ruff; code cleanliness; typo fixes

Author: aeturrell

.pre-commit-config.yaml

@@ -15,15 +15,21 @@ repos:
         entry: nbstripout
         language: python
         types: [jupyter]
-  - repo: https://github.com/psf/black
-    rev: 22.8.0
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.4.1
     hooks:
-      - id: black
-        name: black
-        description: 'applies black formatter to .py files'
-        entry: black
-        language: python
-        types: [python]
+      # Run the linter.
+      - id: ruff
+        types_or: [python, pyi, jupyter]
+        args: [ --fix ]
+      - id: ruff
+        types_or: [python, pyi, jupyter]
+        name: sort imports with ruff
+        args: [--select, I, --fix]
+      # Run the formatter.
+      - id: ruff-format
+        types_or: [python, pyi, jupyter]
   - repo: https://github.com/pycqa/flake8
     rev: 3.9.2  # pick a git hash / tag to point to
     hooks:

auto-office.ipynb

@@ -18,11 +18,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import warnings\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
     "import pandas as pd\n",
-    "from rich import inspect\n",
-    "import matplotlib.pyplot as plt\n",
-    "import warnings\n",
     "\n",
     "# Plot settings\n",
     "plt.style.use(\n",
@@ -34,9 +34,11 @@
     "\n",
     "# Set seed for random numbers\n",
     "seed_for_prng = 78557\n",
-    "prng = np.random.default_rng(seed_for_prng)  # prng=probabilistic random number generator\n",
+    "prng = np.random.default_rng(\n",
+    "    seed_for_prng\n",
+    ")  # prng=probabilistic random number generator\n",
     "# Turn off warnings\n",
-    "warnings.filterwarnings('ignore')"
+    "warnings.filterwarnings(\"ignore\")"
    ]
   },
   {

code-advanced.ipynb

@@ -447,7 +447,7 @@
    "outputs": [],
    "source": [
     "number = 1\n",
-    "for func in [lambda x: x + 1, lambda x: x * 2, lambda x: x ** 2]:\n",
+    "for func in [lambda x: x + 1, lambda x: x * 2, lambda x: x**2]:\n",
     "    number = func(number)\n",
     "    print(number)"
    ]
@@ -662,6 +662,7 @@
    "outputs": [],
    "source": [
     "from datetime import date\n",
+    "\n",
     "year_selection = 2030\n",
     "new_year = date(year=year_selection, month=1, day=1)\n",
     "time_till_ny = new_year - date.today()\n",
@@ -844,7 +845,7 @@
  "metadata": {
   "celltoolbar": "Tags",
   "kernelspec": {
-   "display_name": "Python 3.10.12 ('codeforecon')",
+   "display_name": "codeforecon",
    "language": "python",
    "name": "python3"
   },
@@ -859,11 +860,6 @@
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
    "version": "3.10.13"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "c4570b151692b3082981c89d172815ada9960dee4eb0bedb37dc10c95601d3bd"
-   }
   }
  },
  "nbformat": 4,

code-advcd-best-practice.ipynb

@@ -994,7 +994,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import time\n",
     "import cProfile\n",
     "\n",
     "\n",
@@ -1025,7 +1024,6 @@
    "source": [
     "from pyinstrument import Profiler\n",
     "\n",
-    "\n",
     "profiler = Profiler()\n",
     "profiler.start()\n",
     "\n",

code-basics.ipynb

@@ -767,7 +767,7 @@
    "outputs": [],
    "source": [
     "value = 20\n",
-    "sqrt_val = 20 ** 0.5\n",
+    "sqrt_val = 20**0.5\n",
     "print(f\"The square root of {value:d} is {sqrt_val:.2f}\")"
    ]
   },
@@ -1655,6 +1655,7 @@
    "source": [
     "y = \"I'm a global variable\"\n",
     "\n",
+    "\n",
     "def print_y():\n",
     "    print(\"y is inside a function:\", y)\n",
     "\n",

