gla-data 0.1.1__tar.gz → 0.1.2__tar.gz

{gla_data-0.1.1 → gla_data-0.1.2}/.gitignore

@@ -33,7 +33,8 @@ outputs/
 .DS_Store
 Thumbs.db
 
-# Plan docs — internal working notes, not part of the shipped project
+# Plan docs and Claude instructions — internal, not part of the shipped project
 PLAN*.md
 WORKPLAN.md
 DESIGN.md
+CLAUDE.md

gla_data-0.1.2/PKG-INFO

@@ -0,0 +1,109 @@
+Metadata-Version: 2.4
+Name: gla-data
+Version: 0.1.2
+Summary: Shared tools for loading, transforming, and visualising the GLA datasets used in City Data analysis.
+Author-email: Conor Dempsey <conor.dempsey@london.gov.uk>
+License: MIT
+Requires-Python: >=3.12
+Requires-Dist: geopandas>=1.0
+Requires-Dist: pandas>=2.2
+Requires-Dist: pandera>=0.32.1
+Requires-Dist: pyarrow>=24.0.0
+Requires-Dist: pydantic-settings
+Requires-Dist: requests>=2.32
+Requires-Dist: typer>=0.26.8
+Description-Content-Type: text/markdown
+
+# gla-data
+
+Shared tools for loading, transforming, and visualising the GLA datasets used in City Data analysis.
+
+## Installation
+
+### Global install (CLI)
+
+To install `gla-data` globally so the `gla-data` CLI is available anywhere in your terminal, use `uv tool`:
+
+```bash
+uv tool install gla-data
+```
+
+Normally `pixi global install` would be the preferred approach, but it does not yet support PyPI packages — so `uv tool` is the right choice for now.
+
+If you don't have `uv` installed, you can install it via pixi:
+
+```bash
+pixi global install uv
+```
+
+### pip
+
+```bash
+pip install gla-data
+```
+
+### pixi
+
+```bash
+pixi add gla-data
+```
+
+Pixi pulls geospatial dependencies (geopandas, pyproj, etc.) from conda-forge, which provides reliable pre-built binaries across all platforms and Python versions.
+
+## Usage
+
+### Python API
+
+```python
+import gla_data
+
+# Load 2021 LSOA boundaries for London
+lsoa_gdf = gla_data.load_boundaries(geography='lsoa', year=2021)
+
+# Load census dwelling counts
+dwellings_2021 = gla_data.load_census_dwellings(year=2021)
+dwellings_2011 = gla_data.load_census_dwellings(year=2011)
+
+# Crosswalk 2011 dwelling counts onto 2021 LSOA boundaries
+dwellings_2011_xw = gla_data.crosswalk(
+    dwellings_2011,
+    from_year=2011,
+    to_year=2021,
+    value_cols=['dwellings_total'],
+)
+
+# Load an OA → LSOA geography lookup
+lookup = gla_data.load_geography_lookup(year=2021, smallest_geography='oa')
+
+# Aggregate OA-level data up to LSOA level
+lsoa_totals = gla_data.aggregate(
+    df,
+    from_geography='oa',
+    to_geography='lsoa',
+    value_cols=['count'],
+    year=2021,
+)
+```
+
+### CLI
+
+The package installs a `gla-data` command. Run `catalogue` to list all available datasets:
+
+```bash
+gla-data catalogue
+```
+
+This prints a table of every dataset, the function used to load it, a description, and its access tier (public/S3).
+
+## Development
+
+```bash
+git clone <repo-url>
+cd gla-data
+pixi install
+
+pixi run test       # run tests
+pixi run lint       # check code style
+pixi run format     # auto-format
+pixi run typecheck  # type checking
+```

