Rename import to zdatasets avoid HuggingFace conflict (#37)

.github/workflows/test.yml

@@ -55,12 +55,12 @@ jobs:
 
     - name: Code Quality Check
       run: |
-        poetry run black datasets --check
-        poetry run flake8 datasets
+        poetry run black zdatasets --check
+        poetry run flake8 zdatasets
 
     - name: Execute Python tests
       run: |
-        poetry run pytest datasets
+        poetry run pytest zdatasets
         pip install coverage==6.1.2
         coveragepy-lcov
 

.gitignore

@@ -20,7 +20,7 @@ eggs/
 parts/
 /share/
 /etc/
-datasets.egg-info/
+zdatasets.egg-info/
 .extends-cache
 GENERATED_VERSION
 versioner-*
@@ -91,7 +91,7 @@ man
 
 pip-selfcheck.json
 metastore_db/*
-datasets/tutorials/data/*
-datasets/tests/data/datastore/*
-datasets/tests/data/ds1/*
-datasets/tests/data/pandas.csv
+zdatasets/tutorials/data/*
+zdatasets/tests/data/datastore/*
+zdatasets/tests/data/ds1/*
+zdatasets/tests/data/pandas.csv

.pre-commit-config.yaml

@@ -25,4 +25,4 @@ repos:
       entry: pytest
       pass_filenames: false
       stages: [commit]
-      args: [datasets]
+      args: [zdatasets]

CONTRIBUTING.md

@@ -4,11 +4,11 @@
 
 ## Running Tests
 
-    poetry run pytest datasets
+    poetry run pytest zdatasets
 
 ### Run Single Test
 
-    poetry run pytest datasets -k search_item (e.g., name of test)
+    poetry run pytest zdatasets -k search_item (e.g., name of test)
 
        
 ### Pre-commit

MANIFEST.in

@@ -1,4 +1,4 @@
 # TODO: https://python-poetry.org/docs/pyproject#include-and-exclude
 include VERSION
 include README.md
-recursive-include datasets/docs/*
+recursive-include zdatasets/docs/*

README.md

@@ -3,7 +3,7 @@
 [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/zillow/datasets/main?urlpath=lab/tree/datasets/tutorials)
 
 
-Welcome to @datasets
+# Welcome to zdatasets
 ==================================================
 
 TODO
@@ -12,13 +12,13 @@ TODO
 import pandas as pd
 from metaflow import FlowSpec, step
 
-from datasets import Dataset, Mode
-from datasets.metaflow import DatasetParameter
-from datasets.plugins import BatchOptions
+from zdatasets import Dataset, Mode
+from zdatasets.metaflow import DatasetParameter
+from zdatasets.plugins import BatchOptions
 
 
 # Can also invoke from CLI:
-#  > python datasets/tutorials/0_hello_dataset_flow.py run \
+#  > python zdatasets/tutorials/0_hello_dataset_flow.py run \
 #    --hello_dataset '{"name": "HelloDataset", "mode": "READ_WRITE", \
 #    "options": {"type": "BatchOptions", "partition_by": "region"}}'
 class HelloDatasetFlow(FlowSpec):

docs/conf.py

@@ -197,7 +197,7 @@
 # html_search_scorer = 'scorer.js'
 
 # Output file base name for HTML help builder.
-htmlhelp_basename = "datasets-daldoc"
+htmlhelp_basename = "zdatasets-daldoc"
 
 # -- Options for LaTeX output ---------------------------------------------
 
@@ -215,7 +215,7 @@
 # Grouping the document tree into LaTeX files. List of tuples
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
-latex_documents = [("index", "datasets.tex", "datasets Documentation", "aiplat@zillow.com", "manual")]
+latex_documents = [("index", "zdatasets.tex", "zdatasets Documentation", "aiplat@zillow.com", "manual")]
 
 # The name of an image file (relative to this directory) to place at the top of
 # the title page.
@@ -242,7 +242,7 @@
 
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
-man_pages = [("index", "datasets", "datasets Documentation", ["aiplat@zillow.com"], 1)]
+man_pages = [("index", "zdatasets", "zdatasets Documentation", ["aiplat@zillow.com"], 1)]
 
 # If true, show URL addresses after external links.
 # man_show_urls = False
@@ -256,10 +256,10 @@
 texinfo_documents = [
     (
         "index",
-        "datasets",
-        "datasets Documentation",
+        "zdatasets",
+        "zdatasets Documentation",
         "",
-        "datasets",
+        "zdatasets",
         "One line description of project.",
         "Miscellaneous",
     )

docs/index.rst

@@ -1,8 +1,8 @@
-.. datasets documentation master file
+.. zdatasets documentation master file
    You can adapt this file completely to your liking, but it should at least
    contain the root `toctree` directive.
 
