Add black to pre-commit and requirements.

Follow on PR to reformat existing files
nanne-aben · Oct 19, 2023 · 316c43f · 316c43f
1 parent 293a0ab
commit 316c43f
Show file tree

Hide file tree

Showing 18 changed files with 174 additions and 132 deletions.
diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
@@ -21,6 +21,8 @@ jobs:
           python -m pip install --upgrade pip
           pip install -r requirements.txt
           pip install -r requirements-dev.txt
+      - name: Lint with black
+        run: black --check .
       - name: Lint with flake8
         run: |
           flake8

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -11,6 +11,13 @@ repos:
     entry: mypy
     language: system
     types: [python]
+  - id: black
+    name: black
+    description: "Black: The uncompromising Python code formatter"
+    entry: black
+    language: system
+    require_serial: true
+    files: \.(py|ipynb)$
   - id: pytest
     name: pytest
     entry: coverage run -m pytest --typeguard-packages=strictly_typed_pandas,tests

diff --git a/docs/source/advanced.ipynb b/docs/source/advanced.ipynb
@@ -17,6 +17,7 @@
     "%autoreload 2\n",
     "\n",
     "import sys\n",
+    "\n",
     "sys.path.append(\"../\")"
    ]
   },
@@ -37,19 +38,22 @@
    "source": [
     "from strictly_typed_pandas import DataSet\n",
     "\n",
+    "\n",
     "class SchemaA:\n",
     "    name: str\n",
     "\n",
+    "\n",
     "class SchemaB(SchemaA):\n",
     "    id: int\n",
     "\n",
+    "\n",
     "df = DataSet[SchemaA]({\"name\": [\"John\", \"Jane\", \"Jack\"]})\n",
     "\n",
+    "\n",
     "def foo(df: DataSet[SchemaA]) -> DataSet[SchemaB]:\n",
-    "    return (\n",
-    "        df.assign(id=lambda df: range(df.shape[0]))\n",
-    "        .pipe(DataSet[SchemaB])\n",
-    "    )"
+    "    return df.assign(\n",
+    "        id=lambda df: range(df.shape[0]),\n",
+    "    ).pipe(DataSet[SchemaB])"
    ]
   },
   {
@@ -69,19 +73,19 @@
     "    id: int\n",
     "    name: str\n",
     "\n",
+    "\n",
     "class SchemaB:\n",
     "    id: int\n",
     "    job: str\n",
     "\n",
+    "\n",
     "class SchemaAB(SchemaA, SchemaB):\n",
     "    pass\n",
     "\n",
+    "\n",
     "df1 = DataSet[SchemaA]({\"id\": [1, 2, 3], \"name\": [\"John\", \"Jane\", \"Jack\"]})\n",
     "df2 = DataSet[SchemaB]({\"id\": [1, 2, 3], \"job\": \"Data Scientist\"})\n",
-    "(\n",
-    "    df1.merge(df2, on=\"id\")\n",
-    "    .pipe(DataSet[SchemaAB])\n",
-    ")"
+    "df1.merge(df2, on=\"id\").pipe(DataSet[SchemaAB])"
    ]
   },
   {
@@ -102,6 +106,7 @@
     "    id: int\n",
     "    name: str\n",
     "\n",
+    "\n",
     "DataSet[Schema]()"
    ]
   },
@@ -123,18 +128,20 @@
     "import pandas as pd\n",
     "from typing import Any\n",
     "\n",
+    "\n",
     "class Schema:\n",
     "    name: pd.StringDtype\n",
     "    money: np.float64\n",
     "    eggs: np.int64\n",
     "    potatoes: Any\n",
     "\n",
+    "\n",
     "df = DataSet[Schema](\n",
     "    {\n",
     "        \"name\": pd.Series([\"John\", \"Jane\", \"Jack\"], dtype=\"string\"),\n",
     "        \"money\": pd.Series([100.50, 1000.23, 123.45], dtype=np.float64),\n",
     "        \"eggs\": pd.Series([1, 2, 3], dtype=np.int64),\n",
-    "        \"potatoes\": [\"1\", 0, np.nan]\n",
+    "        \"potatoes\": [\"1\", 0, np.nan],\n",
     "    }\n",
     ")\n",
     "\n",
@@ -158,13 +165,16 @@
    "source": [
     "from strictly_typed_pandas import IndexedDataSet\n",
     "\n",
+    "\n",
     "class IndexSchema:\n",
     "    id: int\n",
     "    job: str\n",
     "\n",
+    "\n",
     "class DataSchema:\n",
     "    name: str\n",
     "\n",
+    "\n",
     "df = (\n",
     "    pd.DataFrame({\"id\": [1, 2, 3], \"name\": [\"John\", \"Jane\", \"Jack\"], \"job\": \"Data Scientist\"})\n",
     "    .set_index([\"id\", \"job\"])\n",
@@ -189,14 +199,14 @@
     "class SchemaA:\n",
     "    name: str\n",
     "\n",
+    "\n",
     "class SchemaB(SchemaA):\n",
     "    id: int\n",
     "\n",
+    "\n",
     "def foo(df: DataSet[SchemaA]) -> DataSet[SchemaB]:\n",
-    "    return (\n",
-    "        df.assign(id=1)\n",
-    "        .pipe(DataSet[SchemaB])\n",
-    "    )\n",
+    "    return df.assign(id=1).pipe(DataSet[SchemaB])\n",
+    "\n",
     "\n",
     "df = DataSet[SchemaA]({\"name\": [\"John\", \"Jane\", \"Jack\"]})\n",
     "df = foo(df)\n",

diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -19,20 +19,20 @@
 
 # -- Project information -----------------------------------------------------
 
-project = 'Strictly Typed Pandas'
-copyright = '2021, Nanne Aben'
-author = 'Nanne Aben'
+project = "Strictly Typed Pandas"
+copyright = "2021, Nanne Aben"
+author = "Nanne Aben"
 
 
 # -- General configuration ---------------------------------------------------
 
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
-extensions = ['sphinx.ext.autodoc', 'sphinx_rtd_theme', 'nbsphinx']
+extensions = ["sphinx.ext.autodoc", "sphinx_rtd_theme", "nbsphinx"]
 
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
+templates_path = ["_templates"]
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
@@ -45,9 +45,9 @@
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'sphinx_rtd_theme'
+html_theme = "sphinx_rtd_theme"
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = ["_static"]
diff --git a/docs/source/deepdive_into_dtypes.ipynb b/docs/source/deepdive_into_dtypes.ipynb
@@ -17,6 +17,7 @@
     "%autoreload 2\n",
     "\n",
     "import sys\n",
+    "\n",
     "sys.path.append(\"../\")\n",
     "\n",
     "import pandas as pd\n",
@@ -45,7 +46,7 @@
     "    {\n",
     "        \"a\": pd.Series([1, 2, 3], dtype=int),\n",
     "        \"b\": pd.Series([1.0, 2.0, 3.0], dtype=float),\n",
-    "        \"c\": pd.Series([True, False, True], dtype=bool)\n",
+    "        \"c\": pd.Series([True, False, True], dtype=bool),\n",
     "    }\n",
     ")\n",
     "\n",
@@ -106,6 +107,7 @@
     "    b: float\n",
     "    c: bool\n",
     "\n",
+    "\n",
     "df = DataSet[Schema]()\n",
     "df.dtypes"
    ]
@@ -121,6 +123,7 @@
     "    b: np.float64\n",
     "    c: np.bool_\n",
     "\n",
+    "\n",
     "df = DataSet[Schema]()\n",
     "df.dtypes"
    ]
@@ -142,11 +145,9 @@
     "    a: np.integer\n",
     "    b: np.float_\n",
     "\n",
+    "\n",
     "df = DataSet[Schema](\n",
-    "    {\n",
-    "        \"a\": pd.Series([1, 2, 3], dtype=np.int64),\n",
-    "        \"b\": pd.Series([1.0, 2.0, 3.0], dtype=np.float64)\n",
-    "    }\n",
+    "    {\"a\": pd.Series([1, 2, 3], dtype=np.int64), \"b\": pd.Series([1.0, 2.0, 3.0], dtype=np.float64)}\n",
     ")\n",
     "df.dtypes"
    ]
@@ -169,6 +170,7 @@
     "    a: np.datetime64\n",
     "    b: np.timedelta64\n",
     "\n",
+    "\n",
     "df = DataSet[Schema]()\n",
     "df.dtypes"
    ]
@@ -202,6 +204,7 @@
