[pre-commit.ci] pre-commit autoupdate

.pre-commit-config.yaml

@@ -2,7 +2,7 @@
 # See https://pre-commit.com/hooks.html for more hooks
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v6.0.0
     hooks:
       - id: trailing-whitespace
       - id: end-of-file-fixer
@@ -14,7 +14,7 @@ repos:
         args: [--allow-missing-credentials]
       - id: detect-private-key
   - repo: https://github.com/igorshubovych/markdownlint-cli
-    rev: v0.39.0
+    rev: v0.49.1
     hooks:
       - id: markdownlint
         name: Markdownlint
@@ -28,14 +28,14 @@ repos:
           ]
 
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.6
+    rev: v2.4.3
     hooks:
       - id: codespell
         name: codespell
         description: Checks for common misspellings in text files
         exclude: 'notebooks/.*'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.3.3
+    rev: v0.16.5
     hooks:
       - id: ruff
         types_or: [python, pyi, jupyter]

notebooks/air-pollution/air-pollution.ipynb

@@ -26,22 +26,19 @@
    },
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
+    "import bokeh\n",
     "import geopandas as gpd\n",
     "import matplotlib.pyplot as plt\n",
-    "\n",
-    "import bokeh\n",
+    "import pandas as pd\n",
+    "from bokeh.core.validation import silence\n",
+    "from bokeh.core.validation.warnings import EMPTY_LAYOUT, MISSING_RENDERERS\n",
     "from bokeh.layouts import column\n",
     "from bokeh.models import Legend, Panel, Tabs\n",
     "\n",
-    "from bokeh.core.validation.warnings import EMPTY_LAYOUT, MISSING_RENDERERS\n",
-    "\n",
-    "from bokeh.core.validation import silence\n",
-    "\n",
     "bokeh.core.validation.silence(EMPTY_LAYOUT, True)\n",
     "bokeh.core.validation.silence(MISSING_RENDERERS, True)\n",
-    "from bokeh.plotting import figure, show, output_notebook, ColumnDataSource\n",
-    "from bokeh.io import output_notebook"
+    "from bokeh.io import output_notebook\n",
+    "from bokeh.plotting import ColumnDataSource, figure, output_notebook, show"
    ]
   },
   {

notebooks/air-pollution/emissions.ipynb

@@ -17,9 +17,9 @@
    },
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
     "import geopandas as gpd\n",
-    "import matplotlib.pyplot as plt"
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd"
    ]
   },
   {
@@ -33,14 +33,13 @@
    "outputs": [],
    "source": [
     "import bokeh\n",
+    "from bokeh.core.validation.warnings import EMPTY_LAYOUT, MISSING_RENDERERS\n",
     "from bokeh.layouts import column\n",
     "from bokeh.models import Legend, Panel, Tabs\n",
     "\n",
-    "from bokeh.core.validation.warnings import EMPTY_LAYOUT, MISSING_RENDERERS\n",
-    "\n",
     "bokeh.core.validation.silence(EMPTY_LAYOUT, True)\n",
     "bokeh.core.validation.silence(MISSING_RENDERERS, True)\n",
-    "from bokeh.plotting import figure, show, output_notebook"
+    "from bokeh.plotting import figure, output_notebook, show"
    ]
   },
   {
@@ -53,10 +52,10 @@
    },
    "outputs": [],
    "source": [
-    "from bokeh.plotting import ColumnDataSource\n",
-    "from bokeh.io import output_notebook\n",
     "from bokeh.core.validation import silence\n",
     "from bokeh.core.validation.warnings import EMPTY_LAYOUT\n",
+    "from bokeh.io import output_notebook\n",
+    "from bokeh.plotting import ColumnDataSource\n",
     "\n",
     "# Use the silence function to ignore the EMPTY_LAYOUT warning\n",
     "silence(EMPTY_LAYOUT, True)\n",
@@ -341,9 +340,10 @@
    },
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
     "import glob\n",
     "\n",
+    "import pandas as pd\n",
+    "\n",
     "# Step 1: List all text files\n",
     "file_paths = glob.glob(\n",
     "    \"../../data/air_pollution/ENE_emi_txt/*.txt\"\n",

notebooks/ais-analysis/01-lebanon.ipynb

@@ -35,14 +35,14 @@
    },
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import folium\n",
-    "import h3.api.numpy_int as h3int\n",
-    "from shapely.geometry import mapping, Polygon\n",
-    "\n",
     "import os\n",
     "import subprocess\n",
-    "import sys"
+    "import sys\n",
+    "\n",
+    "import folium\n",
+    "import h3.api.numpy_int as h3int\n",
+    "import pandas as pd\n",
+    "from shapely.geometry import Polygon, mapping"
    ]
   },
   {
@@ -3041,7 +3041,7 @@
     "        \"append\"\n",
     "    ).partitionBy(\"year\", \"month\").parquet(save_path)\n",
     "\n",
-    "    print(f\"Finished: {datetime.now()-start}\")\n",
+    "    print(f\"Finished: {datetime.now() - start}\")\n",
     "    sdf.unpersist()"
    ]
   },

