=mv9l9XHojfhDK4hpDeV1E4iensgt6zx2ovkGBQ8x9xk,9745
5
- easylink/configuration.py,sha256=lfm8ViUpr1-O-EovTjKZbAlIht2EBv3RndN1mzYbmDE,12565
6
- easylink/graph_components.py,sha256=zZDZXg5smReHO3ryQC4pao24wyKXzWDe6jS3C6fM2ak,13892
7
- easylink/implementation.py,sha256=XLSat6_IXFn-nH6X8AazmfWhDtTK4GtA7yiht9QLlQQ,11366
8
- easylink/implementation_metadata.yaml,sha256=0BQ_NIV29EtJ6G_wGD_-2OYPjYw2sNLAgCg2GbNwcuI,7662
9
- easylink/pipeline.py,sha256=5KOYH5HyJjVlFoBRKGLs2hn5mpC3tPYG_ux3T1qSV9k,17504
10
- easylink/pipeline_graph.py,sha256=9ysX4wAkA-WkUoo15jSLAErncybE4tJwznVx7N_kwIA,23922
11
- easylink/pipeline_schema.py,sha256=Q2sCpsC-F2W0yxVP7ufunowDepOBrRVENXOdap9J5iY,6921
12
- easylink/rule.py,sha256=NusEUtBxx18L7UCcgDi3KKooFxSUgyS4eisVM5aPqFE,16770
13
- easylink/runner.py,sha256=cbCo5_NvvulmjjAaBCG6qCmbtJiHK-7NuDvbngdU_PY,6675
14
- easylink/step.py,sha256=u1AMPrYGNVb3ZH6uB_U0dUeJvOeQ2MoVHdlC8k63AA8,85226
15
- easylink/devtools/implementation_creator.py,sha256=mkiQ9nhtQC3mhxcG8IyvejzSK0WSkwplCztPLXbpXXQ,16199
16
- easylink/images/spark_cluster/Dockerfile,sha256=3PHotbR4jdjVYRHOJ0VQW55b5Qd4tQ1pLLQMrTKWVA0,576
17
- easylink/images/spark_cluster/README.md,sha256=KdgSttZRplNNWqHn4K1GTsTIab3dTOSG4V99QPLxSp8,569
18
- easylink/pipeline_schema_constants/__init__.py,sha256=FUngnh80yfpr76j18iBVKSoR8-5zxQj_mW_muUMrafw,1324
19
- easylink/pipeline_schema_constants/development.py,sha256=XxcYYZDZM4IADp3eFPQCchD6-OtMp99GiyZBfSswzFo,12640
20
- easylink/pipeline_schema_constants/testing.py,sha256=UDmVVjI1SiDktMbJ2CrSb7amHSYNwhgqNkXhl4lYxQw,20459
21
- easylink/steps/dev/README.md,sha256=u9dZUggpY2Lf2qb-xkDLWWgHjcmi4osbQtzSNo4uklE,4549
22
- easylink/steps/dev/build-containers-local.sh,sha256=Wy3pfcyt7I-BNvHcr7ZXDe0g5Ihd00BIPqt9YuRbLeA,259
23
- easylink/steps/dev/build-containers-remote.sh,sha256=Hy-kaaXf-ta6n8SzOz_ahByjMY5T7J71MvzXRXDvQw8,271
24
- easylink/steps/dev/test.py,sha256=4iudKBD6CFz2CxbjSBUkc8LCWlMl-Nmw_rB35ZN6TrQ,6835
25
- easylink/steps/dev/input_data/create_input_files.ipynb,sha256=rHRUFXwTuNXWm8TyaZWFCOewZMDw1G6yiioF8h90erY,2123
26
- easylink/steps/dev/input_data/input_file_1.csv,sha256=mtu3_ldNTxS9PFtLsZzRspaCCuG_yLxhUdl2ZQFwqrE,88906
27
- easylink/steps/dev/input_data/input_file_1.parquet,sha256=Km8jRyfGNdq0MFdz_-bewlAc06cFjWn2dWQ7YKKGa5U,60399
28
- easylink/steps/dev/input_data/input_file_2.csv,sha256=YqKLZDC4d-aYN8Dh9OB6iQWWUKmvueu5CszckH1AApU,100016
29
- easylink/steps/dev/input_data/input_file_2.parquet,sha256=Vpo0sUqQ78qlWLRk8p303Nh89BVcK4uvXJljRGHmsWk,60392
30
- easylink/steps/dev/python_pandas/README.md,sha256=c_FbtkKKOTjt2R_LfHUo5lBga1qHiYkxLdQeewRr45g,977
