diff --git a/.github/workflows/R-CMD-check.yaml b/.github/workflows/R-CMD-check.yaml
index 98fb135..5295f41 100644
--- a/.github/workflows/R-CMD-check.yaml
+++ b/.github/workflows/R-CMD-check.yaml
@@ -22,7 +22,7 @@ jobs:
       R_KEEP_PKG_SOURCE: yes
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Setup pandoc
         uses: r-lib/actions/setup-pandoc@v2
diff --git a/.github/workflows/pkgdown.yaml b/.github/workflows/docs.yaml
similarity index 57%
rename from .github/workflows/pkgdown.yaml
rename to .github/workflows/docs.yaml
index 5912d61..d1b8bfd 100644
--- a/.github/workflows/pkgdown.yaml
+++ b/.github/workflows/docs.yaml
@@ -5,14 +5,18 @@ on:
   push:
     branches: [main, master]
 
-name: pkgdown
+name: docs
+
+env:
+  PYTHONUNBUFFERED: "1"
+  UV_SYSTEM_PYTHON: 1
 
 jobs:
-  build-pkgdown-site:
+  build:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Setup pandoc
         uses: r-lib/actions/setup-pandoc@v2
@@ -28,21 +32,41 @@ jobs:
           extra-packages: any::pkgdown, local::.
           needs: website
 
-      - name: Build pkgdown site
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+        with:
+          enable-cache: true
+          cache-dependency-glob: python/pyproject.toml
+          cache-suffix: docs
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version-file: python/pyproject.toml
+
+      - name: Install Python dependencies
+        working-directory: python
+        shell: bash
+        run: uv pip install .[docs]
+
+      - name: Build R docs
         run: pkgdown::build_site_github_pages(new_process = FALSE, install = FALSE)
         shell: Rscript {0}
 
+      - name: Build Python docs
+        run: sphinx-build python/docs/source docs/python
+
       - name: Configure pages
-        uses: actions/configure-pages@v3
+        uses: actions/configure-pages@v5
 
       - name: Upload artifact
-        uses: actions/upload-pages-artifact@v1
+        uses: actions/upload-pages-artifact@v3
         with:
           path: 'docs'
 
   deploy:
     if: contains(fromJSON('["main", "master"]'), github.ref_name) && github.event_name != 'pull_request'
-    needs: build-pkgdown-site
+    needs: build
     runs-on: ubuntu-latest
     environment:
       name: github-pages
@@ -53,4 +77,4 @@ jobs:
     steps:
       - name: Deploy to GitHub Pages
         id: deployment
-        uses: actions/deploy-pages@v2
+        uses: actions/deploy-pages@v4
diff --git a/.github/workflows/lint.yaml b/.github/workflows/lint.yaml
index 507fedb..2c8b81e 100644
--- a/.github/workflows/lint.yaml
+++ b/.github/workflows/lint.yaml
@@ -10,7 +10,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Setup R
         uses: r-lib/actions/setup-r@v2
diff --git a/.github/workflows/pytest-coverage.yaml b/.github/workflows/pytest-coverage.yaml
new file mode 100644
index 0000000..e758284
--- /dev/null
+++ b/.github/workflows/pytest-coverage.yaml
@@ -0,0 +1,52 @@
+on:
+  pull_request:
+  push:
+    branches: [main, master]
+
+name: pytest-coverage
+
+env:
+  PYTHONUNBUFFERED: "1"
+  UV_SYSTEM_PYTHON: 1
+
+jobs:
+  pytest-coverage:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Install uv
+      uses: astral-sh/setup-uv@v3
+      with:
+        enable-cache: true
+        cache-dependency-glob: python/pyproject.toml
+        cache-suffix: test
+
+    - name: Install Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install Python dependencies
+      working-directory: python
+      shell: bash
+      run: uv pip install .[dev,docs]
+
+    - name: Run pytest
+      working-directory: python
+      shell: bash
+      run: |
+        pytest -v --doctest-modules \
+          --junitxml=junit/test-results-${{ matrix.python-version }}.xmlpytest
+
+    - name: Upload artifacts
+      if: failure()
+      uses: actions/upload-artifact@v4
+      with:
+        name: python/pytest-results-${{ matrix.python-version }}
+        path: python/junit/test-results-${{ matrix.python-version }}.xml
diff --git a/.github/workflows/test-coverage.yaml b/.github/workflows/test-coverage.yaml
index 2d30441..9f6749f 100644
--- a/.github/workflows/test-coverage.yaml
+++ b/.github/workflows/test-coverage.yaml
@@ -10,7 +10,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Setup R
         uses: r-lib/actions/setup-r@v2
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 11a5038..f4e0385 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -10,6 +10,7 @@ repos:
     -   id: use-tidy-description
     -   id: lintr
     -   id: readme-rmd-rendered
+        exclude: ^python/
     -   id: parsable-R
     -   id: no-browser-statement
     -   id: no-debug-statement
@@ -33,3 +34,15 @@ repos:
         entry: Cannot commit .Rhistory, .RData, .Rds or .rds.
