Add release pipeline (#11)

* Add release pipeline * Improve `pyproject.toml` * Remove url property
jessegrabowski · Aug 30, 2024 · 4ca0ea7 · 4ca0ea7
1 parent 251adbd
commit 4ca0ea7
Show file tree

Hide file tree

Showing 14 changed files with 894 additions and 128 deletions.
diff --git a/.gitattributes b/.gitattributes
@@ -0,0 +1 @@
+tsdisagg/_version.py export-subst
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
@@ -0,0 +1,47 @@
+name: release-pipeline
+
+on:
+  release:
+    types:
+      - created
+
+jobs:
+  release-job:
+    runs-on: ubuntu-latest
+    env:
+      PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}
+    steps:
+    - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: 3.11
+    - name: Install release tooling
+      run: |
+        pip install twine wheel numpy setuptools versioneer
+    - name: Build package
+      run: |
+        python setup.py sdist bdist_wheel
+    - name: Check version number match
+      run: |
+        echo "GITHUB_REF: ${GITHUB_REF}"
+        # The GITHUB_REF should be something like "refs/tags/v1.2.3"
+        # Make sure the package version is the same as the tag
+        grep -Rq "^Version: ${GITHUB_REF:11}$" tsdisagg.egg-info/PKG-INFO
+    - name: Publish to PyPI
+      run: |
+        twine check dist/*
+        twine upload --repository pypi --username __token__ --password ${PYPI_TOKEN} dist/*
+  test-install-job:
+    needs: release-job
+    runs-on: ubuntu-latest
+    steps:
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: 3.7
+    - name: Give PyPI a chance to update the index
+      run: sleep 240
+    - name: Install from PyPI
+      run: |
+        pip install tsdisagg==${GITHUB_REF:11}
diff --git a/Examples.ipynb b/Examples.ipynb
@@ -82,21 +82,15 @@
     "sales_a.columns = [\"sales\"]\n",
     "\n",
     "exports_q = pd.read_csv(\"tests/data/exports_q.csv\", index_col=0)\n",
-    "exports_q.index = pd.date_range(\n",
-    "    start=\"1972-01-01\", freq=\"QS\", periods=exports_q.shape[0]\n",
-    ")\n",
+    "exports_q.index = pd.date_range(start=\"1972-01-01\", freq=\"QS\", periods=exports_q.shape[0])\n",
     "exports_q.columns = [\"exports\"]\n",
     "\n",
     "exports_m = pd.read_csv(\"tests/data/exports_m.csv\", index_col=0)\n",
-    "exports_m.index = pd.date_range(\n",
-    "    start=\"1972-01-01\", freq=\"MS\", periods=exports_m.shape[0]\n",
-    ")\n",
+    "exports_m.index = pd.date_range(start=\"1972-01-01\", freq=\"MS\", periods=exports_m.shape[0])\n",
     "exports_m.columns = [\"exports\"]\n",
     "\n",
     "imports_q = pd.read_csv(\"tests/data/imports_q.csv\", index_col=0)\n",
-    "imports_q.index = pd.date_range(\n",
-    "    start=\"1972-01-01\", freq=\"QS-OCT\", periods=imports_q.shape[0]\n",
-    ")\n",
+    "imports_q.index = pd.date_range(start=\"1972-01-01\", freq=\"QS-OCT\", periods=imports_q.shape[0])\n",
     "imports_q.columns = [\"imports\"]"
    ]
   },

diff --git a/conda_envs/tsdisagg_test.yml b/conda_envs/tsdisagg_test.yml
@@ -24,3 +24,4 @@ dependencies:
   - pytest
   - pytest-cov
   - hypothesis
+  - versioneer
diff --git a/pyproject.toml b/pyproject.toml
@@ -1,3 +1,67 @@
+[project]
+name = "tsdisagg"
+dynamic = ['version']
+description = "Statistical tools for converting low frequency time series data to higher frequencies"
+license = { file = 'LICENSE'}
+authors = [{name = "Jesse Grabowski", email="[email protected]"}]
+classifiers = [
+    "License :: OSI Approved :: MIT License",
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering",
+    "Topic :: Scientific/Engineering :: Mathematics"
+]
+
+keywords = [
+  "time series",
+  "decomposition",
+  "datetime",
+  "econometrics"
+]
+
+dependencies = [
+    "numpy",
+    "pandas >= 2.2.0",
+    "scipy"
+]
+
+[project.urls]
+Repository = "https://github.com/jessegrabowski/tsdisagg.git"
+Issues = "https://github.com/jessegrabowski/tsdisagg/issues"
+
+
+[project.optional-dependencies]
+dev = [
+    "pre-commit",
+    "pytest",
+    "pytest-cov",
+    "versioneer"
+]
+
+
+[build-system]
+requires = [
+    "numpy",
+    "setuptools",
+    "versioneer[toml]",
+]
+build-backend = "setuptools.build_meta"
+
+
+[tool.versioneer]
+VCS = "git"
+style = "pep440"
+versionfile_source = "tsdisagg/_version.py"
+versionfile_build = "tsdisagg/_version.py"
+tag_prefix = 'v'
+
+[tool.setuptools]
+py-modules = ['tsdisagg']
+
 [tool.pytest.ini_options]
 minversion = "6.0"
 xfail_strict = true
@@ -13,6 +77,11 @@ exclude_lines = [
   "if TYPE_CHECKING:",
 ]
 