31
- easylink/steps/dev/python_pandas/dummy_step.py,sha256=NvhLUZu40B3Xbj_S-chQ6IkYUPr6X2aGBxYUa3DqwmY,4362
32
- easylink/steps/dev/python_pandas/python_pandas.def,sha256=24cxwGF8Cqkv2a1zVsu94MfC_bAXBqAINLwfW2zyB_0,769
33
- easylink/steps/dev/python_pyspark/README.md,sha256=di29SAfcdTTpar7gdoJRLqKrL8DEfNeayYUyaywdhUg,1563
34
- easylink/steps/dev/python_pyspark/dummy_step.py,sha256=wxHHI3Uv8MTipKG2ffHbT_eL4JkoNpx49bJoErXumdc,5003
35
- easylink/steps/dev/python_pyspark/python_pyspark.def,sha256=j_RmVjspmXGOhJTr10ED13RYfbimgxRU3WVTL7VOIUQ,915
36
- easylink/steps/dev/r/README.md,sha256=dPjZdDTqcJsZCiwhddzlOj1ob0P7YocZUNFrLIGM1-0,1201
37
- easylink/steps/dev/r/dummy_step.R,sha256=1TWZY8CEkT6gavrulBxFsKbDSKJJjk0NtJrGH7TIikE,4975
38
- easylink/steps/dev/r/r-image.def,sha256=LrhXlt0C3k7d_VJWopRPEVARnFWSuq_oILlwo7g03bE,627
39
- easylink/steps/output_dir/dummy_step_1_for_output_dir_example.def,sha256=CkQVG-uDRQ9spAavdkZbhx2GD_fRsKZGELPrr8yltsc,550
40
- easylink/steps/output_dir/dummy_step_1_for_output_dir_example.py,sha256=dI0OWugE35ABLcSwsI-T3C4dvuPTKXwjE52dtSsCo8Y,428
41
- easylink/steps/output_dir/dummy_step_2_for_output_dir_example.def,sha256=9gShg1EDJEHZcz7Z5VfZ1A4Gpm9XQes8ezn6rAZDgDM,550
42
- easylink/steps/output_dir/dummy_step_2_for_output_dir_example.py,sha256=DMJW5TXjhELxhY4U9q2RpLjqxlS1YSosTGL2AfRnaZM,521
43
- easylink/utilities/__init__.py,sha256=0U33kbv4hoMfFQ_lh5hLwifxRPzOgkLkjKLYxmaK10g,196
44
- easylink/utilities/aggregator_utils.py,sha256=pqBog6kEX4MXBBMjQtHFlE5gEMqRWb5VFl64u0Lr__g,972
45
- easylink/utilities/data_utils.py,sha256=CcnM3u0_MQDQo3jMs3E4IK_rz8wAsFdJ674fZxYEFZg,4620
46
- easylink/utilities/general_utils.py,sha256=El1W0nn4P27sRBGotNQb-9du-Gbhk9ggSuu4vmGDfwo,4591
47
- easylink/utilities/paths.py,sha256=KM1GlnsAcKbUJrC4LZKpeJfPljxe_aXP1ZhVp43TYRA,924
48
- easylink/utilities/spark.smk,sha256=kGtpem7LfQc71tMh5WAYaqKnHQKFvcdhPQSdumOP70k,5799
49
- easylink/utilities/splitter_utils.py,sha256=UOz4hjkEPqaAz0RrDkDYYej79lLSaq0VVVSH_tF1z0o,3838
50
- easylink/utilities/validation_utils.py,sha256=rOIeQbbXXdsuL2hI0i2gApAWfiNJXMwYH4pmw8uLrGM,1867
51
- easylink-0.1.17.dist-info/METADATA,sha256=fl6OzaU74KHClV-dADXheUoKBMuIs8pUqLANelfaqBY,3477
52
- easylink-0.1.17.dist-info/WHEEL,sha256=A8Eltl-h0W-qZDVezsLjjslosEH_pdYC2lQ0JcbgCzs,91
53
- easylink-0.1.17.dist-info/entry_points.txt,sha256=OGMZDFltg3yMboT7XjJt3joiPhRfV_7jnREVtrAIQNU,51
54
- easylink-0.1.17.dist-info/top_level.txt,sha256=oHcOpcF_jDMWFiJRzfGQvuskENGDjSPC_Agu9Z_Xvik,9
55
- easylink-0.1.17.dist-info/RECORD,,