gla_data-0.1.2/README.md

@@ -0,0 +1,93 @@
+# gla-data
+
+Shared tools for loading, transforming, and visualising the GLA datasets used in City Data analysis.
+
+## Installation
+
+### Global install (CLI)
+
+To install `gla-data` globally so the `gla-data` CLI is available anywhere in your terminal, use `uv tool`:
+
+```bash
+uv tool install gla-data
+```
+
+Normally `pixi global install` would be the preferred approach, but it does not yet support PyPI packages — so `uv tool` is the right choice for now.
+
+If you don't have `uv` installed, you can install it via pixi:
+
+```bash
+pixi global install uv
+```
+
+### pip
+
+```bash
+pip install gla-data
+```
+
+### pixi
+
+```bash
+pixi add gla-data
+```
+
+Pixi pulls geospatial dependencies (geopandas, pyproj, etc.) from conda-forge, which provides reliable pre-built binaries across all platforms and Python versions.
+
+## Usage
+
+### Python API
+
+```python
+import gla_data
+
+# Load 2021 LSOA boundaries for London
+lsoa_gdf = gla_data.load_boundaries(geography='lsoa', year=2021)
+
+# Load census dwelling counts
+dwellings_2021 = gla_data.load_census_dwellings(year=2021)
+dwellings_2011 = gla_data.load_census_dwellings(year=2011)
+
+# Crosswalk 2011 dwelling counts onto 2021 LSOA boundaries
+dwellings_2011_xw = gla_data.crosswalk(
+    dwellings_2011,
+    from_year=2011,
+    to_year=2021,
+    value_cols=['dwellings_total'],
+)
+
+# Load an OA → LSOA geography lookup
+lookup = gla_data.load_geography_lookup(year=2021, smallest_geography='oa')
+
+# Aggregate OA-level data up to LSOA level
+lsoa_totals = gla_data.aggregate(
+    df,
+    from_geography='oa',
+    to_geography='lsoa',
+    value_cols=['count'],
+    year=2021,
+)
+```
+
+### CLI
+
+The package installs a `gla-data` command. Run `catalogue` to list all available datasets:
+
+```bash
+gla-data catalogue
+```
+
+This prints a table of every dataset, the function used to load it, a description, and its access tier (public/S3).
+
+## Development
+
+```bash
+git clone <repo-url>
+cd gla-data
+pixi install
+
+pixi run test       # run tests
+pixi run lint       # check code style
+pixi run format     # auto-format
+pixi run typecheck  # type checking
+```

{gla_data-0.1.1 → gla_data-0.1.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "gla-data"
-version = "0.1.1"
+version = "0.1.2"
 description = "Shared tools for loading, transforming, and visualising the GLA datasets used in City Data analysis."
 readme = "README.md"
 license = { text = "MIT" }
@@ -49,7 +49,7 @@ disallow_untyped_defs = false
 disallow_incomplete_defs = false
 
 [tool.bumpversion]
-current_version = "0.1.1"
+current_version = "0.1.2"
 commit = true
 tag    = true
 

{gla_data-0.1.1 → gla_data-0.1.2}/src/gla_data/census.py

@@ -25,10 +25,19 @@ _EXCEL_KWARGS = {
 
 
 def _fetch_census_dwellings(year: int) -> pd.DataFrame:
-    """Download and normalise the raw UKDS census dwellings file for the given year."""
+    """Download the raw UKDS census dwellings
+    file for the given year and normalise it."""
     kwargs = _EXCEL_KWARGS.get(year, {})
     raw = _ukds.fetch(f"census_dwellings_{year}", **kwargs)
+    return _clean_census_dwellings(raw, year)
 
+
+def _clean_census_dwellings(raw: pd.DataFrame, year: int) -> pd.DataFrame:
+    """Select and rename the raw UKDS columns into the public schema for a given year.
+
+    Pure and deterministic — no I/O — so it can be unit-tested directly with an
+    in-memory fixture, without mocking ``_ukds.fetch``.
+    """
     cols = _RAW_COLUMNS[year]
     code_col = f"LSOA{str(year)[2:]}CD"
 

{gla_data-0.1.1 → gla_data-0.1.2}/src/gla_data/cli.py

@@ -1,5 +1,7 @@
 """Command-line interface for gla_data."""
 
+from typing import Annotated
+
 import typer
 from rich.console import Console
 from rich.table import Table
@@ -11,6 +13,23 @@ app = typer.Typer(
 )
 
 
+def _version_callback(value: bool) -> None:
+    if value:
+        typer.echo(gla_data.__version__)
+        raise typer.Exit()
+
+
+@app.callback()
+def main_callback(
+    version: Annotated[
+        bool,
+        typer.Option("--version", "-V", callback=_version_callback, is_eager=True,
+                     help="Show version and exit."),
+    ] = False,
+) -> None:
+    pass
+
+
 @app.command()
 def catalogue() -> None:
     """List all datasets available in gla_data."""

{gla_data-0.1.1 → gla_data-0.1.2}/tests/test_census_dwellings.py

@@ -5,6 +5,7 @@ import pytest
 
 import gla_data
 import gla_data._cache as cache_module
+from gla_data.census import _clean_census_dwellings
 
 # ---------------------------------------------------------------------------
 # Fixtures
@@ -31,6 +32,42 @@ def fake_dwellings_2011():
     )
 
