some formatting and add cli compilation

justfile

@@ -13,8 +13,12 @@ test:
 format:
   uv run ruff format src test
 
+example:
+  uv run python src/main.py test/test_ballot.csv
+
 compile:
-  uv run pyinstaller src/main.py
+  uv run pyinstaller --clean -F src/main.py --name smithy
+  
 
 clean:
   uv run pyclean src test

pyproject.toml

@@ -14,7 +14,7 @@ dependencies = [
 ]
 
 [project.scripts]
-smithy = "smithy:main"
+smithy = "smithy:cli"
 
 [build-system]
 requires = ["uv_build>=0.11.7,<0.12.0"]

requirements.txt

@@ -118,7 +118,9 @@ platformdirs==4.9.6
 pluggy==1.6.0
     # via pytest
 polars==1.40.1
-    # via marimo
+    # via
+    #   smithy (pyproject.toml)
+    #   marimo
 polars-runtime-32==1.40.1
     # via polars
 psutil==7.2.2

smithy.spec

@@ -0,0 +1,38 @@
+# -*- mode: python ; coding: utf-8 -*-
+
+
+a = Analysis(
+    ['src/main.py'],
+    pathex=[],
+    binaries=[],
+    datas=[],
+    hiddenimports=[],
+    hookspath=[],
+    hooksconfig={},
+    runtime_hooks=[],
+    excludes=[],
+    noarchive=False,
+    optimize=0,
+)
+pyz = PYZ(a.pure)
+
+exe = EXE(
+    pyz,
+    a.scripts,
+    a.binaries,
+    a.datas,
+    [],
+    name='smithy',
+    debug=False,
+    bootloader_ignore_signals=False,
+    strip=False,
+    upx=True,
+    upx_exclude=[],
+    runtime_tmpdir=None,
+    console=True,
+    disable_windowed_traceback=False,
+    argv_emulation=False,
+    target_arch=None,
+    codesign_identity=None,
+    entitlements_file=None,
+)

src/main.py

@@ -0,0 +1,4 @@
+from smithy import cli
+
+if __name__ == "__main__":
+    cli()

src/smithy/__init__.py

@@ -7,23 +7,20 @@ from rich.panel import Panel
 
 from .rcv import smith_set
 
-console = Console()
 
 @click.command()
-@click.argument(
+@click.argument("spreadsheet", type=click.Path(exists=True, dir_okay=False))
-    "spreadsheet",
+def cli(spreadsheet: str) -> None:
-    type=click.Path(exists=True, dir_okay=False)
-)
-def main(spreadsheet: str) -> None:
     """
     Compute the Smith set from a ranked-choice ballot spreadsheet.
-    
+
     The Smith set is the minimal set of candidates which can beat all others pairwise - if there is a single winner
     in the set they are guaranteed the Condorcet i.e. Majority winner.
     """
 
-    try:
+    console = Console()
 
+    try:
         # Load spreadsheet
         if spreadsheet.endswith(".csv"):
             df = pl.read_csv(spreadsheet)
@@ -33,17 +30,21 @@ def main(spreadsheet: str) -> None:
 
         else:
             console.print(
-                "[bold red]Unsupported file type.[/bold red]\n"
+                "[bold red]Unsupported file type.[/bold red]\nUse CSV or Excel."
-                "Use CSV or Excel."
             )
             raise SystemExit(1)
 
         # Normalize numerical dataframe entries
-        df = df.with_columns([ pl.col(c)
+        df = df.with_columns(
-                             .cast(pl.Utf8)
+            [
-                             .str.strip_chars()
+                pl.col(c)
-                             .cast(pl.Int64, strict=False).fill_null(0)
+                .cast(pl.Utf8)
-                             for c in df.columns ])
+                .str.strip_chars()
+                .cast(pl.Int64, strict=False)
+                .fill_null(0)
+                for c in df.columns
+            ]
+        )
 
         # Compute Smith set
         smiths = smith_set(df)
@@ -66,14 +67,11 @@ def main(spreadsheet: str) -> None:
             Panel.fit(
                 "\n".join(f"• {c}" for c in smiths),
                 title="Resulting Smith Set",
-                border_style="green"
+                border_style="green",
             )
         )
 
     except Exception as e:
-
+        console.print(f"[bold red]Error:[/bold red] {e}")
-        console.print(
-            f"[bold red]Error:[/bold red] {e}"
-        )
 
         raise SystemExit(1)

src/smithy/rcv.py

@@ -1,13 +1,14 @@
 import polars as pl
 from itertools import combinations
 
+
 def smith_set(df: pl.DataFrame) -> list:
     """
     Compute the Smith set from a Ranked-Choice ballot.
-    
+
     The Smith set is the minimal set of candidates which can beat all others pairwise - if there is a single winner
     in the set they are guaranteed the Condorcet i.e. Majority winner.
-    
+
     parameters
     ---
     df : pl.DataFrame
@@ -27,7 +28,7 @@ def smith_set(df: pl.DataFrame) -> list:
     candidates = df.columns
 