         language: fail
         files: '\.(Rhistory|RData|Rds|rds)$'
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.7.4
+    hooks:
+      # Python linter. Ruff recommends running this before the formatter to
+      # avoid conflicts when using the --fix flag
+      - id: ruff
+        args:
+          - --fix
+        files: ^python/
+      # Formatter
+      - id: ruff-format
+        files: ^python/
diff --git a/data-raw/chars_sample.R b/data-raw/chars_sample.R
index fa09860..52907c6 100644
--- a/data-raw/chars_sample.R
+++ b/data-raw/chars_sample.R
@@ -54,6 +54,9 @@ chars_sample_athena <- dbGetQuery(
   "
 )
 usethis::use_data(chars_sample_athena, overwrite = TRUE)
+# Write the data to CSV so that the Python version of the package can consume
+# it as well
+readr::write_csv(chars_sample_athena, "data-raw/chars_sample_athena.csv")
 
 # Get sample ADDCHARS data
 chars_sample_hie <- dbGetQuery(
@@ -69,3 +72,4 @@ chars_sample_hie <- dbGetQuery(
   "
 )
 usethis::use_data(chars_sample_hie, overwrite = TRUE)
+readr::write_csv(chars_sample_hie, "data-raw/chars_sample_hie.csv")
diff --git a/data-raw/chars_sample_athena.csv b/data-raw/chars_sample_athena.csv
new file mode 100644
index 0000000..12447a8
--- /dev/null
+++ b/data-raw/chars_sample_athena.csv
@@ -0,0 +1,71 @@
+pin,year,class,char_yrblt,char_bldg_sf,char_land_sf,char_beds,char_rooms,char_fbath,char_hbath,char_frpl,char_type_resd,char_cnst_qlty,char_apts,char_tp_dsgn,char_attic_fnsh,char_gar1_att,char_gar1_area,char_gar1_size,char_gar1_cnst,char_attic_type,char_bsmt,char_ext_wall,char_heat,char_repair_cnd,char_bsmt_fin,char_roof_cnst,char_use,char_age,char_site,char_ncu,char_renovation,char_porch,char_air,char_tp_plan
+10254170360000,2015,205,1948,1775,4340,4,7,2,1,2,2,2,6,2,3,2,2,7,0,3,1,2,1,2,1,1,1,67,2,0,0,0,1,2
+09363230550000,2019,203,1923,1200,4375,3,5,1,1,0,1,2,6,2,3,2,2,7,0,3,1,3,2,2,3,1,1,95,2,0,0,1,2,2
+09363230550000,2016,203,1923,1200,4375,3,5,1,1,0,1,2,6,2,3,2,2,7,0,3,1,3,2,2,3,1,1,92,2,0,0,1,2,2
+14321260280000,2018,211,1878,2850,3125,4,9,3,0,0,3,2,2,2,3,2,2,7,0,3,3,2,1,2,1,2,2,140,2,0,0,0,2,2
+10253190450000,2018,204,1951,2469,11160,3,8,2,1,1,1,2,6,0,3,1,2,3,2,3,3,2,1,2,3,1,1,67,2,0,0,0,1,2
+14321260280000,2016,211,1878,2850,3125,4,9,3,0,0,3,2,2,2,3,2,2,7,0,3,3,2,1,2,1,2,2,137,2,0,0,0,2,2
+09254040180000,2020,203,1955,1571,3750,3,6,1,0,0,5,2,6,2,1,2,2,7,0,1,1,2,1,2,3,1,1,63,2,0,0,0,1,2
+13362270230000,2015,202,1890,756,2750,2,4,1,1,0,1,2,6,0,3,2,2,3,1,1,1,3,2,3,1,1,1,125,2,0,0,1,2,2
+13253160160000,2020,202,1904,706,3150,2,5,1,0,0,1,2,6,2,3,2,2,3,1,1,1,2,2,2,3,1,1,117,2,0,0,0,2,2
+10254170360000,2018,205,1948,1829,4340,3,7,2,1,2,2,2,6,2,3,2,2,3,1,3,1,2,1,2,1,1,1,70,2,0,0,0,1,2
+13253160160000,2017,202,1901,706,3150,2,5,1,0,0,1,2,6,2,3,2,2,3,1,1,1,2,2,2,3,1,1,114,2,0,0,0,2,2
+09363230550000,2017,203,1923,1200,4375,3,5,1,1,0,1,2,6,2,3,2,2,7,0,3,1,3,2,2,3,1,1,92,2,0,0,1,2,2
+10253190450000,2017,204,1951,2469,11160,3,8,2,1,1,1,2,6,0,3,1,2,3,2,3,3,2,1,2,3,1,1,64,2,0,0,0,1,2
+13253230040000,2019,203,1969,1040,3150,2,5,1,0,0,1,2,6,2,3,2,2,7,0,3,1,2,1,2,3,1,1,49,2,0,0,0,2,2
+17032010190000,2016,211,1887,3299,1204,8,11,3,0,2,3,2,2,2,3,2,2,7,0,3,1,2,2,2,1,6,2,128,2,0,0,0,1,2
+09361030150000,2016,203,1928,1200,5280,2,5,1,0,0,1,2,6,0,3,1,1,1,1,1,1,3,2,2,3,1,1,87,3,0,0,0,2,0
+09361030150000,2015,203,1928,1200,5280,2,5,1,0,0,1,2,6,0,3,1,1,1,1,1,1,3,2,2,3,1,1,87,3,0,0,0,2,0