-Welcome to datasets
+Welcome to zdatasets
 ==================================================
 
 TODO
@@ -11,8 +11,8 @@ TODO
     import pandas as pd
     from metaflow import FlowSpec, step
 
-    from datasets.datasets_decorator import datasets
-    from datasets.mode import Mode
+    from zdatasets.datasets_decorator import datasets
+    from zdatasets.mode import Mode
 
 
     class HelloDatasetFlow(FlowSpec):

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "zdatasets"
-version = "0.2.5"
+version = "1.2.5"
 description = "Dataset SDK for consistent read/write [batch, online, streaming] data."
 classifiers = [
   "Development Status :: 2 - Pre-Alpha",
@@ -13,17 +13,17 @@ authors = ["Taleb Zeghmi"]
 readme = "README.md"
 
 [[tool.poetry.packages]]
-include = "datasets"
+include = "zdatasets"
 
 # https://packaging.python.org/guides/creating-and-discovering-plugins/
 [tool.poetry.plugins]
-[tool.poetry.plugins."datasets.plugins"]
-batch_dataset = "datasets.plugins:BatchDataset"
-flow_dataset = "datasets.plugins:FlowDataset"
-hive_dataset = "datasets.plugins:HiveDataset"
+[tool.poetry.plugins."zdatasets.plugins"]
+batch_dataset = "zdatasets.plugins:BatchDataset"
+flow_dataset = "zdatasets.plugins:FlowDataset"
+hive_dataset = "zdatasets.plugins:HiveDataset"
 
-[tool.poetry.plugins."datasets.executors"]
-metaflow_executor = "datasets.plugins:MetaflowExecutor"
+[tool.poetry.plugins."zdatasets.executors"]
+metaflow_executor = "zdatasets.plugins:MetaflowExecutor"
 
 [tool.poetry.dependencies]
 python = ">=3.8.0,<4"
@@ -57,8 +57,8 @@ spark = ["pyspark"]
 kubernetes = ["kubernetes"]
 
 [tool.isort]
-known_first_party = 'datasets'
-known_third_party = ["datasets", "numpy", "orbital_core", "pandas"]
+known_first_party = 'zdatasets'
+known_third_party = ["zdatasets", "numpy", "orbital_core", "pandas"]
 multi_line_output = 3
 lines_after_imports = 2
 force_grid_wrap = 0

setup.cfg

@@ -2,7 +2,7 @@
 # coverage.py
 [coverage:run]
 branch = true
-source = datasets
+source = zdatasets
 omit = **/tests/*
 
 [coverage:report]
@@ -27,8 +27,8 @@ exclude = .git,__pycache__,docs/*,doc/*,build,dist
 [tool:pytest]
 log_cli=true
 ;addopts = -vv -m "not spark"  --cov-report=term -rP
-;addopts = --cov=datasets --cov-report=term --cov-report=html --cov-report xml
-addopts = --cov=datasets --cov-config=setup.cfg --cov-report=term --cov-report=html --cov-report xml
+;addopts = --cov=zdatasets --cov-report=term --cov-report=html --cov-report xml
+addopts = --cov=zdatasets --cov-config=setup.cfg --cov-report=term --cov-report=html --cov-report xml
 
 markers =
     spark: marks tests as slow (deselect with '-m "not slow"')

zdatasets/__init__.py

@@ -0,0 +1,18 @@
+# isort: skip_file
+# flake8: noqa: F401
+from zdatasets.mode import Mode
+from zdatasets.dataset_plugin import DatasetPlugin
+
+
+from zdatasets.context import Context
+from zdatasets.datasets_decorator import dataset
+
+
+from zdatasets import plugins
+from zdatasets.plugins.batch.hive_dataset import HiveDataset
+
+from zdatasets._typing import ColumnNames, DataFrameType
+
+from zdatasets.utils import SecretFetcher
+
+Dataset = DatasetPlugin.factory

datasets/dataset_plugin.py → zdatasets/dataset_plugin.py

@@ -6,9 +6,9 @@
 from dataclasses import dataclass
 from typing import Callable, Dict, Iterable, Optional, Tuple, Type, Union
 
