geoai-py 0.9.1__tar.gz → 0.10.0__tar.gz

geoai_py-0.10.0/.dockerignore

@@ -0,0 +1,20 @@
+# Exclude everything under docs
+docs/*
+
+# But keep these two directories
+!docs/notebooks
+!docs/maplibre
+
+# Optionally exclude other common files
+.git
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+*.ipynb_checkpoints
+.env
+.DS_Store
+tests/
+build/
+dist/
+*.egg-info/

{geoai_py-0.9.1 → geoai_py-0.10.0}/.github/workflows/docker-image.yml

@@ -11,6 +11,6 @@ jobs:
         runs-on: ubuntu-latest
 
         steps:
-            - uses: actions/checkout@v4
+            - uses: actions/checkout@v5
             - name: Build the Docker image
               run: docker build . --file Dockerfile --tag ${{ github.repository }}:$(date +%s)

{geoai_py-0.9.1 → geoai_py-0.10.0}/.github/workflows/docker-publish.yml

@@ -13,7 +13,7 @@ jobs:
             contents: read
         steps:
             - name: Check out the repo
-              uses: actions/checkout@v4
+              uses: actions/checkout@v5
 
             - name: Log in to Docker Hub
               uses: docker/login-action@v3

{geoai_py-0.9.1 → geoai_py-0.10.0}/.github/workflows/docs-build.yml

@@ -12,7 +12,7 @@ jobs:
                 python-version: ["3.12"]
 
         steps:
-            - uses: actions/checkout@v4
+            - uses: actions/checkout@v5
               with:
                   fetch-depth: 0
 

{geoai_py-0.9.1 → geoai_py-0.10.0}/.github/workflows/docs.yml

@@ -11,7 +11,7 @@ jobs:
                 python-version: ["3.12"]
 
         steps:
-            - uses: actions/checkout@v4
+            - uses: actions/checkout@v5
               with:
                   fetch-depth: 0
 

{geoai_py-0.9.1 → geoai_py-0.10.0}/.github/workflows/macos.yml

@@ -19,7 +19,7 @@ jobs:
         env:
             SDKROOT: /Library/Developer/CommandLineTools/SDKs/MacOSX.sdk
         steps:
-            - uses: actions/checkout@v4
+            - uses: actions/checkout@v5
 
             - name: Install uv
               uses: astral-sh/setup-uv@v6

{geoai_py-0.9.1 → geoai_py-0.10.0}/.github/workflows/pypi.yml

@@ -12,7 +12,7 @@ jobs:
         runs-on: ubuntu-latest
 
         steps:
-            - uses: actions/checkout@v4
+            - uses: actions/checkout@v5
             - name: Set up Python
               uses: actions/setup-python@v5
               with:

{geoai_py-0.9.1 → geoai_py-0.10.0}/.github/workflows/ubuntu.yml

@@ -17,7 +17,7 @@ jobs:
                 python-version: ["3.10", "3.11", "3.12"]
 
         steps:
-            - uses: actions/checkout@v4
+            - uses: actions/checkout@v5
 
             # - name: Install GDAL system dependencies
             #   run: sudo apt-get update && sudo apt-get install -y gdal-bin libgdal-dev

{geoai_py-0.9.1 → geoai_py-0.10.0}/.github/workflows/windows.yml

@@ -15,7 +15,7 @@ jobs:
                 python-version: ["3.12"]
 
         steps:
-            - uses: actions/checkout@v4
+            - uses: actions/checkout@v5
 
             - name: Install uv
               uses: astral-sh/setup-uv@v6

{geoai_py-0.9.1 → geoai_py-0.10.0}/.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
     - repo: https://github.com/pre-commit/pre-commit-hooks
-      rev: v5.0.0
+      rev: v6.0.0
       hooks:
           - id: check-toml
           - id: check-yaml

{geoai_py-0.9.1 → geoai_py-0.10.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: geoai-py
-Version: 0.9.1
+Version: 0.10.0
 Summary: A Python package for using Artificial Intelligence (AI) with geospatial data
 Author-email: Qiusheng Wu <giswqs@gmail.com>
 License: MIT License

{geoai_py-0.9.1 → geoai_py-0.10.0}/docs/examples/change_detection.ipynb

@@ -165,6 +165,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Make sure model directory exists\n",
+    "Path(\"~/.cache/torch/hub/checkpoints/\").expanduser().mkdir(parents=True, exist_ok=True)\n",
+    "\n",
     "# Initialize change detection\n",
     "detector = geoai.ChangeDetection(sam_model_type=\"vit_h\")\n",
     "\n",