+17032010190000,2015,211,1887,3299,1204,8,11,3,0,2,3,2,2,2,3,2,2,7,0,3,1,2,2,2,1,6,2,128,2,0,0,0,1,2
+10253190450000,2021,209,1954,6027,11160,5,12,4,1,1,2,2,6,2,3,1,2,3,2,3,3,4,1,2,3,1,1,70,2,0,0,0,1,2
+09254040180000,2018,203,1955,1571,3750,3,6,1,0,0,5,2,6,2,1,2,2,7,0,1,1,2,1,2,3,1,1,63,2,0,0,0,1,2
+09254040180000,2017,203,1955,1571,3750,3,6,1,0,0,5,2,6,2,1,2,2,7,0,1,1,2,1,2,3,1,1,60,2,0,0,0,1,2
+13362270230000,2016,202,1890,756,2750,2,4,1,1,0,1,2,6,0,3,2,2,3,1,1,1,3,2,3,1,1,1,125,2,0,0,1,2,2
+13253230040000,2021,278,1972,2210,3150,4,9,3,0,0,2,2,6,2,3,2,2,7,0,3,1,2,1,2,1,1,1,52,2,0,0,0,1,2
+09254040180000,2015,203,1955,1571,3750,3,6,1,0,0,5,2,6,2,1,2,2,7,0,1,1,2,1,2,3,1,1,60,2,0,0,0,1,2
+13362270230000,2017,202,1890,756,2750,2,4,1,1,0,1,2,6,0,3,2,2,3,1,1,1,3,2,3,1,1,1,125,2,0,0,1,2,2
+13253230040000,2015,203,1969,1040,3150,2,5,1,0,0,1,2,6,0,3,2,2,3,1,3,2,2,1,2,3,1,1,46,2,0,0,0,2,2
+13253160160000,2019,202,1901,706,3150,2,5,1,0,0,1,2,6,2,3,2,2,3,1,1,1,2,2,2,3,1,1,117,2,0,0,0,2,2
+10254170360000,2017,205,1948,1829,4340,3,7,2,1,2,2,2,6,2,3,2,2,3,1,3,1,2,1,2,1,1,1,67,2,0,0,0,1,2
+10253190450000,2019,204,1951,2469,11160,3,8,2,1,1,1,2,6,0,3,1,2,3,2,3,3,2,1,2,3,1,1,67,2,0,0,0,1,2
+14321260280000,2021,206,1880,3660,3125,4,11,5,0,0,3,2,6,2,3,2,2,4,2,3,3,2,1,2,1,2,1,143,2,0,1,0,2,2
+09361030150000,2018,203,1928,1357,5280,2,6,1,1,0,1,2,6,2,3,2,2,1,1,3,1,2,2,2,3,1,1,90,3,0,0,0,2,2
+09361030150000,2021,206,1931,2772,5280,5,9,3,1,0,2,2,6,2,3,2,2,1,1,3,1,3,2,2,3,1,1,93,3,0,0,0,1,2
+17032010190000,2021,210,1887,3299,1204,8,11,3,1,2,3,2,6,2,3,2,2,7,0,3,1,2,2,2,1,6,1,134,2,0,1,0,1,2
+13253160160000,2021,205,1904,1790,3150,3,7,3,0,0,2,2,6,2,3,2,2,3,1,1,1,2,2,2,1,1,1,120,2,0,1,0,1,2
+10254170360000,2021,206,1959,2312,4340,4,8,3,1,2,2,2,6,2,3,2,2,3,1,3,1,2,1,2,1,1,1,73,2,0,0,0,1,2
+13362270230000,2020,202,1890,756,2750,2,4,1,1,0,1,2,6,0,3,2,2,3,1,1,1,3,2,3,1,1,1,128,2,0,0,1,2,2
+09361030150000,2017,203,1928,1357,5280,2,6,1,1,0,1,2,6,2,3,2,2,1,1,3,1,2,2,2,3,1,1,87,3,0,0,0,2,2
+17032010190000,2017,211,1887,3299,1204,8,11,3,0,2,3,2,2,2,3,2,2,7,0,3,1,2,2,2,1,6,2,128,2,0,0,0,1,2
+13253230040000,2017,203,1969,1040,3150,2,5,1,0,0,1,2,6,2,3,2,2,3,1,3,1,2,1,2,3,1,1,46,2,0,0,0,2,2
+17032010190000,2019,211,1888,3299,1204,8,11,3,0,2,3,2,2,2,3,2,2,7,0,3,1,2,2,2,1,6,2,131,2,0,0,0,1,2
+09361030150000,2019,203,1928,1357,5280,2,6,1,1,0,1,2,6,2,3,2,2,1,1,3,1,2,2,2,3,1,1,90,3,0,0,0,2,2
+09363230550000,2015,203,1923,1200,4375,3,5,1,1,0,1,2,6,2,3,2,2,7,0,3,1,3,2,2,3,1,1,92,2,0,0,1,2,2
+09254040180000,2016,203,1955,1571,3750,3,6,1,0,0,5,2,6,2,1,2,2,7,0,1,1,2,1,2,3,1,1,60,2,0,0,0,1,2
+13362270230000,2019,202,1890,756,2750,2,4,1,1,0,1,2,6,0,3,2,2,3,1,1,1,3,2,3,1,1,1,128,2,0,0,1,2,2
+13253160160000,2018,202,1901,706,3150,2,5,1,0,0,1,2,6,2,3,2,2,3,1,1,1,2,2,2,3,1,1,117,2,0,0,0,2,2
+09363230550000,2021,206,1926,2376,4375,4,7,3,1,0,2,2,6,2,3,2,2,3,1,3,1,3,2,2,3,1,1,98,2,0,0,1,1,2
+13253230040000,2016,203,1969,1040,3150,2,5,1,0,0,1,2,6,0,3,2,2,3,1,3,2,2,1,2,3,1,1,46,2,0,0,0,2,2
+10254170360000,2016,205,1948,1775,4340,4,7,2,1,2,2,2,6,2,3,2,2,7,0,3,1,2,1,2,1,1,1,67,2,0,0,0,1,2
+13362270230000,2021,205,1893,1476,2750,4,6,3,1,0,2,2,6,2,3,2,2,3,1,1,1,3,2,3,1,1,1,131,2,0,1,1,1,2
+17032010190000,2018,211,1887,3299,1204,8,11,3,0,2,3,2,2,2,3,2,2,7,0,3,1,2,2,2,1,6,2,131,2,0,0,0,1,2
+14321260280000,2015,211,1878,2850,3125,6,15,3,0,0,3,2,2,0,3,2,2,7,0,3,1,2,2,2,3,2,2,137,2,0,0,1,2,2
