spells-mtg 0.9.7__tar.gz → 0.10.0__tar.gz

{spells_mtg-0.9.7 → spells_mtg-0.10.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spells-mtg
-Version: 0.9.7
+Version: 0.10.0
 Summary: analaysis of 17Lands.com public datasets
 Author-Email: Joel Barnes <oelarnes@gmail.com>
 License: MIT

{spells_mtg-0.9.7 → spells_mtg-0.10.0}/pyproject.toml

@@ -11,7 +11,7 @@ dependencies = [
 ]
 requires-python = ">=3.11"
 readme = "README.md"
-version = "0.9.7"
+version = "0.10.0"
 
 [project.license]
 text = "MIT"

{spells_mtg-0.9.7 → spells_mtg-0.10.0}/spells/config.py

@@ -11,6 +11,7 @@ all_sets = [
     "WOE",
     "LTR",
     "MOM",
+    "SIR",
     "ONE",
     "BRO",
     "DMU",

{spells_mtg-0.9.7 → spells_mtg-0.10.0}/spells/log.py

@@ -63,10 +63,12 @@ def console_logging(log_level):
         logger.removeHandler(console_handler)
 
 
-def make_verbose(level: int = logging.ERROR) -> Callable:
+def make_verbose(level: int | None = None) -> Callable:
     def decorator(func: Callable) -> Callable:
         @wraps(func)
-        def wrapped(*args, log_to_console: int = level, **kwargs):
+        def wrapped(*args, log_to_console: int | None = level, **kwargs):
+            if log_to_console is None:
+                return func(*args, **kwargs)
             with console_logging(log_to_console):
                 return func(*args, **kwargs)
 

spells_mtg-0.10.0/spells/utils.py

@@ -0,0 +1,55 @@
+import polars as pl
+
+def convert_to_expr_list(
+    input: str | pl.Expr | list[str | pl.Expr] | None
+):
+    if input is None:
+        return []
+
+    input_list = [input] if isinstance(input, str | pl.Expr) else input
+    return [pl.col(i) if isinstance(i, str) else i for i in input_list]
+
+
+def wavg(
+    df: pl.DataFrame, 
+    cols: str | pl.Expr | list[str | pl.Expr],
+    weights: str | pl.Expr | list[str | pl.Expr],
+    group_by: str | pl.Expr | list[str | pl.Expr] | None = None,
+    new_names: str | list[str] | None = None,
+) -> pl.DataFrame:
+    col_list = convert_to_expr_list(cols)
+    weight_list = convert_to_expr_list(weights)
+    gbs = convert_to_expr_list(group_by)
+
+    name_list: list[str]
+    if isinstance(new_names, str):
+        name_list = [new_names]
+    elif new_names is None:
+        name_list = [c.meta.output_name() for c in col_list]
+    else:
+        name_list = list(new_names)
+
+    assert len(name_list) == len(col_list), f"{len(name_list)} names provided for {len(col_list)} columns"
+    assert len(name_list) == len(set(name_list)), "Output names must be unique"
+    assert len(weight_list) == len(col_list) or len(weight_list) == 1, f"{len(weight_list)} weights provided for {len(col_list)} columns" 
+
+    enum_wl = weight_list * int(len(col_list) / len(weight_list))
+    wl_names = [w.meta.output_name() for w in weight_list]
+    assert len(wl_names) == len(set(wl_names)), "Weights must have unique names. Send one weight column or n uniquely named ones"
+    
+    to_group = df.select(gbs + weight_list + [ 
+        (c * enum_wl[i]).alias(name_list[i]) for i, c in enumerate(col_list)
+    ]) 
+
+    grouped = to_group if not gbs else to_group.group_by(gbs)
+
+    ret_df = grouped.sum().select(
+        gbs + 
+        wl_names + 
+        [(pl.col(name) / pl.col(enum_wl[i].meta.output_name())) for i, name in enumerate(name_list)]
+    )
+   
+    if gbs:
+        ret_df = ret_df.sort(by=gbs)
+
+    return ret_df