code-further-advanced.ipynb

@@ -64,11 +64,11 @@
    "outputs": [],
    "source": [
     "def square(x):\n",
-    "    return x ** 2\n",
+    "    return x**2\n",
     "\n",
     "\n",
     "def cube(x):\n",
-    "    return x ** 3\n",
+    "    return x**3\n",
     "\n",
     "\n",
     "def higher_order_function(type):  # a higher order function returning a function\n",
@@ -311,7 +311,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sq_nums_lc = [num ** 2 for num in range(2, 6)]\n",
+    "sq_nums_lc = [num**2 for num in range(2, 6)]\n",
     "sq_nums_lc"
    ]
   },
@@ -321,7 +321,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "sq_nums_gc = (num ** 2 for num in range(2, 6))\n",
+    "sq_nums_gc = (num**2 for num in range(2, 6))\n",
     "sq_nums_gc"
    ]
   },
@@ -718,7 +718,7 @@
     "        self.radius = radius\n",
     "\n",
     "    def area(self) -> float:\n",
-    "        return np.pi * self.radius ** 2\n",
+    "        return np.pi * self.radius**2\n",
     "\n",
     "\n",
     "circle1 = Circle1(\"red\", 2)\n",
@@ -763,7 +763,7 @@
     "    radius: float\n",
     "\n",
     "    def area(self) -> float:\n",
-    "        return np.pi * self.radius ** 2\n",
+    "        return np.pi * self.radius**2\n",
     "\n",
     "\n",
     "circle2 = Circle2(\"blue\", 2)\n",
@@ -1050,12 +1050,15 @@
    "outputs": [],
    "source": [
     "def outer_function():\n",
-    "  x = \"hello\"\n",
-    "  def nested_function():\n",
-    "    nonlocal x\n",
-    "    x = \"world\"\n",
-    "  nested_function()\n",
-    "  return x\n",
+    "    x = \"hello\"\n",
+    "\n",
+    "    def nested_function():\n",
+    "        nonlocal x\n",
+    "        x = \"world\"\n",
+    "\n",
+    "    nested_function()\n",
+    "    return x\n",
+    "\n",
     "\n",
     "print(outer_function())"
    ]

coding-for-economists-quickstart.ipynb

@@ -176,9 +176,10 @@
    "outputs": [],
    "source": [
     "# !pip install tqdm\n",
-    "from tqdm import tqdm\n",
     "from time import sleep\n",
     "\n",
+    "from tqdm import tqdm\n",
+    "\n",
     "text = \"\\n Text: \"\n",
     "for bit_of_text in tqdm([\"This\", \"is\", \"a\", \"string\"]):\n",
     "    sleep(0.25)\n",
@@ -296,9 +297,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
     "import os\n",
     "\n",
+    "import pandas as pd\n",
+    "\n",
     "# (Change to link)\n",
     "df = pd.read_csv(os.path.join(\"data\", \"ames_iowa_house_prices.csv\"))\n",
     "df.head()"
@@ -374,9 +376,9 @@
    "outputs": [],
    "source": [
     "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns\n",
-    "import scipy.stats as st\n",
     "import numpy as np\n",
+    "import scipy.stats as st\n",
+    "import seaborn as sns\n",
     "\n",
     "plt.style.use(\"seaborn-notebook\")\n",
     "sns.distplot(df[\"SalePrice\"], bins=100, kde=False, fit=st.lognorm);"

craft_diss_pyramid.py

@@ -1,8 +1,8 @@
-import numpy as np
-import matplotlib.pyplot as plt
-import matplotlib.patches as mpatches
 import textwrap as txtwrp
 
+import matplotlib.patches as mpatches
+import matplotlib.pyplot as plt
+import numpy as np
 