+17032010190000,2020,211,1888,3299,1204,8,11,3,0,2,3,2,2,2,3,2,2,7,0,3,1,2,2,2,1,6,2,131,2,0,0,0,1,2
+13253160160000,2015,202,1901,706,3150,2,5,1,0,0,1,2,6,2,3,2,2,3,1,1,1,2,2,2,3,1,1,114,2,0,0,1,2,2
+09363230550000,2018,203,1923,1200,4375,3,5,1,1,0,1,2,6,2,3,2,2,7,0,3,1,3,2,2,3,1,1,95,2,0,0,1,2,2
+09254040180000,2019,203,1955,1571,3750,3,6,1,0,0,5,2,6,2,1,2,2,7,0,1,1,2,1,2,3,1,1,63,2,0,0,0,1,2
+10253190450000,2020,204,1951,2469,11160,3,8,2,1,1,1,2,6,0,3,1,2,3,2,3,3,2,1,2,3,1,1,67,2,0,0,0,1,2
+09361030150000,2020,203,1928,1357,5280,2,6,1,1,0,1,2,6,2,3,2,2,1,1,3,1,2,2,2,3,1,1,90,3,0,0,0,2,2
+13362270230000,2018,202,1890,756,2750,2,4,1,1,0,1,2,6,0,3,2,2,3,1,1,1,3,2,3,1,1,1,128,2,0,0,1,2,2
+10253190450000,2015,204,1951,2469,11160,3,8,2,1,1,1,2,6,0,3,1,2,3,2,3,3,2,1,2,3,1,1,64,2,0,0,0,1,2
+13253230040000,2018,203,1969,1040,3150,2,5,1,0,0,1,2,6,2,3,2,2,3,1,3,1,2,1,2,3,1,1,49,2,0,0,0,2,2
+10253190450000,2016,204,1951,2469,11160,3,8,2,1,1,1,2,6,0,3,1,2,3,2,3,3,2,1,2,3,1,1,64,2,0,0,0,1,2
+14321260280000,2019,211,1878,2850,3125,4,9,3,0,0,3,2,2,2,3,2,2,7,0,3,3,2,1,2,1,2,2,140,2,0,0,0,2,2
+13253160160000,2016,202,1901,706,3150,2,5,1,0,0,1,2,6,2,3,2,2,3,1,1,1,2,2,2,3,1,1,114,2,0,0,0,2,2
+09363230550000,2020,203,1923,1200,4375,3,5,1,1,0,1,2,6,2,3,2,2,7,0,3,1,3,2,2,3,1,1,95,2,0,0,1,2,2
+10254170360000,2019,205,1948,1829,4340,3,7,2,1,2,2,2,6,2,3,2,2,3,1,3,1,2,1,2,1,1,1,70,2,0,0,0,1,2
+13253230040000,2020,203,1969,1040,3150,2,5,1,0,0,1,2,6,2,3,2,2,7,0,3,1,2,1,2,3,1,1,49,2,0,0,0,2,2
+10254170360000,2020,205,1948,1829,4340,3,7,2,1,2,2,2,6,2,3,2,2,3,1,3,1,2,1,2,1,1,1,70,2,0,0,0,1,2
+09254040180000,2021,203,1958,1568,3750,3,8,3,0,0,6,2,6,2,1,2,2,3,1,1,1,2,1,2,1,1,1,66,2,0,0,0,1,2
+14321260280000,2020,211,1878,2850,3125,4,9,3,0,0,3,2,2,2,3,2,2,7,0,3,3,2,1,2,1,2,2,140,2,0,0,0,2,2
+14321260280000,2017,211,1878,2850,3125,4,9,3,0,0,3,2,2,2,3,2,2,7,0,3,3,2,1,2,1,2,2,137,2,0,0,0,2,2
diff --git a/data-raw/chars_sample_hie.csv b/data-raw/chars_sample_hie.csv
new file mode 100644
index 0000000..f8ed4cc
--- /dev/null
+++ b/data-raw/chars_sample_hie.csv
@@ -0,0 +1,12 @@
+pin,qu_town,qu_mlt_cd,qu_home_improvement,qu_use,qu_exterior_wall,qu_roof,qu_basement_type,qu_basement_finish,qu_heat,qu_air,qu_attic_type,qu_attic_finish,qu_type_plan,qu_type_design,qu_construct_quality,qu_porch,qu_garage_size,qu_garage_const,qu_garage_attached,qu_garage_area,qu_num_apts,qu_sqft_bld,qu_lnd_sqft,qu_class,qu_rooms,qu_beds,qu_full_bath,qu_half_bath,qu_fire_place,qu_no_com_unit,qu_type_of_res,qu_upload_date,hie_last_year_active,year
+13253230040000,77,4,1,0,0,0,0,0,0,0,0,0,0,0,0,0,3,1,2,2,0,0,0,203,0,0,0,0,0,0,0,2019-06-19,2023,2019
+10254170360000,75,3,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,483,0,206,1,1,1,0,0,0,0,2017-01-23,2020,2017
+13253230040000,77,3,1,0,0,0,1,1,0,1,0,0,0,0,0,0,0,0,0,0,0,1170,0,278,4,2,2,0,0,0,2,2017-04-20,2020,2017
+09361030150000,71,3,1,0,3,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,1415,0,206,3,3,2,0,0,0,2,2017-06-09,2020,2017
+13362270230000,77,3,1,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,720,0,205,2,2,2,0,0,0,2,2015-07-01,2020,2015
+09254040180000,71,3,1,0,0,0,0,0,0,1,0,0,0,0,0,0,3,1,2,2,0,845,0,207,2,2,2,0,0,0,2,2015-08-01,2020,2015
+09363230550000,71,3,1,0,0,0,0,0,0,1,0,0,0,0,0,0,3,1,2,2,0,1176,0,206,2,1,2,0,0,0,2,2015-08-01,2020,2015
