datadepot 0.0.35.post0__tar.gz

datadepot-0.0.35.post0/.github/workflows/release.yaml

@@ -0,0 +1,33 @@
+name: Release
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+      contents: read
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.11
+
+      - name: Install build tools
+        run: pip install build setuptools_scm wheel
+
+      - name: Build package
+        run: python -m build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

datadepot-0.0.35.post0/.gitignore

@@ -0,0 +1,6 @@
+# Ignore build output
+build/
+dist/
+dsf/__pycache__/
+*.egg-info/
+*.egg

datadepot-0.0.35.post0/LICENSE

@@ -0,0 +1,21 @@
+Copyright (c) 2025 Jeroen van Raak
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

datadepot-0.0.35.post0/MANIFEST.in

@@ -0,0 +1,3 @@
+include README.md
+include LICENSE
+recursive-include dsf/data *

datadepot-0.0.35.post0/PKG-INFO

@@ -0,0 +1,107 @@
+Metadata-Version: 2.4
+Name: datadepot
+Version: 0.0.35.post0
+Summary: The datadepot package provides a collection of datasets used in the book Data Science Foundations and Machine Learning with Python.
+Author-email: Jeroen van Raak <j.j.f.vanraak@uva.nl>
+License: Copyright (c) 2025 Jeroen van Raak
+        
+        MIT License
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Project-URL: Homepage, https://github.com/vanraak/datadepot
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=1.5
+Requires-Dist: numpy>=1.21
+Dynamic: license-file
+
+# Package `datadepot`
+
+
+**Package ‘datadepot’**
+
+**Title** \`\`DataDepot’’
+
+**Description**
+
+The **datadepot** package provides a collection of datasets used in the book `Data Science Foundations and Machine Learning with Python`.
+
+**URL** <https://github.com/vanraak/datadepot>
+
+**Depends** Python (\>= 3.8) and Pandas (\>2.0)
+
+**License** GPL (\>= 2)
+
+**Repository** Pypi
+
+**Authors** Jeroen van Raak and Reza Mohammadi
+
+**Maintainer** Jeroen van Raak, <j.j.f.vanraak@uva.nl>
+
+**NeedsCompilation** no
+
+**Installation**
+
+    pip install datadepot
+
+**Usage**
+
+    import datadepot
+    df=datadepot.load('<dataset>')
+
+Replace <dataset> with the name of the dataset, such as ‘bank’, ‘house’, or ‘churn’.
+
+**Example**
+
+    df=datadepot.load('bank') # Load the bank dataset.
+
+**Datasets**
+
+The following datasets are included:
+
+- adult
+- advertising
+- bank
+- caravan
+- cereal
+- churn
+- churn_ibm
+- churn_tel
+- corona
+- diamonds
+- drug
+- gapminder
+- house
+- house_price
+- insurance
+- marketing
+- mpg
+- red_wines
+- risk
+- white_wines
+
+**Documentation**
+
+The full documentation is available at:
+<https://github.com/vanraak/datadepot/blob/main/README.pdf>

datadepot-0.0.35.post0/README.md

@@ -0,0 +1,69 @@
+# Package `datadepot`
+
+
+**Package ‘datadepot’**
+
+**Title** \`\`DataDepot’’
+
+**Description**
+
+The **datadepot** package provides a collection of datasets used in the book `Data Science Foundations and Machine Learning with Python`.
+
+**URL** <https://github.com/vanraak/datadepot>
+
+**Depends** Python (\>= 3.8) and Pandas (\>2.0)
+
+**License** GPL (\>= 2)
+
+**Repository** Pypi
+
+**Authors** Jeroen van Raak and Reza Mohammadi
+
+**Maintainer** Jeroen van Raak, <j.j.f.vanraak@uva.nl>
+
+**NeedsCompilation** no
+
+**Installation**
+
+    pip install datadepot
+
+**Usage**
+
+    import datadepot
+    df=datadepot.load('<dataset>')
+
+Replace <dataset> with the name of the dataset, such as ‘bank’, ‘house’, or ‘churn’.
+
+**Example**
+
+    df=datadepot.load('bank') # Load the bank dataset.
+
+**Datasets**
+
+The following datasets are included:
+
+- adult
+- advertising
+- bank
+- caravan
+- cereal
+- churn
+- churn_ibm
+- churn_tel
+- corona
+- diamonds
+- drug
+- gapminder
+- house
+- house_price
+- insurance
+- marketing
+- mpg
+- red_wines
+- risk
+- white_wines
+
+**Documentation**
+
+The full documentation is available at:
+<https://github.com/vanraak/datadepot/blob/main/README.pdf>