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+extend-exclude = ["tsdisagg/_version.py", "setup.py"]
+
 
 [tool.ruff.lint]
 select = ["D", "E", "F", "I", "UP", "W", "RUF"]
@@ -46,5 +115,6 @@ ignore = [
   "D417",
 ]
 
+
 [tool.ruff.lint.isort]
 lines-between-types = 1
diff --git a/setup.cfg b/setup.cfg
diff --git a/setup.py b/setup.py
@@ -1,3 +1,19 @@
-from setuptools import setup
+from setuptools import find_packages, setup
+from setuptools.dist import Distribution
 
-setup()
+import versioneer
+
+dist = Distribution()
+dist.parse_config_files()
+
+
+NAME: str = dist.get_name()  # type: ignore
+
+
+if __name__ == "__main__":
+    setup(
+        name=NAME,
+        version=versioneer.get_version(),
+        cmdclass=versioneer.get_cmdclass(),
+        packages=find_packages(exclude=["tests*"]),
+    )
diff --git a/tests/test_disaggregation.py b/tests/test_disaggregation.py
@@ -1,6 +1,6 @@
 import unittest
 
-from typing import Callable
+from collections.abc import Callable
 
 import numpy as np
 import pandas as pd
@@ -46,9 +46,7 @@ def generate_random_index_pair(
         A tuple containing the low-frequency and high-frequency DatetimeIndexes.
     """
     if start is None:
-        start = pd.Timestamp.now().normalize() - pd.DateOffset(
-            years=np.random.randint(0, 30)
-        )
+        start = pd.Timestamp.now().normalize() - pd.DateOffset(years=np.random.randint(0, 30))
 
     low_freq_index = pd.date_range(start=start, periods=low_periods, freq=low_freq)
     high_freq = pd._libs.tslibs.to_offset(high_freq)
@@ -57,13 +55,9 @@ def generate_random_index_pair(
     high_end = low_freq_index[-1] + high_freq * extra_high_freq_end
 
     if high_periods is None:
-        high_periods = len(
-            pd.date_range(start=high_start, end=high_end, freq=high_freq)
-        )
+        high_periods = len(pd.date_range(start=high_start, end=high_end, freq=high_freq))
 
-    high_freq_index = pd.date_range(
-        start=high_start, periods=max(0, high_periods), freq=high_freq
-    )
+    high_freq_index = pd.date_range(start=high_start, periods=max(0, high_periods), freq=high_freq)
 
     return (
         pd.Series(1.0, index=low_freq_index, name="low_freq"),
@@ -135,20 +129,14 @@ def test_build_C_matrix(agg_func, frequencies):
         full_size = 4 if high_name == "quarterly" else 12
         full_size_mask = group_size.values == full_size
         expected_result = groups.high_freq.agg(agg_func).values
-        np.testing.assert_allclose(
-            high_agg[full_size_mask], expected_result[full_size_mask]
-        )
+        np.testing.assert_allclose(high_agg[full_size_mask], expected_result[full_size_mask])
 
     elif low_name == "quarterly":
-        groups = high_with_info.groupby(
-            ["year", "quarter"]
-        )  # .high_freq.agg(agg_func).values
+        groups = high_with_info.groupby(["year", "quarter"])  # .high_freq.agg(agg_func).values
         group_size = groups.size()
         full_size_mask = group_size.values == 3
         expected_result = groups.high_freq.agg(agg_func).values
-        np.testing.assert_allclose(
-            high_agg[full_size_mask], expected_result[full_size_mask]
-        )
+        np.testing.assert_allclose(high_agg[full_size_mask], expected_result[full_size_mask])
 
 
 class DisaggregationTests(unittest.TestCase):
@@ -232,9 +220,7 @@ def test_chow_lin_backcasting_error(self):
         )
 
         assert np.all(expected.index == m_chow_lin.index)
-        np.testing.assert_allclose(
-            expected.values.ravel(), m_chow_lin.values, rtol=1e-3
-        )
+        np.testing.assert_allclose(expected.values.ravel(), m_chow_lin.values, rtol=1e-3)
 