+17032010190000,74,3,1,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,6,0,0,210,0,0,0,1,0,0,0,2015-09-02,2020,2015
+10253190450000,75,3,1,0,4,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,3558,0,209,4,2,2,0,0,0,2,2016-02-03,2020,2016
+13253160160000,77,3,1,0,0,0,1,1,0,1,0,0,0,0,0,0,0,0,0,0,0,1084,0,205,2,1,2,0,0,0,2,2016-08-01,2020,2016
+14321260280000,74,3,1,1,0,0,0,0,0,0,0,0,0,0,0,0,4,2,2,2,6,810,0,206,2,0,2,0,0,0,0,2016-09-13,2020,2016
diff --git a/python/.gitignore b/python/.gitignore
new file mode 100644
index 0000000..c7bd47a
--- /dev/null
+++ b/python/.gitignore
@@ -0,0 +1,40 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+uv.lock
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Sphinx documentation
+_build/
diff --git a/python/README.md b/python/README.md
new file mode 100644
index 0000000..550d607
--- /dev/null
+++ b/python/README.md
@@ -0,0 +1,51 @@
+# CCAO Python package
+
+This is a Python version of the [`ccao` R
+package](https://ccao-data.github.io/ccao/), providing utilities for
+managing, distributing, and version controlling *CCAO-specific* functions
+used throughout CCAO applications, models, and diagnostics. For generalized
+versions of assessment-related functions, see
+[assesspy](https://github.com/ccao-data/assesspy).
+
+## Installation
+
+Install the latest release of `ccao` from PyPI:
+
+```bash
+pip install ccao
+```
+
+You can also install the most recent code directly from GitHub:
+
+```bash
+pip install "git+https://github.com/ccao-data/ccao.git#egg=ccao&subdirectory=python"
+```
+
+## Development
+
+Create a development environment using [`uv`](https://docs.astral.sh/uv/):
+
+```
+uv venv
+source .venv/bin/activate
+uv python install
+uv pip install .[dev,docs]
+```
+
+### Running tests
+
+Run tests with pytest:
+
+```
+pytest
+```
+
+### Building docs
+
+Build and serve the docs locally with sphinx:
+
+```
+sphinx-autobuild docs/source _build/html
+```
+
+Navigate to http://localhost:8000 to view the docs.
diff --git a/python/ccao/__init__.py b/python/ccao/__init__.py
new file mode 100644
index 0000000..f203ad4
--- /dev/null
+++ b/python/ccao/__init__.py
@@ -0,0 +1 @@
+from ccao.vars_funs import vars_dict, vars_rename
diff --git a/python/ccao/data/__init__.py b/python/ccao/data/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/python/ccao/data/vars_dict.csv b/python/ccao/data/vars_dict.csv
new file mode 120000
index 0000000..f61f4c0
--- /dev/null
+++ b/python/ccao/data/vars_dict.csv
@@ -0,0 +1 @@
+../../../data-raw/vars_dict.csv
\ No newline at end of file
diff --git a/python/ccao/vars_funs.py b/python/ccao/vars_funs.py
new file mode 100644
index 0000000..2a4ddec
--- /dev/null
+++ b/python/ccao/vars_funs.py
@@ -0,0 +1,128 @@
+# Functions for translating variables between different data sources
+import importlib.resources
+
+import pandas as pd
+
+import ccao.data
+
+# Load the default variable dictionary
+_data_path = importlib.resources.files(ccao.data)
+vars_dict = pd.read_csv(str(_data_path / "vars_dict.csv"))
+
+# Prefix we use to identify variable name columns in the variable dictionary
+VAR_NAME_PREFIX = "var_name"
+
+
+def vars_rename(
+    data: list[str] | pd.DataFrame,
+    names_from: str,
+    names_to: str,
+    output_type: str = "inplace",
+    dictionary: pd.DataFrame | None = None,
+) -> list[str] | pd.DataFrame:
+    """
+    Rename variables from one naming convention to another.