geoai_py-0.10.0/docs/examples/wetland_dynamics.ipynb

@@ -0,0 +1,517 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Wetland Mapping with GeoAI\n",
+    "\n",
+    "[![image](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/opengeos/geoai/blob/main/docs/examples/wetland_dynamics.ipynb)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Install packages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %pip install geoai-py"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Import libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import geoai\n",
+    "import leafmap"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create an interactive map"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "m = geoai.Map(center=[47.229011, -99.878662], zoom=13)\n",
+    "m.add_basemap(\"Esri.WorldImagery\")\n",
+    "m"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Draw an area of interest"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if m.user_roi is not None:\n",
+    "    bbox = m.user_roi_bounds()\n",
+    "else:\n",
+    "    bbox = [-99.9057, 47.2143, -99.8686, 47.2419]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Get the year of NWI data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nwi_year = leafmap.get_nwi_year(bbox=bbox, return_geometry=False)[0]\n",
+    "nwi_year"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nwi_year_geom = leafmap.get_nwi_year(bbox=bbox)\n",
+    "nwi_year_geom"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "m.add_gdf(nwi_year_geom, layer_name=\"NWI Year\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Search for NAIP images for the corresponding NWI year"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "items = geoai.pc_stac_search(\n",
+    "    collection=\"naip\",\n",
+    "    bbox=bbox,\n",
+    "    time_range=f\"{nwi_year}-01-01/{nwi_year}-12-30\",\n",
+    ")\n",
+    "items"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Visualize NAIP images"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.view_pc_items(items=items)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Download NAIP images"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "images = geoai.pc_stac_download(items, output_dir=\"naip\", assets=[\"image\"])\n",
+    "images"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "first_image = list(images.values())[0][\"image\"]\n",
+    "first_image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "second_image = list(images.values())[1][\"image\"]\n",
+    "second_image"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Download NWI data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "image_bbox = leafmap.image_bbox(first_image, to_crs=\"EPSG:4326\")\n",
+    "image_bbox"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nwi_gdf = leafmap.get_nwi(\n",
+    "    geometry=image_bbox, clip=True, add_class=True, output=\"wetlands.geojson\"\n",
+    ")\n",
+    "nwi_gdf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "wetlands_classes = nwi_gdf[\"WETLAND_TY\"].unique()\n",
+    "wetlands_classes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "num_classes = len(wetlands_classes) + 1\n",
+    "num_classes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Visualize NWI data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "m.remove_layer(m.layers[-1])\n",
+    "m.add_raster(first_image, layer_name=\"NAIP\")\n",
+    "m.add_nwi(nwi_gdf, layer_name=\"NWI\")\n",
+    "m"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Select training and test images"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_raster_path = first_image\n",
+    "test_raster_path = second_image\n",
+    "train_vector_path = \"wetlands.geojson\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.view_vector_interactive(\n",
+    "    train_vector_path, column=\"WETLAND_TY\", tiles=train_raster_path\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create image chips for training"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "out_folder = \"output\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tiles = geoai.export_geotiff_tiles(\n",
+    "    in_raster=train_raster_path,\n",
+    "    out_folder=out_folder,\n",
+    "    in_class_data=train_vector_path,\n",
+    "    tile_size=1024,\n",
+    "    stride=256,\n",
+    "    buffer_radius=0,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Train a segmentation model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Train U-Net model\n",
+    "geoai.train_segmentation_model(\n",
+    "    images_dir=f\"{out_folder}/images\",\n",
+    "    labels_dir=f\"{out_folder}/labels\",\n",
+    "    output_dir=f\"{out_folder}/unet_models\",\n",
+    "    architecture=\"unet\",\n",
+    "    encoder_name=\"resnet34\",\n",
+    "    encoder_weights=\"imagenet\",\n",
+    "    num_channels=4,\n",
+    "    num_classes=num_classes,  # background and wetlands classes\n",
+    "    batch_size=8,\n",
+    "    num_epochs=50,\n",
+    "    learning_rate=0.001,\n",
+    "    val_split=0.2,\n",
+    "    verbose=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Evaluate the model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.plot_performance_metrics(\n",
+    "    history_path=f\"{out_folder}/unet_models/training_history.pth\",\n",
+    "    figsize=(15, 5),\n",
+    "    verbose=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Run inference on a single image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define paths\n",
+    "masks_path = second_image.replace(\"naip\", \"prediction\")\n",
+    "model_path = f\"{out_folder}/unet_models/best_model.pth\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.semantic_segmentation(\n",
+    "    input_path=test_raster_path,\n",
+    "    output_path=masks_path,\n",
+    "    model_path=model_path,\n",
+    "    architecture=\"unet\",\n",
+    "    encoder_name=\"resnet34\",\n",
+    "    num_channels=4,\n",
+    "    num_classes=6,\n",
+    "    window_size=1024,\n",
+    "    overlap=256,\n",
+    "    batch_size=4,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Vectorize the results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "output_path = masks_path.replace(\".tif\", \"_mask.geojson\")\n",
+    "gdf = geoai.raster_to_vector(\n",
+    "    masks_path, output_path, min_area=300, simplify_tolerance=1\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.view_vector_interactive(output_path, tiles=test_raster_path)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Download more images"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "items = geoai.pc_stac_search(\n",
+    "    collection=\"naip\",\n",
+    "    bbox=bbox,\n",
+    ")\n",
+    "items"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "images = geoai.pc_stac_download(items, output_dir=\"naip\", assets=[\"image\"])\n",
+    "images"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Run inference on multiple images"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.semantic_segmentation_batch(\n",
+    "    input_dir=\"naip\",\n",
+    "    output_dir=\"prediction\",\n",
+    "    model_path=model_path,\n",
+    "    architecture=\"unet\",\n",
+    "    encoder_name=\"resnet34\",\n",
+    "    num_channels=4,\n",
+    "    num_classes=6,\n",
+    "    window_size=1024,\n",
+    "    overlap=256,\n",
+    "    batch_size=4,\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "geo",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}