     "    f: pd.Int64Dtype\n",
     "    h: pd.BooleanDtype\n",
     "\n",
+    "\n",
     "df = DataSet[Schema]()\n",
     "df.dtypes"
    ]
@@ -224,14 +227,13 @@
     "class SchemaA:\n",
     "    a: pd.Int64Dtype\n",
     "\n",
+    "\n",
     "class SchemaB:\n",
     "    a: np.int64\n",
     "\n",
+    "\n",
     "try:\n",
-    "    (\n",
-    "        DataSet[SchemaA]()\n",
-    "        .pipe(DataSet[SchemaB])\n",
-    "    )\n",
+    "    (DataSet[SchemaA]().pipe(DataSet[SchemaB]))\n",
     "except TypeError as e:\n",
     "    print(e)"
    ]
@@ -254,10 +256,11 @@
     "    a: str\n",
     "    b: pd.StringDtype\n",
     "\n",
+    "\n",
     "df = DataSet[Schema](\n",
     "    {\n",
     "        \"a\": pd.Series([\"a\", \"b\", \"c\"], dtype=\"string\"),\n",
-    "        \"b\": pd.Series([\"a\", \"b\", \"c\"], dtype=\"string\")\n",
+    "        \"b\": pd.Series([\"a\", \"b\", \"c\"], dtype=\"string\"),\n",
     "    }\n",
     ")\n",
     "df.dtypes"
@@ -296,6 +299,7 @@
     "class Schema:\n",
     "    a: str\n",
     "\n",
+    "\n",
     "df = DataSet[Schema]({\"a\": [\"a\", \"b\", \"c\"]})\n",
     "df.dtypes"
    ]
@@ -316,11 +320,8 @@
     "class Schema:\n",
     "    a: str\n",
     "\n",
-    "df = DataSet[Schema](\n",
-    "    {\n",
-    "        \"a\": [None, 42, lambda x: x]\n",
-    "    }\n",
-    ")\n",
+    "\n",
+    "df = DataSet[Schema]({\"a\": [None, 42, lambda x: x]})\n",
     "df.dtypes"
    ]
   },
@@ -340,11 +341,8 @@
     "class Schema:\n",
     "    a: pd.StringDtype\n",
     "\n",
-    "df = DataSet[Schema](\n",
-    "    {\n",
-    "        \"a\": pd.Series([\"a\", \"b\", \"c\"], dtype=\"string\")\n",
-    "    }\n",
-    ")"
+    "\n",
+    "df = DataSet[Schema]({\"a\": pd.Series([\"a\", \"b\", \"c\"], dtype=\"string\")})"
    ]
   },
   {
@@ -354,11 +352,7 @@
    "outputs": [],
    "source": [
     "try:\n",
-    "    DataSet[Schema](\n",
-    "        {\n",
-    "            \"a\": [None, 42, lambda x: x]\n",
-    "        }\n",
-    "    )\n",
+    "    DataSet[Schema]({\"a\": [None, 42, lambda x: x]})\n",
     "except TypeError as e:\n",
     "    print(e)"
    ]
@@ -382,10 +376,11 @@
     "    a: Any\n",
     "    b: Any\n",
     "\n",
+    "\n",
     "df = DataSet[Schema](\n",
     "    {\n",
     "        \"a\": [1, 2, 3],\n",
-    "        \"b\": [\"1\", 2, None]\n",
+    "        \"b\": [\"1\", 2, None],\n",
     "    }\n",
     ")\n",
     "df.dtypes"