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.

Sign up for GitHub

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

Jump to bottom

fix(datasets): Cleanup of dependency #822

Merged
merged 4 commits into from
Sep 9, 2024
Merged

fix(datasets): Cleanup of dependency #822

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3425b28
Update dependencies
DmitrySorokinQB Sep 3, 2024
1e8e49c
Unpin tables
DmitrySorokinQB Sep 6, 2024
54aae58
Merge branch 'main' into 747-kedro-datasets-cleanup-of-dependency-groups
DimedS Sep 6, 2024
25d93a0
Merge branch 'main' into 747-kedro-datasets-cleanup-of-dependency-groups
DimedS Sep 9, 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
28 changes: 19 additions & 9 deletions kedro-datasets/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,8 +33,9 @@ api = ["kedro-datasets[api-apidataset]"]
biosequence-biosequencedataset = ["biopython~=1.73"]
biosequence = ["kedro-datasets[biosequence-biosequencedataset]"]

dask-csvdataset = ["dask[dataframe]>=2021.10"]
dask-parquetdataset = ["dask[complete]>=2021.10", "triad>=0.6.7, <1.0"]
dask = ["kedro-datasets[dask-parquetdataset]"]
dask = ["kedro-datasets[dask-parquetdataset, dask-csvdataset]"]

databricks-managedtabledataset = ["kedro-datasets[spark-base,pandas-base,delta-base,hdfs-base,s3fs-base]"]
databricks = ["kedro-datasets[databricks-managedtabledataset]"]
Expand Down Expand Up @@ -92,7 +93,7 @@ pandas-featherdataset = ["kedro-datasets[pandas-base]"]
pandas-gbqtabledataset = ["kedro-datasets[pandas-base]", "pandas-gbq>=0.12.0"]
pandas-gbqquerydataset = ["kedro-datasets[pandas-base]", "pandas-gbq>=0.12.0"]
pandas-genericdataset = ["kedro-datasets[pandas-base]"]
pandas-hdfdataset = ["kedro-datasets[pandas-base]", "tables~=3.6"]
pandas-hdfdataset = ["kedro-datasets[pandas-base]", "tables>=3.6"]
pandas-jsondataset = ["kedro-datasets[pandas-base]"]
pandas-parquetdataset = ["kedro-datasets[pandas-base]", "pyarrow>=6.0"]
pandas-sqltabledataset = ["kedro-datasets[pandas-base]", "SQLAlchemy>=1.4, <3.0"]
Expand Down Expand Up @@ -127,9 +128,12 @@ plotly = ["kedro-datasets[plotly-htmldataset,plotly-jsondataset,plotly-plotlydat

polars-csvdataset = ["kedro-datasets[polars-base]"]
polars-eagerpolarsdataset = ["kedro-datasets[polars-base]", "pyarrow>=4.0", "xlsx2csv>=0.8.0", "deltalake >= 0.6.2"]
polars-genericdataset = ["kedro-datasets[polars-base]", "pyarrow>=4.0", "xlsx2csv>=0.8.0", "deltalake >= 0.6.2"]
polars-lazypolarsdataset = ["kedro-datasets[polars-base]", "pyarrow>=4.0", "deltalake >= 0.6.2"]
polars = ["kedro-datasets[polars-genericdataset]"]
polars = [
"""kedro-datasets[polars-csvdataset,\
polars-eagerpolarsdataset,\
polars-lazypolarsdataset]"""
]

redis-pickledataset = ["redis~=4.1"]
redis = ["kedro-datasets[redis-pickledataset]"]
Expand All @@ -140,8 +144,15 @@ snowflake = ["kedro-datasets[snowflake-snowparktabledataset]"]
spark-deltatabledataset = ["kedro-datasets[spark-base,hdfs-base,s3fs-base,delta-base]"]
spark-sparkdataset = ["kedro-datasets[spark-base,hdfs-base,s3fs-base]"]
spark-sparkhivedataset = ["kedro-datasets[spark-base,hdfs-base,s3fs-base]"]
spark-sparkjdbcdataset = ["kedro-datasets[spark-base,hdfs-base,s3fs-base]"]
spark = ["kedro-datasets[spark-deltatabledataset]"]
spark-sparkjdbcdataset = ["kedro-datasets[spark-base]"]
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

does jbdbcdataset not need the hdfs-base or s3fs-base anymore?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I believe JDBC is intended for relational databases and cannot be used with HDFS or S3FS?

spark-sparkstreamingdataset = ["kedro-datasets[spark-base,hdfs-base,s3fs-base]"]
spark = [
"""kedro-datasets[spark-deltatabledataset,\
spark-sparkdataset,\
spark-sparkhivedataset,\
spark-sparkjdbcdataset,\
spark-sparkstreamingdataset]"""
]

svmlight-svmlightdataset = ["scikit-learn>=1.0.2", "scipy~=1.7.3"]
svmlight = ["kedro-datasets[svmlight-svmlightdataset]"]
Expand Down Expand Up @@ -209,7 +220,7 @@ test = [
"ibis-framework[duckdb,examples]",
"import-linter[toml]==1.2.6",
"ipython>=7.31.1, <8.0",
"Jinja2<3.1.0",
"Jinja2<3.2.0",
"joblib>=0.14",
"jupyterlab>=3.0",
"jupyter~=1.0",
Expand Down Expand Up @@ -248,8 +259,7 @@ test = [
"scipy>=1.7.3",
"packaging",
"SQLAlchemy>=1.2",
"tables>=3.8.0; platform_system == 'Windows'", # Import issues with python 3.8 with pytables pinning to 3.8.0 fixes this https://github.com/PyTables/PyTables/issues/933#issuecomment-1555917593
"tables~=3.6; platform_system != 'Windows'",
"tables>=3.6",
"tensorflow-macos~=2.0; platform_system == 'Darwin' and platform_machine == 'arm64'",
"tensorflow~=2.0; platform_system != 'Darwin' or platform_machine != 'arm64'",
"triad>=0.6.7, <1.0",
Expand Down