[pre-commit.ci] pre-commit autoupdate (#327)

* [pre-commit.ci] pre-commit autoupdate

updates:
- [github.com/pre-commit/pre-commit-hooks: v4.6.0 → v5.0.0](pre-commit/pre-commit-hooks@v4.6.0...v5.0.0)
- [github.com/astral-sh/ruff-pre-commit: v0.5.0 → v0.6.9](astral-sh/ruff-pre-commit@v0.5.0...v0.6.9)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Change per-file-ignores to lint.per-file-ignores in ruff.toml

* Fix E501 line too long lint errors

* Fix F821 Undefined name `predicted`

Use %%time cell magic instead of %time line magic.

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Wei Ji <[email protected]>

.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: v4.6.0
+  rev: v5.0.0
   hooks:
     - id: check-added-large-files
       args: [ '--maxkb=512', '--enforce-all' ]
@@ -11,7 +11,7 @@ repos:
     - id: end-of-file-fixer
     - id: trailing-whitespace
 - repo: https://github.com/astral-sh/ruff-pre-commit
-  rev: v0.5.0
+  rev: v0.6.9
   hooks:
     - id: ruff  # Run the linter
       args: [ --fix ]

docs/finetune/finetune-on-embeddings.ipynb

@@ -19,7 +19,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# If not already installed, add lonboard to the environment by uncommenting the following line.\n",
+    "# If not installed, add lonboard to the environment by uncommenting the following line\n",
     "# ! pip install lonboard"
    ]
   },
@@ -31,17 +31,15 @@
    "source": [
     "from pathlib import Path\n",
     "\n",
-    "import requests\n",
     "import geopandas as gpd\n",
     "import numpy as np\n",
     "import pandas as pd\n",
-    "from sklearn import svm\n",
-    "from sklearn.metrics import accuracy_score, precision_score, recall_score\n",
-    "from sklearn.model_selection import train_test_split\n",
+    "import requests\n",
+    "from lonboard import Map, PolygonLayer\n",
+    "from lonboard.colormap import apply_categorical_cmap\n",
     "from sklearn.ensemble import RandomForestClassifier\n",
-    "\n",
-    "from lonboard import Map, PolygonLayer, ScatterplotLayer\n",
-    "from lonboard.colormap import apply_categorical_cmap"
+    "from sklearn.metrics import accuracy_score, precision_score, recall_score\n",
+    "from sklearn.model_selection import train_test_split"
    ]
   },
   {
@@ -558,11 +556,13 @@
    "source": [
     "# Open marinas training data\n",
     "points = gpd.read_file(\n",
-    "    f\"../../data/classify-embeddings-sf-baseball-marinas/marinas.geojson\"\n",
+    "    \"../../data/classify-embeddings-sf-baseball-marinas/marinas.geojson\"\n",
     ")\n",
     "\n",
-    "# Uncomement this to use the baseball training dataset.\n",
-    "# points = gpd.read_file(f\"../../data/classify-embeddings-sf-baseball-marinas/baseball.geojson\")\n",
+    "# Uncomment this to use the baseball training dataset.\n",
+    "# points = gpd.read_file(\n",
+    "#     \"../../data/classify-embeddings-sf-baseball-marinas/baseball.geojson\"\n",
+    "# )\n",
     "\n",
     "# Spatial join of training data with embeddings\n",
     "merged = embeddings.sjoin(points)\n",
@@ -692,9 +692,10 @@
     }
    ],
    "source": [
+    "%%time\n",
     "# Make inference on entire embedding dataset\n",
     "X = np.array([x for x in embeddings[\"embeddings\"]])\n",
-    "%time predicted = model.predict(X)\n",
+    "predicted = model.predict(X)\n",
     "print(f\"Found {np.sum(predicted)} locations\")\n",
     "\n",
     "# Add inference to geopandas df and export\n",

docs/tutorials/v1-inference-simsearch-naip-stacchip.ipynb

@@ -73,21 +73,21 @@
     "import math\n",
     "import os\n",
     "import random\n",
-    "import requests\n",
     "\n",
     "import geopandas as gpd\n",
     "import lancedb\n",
     "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "import pystac_client\n",
+    "import requests\n",
     "import shapely\n",
-    "from shapely.geometry import box, Polygon\n",
     "import torch\n",
     "import yaml\n",
     "from box import Box\n",
     "from pyproj import Transformer\n",
     "from rasterio.io import MemoryFile\n",
+    "from shapely.geometry import box\n",
     "from stacchip.chipper_mod import Chipper\n",
     "from stacchip.indexer import NoStatsChipIndexer\n",
     "from stacchip.processors.prechip import normalize_timestamp\n",
@@ -214,7 +214,7 @@
     "    # Obtain the item bounds and centroid\n",
     "    bounds, centroid_x, centroid_y = get_bounds_centroid(item.assets[\"image\"].href)\n",
     "    print(\n",
-    "        f\"Bounds coordinates: {bounds}, centroid coordinates: {centroid_x}, {centroid_y}\"\n",
+    "        f\"Bbox coordinates: {bounds}, centroid coordinates: {centroid_x}, {centroid_y}\"\n",
     "    )\n",
     "\n",
     "    # Instantiate the chipper\n",

ruff.toml

@@ -1,7 +1,3 @@
-[per-file-ignores]
-"docs/clay_over_aoi.ipynb" = ["E501"]
-"scripts/worldcover/worldcover_vrt.py" = ["E501"]
-
 [format]
 # https://docs.astral.sh/ruff/settings/#format
 line-ending = "lf"  # Use UNIX `\n` line endings for all files
@@ -18,5 +14,9 @@ select = [
     "W",    # pycodestyle warnings
 ]
 
+[lint.per-file-ignores]
+"docs/clay_over_aoi.ipynb" = ["E501"]
+"scripts/worldcover/worldcover_vrt.py" = ["E501"]
+
 [lint.pylint]
 max-args = 6