datadepot-0.0.35.post0/datadepot/__init__.py

@@ -0,0 +1,25 @@
+from ._version import __version__
+from .datasets import load, datasets, dataset_table
+
+
+def version():
+    """Prints DataDepot package version."""
+    print(f"Version: {__version__}")
+
+
+__all__ = ["load", "datasets", "dataset_table"]
+
+__doc__ = f"""
+DataDepot package: Example datasets for Python users
+
+Available datasets:
+{dataset_table()}
+
+# Load a dataset from the DataDepot package as a pandas DataFrame
+
+>>> import datadepot
+>>> df = datadepot.load('<dataset_name>')  # Load a dataset as a pandas DataFrame
+
+# Show the version of the DataDepot library:
+>>> datadepot.version()  # DataDepot version {__version__}
+"""

datadepot-0.0.35.post0/datadepot/_version.py

@@ -0,0 +1,34 @@
+# file generated by setuptools-scm
+# don't change, don't track in version control
+
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple
+    from typing import Union
+
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+    COMMIT_ID = Union[str, None]
+else:
+    VERSION_TUPLE = object
+    COMMIT_ID = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+commit_id: COMMIT_ID
+__commit_id__: COMMIT_ID
+
+__version__ = version = '0.0.35.post0'
+__version_tuple__ = version_tuple = (0, 0, 35, 'post0')
+
+__commit_id__ = commit_id = 'g34844a160'

datadepot-0.0.35.post0/datadepot/datasets.py

@@ -0,0 +1,62 @@
+import pandas as pd
+import importlib.resources
+
+datasets = {
+    "adult": "Adult census income dataset.",
+    "advertising": "The dataset from an organization’s social media ad campaign.",
+    "bank": "Bank marketing dataset.",
+    "caravan": "Caravan insurance dataset.",
+    "cereal": "Cereal nutrition dataset.",
+    "churn": "Credit card churn dataset.",
+    "churn_ibm": "Telecom churn dataset (IBM).",
+    "churn_tel": "Telecom churn dataset (MLC).",
+    "corona": "COVID-19 related dataset.",
+    "diamonds": "Diamonds dataset.",
+    "drug": "Drug classification dataset.",
+    "gapminder": "Gapminder dataset.",
+    "house": "House sales dataset.",
+    "house_price": "House price dataset.",
+    "insurance": "Insurance dataset.",
+    "marketing": "Marketing campaigns dataset.",
+    "mpg": "Auto MPG dataset.",
+    "red_wines": "Red wine quality dataset.",
+    "risk": "Risk analysis dataset.",
+    "transcripts": "Earnings conference call transcripts",
+    "white_wines": "White wine quality dataset.",
+}
+
+
+def load(name: str) -> pd.DataFrame:
+    name = name.strip().lower().replace("_", "")  # remove underscores
+    # Build a lookup dict: stripped keys -> canonical keys
+    lookup = {k.replace("_", ""): k for k in datasets.keys()}
+
+    if name in lookup:
+        canonical_name = lookup[name]  # get the actual dataset key (with underscore)
+        try:
+            with (
+                importlib.resources.files("datadepot.data")
+                .joinpath(f"{canonical_name}.pkl")
+                .open("rb") as f
+            ):
+                return pd.read_pickle(f)
+        except Exception as e:
+            raise RuntimeError(f"Failed to load dataset '{canonical_name}': {e}")
+    else:
+        raise ValueError(f"Dataset '{name}' does not exist.")
+
+
+def dataset_table() -> str:
+    """Generate a dynamic-width table of datasets."""
+    name_width = max(len(name) for name in datasets) + 2
+    desc_width = max(len(desc) for desc in datasets) + 2
+
+    table_lines = [
+        f"{'Dataset':<{name_width}} {'Description':<{desc_width}}",
+        "-" * (name_width + desc_width),
+    ]
+
+    for name, desc in datasets.items():
+        table_lines.append(f"{name:<{name_width}} {desc:<{desc_width}}")
+
+    return "\n".join(table_lines)