-from datasets._typing import ColumnNames, DataFrameType
-from datasets.context import Context
-from datasets.utils.case_utils import is_upper_pascal_case
+from zdatasets._typing import ColumnNames, DataFrameType
+from zdatasets.context import Context
+from zdatasets.utils.case_utils import is_upper_pascal_case
 
 from .mode import Mode
 from .program_executor import ProgramExecutor

datasets/datasets_decorator.py → zdatasets/datasets_decorator.py

@@ -2,10 +2,10 @@
 import keyword
 from typing import Callable, Dict, Optional, Union
 
-from datasets._typing import ColumnNames
-from datasets.dataset_plugin import Context, DatasetPlugin, StorageOptions
-from datasets.mode import Mode
-from datasets.utils.case_utils import pascal_to_snake_case
+from zdatasets._typing import ColumnNames
+from zdatasets.dataset_plugin import Context, DatasetPlugin, StorageOptions
+from zdatasets.mode import Mode
+from zdatasets.utils.case_utils import pascal_to_snake_case
 
 
 def dataset(

datasets/metaflow.py → zdatasets/metaflow.py

@@ -6,12 +6,12 @@
 from metaflow._vendor.click import ParamType
 from metaflow.parameters import Parameter
 
-from datasets import DataFrameType
-from datasets._typing import ColumnNames
-from datasets.context import Context
-from datasets.dataset_plugin import DatasetPlugin, StorageOptions
-from datasets.mode import Mode
-from datasets.utils.secret_fetcher import SecretFetcher
+from zdatasets import DataFrameType
+from zdatasets._typing import ColumnNames
+from zdatasets.context import Context
+from zdatasets.dataset_plugin import DatasetPlugin, StorageOptions
+from zdatasets.mode import Mode
+from zdatasets.utils.secret_fetcher import SecretFetcher
 
 
 class _DatasetTypeClass(ParamType):

zdatasets/plugins/__init__.py

@@ -0,0 +1,10 @@
+# isort: skip_file
+# flake8: noqa: F401
+from zdatasets.plugins.executors.metaflow_executor import MetaflowExecutor
+from zdatasets.plugins.batch.batch_dataset import BatchDataset, BatchOptions
+from zdatasets.plugins.batch.flow_dataset import FlowDataset, FlowOptions
+from zdatasets.plugins.batch.hive_dataset import HiveDataset, HiveOptions
+from zdatasets.plugins.register_plugins import register
+
+
+register()

datasets/plugins/batch/batch_base_plugin.py → zdatasets/plugins/batch/batch_base_plugin.py

@@ -12,11 +12,11 @@
     Union,
 )
 
-from datasets._typing import ColumnNames, DataFrameType
-from datasets.dataset_plugin import DatasetPlugin, StorageOptions
-from datasets.exceptions import InvalidOperationException
-from datasets.mode import Mode
-from datasets.utils.case_utils import pascal_to_snake_case
+from zdatasets._typing import ColumnNames, DataFrameType
+from zdatasets.dataset_plugin import DatasetPlugin, StorageOptions
+from zdatasets.exceptions import InvalidOperationException
+from zdatasets.mode import Mode
+from zdatasets.utils.case_utils import pascal_to_snake_case
 
 
 _logger = logging.getLogger(__name__)

datasets/plugins/batch/batch_dataset.py → zdatasets/plugins/batch/batch_dataset.py

@@ -3,12 +3,12 @@
 
 import pandas as pd
 
-from datasets import Mode
-from datasets._typing import ColumnNames, DataFrameType
-from datasets.context import Context
-from datasets.dataset_plugin import DatasetPlugin
-from datasets.exceptions import InvalidOperationException
-from datasets.plugins.batch.batch_base_plugin import (
+from zdatasets import Mode
+from zdatasets._typing import ColumnNames, DataFrameType
+from zdatasets.context import Context
+from zdatasets.dataset_plugin import DatasetPlugin
+from zdatasets.exceptions import InvalidOperationException
+from zdatasets.plugins.batch.batch_base_plugin import (
     BatchBasePlugin,
     BatchOptions,
 )

datasets/plugins/batch/flow_dataset.py → zdatasets/plugins/batch/flow_dataset.py

@@ -1,11 +1,11 @@
 from dataclasses import dataclass
 from typing import TYPE_CHECKING, Optional, Tuple, Union
 
-from datasets._typing import ColumnNames
-from datasets.context import Context
-from datasets.dataset_plugin import DatasetPlugin, StorageOptions
-from datasets.mode import Mode
-from datasets.plugins import BatchDataset
+from zdatasets._typing import ColumnNames
+from zdatasets.context import Context
+from zdatasets.dataset_plugin import DatasetPlugin, StorageOptions
+from zdatasets.mode import Mode
+from zdatasets.plugins import BatchDataset
 
 
 if TYPE_CHECKING: