chore: ensure pre-commit run --all-files runs (#227)

docsite/docs/assets/styles.css

@@ -4,4 +4,4 @@
 
 .jp-Collapser {
     --jp-cell-collapser-width: 0px;
-}
+}

docsite/docs/guides/contrasts.ipynb

@@ -104,14 +104,17 @@
     }
    ],
    "source": [
+    "from pandas import Categorical, DataFrame\n",
+    "\n",
     "from formulaic import model_matrix\n",
-    "from pandas import DataFrame, Categorical\n",
     "\n",
-    "df = DataFrame({\n",
-    "    \"letters\": [\"a\", \"b\", \"c\"],\n",
-    "    \"numbers\": Categorical([1,2,3]),\n",
-    "    \"values\": [20, 200, 30],\n",
-    "})\n",
+    "df = DataFrame(\n",
+    "    {\n",
+    "        \"letters\": [\"a\", \"b\", \"c\"],\n",
+    "        \"numbers\": Categorical([1, 2, 3]),\n",
+    "        \"values\": [20, 200, 30],\n",
+    "    }\n",
+    ")\n",
     "\n",
     "model_matrix(\"letters + numbers + values\", df)"
    ]
@@ -1220,13 +1223,16 @@
    ],
    "source": [
     "import numpy\n",
-    "Z = numpy.array([\n",
-    "    [1, 0, 0, 0],  # A\n",
-    "    [-1, 1, 0, 0], # B - A\n",
-    "    [0, -1, 1, 0],  # C - B\n",
-    "    [-1, 0, 0, 1],  # D - A\n",
-    "])\n",
-    "coding = numpy.linalg.inv(Z)[:,1:]\n",
+    "\n",
+    "Z = numpy.array(\n",
+    "    [\n",
+    "        [1, 0, 0, 0],  # A\n",
+    "        [-1, 1, 0, 0],  # B - A\n",
+    "        [0, -1, 1, 0],  # C - B\n",
+    "        [-1, 0, 0, 1],  # D - A\n",
+    "    ]\n",
+    ")\n",
+    "coding = numpy.linalg.inv(Z)[:, 1:]\n",
     "coding"
    ]
   },
@@ -1315,7 +1321,9 @@
     }
    ],
    "source": [
-    "model_matrix(\"C(letters, contr.custom(coding))\", DataFrame({\"letters\": [\"A\", \"B\", \"C\", \"D\"]}))"
+    "model_matrix(\n",
+    "    \"C(letters, contr.custom(coding))\", DataFrame({\"letters\": [\"A\", \"B\", \"C\", \"D\"]})\n",
+    ")"
    ]
   },
   {

docsite/docs/guides/formulae.ipynb

@@ -89,9 +89,13 @@
    "source": [
     "from formulaic.parser.types import Factor\n",
     "\n",
-    "Factor(\"1\", eval_method=\"literal\")  # a factor that represents the numerical constant of 1\n",
+    "Factor(\n",
+    "    \"1\", eval_method=\"literal\"\n",
+    ")  # a factor that represents the numerical constant of 1\n",
     "Factor(\"a\")  # a factor that will be looked up from the data context\n",
-    "Factor(\"a + b\", eval_method=\"python\")  # a factor that will return the sum of `a` and `b`"
+    "Factor(\n",
+    "    \"a + b\", eval_method=\"python\"\n",
+    ")  # a factor that will return the sum of `a` and `b`"
    ]
   },
   {
@@ -179,10 +183,13 @@
     "from formulaic import Formula\n",
     "\n",
     "# Unstructured formula (a simple list of terms)\n",
-    "Formula([\n",
-    "    Term(factors=[Factor(\"c\"), Factor(\"d\"), Factor(\"e\")]),\n",
-    "    Term(factors=[Factor(\"a\"), Factor(\"b\")]),\n",
-    "])"
+    "f = Formula(\n",
+    "    [\n",
+    "        Term(factors=[Factor(\"c\"), Factor(\"d\"), Factor(\"e\")]),\n",
+    "        Term(factors=[Factor(\"a\"), Factor(\"b\")]),\n",
+    "    ]\n",
+    ")\n",
+    "f"
    ]
   },
   {
@@ -210,7 +217,7 @@
     }
    ],
    "source": [
-    "type(_), list(_)"
+    "type(f), list(f)"
    ]
   },
   {
@@ -266,7 +273,7 @@
     "        really_nested=[\n",
     "            Term(factors=[Factor(\"really_nested_col\")]),\n",
     "        ],\n",
-    "    )\n",
+    "    ),\n",
     ")\n",
     "f"
    ]
@@ -295,7 +302,7 @@
     }
    ],
    "source": [
-    "type(_)"
+    "type(f)"
    ]
   },
   {
@@ -484,8 +491,9 @@
     "[\n",
     "    f\"{token.token} : {token.kind.value}\"\n",
     "    for token in (\n",
-    "        DefaultFormulaParser(include_intercept=False)\n",
-    "        .get_tokens(\"y ~ 1 + b:log(c) | `d$in^df` + {e + f}\")\n",
+    "        DefaultFormulaParser(include_intercept=False).get_tokens(\n",
+    "            \"y ~ 1 + b:log(c) | `d$in^df` + {e + f}\"\n",
+    "        )\n",
     "    )\n",
     "]"
    ]
@@ -636,7 +644,6 @@
     }
    ],
    "source": [
-    "\n",
     "Formula(\"y ~ a + b:c\", _parser=DefaultFormulaParser(include_intercept=False))"
    ]
   },
@@ -727,7 +734,9 @@
    "source": [
     "import pandas\n",
     "\n",
-    "data = pandas.DataFrame({\"a\": [1,2,3], \"b\": [4,5,6], \"c\": [7, 8, 9], \"A\": [\"a\", \"b\", \"c\"]})\n",
+    "data = pandas.DataFrame(\n",
+    "    {\"a\": [1, 2, 3], \"b\": [4, 5, 6], \"c\": [7, 8, 9], \"A\": [\"a\", \"b\", \"c\"]}\n",
+    ")\n",
     "Formula(\"a + b:c\").get_model_matrix(data)"
    ]
   },
@@ -852,6 +861,7 @@
    ],
    "source": [
     "from formulaic.materializers import PandasMaterializer\n",
+    "\n",
     "PandasMaterializer(data).get_model_matrix(Formula(\"a + b:c\"), output=\"pandas\")"
    ]
   },
@@ -885,6 +895,7 @@
    ],
    "source": [
     "import numpy\n",
+    "\n",
     "from formulaic import ModelMatrix\n",
     "\n",
     "mm = Formula(\"a + b:c\").get_model_matrix(data, output=\"numpy\")\n",

docsite/docs/guides/integration.ipynb

@@ -95,14 +95,15 @@
    ],
    "source": [
     "import pandas\n",
-    "from formulaic import model_matrix\n",
     "from statsmodels.api import OLS\n",
-    "data = pandas.DataFrame({\"y\": [0.1, 0.4, 3], \"a\": [1,2,3], \"b\": [\"A\", \"B\", \"C\"]})\n",
+    "\n",
+    "from formulaic import model_matrix\n",
+    "\n",
+    "data = pandas.DataFrame({\"y\": [0.1, 0.4, 3], \"a\": [1, 2, 3], \"b\": [\"A\", \"B\", \"C\"]})\n",
     "y, X = model_matrix(\"y ~ a + b\", data)\n",
     "model = OLS(y, X)\n",
     "results = model.fit()\n",
-    "print(results.summary())\n",
-    "\n"
+    "print(results.summary())"
    ]
   },
   {
@@ -143,54 +144,64 @@
     "from typing import Iterable, List, Optional\n",
     "\n",
     "from sklearn.base import BaseEstimator, TransformerMixin\n",
-    "from sklearn.pipeline import Pipeline\n",
     "from sklearn.linear_model import LinearRegression\n",
+    "from sklearn.pipeline import Pipeline\n",
+    "\n",
     "from formulaic import Formula, FormulaSpec, ModelSpec\n",
     "\n",
     "\n",
     "class FormulaicTransformer(TransformerMixin, BaseEstimator):\n",
-    "\n",
     "    def __init__(self, formula: FormulaSpec):\n",
     "        self.formula: Formula = Formula.from_spec(formula)\n",
     "        self.model_spec: Optional[ModelSpec] = None\n",
     "        if self.formula._has_structure:\n",
-    "            raise ValueError(f\"Formula specification {repr(formula)} results in a structured formula, which is not supported.\")\n",
+    "            raise ValueError(\n",
+    "                f\"Formula specification {repr(formula)} results in a structured formula, which is not supported.\"\n",
+    "            )\n",
     "\n",
-    "    def fit(self, X, y = None):\n",
+    "    def fit(self, X, y=None):\n",
     "        \"\"\"\n",
     "        Generate the initial model spec by which subsequent X's will be\n",
     "        transformed.\n",
     "        \"\"\"\n",
     "        self.model_spec = self.formula.get_model_matrix(X).model_spec\n",
     "        return self\n",
     "\n",
-    "    def transform(self, X, y = None):\n",
+    "    def transform(self, X, y=None):\n",
     "        \"\"\"\n",
     "        Transform `X` by generating a model matrix from it based on the fit\n",
     "        model spec.\n",
     "        \"\"\"\n",
     "        if self.model_spec is None:\n",
-    "            raise RuntimeError(\"`FormulaicTransformer.fit()` must be called before `.transform()`.\")\n",
+    "            raise RuntimeError(\n",
+    "                \"`FormulaicTransformer.fit()` must be called before `.transform()`.\"\n",
+    "            )\n",
     "        X_ = self.model_spec.get_model_matrix(X)\n",
     "        return X_\n",
     "\n",
-    "    def get_feature_names_out(self, input_features: Optional[Iterable[str]] = None) -> List[str]:\n",
+    "    def get_feature_names_out(\n",
+    "        self, input_features: Optional[Iterable[str]] = None\n",
+    "    ) -> List[str]:\n",
     "        \"\"\"\n",
     "        Expose model spec column names to scikit learn to allow column transforms later in the pipeline.\n",
     "        \"\"\"\n",
     "        if self.model_spec is None:\n",
-    "            raise RuntimeError(\"`FormulaicTransformer.fit()` must be called before columns can be assigned names.\")\n",
+    "            raise RuntimeError(\n",
+    "                \"`FormulaicTransformer.fit()` must be called before columns can be assigned names.\"\n",
+    "            )\n",
     "        return self.model_spec.column_names\n",
     "\n",
     "\n",
-    "pipe = Pipeline([\n",
-    "    (\"formula\", FormulaicTransformer(\"x1 + x2 + x3\")),\n",
-    "    (\"model\", LinearRegression())\n",
-    "])\n",
-    "pipe_fit = pipe.fit(pandas.DataFrame({\"x1\": [1,2,3], \"x2\": [2, 3.4, 6], \"x3\": [7, 3, 1]}), y=pandas.Series([1,3,5]))\n",
+    "pipe = Pipeline(\n",
+    "    [(\"formula\", FormulaicTransformer(\"x1 + x2 + x3\")), (\"model\", LinearRegression())]\n",
+    ")\n",
+    "pipe_fit = pipe.fit(\n",
+    "    pandas.DataFrame({\"x1\": [1, 2, 3], \"x2\": [2, 3.4, 6], \"x3\": [7, 3, 1]}),\n",
+    "    y=pandas.Series([1, 3, 5]),\n",
+    ")\n",
     "pipe_fit\n",
     "# Note: You could optionally serialize `pipe_fit` here.\n",
-    "# Then: Use the pipe to predict outcomes for new data.\n"
+    "# Then: Use the pipe to predict outcomes for new data."
    ]
   }
  ],

docsite/docs/guides/missing_data.ipynb

@@ -108,14 +108,19 @@
     }
    ],
    "source": [
+    "from pandas import Categorical, DataFrame\n",
+    "\n",
     "from formulaic import model_matrix\n",
     "from formulaic.materializers import NAAction\n",
-    "from pandas import DataFrame, Categorical\n",
     "\n",
-    "df = DataFrame({\n",
-    "    \"c\": [1, 2, None, 4, 5],\n",
-    "    \"C\": Categorical([\"a\", \"b\", \"c\", None, \"e\"], categories=[\"a\", \"b\", \"c\", \"d\", \"e\"])\n",
-    "})\n",
+    "df = DataFrame(\n",
+    "    {\n",
+    "        \"c\": [1, 2, None, 4, 5],\n",
+    "        \"C\": Categorical(\n",
+    "            [\"a\", \"b\", \"c\", None, \"e\"], categories=[\"a\", \"b\", \"c\", \"d\", \"e\"]\n",
+    "        ),\n",
+    "    }\n",
+    ")\n",
     "\n",
     "model_matrix(\"c + C\", df, na_action=NAAction.DROP)\n",
     "# Equivlent to:\n",