notebooks/ais-analysis/03-lebanon.ipynb

@@ -68,11 +68,10 @@
    },
    "outputs": [],
    "source": [
-    "from pyspark.sql import functions as F\n",
+    "import h3.api.numpy_int as h3int\n",
     "from pyspark.sql import Window\n",
-    "from pyspark.sql.types import LongType\n",
-    "\n",
-    "import h3.api.numpy_int as h3int"
+    "from pyspark.sql import functions as F\n",
+    "from pyspark.sql.types import LongType"
    ]
   },
   {
@@ -84,10 +83,10 @@
    },
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import geopandas as gpd\n",
+    "import json\n",
     "\n",
-    "import json"
+    "import geopandas as gpd\n",
+    "import pandas as pd"
    ]
   },
   {

notebooks/ais-analysis/04-lebanon.ipynb

@@ -39,9 +39,10 @@
    },
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
+    "import os\n",
+    "\n",
     "import numpy as np\n",
-    "import os"
+    "import pandas as pd"
    ]
   },
   {

notebooks/aviation-trends/aviation.ipynb

@@ -10,8 +10,8 @@
    },
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import matplotlib.pyplot as plt"
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd"
    ]
   },
   {
@@ -409,9 +409,8 @@
     }
    ],
    "source": [
-    "import numpy as np\n",
     "import matplotlib.patches as mpatches\n",
-    "\n",
+    "import numpy as np\n",
     "\n",
     "df = top_categories_seats\n",
     "sorted_df = df.sort_values(by=[\"date\", \"total_seats\"], ascending=[True, False])\n",

notebooks/aviation-trends/aviation_update.ipynb

@@ -63,8 +63,8 @@
    "outputs": [],
    "source": [
     "# Define empty dataset to concat all the arrivals and departures\n",
-    "departures = pd.read_csv('../../data/aviation/departures_BEY_2026-01-01_2026-04-07.csv')\n",
-    "arrivals = pd.read_csv('../../data/aviation/arrivals_BEY_2026-01-01_2026-04-07.csv')"
+    "departures = pd.read_csv(\"../../data/aviation/departures_BEY_2026-01-01_2026-04-07.csv\")\n",
+    "arrivals = pd.read_csv(\"../../data/aviation/arrivals_BEY_2026-01-01_2026-04-07.csv\")"
    ]
   },
   {
@@ -124,7 +124,6 @@
    },
    "outputs": [],
    "source": [
-    "from bokeh.plotting import figure, show\n",
     "from bokeh.io import output_notebook\n",
     "from bokeh.models import (\n",
     "    ColumnDataSource,\n",
@@ -133,10 +132,11 @@
     "    HoverTool,\n",
     "    Label,\n",
     "    Span,\n",
-    "    Tabs,\n",
     "    TabPanel,\n",
+    "    Tabs,\n",
     ")\n",
     "from bokeh.palettes import Spectral6\n",
+    "from bokeh.plotting import figure, show\n",
     "\n",
     "\n",
     "def get_area_plot(\n",
@@ -437,7 +437,7 @@
     "\n",
     "after = departures_exploded.shape[0]\n",
     "print(\n",
-    "    f\"There are {after} flights after duplication check. {before-after} flights were duplicated\"\n",
+    "    f\"There are {after} flights after duplication check. {before - after} flights were duplicated\"\n",
     ")"
    ]
   },
@@ -996,7 +996,9 @@
     "# Initialize an empty list to store the tabs\n",
     "tabs = []\n",
     "\n",
-    "departures_last_date = pd.to_datetime(departures_exploded[\"flight_date\"]).max().strftime(\"%B %d %Y\")\n",
+    "departures_last_date = (\n",
+    "    pd.to_datetime(departures_exploded[\"flight_date\"]).max().strftime(\"%B %d %Y\")\n",
+    ")\n",
     "\n",
     "# Loop through each dataset and its corresponding color\n",
     "for (title, data), color in zip(datasets.items(), colors):\n",
@@ -1069,7 +1071,7 @@
     "layout = column(main_title, tabs_layout)\n",
     "\n",
     "# Show the tabs\n",
-    "show(layout)\n"
+    "show(layout)"
    ]
   },
   {
@@ -1242,7 +1244,7 @@
     "\n",
     "after = arrivals_exploded.shape[0]\n",
     "print(\n",
-    "    f\"There are {after} flights after duplication check. {before-after} flights were duplicated\"\n",
+    "    f\"There are {after} flights after duplication check. {before - after} flights were duplicated\"\n",
     ")"
    ]
   },
@@ -1642,7 +1644,9 @@
     "# Initialize an empty list to store the tabs\n",
     "tabs = []\n",
     "\n",
-    "arrivals_last_date = pd.to_datetime(arrivals_exploded[\"flight_date\"]).max().strftime(\"%B %d %Y\")\n",
+    "arrivals_last_date = (\n",
+    "    pd.to_datetime(arrivals_exploded[\"flight_date\"]).max().strftime(\"%B %d %Y\")\n",
+    ")\n",
     "\n",
     "# Loop through each dataset and its corresponding color\n",
     "for (title, data), color in zip(datasets.items(), colors):\n",
@@ -1715,7 +1719,7 @@
     "layout = column(main_title, tabs_layout)\n",
     "\n",
     "# Show the tabs\n",
-    "show(layout)\n"
+    "show(layout)"
    ]
   },
   {