 # Plot settings
 plt.style.use(

data-advanced.ipynb

@@ -304,7 +304,6 @@
     "\n",
     "\n",
     "class Schema(pa.SchemaModel):\n",
-    "\n",
     "    column1: Series[int] = pa.Field(le=10)\n",
     "    column2: Series[float] = pa.Field(lt=-1.2)\n",
     "    column3: Series[str] = pa.Field(str_startswith=\"value_\")\n",
@@ -512,6 +511,7 @@
    "source": [
     "from datetime import datetime\n",
     "from typing import List, Optional\n",
+    "\n",
     "from pydantic import BaseModel\n",
     "\n",
     "\n",

data-analysis-quickstart.ipynb

@@ -35,9 +35,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
-    "import matplotlib.pyplot as plt"
+    "import pandas as pd"
    ]
   },
   {
@@ -48,7 +48,9 @@
    "source": [
     "# Set seed for random numbers\n",
     "seed_for_prng = 78557\n",
-    "prng = np.random.default_rng(seed_for_prng)  # prng=probabilistic random number generator\n"
+    "prng = np.random.default_rng(\n",
+    "    seed_for_prng\n",
+    ")  # prng=probabilistic random number generator"
    ]
   },
   {
@@ -87,12 +89,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df = (pd.read_csv(\n",
+    "df = pd.read_csv(\n",
     "    \"https://github.com/aeturrell/coding-for-economists/raw/main/data/starwars.csv\",\n",
     "    index_col=0,\n",
-    "    )\n",
-    "    .dropna(subset=[\"species\"])\n",
-    "    )\n",
+    ").dropna(subset=[\"species\"])\n",
     "# Check info about dataframe\n",
     "df.info()"
    ]
@@ -307,7 +307,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df['height_m'] = df['height']/100\n",
+    "df[\"height_m\"] = df[\"height\"] / 100\n",
     "df.head()"
    ]
   },
@@ -420,7 +420,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df[\"mass_demean_species\"] = df.groupby(\"species\")[\"mass\"].transform(lambda x: x - x.mean())\n",
+    "df[\"mass_demean_species\"] = df.groupby(\"species\")[\"mass\"].transform(\n",
+    "    lambda x: x - x.mean()\n",
+    ")\n",
     "df.head()"
    ]
   },

data-categorical.ipynb

@@ -25,11 +25,13 @@
    "outputs": [],
    "source": [
     "# remove cell\n",
-    "import matplotlib_inline.backend_inline\n",
     "import matplotlib.pyplot as plt\n",
+    "import matplotlib_inline.backend_inline\n",
     "\n",
     "# Plot settings\n",
-    "plt.style.use(\"https://github.com/aeturrell/coding-for-economists/raw/main/plot_style.txt\")\n",
+    "plt.style.use(\n",
+    "    \"https://github.com/aeturrell/coding-for-economists/raw/main/plot_style.txt\"\n",
+    ")\n",
     "matplotlib_inline.backend_inline.set_matplotlib_formats(\"svg\")"
    ]
   },

data-databases.ipynb

@@ -491,7 +491,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "track.group_by(\"AlbumId\").mutate(mean_mins_track=track.Milliseconds.mean()/1e3/60).order_by(\"mean_mins_track\").limit(5)"
+    "track.group_by(\"AlbumId\").mutate(\n",
+    "    mean_mins_track=track.Milliseconds.mean() / 1e3 / 60\n",
+    ").order_by(\"mean_mins_track\").limit(5)"
    ]
   },
   {

data-exploratory-analysis.ipynb

@@ -20,10 +20,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
+    "import warnings\n",
+    "\n",
     "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
-    "import warnings\n",
+    "import pandas as pd\n",
     "from rich import print"
    ]
   },
@@ -49,7 +50,7 @@
     "# Set max rows displayed for readability\n",
     "pd.set_option(\"display.max_rows\", 6)\n",
     "\n",
-    "warnings.filterwarnings('ignore')"
+    "warnings.filterwarnings(\"ignore\")"
    ]
   },
   {
@@ -333,8 +334,7 @@
    "outputs": [],
    "source": [
     "(\n",
-    "    df.groupby([\"year_sold\", \"bedrooms\"])\n",
-    "    [\"sale_price\"]\n",
+    "    df.groupby([\"year_sold\", \"bedrooms\"])[\"sale_price\"]\n",
     "    .mean()\n",
     "    .unstack()\n",
     "    .apply(lambda x: x / 1e3)\n",