spells_mtg-0.10.0/tests/utils_test.py

@@ -0,0 +1,174 @@
+
+"""
+Test behavior of wavg utility for Polars DataFrames
+"""
+
+import pytest
+import polars as pl
+
+import spells.utils as utils
+
+def format_test_string(test_string: str) -> str:
+    """
+    strip whitespace from each line to test pasted dataframe outputs
+    """
+    return "\n".join(
+        [line.strip() for line in test_string.splitlines() if line.strip()]
+    )
+
+test_df = pl.DataFrame({
+    'cat': ['a',    'a',    'b',    'b',    'b',    'c'     ],
+    'va1': [1.0,    -1.0,   0.2,    0.4,    0.0,    10.0    ],
+    'va2': [4.0,    3.0,    1.0,    -2.0,   2.0,    1.0     ],
+    'wt1': [1,      2,      0,      2,      3,      1       ],
+    'wt2': [2,      4,      1,      1,      1,      2,      ],
+})
+
+
+# test wavg with default args 
+@pytest.mark.parametrize(
+    "cols, weights, expected",
+    [
+        (
+            'va1', 
+            'wt1', 
+            """
+shape: (1, 2)
+┌─────┬──────────┐
+│ wt1 ┆ va1      │
+│ --- ┆ ---      │
+│ i64 ┆ f64      │
+╞═════╪══════════╡
+│ 9   ┆ 1.088889 │
+└─────┴──────────┘
+"""
+         ),
+        (
+            ['va1', 'va2'],
+            'wt1',
+            """
+shape: (1, 3)
+┌─────┬──────────┬──────────┐
+│ wt1 ┆ va1      ┆ va2      │
+│ --- ┆ ---      ┆ ---      │
+│ i64 ┆ f64      ┆ f64      │
+╞═════╪══════════╪══════════╡
+│ 9   ┆ 1.088889 ┆ 1.444444 │
+└─────┴──────────┴──────────┘
+"""
+        ),
+        (
+            ['va1', 'va2'],
+            ['wt1', 'wt2'],
+            """
+shape: (1, 4)
+┌─────┬─────┬──────────┬──────────┐
+│ wt1 ┆ wt2 ┆ va1      ┆ va2      │
+│ --- ┆ --- ┆ ---      ┆ ---      │
+│ i64 ┆ i64 ┆ f64      ┆ f64      │
+╞═════╪═════╪══════════╪══════════╡
+│ 9   ┆ 11  ┆ 1.088889 ┆ 2.090909 │
+└─────┴─────┴──────────┴──────────┘
+"""
+        ),
+        (
+            [pl.col('va1') + 1, 'va2'],
+            ['wt1', pl.col('wt2') + 1],
+            """
+shape: (1, 4)
+┌─────┬─────┬──────────┬──────────┐
+│ wt1 ┆ wt2 ┆ va1      ┆ va2      │
+│ --- ┆ --- ┆ ---      ┆ ---      │
+│ i64 ┆ i64 ┆ f64      ┆ f64      │
+╞═════╪═════╪══════════╪══════════╡
+│ 9   ┆ 17  ┆ 2.088889 ┆ 1.882353 │
+└─────┴─────┴──────────┴──────────┘
+"""
+        ),
+    ] 
+)
+def test_wavg_defaults(cols: str | pl.Expr | list[str | pl.Expr], weights: str | pl.Expr | list[str | pl.Expr], expected: str):
+    result = utils.wavg(test_df, cols, weights)
+
+    test_str = str(result)
+    print(test_str)
+    assert test_str == format_test_string(expected)
+
+
+# test wavg with named args
+@pytest.mark.parametrize(
+    "cols, weights, group_by, new_names, expected",
+    [
+        (
+            "va1",
+            "wt1",
+            [],
+            "v1",
+            """
+shape: (1, 2)
+┌─────┬──────────┐
+│ wt1 ┆ v1       │
+│ --- ┆ ---      │
+│ i64 ┆ f64      │
+╞═════╪══════════╡
+│ 9   ┆ 1.088889 │
+└─────┴──────────┘
+"""
+        ),
+        (
+            "va1",
+            "wt1",
+            "cat",
+            "va1",
+            """
+shape: (3, 3)
+┌─────┬─────┬───────────┐
+│ cat ┆ wt1 ┆ va1       │
+│ --- ┆ --- ┆ ---       │
+│ str ┆ i64 ┆ f64       │
+╞═════╪═════╪═══════════╡
+│ a   ┆ 3   ┆ -0.333333 │
+│ b   ┆ 5   ┆ 0.16      │
+│ c   ┆ 1   ┆ 10.0      │
+└─────┴─────┴───────────┘
+"""
+        ),
+        (
+            ["va1", "va1"],
+            ["wt1", "wt2"],
+            ["cat"],
+            ["v@1", "v@2"],
+            """
+shape: (3, 5)
+┌─────┬─────┬─────┬───────────┬───────────┐
+│ cat ┆ wt1 ┆ wt2 ┆ v@1       ┆ v@2       │
+│ --- ┆ --- ┆ --- ┆ ---       ┆ ---       │
+│ str ┆ i64 ┆ i64 ┆ f64       ┆ f64       │
+╞═════╪═════╪═════╪═══════════╪═══════════╡
+│ a   ┆ 3   ┆ 6   ┆ -0.333333 ┆ -0.333333 │
+│ b   ┆ 5   ┆ 3   ┆ 0.16      ┆ 0.2       │
+│ c   ┆ 1   ┆ 2   ┆ 10.0      ┆ 10.0      │
+└─────┴─────┴─────┴───────────┴───────────┘
+"""
+        )
+    ]
+)
+def test_wavg(
+    cols: str | pl.Expr | list[str | pl.Expr], 
+    weights: str | pl.Expr | list[str | pl.Expr], 
+    group_by: str | pl.Expr | list[str | pl.Expr],
+    new_names: str | list[str],
+    expected: str,
+):
+    result = utils.wavg(
+        test_df, 
+        cols, 
+        weights,
+        group_by=group_by,
+        new_names=new_names,
+    )
+
+    test_str = str(result)
+    print(test_str)
+    assert test_str == format_test_string(expected)
+