+
+    This function renames columns in a dataset based on a dictionary that maps
+    names from one convention to another. It can rename columns in-place or return
+    a character vector of renamed columns, behavior that is configurable using
+    the `output_type` argument.
+
+    :param data:
+        DataFrame or list of column names to rename.
+        If a DataFrame, renames columns directly.
+    :type data: pandas.DataFrame or list[str]
+
+    :param names_from:
+        The source naming convention to rename from.
+        Must match a key in the dictionary.
+    :type names_from: str
+
+    :param names_to:
+        The target naming convention to rename to.
+        Must match a key in the dictionary.
+    :type names_to: str
+
+    :param output_type:
+        Output type. Either ``"inplace"``, which mutates the input data frame,
+        or ``"vector"``, which returns a list of strings with the construction
+        new_col_name = old_col_name.
+    :type output_type: str
+
+    :param dictionary:
+        The dictionary for mapping column names.
+        Must contain keys like ``var_name_<names_from>`` and ``var_name_<names_to>``.
+    :type dictionary: pandas.DataFrame
+
+    :raises ValueError: If required arguments are invalid or the dictionary does not meet format requirements.
+    :raises TypeError: If ``data`` is neither a DataFrame nor a list of column names.
+
+    :return:
+        Either the input data with renamed columns if ``output_type`` is
+        ``"inplace"`` and the input data is a DataFrame, otherwise a list of
+        renamed columns.
+    :rtype: pandas.DataFrame or list[str]
+
+    :example:
+
+    .. code-block:: python
+
+        import ccao
+
+        ccao.vars_rename(
+            data=["char_yrblt"],
+            names_from="athena",
+            names_to="pretty",
+            output_type="vector"
+        )
+    """
+    # Validate the dictionary schema
+    dictionary = dictionary if dictionary is not None else vars_dict
+    if dictionary.empty:
+        raise ValueError("dictionary must be a non-empty pandas DataFrame")
+
+    # Make sure the dictionary contains variable columns
+    dictionary_var_columns = [
+        col
+        for col in list(dictionary.columns.values)
+        if col.startswith(VAR_NAME_PREFIX)
+    ]
+    if not len(dictionary_var_columns) >= 2:
+        raise ValueError(
+            f"dictionary must contain at least two columns starting with "
+            f"{VAR_NAME_PREFIX}"
+        )
+
+    # Get a list of possible names_from and names_to from dictionary
+    possible_names_args = [
+        col.replace(f"{VAR_NAME_PREFIX}_", "")
+        for col in dictionary_var_columns
+    ]
+
+    # If names arguments aren't possible, throw error and list possible names
+    for label, var in [("names_from", names_from), ("names_to", names_to)]:
+        if var not in possible_names_args:
+            raise ValueError(
+                f"{label} must be one of {possible_names_args} (got '{var}')"
+            )
+
+    # Validate output type
+    if output_type not in ["inplace", "vector"]:
+        raise ValueError("output_type must be one of 'inplace' or 'vector'")
+
+    # Get a mapping from names_from to names_to
+    from_ = f"{VAR_NAME_PREFIX}_{names_from}"
+    to = f"{VAR_NAME_PREFIX}_{names_to}"
+    mapping = dict(zip(dictionary[from_], dictionary[to]))
+
+    # Handle output differently depending on the input and output type args
+    if isinstance(data, pd.DataFrame):
+        if output_type == "inplace":
+            data.rename(columns=mapping, inplace=True)
+            return data
+        else:
+            return [mapping.get(col, col) for col in list(data.columns.values)]
+    else:
+        # If the input data is a list, it's not possible to update it inplace,
+        # so ignore that argument
+        return [mapping.get(col, col) for col in data]
diff --git a/python/docs/images/logo.png b/python/docs/images/logo.png
new file mode 120000
index 0000000..1b1dd05
--- /dev/null
+++ b/python/docs/images/logo.png
@@ -0,0 +1 @@
+../../../man/figures/logo.png
\ No newline at end of file
diff --git a/python/docs/source/authors.rst b/python/docs/source/authors.rst
new file mode 100644
index 0000000..c0c6217
--- /dev/null
+++ b/python/docs/source/authors.rst
@@ -0,0 +1,7 @@
+=======
+Authors
+=======
+
+**Jean Cochrane**. Author, maintainer.