 
+# ---------------------------------------------------------------------------
+# Pure transform (no I/O, no mocking needed)
+# ---------------------------------------------------------------------------
+
+
+def test_clean_census_dwellings_2021_selects_and_renames():
+    raw = pd.DataFrame(
+        {
+            "Lower layer Super Output Areas Code": ["E01000001", "E01000002"],
+            "Observation": [1079, 1178],
+            "Some Other Column": ["x", "y"],
+        }
+    )
+
+    result = _clean_census_dwellings(raw, year=2021)
+
+    assert list(result.columns) == ["LSOA21CD", "dwellings_total"]
+    assert result["LSOA21CD"].tolist() == ["E01000001", "E01000002"]
+    assert result["dwellings_total"].tolist() == [1079, 1178]
+
+
+def test_clean_census_dwellings_2011_selects_and_renames():
+    raw = pd.DataFrame(
+        {
+            "GEO_CODE": ["E01000001", "E01000002"],
+            "Dwellings : Total\\ Dwellings - Unit : Dwellings": [950, 1050],
+        }
+    )
+
+    result = _clean_census_dwellings(raw, year=2011)
+
+    assert list(result.columns) == ["LSOA11CD", "dwellings_total"]
+    assert result["LSOA11CD"].tolist() == ["E01000001", "E01000002"]
+    assert result["dwellings_total"].tolist() == [950, 1050]
+
+
 # ---------------------------------------------------------------------------
 # Validation (no network calls)
 # ---------------------------------------------------------------------------

gla_data-0.1.2/tests/test_cli.py

@@ -0,0 +1,19 @@
+"""Tests for the gla_data command-line interface."""
+
+from typer.testing import CliRunner
+
+from gla_data.cli import app
+
+runner = CliRunner()
+
+
+def test_catalogue_command_exits_cleanly():
+    result = runner.invoke(app, ["catalogue"])
+    assert result.exit_code == 0
+
+
+def test_catalogue_command_lists_implemented_datasets():
+    result = runner.invoke(app, ["catalogue"])
+    assert "Census Dwellings" in result.output
+    assert "load_census_dwel" in result.output
+    assert "ONS Boundaries" in result.output

gla_data-0.1.1/PKG-INFO

@@ -1,43 +0,0 @@
-Metadata-Version: 2.4
-Name: gla-data
-Version: 0.1.1
-Summary: Shared tools for loading, transforming, and visualising the GLA datasets used in City Data analysis.
-Author-email: Conor Dempsey <conor.dempsey@london.gov.uk>
-License: MIT
-Requires-Python: >=3.12
-Requires-Dist: geopandas>=1.0
-Requires-Dist: pandas>=2.2
-Requires-Dist: pandera>=0.32.1
-Requires-Dist: pyarrow>=24.0.0
-Requires-Dist: pydantic-settings
-Requires-Dist: requests>=2.32
-Requires-Dist: typer>=0.26.8
-Description-Content-Type: text/markdown
-
-# gla-data
-
-Shared tools for loading, transforming, and visualising the GLA datasets used in City Data analysis.
-
-## Installation
-
-Add `gla-data` as a PyPI dependency in your `pixi.toml`:
-
-```toml
-[pypi-dependencies]
-gla-data = ">=0.1"
-```
-
-Then run `pixi install`. Pixi pulls geospatial dependencies (geopandas, pyproj, etc.) from conda-forge, which provides reliable pre-built binaries across all platforms and Python versions.
-
-## Development
-
-```bash
-git clone <repo-url>
-cd gla-data
-pixi install
-
-pixi run test       # run tests
-pixi run lint       # check code style
-pixi run format     # auto-format
-pixi run typecheck  # type checking
-```

gla_data-0.1.1/README.md

@@ -1,27 +0,0 @@
-# gla-data
-
-Shared tools for loading, transforming, and visualising the GLA datasets used in City Data analysis.
-
-## Installation
-
-Add `gla-data` as a PyPI dependency in your `pixi.toml`:
-
-```toml
-[pypi-dependencies]
-gla-data = ">=0.1"
-```
-
-Then run `pixi install`. Pixi pulls geospatial dependencies (geopandas, pyproj, etc.) from conda-forge, which provides reliable pre-built binaries across all platforms and Python versions.
-
-## Development
-
-```bash
-git clone <repo-url>
-cd gla-data
-pixi install
-
-pixi run test       # run tests
-pixi run lint       # check code style
-pixi run format     # auto-format
-pixi run typecheck  # type checking
-```

gla_data-0.1.1/tests/test_placeholder.py

@@ -1,6 +0,0 @@
-# Replace this file with real tests as you add functions to the package.
-import gla_data
-
-
-def test_package_importable():
-    assert gla_data.__version__ is not None

{gla_data-0.1.1 → gla_data-0.1.2}/src/gla_data/__init__.py

@@ -8,9 +8,9 @@ from gla_data.transforms import aggregate, crosswalk
 __version__ = version("gla-data")
 __all__ = [
     "load_boundaries",
-    "crosswalk",
-    "aggregate",
     "load_geography_lookup",
     "load_census_dwellings",
+    "crosswalk",
+    "aggregate",
     "catalogue",
 ]