     # Build pairwise majority graph
-    graph: dict[str, set[str]] = { c: set() for c in candidates }
+    graph: dict[str, set[str]] = {c: set() for c in candidates}
 
     for a, b in combinations(candidates, 2):
         result = df.select(
@@ -46,17 +47,13 @@ def smith_set(df: pl.DataFrame) -> list:
 
     # Find Smith set
     for size in range(1, len(candidates) + 1):
-
         for sub in combinations(candidates, size):
-
             subset = set(sub)
             out = set(candidates) - subset
 
             dom = True
 
             for member in subset:
-
-                # DIRECT dominance only
                 if not out.issubset(graph[member]):
                     dom = False
                     break

test/test_nb.py

@@ -23,18 +23,23 @@ def _():
 @app.cell
 def _(mo, pl):
     df = pl.read_csv(mo.notebook_dir() / "test_ballot.csv")
-    df = df.with_columns([ pl.col(c) # make safe, clean up
+    df = df.with_columns(
-                             .cast(pl.Utf8)
+        [
-                              .str.strip_chars()
+            pl.col(c)  # make safe, clean up
-                              .cast(pl.Int64, strict=False).fill_null(df.width + 1)
+            .cast(pl.Utf8)
-                                 for c in df.columns ])
+            .str.strip_chars()
+            .cast(pl.Int64, strict=False)
+            .fill_null(df.width + 1)
+            for c in df.columns
+        ]
+    )
     df
     return (df,)
 
 
 @app.cell
 def _(df, smith_set):
-    smith_set(df) # find the smith set (should be "Alice" and "Bob" as a pair)
+    smith_set(df)  # find the smith set (should be "Alice" and "Bob" as a pair)
     return
 
 

test/test_rcvs.py

@@ -1,35 +1,41 @@
 import polars as pl
 from smithy import smith_set
 
+
 def test_condorcet():
-    df = pl.DataFrame({
+    df = pl.DataFrame(
-                          'A': [1, 1, 2, 1],
+        {
-                          'B': [2, 2, 1, 2],
+            "A": [1, 1, 2, 1],
-                          'C': [3, 3, 3, 3],
+            "B": [2, 2, 1, 2],
-                      })
+            "C": [3, 3, 3, 3],
-    assert smith_set(df) == ['A']
+        }
+    )
+    assert smith_set(df) == ["A"]
+
 
 def test_rockpprscrcycle():
-    df = pl.DataFrame({
+    df = pl.DataFrame(
-                             'A': [1, 2, 3],
+        {
-                             'B': [2, 3, 1],
+            "A": [1, 2, 3],
-                             'C': [3, 1, 2],
+            "B": [2, 3, 1],
-                         })
+            "C": [3, 1, 2],
-    assert smith_set(df) == ['A', 'B', 'C']
+        }
+    )
+    assert smith_set(df) == ["A", "B", "C"]
+
 
 def test_abpair():
-    df = pl.DataFrame({
+    df = pl.DataFrame({"A": [1, 2, 1, 3], "B": [2, 1, 3, 1], "C": [3, 3, 2, 2]})
-        "A": [1, 2, 1, 3],
+    assert smith_set(df) == ["A", "B"]
-        "B": [2, 1, 3, 1],
+
-        "C": [3, 3, 2, 2]
-        })
-    assert smith_set(df) == ['A', 'B']
 
 def test_fourcycle():
-    df = pl.DataFrame({
+    df = pl.DataFrame(
-        "A": [1,2,3,4],
+        {
-        "B": [2,3,4,1],
+            "A": [1, 2, 3, 4],
-        "C": [3,4,1,2],
+            "B": [2, 3, 4, 1],
-        "D": [4,1,2,3],
+            "C": [3, 4, 1, 2],
-    })
+            "D": [4, 1, 2, 3],
-    assert smith_set(df) == ['A', 'B', 'C', 'D']
+        }
+    )
+    assert smith_set(df) == ["A", "B", "C", "D"]