Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Build transforms wheel #493

Merged
merged 35 commits into from
Sep 24, 2024
Merged
Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
35 commits
Select commit Hold shift + click to select a range
ddedccc
pytest for most but faild for pdf2parquet and resize
touma-I Aug 8, 2024
134c2c2
header_cleanser available for non Darwin installation
touma-I Aug 9, 2024
e227b9d
Added make file with unit tests for all transforms
touma-I Aug 10, 2024
d155a24
Build and deploy pypi package using makefile
touma-I Aug 12, 2024
fe0d380
remove pandas and keep pandas=2.2.2
touma-I Aug 13, 2024
b1e2707
Merge branch 'dev' into build-transforms-wheel
touma-I Aug 21, 2024
d96477a
added PII and HTML2Parquet
touma-I Aug 21, 2024
3c57682
Merge branch 'dev' into build-transforms-wheel
touma-I Aug 28, 2024
35c7e60
Update with latest available transforms
touma-I Aug 28, 2024
d66df27
restructure things to be able to test and build independently
touma-I Aug 28, 2024
a4f7e0a
publish dev2 for python
touma-I Aug 30, 2024
0af03cc
finish testing and publish dev2 python and ray packages:
touma-I Aug 30, 2024
65f4ac4
merge with dev
touma-I Sep 8, 2024
703ebe0
try different dependencies in attempt to resolve conflicts
touma-I Sep 9, 2024
d54708a
added pii redactor
touma-I Sep 11, 2024
e1309e5
Merge branch 'dev' into build-transforms-wheel
touma-I Sep 11, 2024
109ea29
updated with latest release for pdf2parquet
touma-I Sep 11, 2024
a874358
fixes for dev3 release
touma-I Sep 11, 2024
440975d
simplify test-src by using exiting targets
touma-I Sep 12, 2024
10c9159
Merge branch 'dev' into build-transforms-wheel
touma-I Sep 23, 2024
db60963
renamed requirement files
touma-I Sep 23, 2024
9bb36c5
use - in transform library name
touma-I Sep 23, 2024
ee63628
update requirements.txt files as appropriate when setting versions
touma-I Sep 23, 2024
346b82e
Added readme file to test, build and publish package to pypi
touma-I Sep 23, 2024
071836e
fix typos and removed double quotes
touma-I Sep 23, 2024
07b827f
Apply version update to all transforms
touma-I Sep 23, 2024
0369842
generate workflow for packaging folder
touma-I Sep 23, 2024
aa297e0
fix ededup dummy version
daw3rd Sep 23, 2024
32578d5
fix filter/spark dummy version
daw3rd Sep 23, 2024
3b52ecf
updated requirements based on latest release for docling
touma-I Sep 23, 2024
eb499de
Merge branch 'build-transforms-wheel' of github.com:IBM/data-prep-kit…
touma-I Sep 23, 2024
8d69b71
fix missing steps
touma-I Sep 23, 2024
d27a1c2
-sUpdate makefile to build and publish wheels
touma-I Sep 23, 2024
e155d2c
update based on reviewers comments
touma-I Sep 24, 2024
33b8853
fix packaging test workflow paths
daw3rd Sep 24, 2024
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 45 additions & 0 deletions transforms/packaging/python/pyproject.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,45 @@
[project]
name = "data_prep_toolkit_transforms"
version = "0.2.1.dev0"
requires-python = ">=3.10,<3.12"
keywords = ["transforms", "data preprocessing", "data preparation", "llm", "generative", "ai", "fine-tuning", "llmapps" ]
description = "Data Preparation Toolkit Transforms"
license = {text = "Apache-2.0"}
readme = {file = "README.md", content-type = "text/markdown"}
authors = [
{ name = "Maroun Touma", email = "[email protected]" },
]

dependencies = [
## Code
"dpk_code_quality_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/code/code_quality/python",
daw3rd marked this conversation as resolved.
Show resolved Hide resolved
"dpk_code2parquet_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/code/code2parquet/python",
"dpk_header_cleanser_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/code/header_cleanser/python ; platform_system != 'Darwin'",
"dpk_malware_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/code/malware/python",
"dpk_proglang_select_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/code/proglang_select/python",
## Language
"dpk_doc_chunk_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/language/doc_chunk/python",
"dpk_doc_quality_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/language/doc_quality/python",
"dpk_lang_id_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/language/lang_id/python",
"dpk_pdf2parquet_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/language/pdf2parquet/python",
"dpk_text_encoder_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/language/text_encoder/python",
## Universal
"dpk_ededup_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/universal/ededup/python",
"dpk_filter_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/universal/filter/python",
"dpk_resize_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/universal/resize/python",
"dpk_tokenization_transform_python @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/universal/tokenization/python",
]

[project_urls]
Repository = "https://github.com/IBM/data-prep-kit"
Issues = "https://github.com/IBM/data-prep-kit/issues"
Documentation = "https://ibm.github.io/data-prep-kit/"

[build-system]
requires = ["setuptools>=68.0.0", "wheel", "setuptools_scm[toml]>=7.1.0"]
build-backend = "setuptools.build_meta"

[tool.setuptools.packages]
find = {namespaces = false} # Disable implicit namespaces


50 changes: 50 additions & 0 deletions transforms/packaging/ray/pyproject.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,50 @@
[project]
name = "data_prep_toolkit_transforms_ray"
version = "0.2.1.dev0"
requires-python = ">=3.10,<3.12"
keywords = ["transforms", "data preprocessing", "data preparation", "llm", "generative", "ai", "fine-tuning", "llmapps" ]
description = "Data Preparation Toolkit Transforms"
license = {text = "Apache-2.0"}
readme = {file = "README.md", content-type = "text/markdown"}
authors = [
{ name = "Maroun Touma", email = "[email protected]" },
]


dependencies = [
## Code
"dpk_code_quality_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/code/code_quality/ray",
"dpk_code2parquet_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/code/code2parquet/ray",
"dpk_header_cleanser_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/code/header_cleanser/ray ; platform_system != 'Darwin'",
"dpk_malware_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/code/malware/ray",
"dpk_proglang_select_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/code/proglang_select/ray",
"dpk_repo_level_order_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/code/repo_level_ordering/ray",
## Language
"dpk_doc_chunk_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/language/doc_chunk/ray",
"dpk_doc_quality_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/language/doc_quality/ray",
"dpk_lang_id_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/language/lang_id/ray",
"dpk_pdf2parquet_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/language/pdf2parquet/ray",
"dpk_text_encoder_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/language/text_encoder/ray",
## Universal
"dpk_docid_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/universal/doc_id/ray",
"dpk_ededup_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/universal/ededup/ray",
"dpk_fdedup_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/universal/fdedup/ray",
"dpk_filter_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/universal/filter/ray",
"dpk_resize_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/universal/resize/ray",
"dpk_profiler_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/universal/profiler/ray",
"dpk_tokenization_transform_ray @ git+https://github.com/IBM/data-prep-kit.git#subdirectory=transforms/universal/tokenization/ray",
]

[project_urls]
Repository = "https://github.com/IBM/data-prep-kit"
Issues = "https://github.com/IBM/data-prep-kit/issues"
Documentation = "https://ibm.github.io/data-prep-kit/"

[build-system]
requires = ["setuptools>=68.0.0", "wheel", "setuptools_scm[toml]>=7.1.0"]
build-backend = "setuptools.build_meta"

[tool.setuptools.packages]
find = {namespaces = false} # Disable implicit namespaces