datadepot-0.0.35.post0/datadepot.egg-info/PKG-INFO

@@ -0,0 +1,107 @@
+Metadata-Version: 2.4
+Name: datadepot
+Version: 0.0.35.post0
+Summary: The datadepot package provides a collection of datasets used in the book Data Science Foundations and Machine Learning with Python.
+Author-email: Jeroen van Raak <j.j.f.vanraak@uva.nl>
+License: Copyright (c) 2025 Jeroen van Raak
+        
+        MIT License
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Project-URL: Homepage, https://github.com/vanraak/datadepot
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=1.5
+Requires-Dist: numpy>=1.21
+Dynamic: license-file
+
+# Package `datadepot`
+
+
+**Package ‘datadepot’**
+
+**Title** \`\`DataDepot’’
+
+**Description**
+
+The **datadepot** package provides a collection of datasets used in the book `Data Science Foundations and Machine Learning with Python`.
+
+**URL** <https://github.com/vanraak/datadepot>
+
+**Depends** Python (\>= 3.8) and Pandas (\>2.0)
+
+**License** GPL (\>= 2)
+
+**Repository** Pypi
+
+**Authors** Jeroen van Raak and Reza Mohammadi
+
+**Maintainer** Jeroen van Raak, <j.j.f.vanraak@uva.nl>
+
+**NeedsCompilation** no
+
+**Installation**
+
+    pip install datadepot
+
+**Usage**
+
+    import datadepot
+    df=datadepot.load('<dataset>')
+
+Replace <dataset> with the name of the dataset, such as ‘bank’, ‘house’, or ‘churn’.
+
+**Example**
+
+    df=datadepot.load('bank') # Load the bank dataset.
+
+**Datasets**
+
+The following datasets are included:
+
+- adult
+- advertising
+- bank
+- caravan
+- cereal
+- churn
+- churn_ibm
+- churn_tel
+- corona
+- diamonds
+- drug
+- gapminder
+- house
+- house_price
+- insurance
+- marketing
+- mpg
+- red_wines
+- risk
+- white_wines
+
+**Documentation**
+
+The full documentation is available at:
+<https://github.com/vanraak/datadepot/blob/main/README.pdf>

datadepot-0.0.35.post0/datadepot.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+.gitignore
+LICENSE
+MANIFEST.in
+README.md
+README.pdf
+pyproject.toml
+.github/workflows/release.yaml
+datadepot/__init__.py
+datadepot/_version.py
+datadepot/datasets.py
+datadepot.egg-info/PKG-INFO
+datadepot.egg-info/SOURCES.txt
+datadepot.egg-info/dependency_links.txt
+datadepot.egg-info/requires.txt
+datadepot.egg-info/top_level.txt

datadepot-0.0.35.post0/datadepot.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

datadepot-0.0.35.post0/datadepot.egg-info/requires.txt

@@ -0,0 +1,2 @@
+pandas>=1.5
+numpy>=1.21

datadepot-0.0.35.post0/datadepot.egg-info/top_level.txt

@@ -0,0 +1 @@
+datadepot

datadepot-0.0.35.post0/pyproject.toml

@@ -0,0 +1,38 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel", "setuptools_scm"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "datadepot"
+dynamic = ["version"]
+description = "The datadepot package provides a collection of datasets used in the book Data Science Foundations and Machine Learning with Python."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { file = "LICENSE" }
+dependencies = [
+    "pandas>=1.5",
+    "numpy>=1.21",
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+authors = [
+    { name = "Jeroen van Raak", email = "j.j.f.vanraak@uva.nl" }
+]
+
+urls = { "Homepage" = "https://github.com/vanraak/datadepot" }
+
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["datadepot*"]
+exclude = ["csv", "pickle", "sourcedata"]
+
+[tool.setuptools_scm]
+version_scheme = "post-release"
+local_scheme = "no-local-version"
+write_to = "datadepot/_version.py"

datadepot-0.0.35.post0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+