+
+**Dan Snow**. Author, maintainer.
diff --git a/python/docs/source/conf.py b/python/docs/source/conf.py
new file mode 100644
index 0000000..ceabeaf
--- /dev/null
+++ b/python/docs/source/conf.py
@@ -0,0 +1,14 @@
+import pathlib
+import sys
+
+from sphinx_pyproject import SphinxConfig
+
+# Add source path to sys path so that autodoc can load functions
+rootdir = pathlib.Path(__file__).resolve().parent.parent.parent
+sys.path.append(str(rootdir.resolve()))
+
+# Loads config from pyproject.toml
+config = SphinxConfig(rootdir / "pyproject.toml", globalns=globals())
+
+# Options that can't be parsed by sphinx-pyproject
+html_sidebars = {"**": []}
diff --git a/python/docs/source/index.rst b/python/docs/source/index.rst
new file mode 100644
index 0000000..1df6361
--- /dev/null
+++ b/python/docs/source/index.rst
@@ -0,0 +1,42 @@
+CCAO Python package
+===================
+
+.. toctree::
+   :hidden:
+   :caption: Contents:
+
+   reference
+
+.. toctree::
+   :hidden:
+   :caption: Appendix:
+
+   authors
+   license
+   Source Code <https://github.com/ccao-data/ccao>
+
+This is a Python version of the ``ccao`` `R
+package <https://ccao-data.github.io/ccao/>`_, providing utilities for
+managing, distributing, and version controlling CCAO-specific functions
+used throughout CCAO applications, models, and diagnostics. For generalized
+versions of assessment-related functions, see
+`assesspy <https://github.com/ccao-data/assesspy>`_.
+
+For detailed documentation on included functions and data, `visit the full reference
+list <https://ccao-data.github.io/ccao/python/reference.html>`_.
+
+
+Installation
+------------
+
+Install the latest release of ``ccao`` from PyPI:
+
+.. code-block:: python
+
+    pip install ccao
+
+You can also install the most recent code directly from GitHub:
+
+.. code-block:: python
+
+    pip install "git+https://github.com/ccao-data/ccao.git#egg=ccao&subdirectory=python"
diff --git a/python/docs/source/license.rst b/python/docs/source/license.rst
new file mode 100644
index 0000000..546489a
--- /dev/null
+++ b/python/docs/source/license.rst
@@ -0,0 +1,5 @@
+=======
+License
+=======
+
+.. literalinclude:: ../../../LICENSE
diff --git a/python/docs/source/reference.rst b/python/docs/source/reference.rst
new file mode 100644
index 0000000..3dc531e
--- /dev/null
+++ b/python/docs/source/reference.rst
@@ -0,0 +1,14 @@
+=========
+Reference
+=========
+
+Functions
+---------
+
+Manage characteristics
+^^^^^^^^^^^^^^^^^^^^^^
+
+Recode/rename characteristic columns, merge HIE data, and fix characteristic
+errors.
+
+:doc:`vars_rename() <vars_rename>`
diff --git a/python/docs/source/vars_rename.rst b/python/docs/source/vars_rename.rst
new file mode 100644
index 0000000..db93a1d
--- /dev/null
+++ b/python/docs/source/vars_rename.rst
@@ -0,0 +1,5 @@
+==================================================================================
+Bulk rename variables from CCAO SQL to standardized or pretty names and visa versa
+==================================================================================
+
+.. autofunction:: ccao.vars_rename
diff --git a/python/pyproject.toml b/python/pyproject.toml
new file mode 100644
index 0000000..733619b
--- /dev/null
+++ b/python/pyproject.toml
@@ -0,0 +1,57 @@
+[project]
+name = "ccao"
+version = "1.3.0"
+description = "Convenience Functions and Datasets for the Cook County Assessor's Office"
+readme = "README.md"
+requires-python = ">=3.10"
+authors = [
+    {name = "Jean Cochrane", email="jean.cochrane@cookcountyil.gov"},
+    {name = "Dan Snow", email="daniel.snow@cookcountyil.gov"},
+]
+dependencies = [
+    "pandas>=2.2.3",
+]
+
+[project.optional-dependencies]
+dev = [
+    "mypy>=1.13.0",
+    "pytest>=8.3.3",
+    "ruff>=0.7.4",
+]
+docs = [
+    "Sphinx>=8.1.3",
+    "myst-parser>=4.0.0",
+    "pydata-sphinx-theme>=0.16.0",
+    "sphinx-pyproject>=0.3.0"
+]
+
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.package-data]
+"*" = ["*.csv"]
+
+[tool.ruff]
+line-length = 79
+
+[tool.ruff.lint]
+extend-select = ["I"]
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["F401"]
+
+[tool.sphinx-pyproject]
+github_username = "ccao-data"
+github_repository = "ccao"
+project = "ccao"
+copyright = "2024, Cook County Assessor's Office"
+language = "en"
+extensions = [
+  "sphinx.ext.autodoc",
+  "sphinx.ext.doctest",
+  "myst_parser"
+]
+highlight_language = "none"
+html_theme = "pydata_sphinx_theme"
+html_logo = "../images/logo.png"
+html_show_copyright = false
diff --git a/python/tests/__init__.py b/python/tests/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/python/tests/conftest.py b/python/tests/conftest.py
new file mode 100644
index 0000000..2d59d8b
--- /dev/null
+++ b/python/tests/conftest.py
@@ -0,0 +1,18 @@
+import pathlib
+
+import pandas as pd
+import pytest
+
+fixture_dir = pathlib.Path(__file__).parent / "fixtures"
+
+
+@pytest.fixture(scope="module")
+def chars_sample_athena() -> pd.DataFrame:
+    """Sample chars with Athena variable names"""
+    return pd.read_csv(fixture_dir / "chars_sample_athena.csv")
+
+
+@pytest.fixture(scope="module")
+def chars_sample_hie() -> pd.DataFrame:
+    """Sample chars with HIE variable names"""