     def test_chow_lin_backcasting_error_YtoQ(self):
         expected = pd.read_csv("tests/data/AL_A_to_Q_expected.csv")
@@ -275,14 +261,10 @@ def test_chow_lin_backcasting_error_YtoQ(self):
 
         assert res.success
         assert np.all(expected.index == q_chow_lin.index)
-        np.testing.assert_allclose(
-            expected.values.ravel(), q_chow_lin.values.ravel(), rtol=1e-3
-        )
+        np.testing.assert_allclose(expected.values.ravel(), q_chow_lin.values.ravel(), rtol=1e-3)
 
     def test_chow_lin_two_indicator(self):
-        expected = pd.read_csv(
-            "tests/data/R_output_chow_lin_two_indicator.csv", index_col=0
-        )
+        expected = pd.read_csv("tests/data/R_output_chow_lin_two_indicator.csv", index_col=0)
         expected.index = self.exports_q.index
         expected.columns = ["sales"]
 
@@ -327,9 +309,7 @@ def test_denton_cholette_w_constant(self):
         self.assertEqual(expected, sales_q_dc.to_frame())
 
     def test_denton_cholette_w_indicator(self):
-        expected = pd.read_csv(
-            "tests/data/R_output_denton_cholette_w_indicator.csv", index_col=0
-        )
+        expected = pd.read_csv("tests/data/R_output_denton_cholette_w_indicator.csv", index_col=0)
         expected.index = self.exports_q.index
         expected.columns = ["sales"]
 

diff --git a/tests/test_frequency_conversion.py b/tests/test_frequency_conversion.py
@@ -1,7 +1,7 @@
 import calendar
 import unittest
 
-from typing import Callable, List, Tuple
+from collections.abc import Callable
 
 import pandas as pd
 
@@ -14,8 +14,8 @@
 
 @composite
 def freq(
-    draw: Callable[[SearchStrategy[int]], int], base: str, suffix_list: List[str]
-) -> Tuple[str, str, str]:
+    draw: Callable[[SearchStrategy[int]], int], base: str, suffix_list: list[str]
+) -> tuple[str, str, str]:
     bases = [f"{base}E", f"B{base}E", f"{base}S", f"B{base}S"]
     suffixes = [f"-{x}" for x in suffix_list] + [""]
 
@@ -51,9 +51,7 @@ def test_dataframe_merge(self, params):
         low_freq_name, high_freq_name = get_frequency_names(low_freq_df, target_freq)
 
         high_freq_df = pd.Series(1, index=index, name=high_freq_name)
-        result = pd.merge(
-            low_freq_df, high_freq_df, left_index=True, right_index=True, how="outer"
-        )
+        result = pd.merge(low_freq_df, high_freq_df, left_index=True, right_index=True, how="outer")
 
         df, *_ = prepare_input_dataframes(low_freq_df, None, target_freq, "denton")
         self.assertEqual(df.shape[0], result.shape[0])
@@ -71,9 +69,7 @@ def test_dataframe_merge_A_to_M(self, params):
         low_freq_name, high_freq_name = get_frequency_names(low_freq_df, target_freq)
 
         high_freq_df = pd.Series(1, index=index, name=high_freq_name)
-        result = pd.merge(
-            low_freq_df, high_freq_df, left_index=True, right_index=True, how="outer"
-        )
+        result = pd.merge(low_freq_df, high_freq_df, left_index=True, right_index=True, how="outer")
 
         df, *_ = prepare_input_dataframes(low_freq_df, None, target_freq, "denton")
 
@@ -92,9 +88,7 @@ def test_dataframe_merge_Q_to_M(self):
         low_freq_name, high_freq_name = get_frequency_names(low_freq_df, target_freq)
 
         high_freq_df = pd.Series(1, index=index, name=high_freq_name)
-        result = pd.merge(
-            low_freq_df, high_freq_df, left_index=True, right_index=True, how="outer"
-        )
+        result = pd.merge(low_freq_df, high_freq_df, left_index=True, right_index=True, how="outer")
 
         df, df_low, df_high, factor = prepare_input_dataframes(
             low_freq_df, None, target_freq, "denton"
@@ -125,9 +119,7 @@ def test_build_conversion_matrix():
     df.iloc[:, 0].dropna().values
     df.drop(columns=df.columns[0]).values
 
-    C = build_conversion_matrix(
-        low_freq_df, high_freq_df, time_conversion_factor, agg_func="sum"
-    )
+    C = build_conversion_matrix(low_freq_df, high_freq_df, time_conversion_factor, agg_func="sum")
 
     assert C.shape[0] == low_freq_df.shape[0]
     assert C.shape[1] == high_freq_df.shape[0]