docsite/docs/guides/model_specs.ipynb

@@ -219,10 +219,11 @@
    ],
    "source": [
     "# Let's get ourselves a simple `ModelMatrix` instance to play with.\n",
-    "from formulaic import model_matrix\n",
     "from pandas import DataFrame\n",
     "\n",
-    "mm = model_matrix(\"center(a) + b\", DataFrame({\"a\": [1,2,3], \"b\": [\"A\", \"B\", \"C\"]}))\n",
+    "from formulaic import model_matrix\n",
+    "\n",
+    "mm = model_matrix(\"center(a) + b\", DataFrame({\"a\": [1, 2, 3], \"b\": [\"A\", \"B\", \"C\"]}))\n",
     "mm"
    ]
   },
@@ -399,9 +400,7 @@
    ],
    "source": [
     "mm_numpy = model_matrix(\n",
-    "    \"center(a) + b\",\n",
-    "    DataFrame({\"a\": [1,2,3], \"b\": [\"A\", \"B\", \"C\"]}),\n",
-    "    output='numpy'\n",
+    "    \"center(a) + b\", DataFrame({\"a\": [1, 2, 3], \"b\": [\"A\", \"B\", \"C\"]}), output=\"numpy\"\n",
     ")\n",
     "mm_numpy"
    ]
@@ -426,7 +425,7 @@
    ],
    "source": [
     "ms_numpy = mm_numpy.model_spec\n",
-    "mm_numpy[:, ms_numpy.term_indices['b']]"
+    "mm_numpy[:, ms_numpy.term_indices[\"b\"]]"
    ]
   },
   {
@@ -539,7 +538,7 @@
     }
    ],
    "source": [
-    "ms.get_model_matrix(DataFrame({\"a\": [4,5,6], \"b\": [\"A\", \"B\", \"D\"]}))"
+    "ms.get_model_matrix(DataFrame({\"a\": [4, 5, 6], \"b\": [\"A\", \"B\", \"D\"]}))"
    ]
   },
   {
@@ -624,7 +623,7 @@
     }
    ],
    "source": [
-    "model_matrix(ms, data=DataFrame({\"a\": [4,5,6], \"b\": [\"A\", \"A\", \"A\"]}))"
+    "model_matrix(ms, data=DataFrame({\"a\": [4, 5, 6], \"b\": [\"A\", \"A\", \"A\"]}))"
    ]
   },
   {
@@ -660,7 +659,7 @@
    "source": [
     "from formulaic import ModelSpec\n",
     "\n",
-    "ms = ModelSpec(\"a+b+c\", output='numpy', ensure_full_rank=False)\n",
+    "ms = ModelSpec(\"a+b+c\", output=\"numpy\", ensure_full_rank=False)\n",
     "ms"
    ]
   },
@@ -684,7 +683,10 @@
    ],
    "source": [
     "import pandas\n",
-    "mm = ms.get_model_matrix(pandas.DataFrame({'a': [1,2,3], 'b': [4,5,6], 'c': [7,8,9]}))\n",
+    "\n",
+    "mm = ms.get_model_matrix(\n",
+    "    pandas.DataFrame({\"a\": [1, 2, 3], \"b\": [4, 5, 6], \"c\": [7, 8, 9]})\n",
+    ")\n",
     "mm"
    ]
   },
@@ -756,7 +758,9 @@
    "source": [
     "from formulaic import Formula, ModelSpecs\n",
     "\n",
-    "ModelSpecs(ModelSpec(\"a\"), substructure=ModelSpec(\"b\"), another_substructure=ModelSpec(\"c\"))"
+    "ModelSpecs(\n",
+    "    ModelSpec(\"a\"), substructure=ModelSpec(\"b\"), another_substructure=ModelSpec(\"c\")\n",
+    ")"
    ]
   },
   {