+    return pd.read_csv(fixture_dir / "chars_sample_hie.csv")
diff --git a/python/tests/fixtures/chars_sample_athena.csv b/python/tests/fixtures/chars_sample_athena.csv
new file mode 120000
index 0000000..6ab79aa
--- /dev/null
+++ b/python/tests/fixtures/chars_sample_athena.csv
@@ -0,0 +1 @@
+../../../data-raw/chars_sample_athena.csv
\ No newline at end of file
diff --git a/python/tests/fixtures/chars_sample_hie.csv b/python/tests/fixtures/chars_sample_hie.csv
new file mode 120000
index 0000000..1340c3f
--- /dev/null
+++ b/python/tests/fixtures/chars_sample_hie.csv
@@ -0,0 +1 @@
+../../../data-raw/chars_sample_hie.csv
\ No newline at end of file
diff --git a/python/tests/test_vars_funs.py b/python/tests/test_vars_funs.py
new file mode 100644
index 0000000..63c7c93
--- /dev/null
+++ b/python/tests/test_vars_funs.py
@@ -0,0 +1,124 @@
+import pandas as pd
+import pytest
+
+import ccao
+import ccao.vars_funs
+
+
+class TestVarsRename:
+    @pytest.mark.parametrize("output_type", ["inplace", "vector"])
+    def test_vars_rename_input_data_is_dataframe(
+        self, output_type, chars_sample_athena
+    ):
+        data = chars_sample_athena.iloc[:, 13:19].copy()
+        result = ccao.vars_rename(
+            data=data,
+            names_from="athena",
+            names_to="pretty",
+            output_type=output_type,
+        )
+        expected = [
+            "Apartments",
+            "Cathedral Ceiling",
+            "Attic Finish",
+            "Garage 1 Attached",
+            "Garage 1 Area Included",
+            "Garage 1 Size",
+        ]
+        if output_type == "inplace":
+            assert list(result.columns) == expected
+        else:
+            assert result == expected
+
+    @pytest.mark.parametrize("output_type", ["inplace", "vector"])
+    def test_vars_rename_input_data_is_list(self, output_type):
+        result = ccao.vars_rename(
+            data=["Apartments", "Cathedral Ceiling"],
+            names_from="pretty",
+            names_to="model",
+            output_type=output_type,
+        )
+        expected = ["char_apts", "char_tp_dsgn"]
+        # Output should be the same regardless of the value of `output_type`
+        assert result == expected
+
+    def test_vars_rename_hie_to_athena(self, chars_sample_hie):
+        data = chars_sample_hie.iloc[:, 1:3].copy()
+        result = ccao.vars_rename(
+            data=data,
+            names_from="hie",
+            names_to="athena",
+            output_type="vector",
+        )
+        expected = ["township_code", "card"]
+        assert result == expected
+
+    def test_vars_rename_unmatched_cols_unchanged(self):
+        # If columns are not present in the dictionary, leave them as-is
+        unmatched_colnames = ["foo", "bar", "baz"]
+        result = ccao.vars_rename(
+            data=unmatched_colnames, names_from="hie", names_to="athena"
+        )
+        assert result == unmatched_colnames
+
+    def test_vars_rename_custom_dictionary(self):
+        result = ccao.vars_rename(
+            data=["1", "2", "3"],
+            names_from="foo",
+            names_to="bar",
+            dictionary=pd.DataFrame(
+                {
+                    "var_name_foo": ["1", "2", "3"],
+                    "var_name_bar": ["char_1", "char_2", "char_3"],
+                }
+            ),
+        )
+        expected = ["char_1", "char_2", "char_3"]
+        assert result == expected
+
+    def test_vars_rename_invalid_dictionary_empty(self):
+        with pytest.raises(ValueError) as exc:
+            ccao.vars_rename(
+                data=["1", "2", "3"],
+                names_from="sql",
+                names_to="char",
+                dictionary=pd.DataFrame(),
+            )
+        assert "non-empty" in str(exc.value)
+
+    def test_vars_rename_invalid_dictionary_missing_variable_columns(self):
+        with pytest.raises(ValueError) as exc:
+            ccao.vars_rename(
+                data=["1", "2", "3"],
+                names_from="foo",
+                names_to="bar",
+                dictionary=pd.DataFrame(
+                    {
+                        "foo": ["1", "2", "3"],
+                        "bar": ["char_1", "char_2", "char_3"],
+                    }
+                ),
+            )
+        assert f"starting with {ccao.vars_funs.VAR_NAME_PREFIX}" in str(
+            exc.value
+        )
+
+    @pytest.mark.parametrize(
+        "names_from,names_to", [("1", "pretty"), ("pretty", "1")]
+    )
+    def test_vars_rename_invalid_names(self, names_from, names_to):
+        with pytest.raises(ValueError) as exc:
+            ccao.vars_rename(
+                data=["1", "2", "3"], names_from=names_from, names_to=names_to
+            )
+        assert "must be one of" in str(exc.value)
+
+    def test_vars_rename_invalid_output_type(self):
+        with pytest.raises(ValueError) as exc:
+            ccao.vars_rename(
+                data=["Apartments", "Cathedral Ceiling"],
+                names_from="pretty",
+                names_to="model",
+                output_type="foo",
+            )
+        assert "output_type must be one of" in str(exc.value)