geoai-py 0.5.5__py2.py3-none-any.whl → 0.6.0__py2.py3-none-any.whl

geoai/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = """Qiusheng Wu"""
 __email__ = "giswqs@gmail.com"
-__version__ = "0.5.5"
+__version__ = "0.6.0"
 
 
 import os

geoai/classify.py

@@ -1,6 +1,7 @@
 """The module for training semantic segmentation models for classifying remote sensing imagery."""
 
 import os
+
 import numpy as np
 
 
@@ -110,23 +111,24 @@ def train_classifier(
     Returns:
         object: Trained SemanticSegmentationTask model.
     """
+    import multiprocessing as mp
+    import timeit
+
+    import albumentations as A
     import lightning.pytorch as pl
+    import torch
+    from lightning.pytorch.callbacks import ModelCheckpoint
+    from lightning.pytorch.loggers import CSVLogger
     from torch.utils.data import DataLoader
-    from torchgeo.datasets import stack_samples, RasterDataset
+    from torchgeo.datamodules import GeoDataModule
+    from torchgeo.datasets import RasterDataset, stack_samples
     from torchgeo.datasets.splits import random_bbox_assignment
     from torchgeo.samplers import (
-        RandomGeoSampler,
-        RandomBatchGeoSampler,
         GridGeoSampler,
+        RandomBatchGeoSampler,
+        RandomGeoSampler,
     )
-    import torch
-    import multiprocessing as mp
-    import timeit
-    import albumentations as A
-    from torchgeo.datamodules import GeoDataModule
     from torchgeo.trainers import SemanticSegmentationTask
-    from lightning.pytorch.callbacks import ModelCheckpoint
-    from lightning.pytorch.loggers import CSVLogger
 
     # Create a wrapper class for albumentations to work with TorchGeo format
     class AlbumentationsWrapper:
@@ -376,21 +378,19 @@ def _classify_image(
     Returns:
         str: Path to the saved classified image.
     """
-    import numpy as np
     import timeit
-    from tqdm import tqdm
 
+    import numpy as np
+    import rasterio
     import torch
+    from rasterio.io import MemoryFile
+    from rasterio.merge import merge
+    from rasterio.transform import from_origin
     from torch.utils.data import DataLoader
-
     from torchgeo.datasets import RasterDataset, stack_samples
     from torchgeo.samplers import GridGeoSampler
     from torchgeo.trainers import SemanticSegmentationTask
-
-    import rasterio
-    from rasterio.transform import from_origin
-    from rasterio.io import MemoryFile
-    from rasterio.merge import merge
+    from tqdm import tqdm
 
     # Set default output path if not provided
     if output_path is None:
@@ -619,14 +619,12 @@ def classify_image(
         str: Path to the saved classified image.
     """
     import timeit
-
-    import torch
-    from torchgeo.trainers import SemanticSegmentationTask
+    import warnings
 
     import rasterio
-
-    import warnings
+    import torch
     from rasterio.errors import NotGeoreferencedWarning
+    from torchgeo.trainers import SemanticSegmentationTask
 
     # Disable specific GDAL/rasterio warnings
     warnings.filterwarnings("ignore", category=UserWarning, module="rasterio._.*")
@@ -863,9 +861,10 @@ def classify_images(
         list: List of paths to the saved classified images.
     """
     # Import required libraries
-    from tqdm import tqdm
     import glob
 
+    from tqdm import tqdm
+
     # Process directory input
     if isinstance(image_paths, str) and os.path.isdir(image_paths):
         # Set default output directory if not provided

geoai/download.py

@@ -1135,7 +1135,37 @@ def view_pc_item(
     map_args=None,
     **kwargs,
 ):
+    """
+    Visualize a STAC item from the Planetary Computer on an interactive map.
+
+    This function allows users to display a STAC item on a map using either the
+    `folium` or `ipyleaflet` backend. It supports adding basemaps, configuring
+    map options, and customizing the visualization of the STAC item.
+
+    Args:
+        url (str, optional): URL of the STAC item to visualize. Defaults to None.
+        collection (str, optional): The collection ID of the STAC item. Defaults to None.
+        item (str or pystac.Item, optional): The STAC item or its ID. Defaults to None.
+        assets (list, optional): List of asset keys to visualize. Defaults to None.
+        bands (list, optional): List of specific bands to visualize. Defaults to None.
+        titiler_endpoint (str, optional): URL of the Titiler endpoint for rendering. Defaults to None.
+        name (str, optional): Name of the layer to display on the map. Defaults to "STAC Item".
+        attribution (str, optional): Attribution text for the layer. Defaults to "Planetary Computer".
+        opacity (float, optional): Opacity of the layer (0.0 to 1.0). Defaults to 1.0.
+        shown (bool, optional): Whether the layer is visible by default. Defaults to True.
+        fit_bounds (bool, optional): Whether to fit the map bounds to the layer. Defaults to True.
+        layer_index (int, optional): Index of the layer in the map's layer stack. Defaults to None.
+        backend (str, optional): Map backend to use ('folium' or 'ipyleaflet'). Defaults to "folium".
+        basemap (str, optional): Name of the basemap to add to the map. Defaults to None.
+        map_args (dict, optional): Additional arguments for configuring the map. Defaults to None.
+        **kwargs: Additional keyword arguments passed to the `add_stac_layer` method.
 
+    Returns:
+        leafmap.Map: An interactive map with the STAC item visualized.
+
+    Raises:
+        ValueError: If an unsupported backend is specified.
+    """
     if backend == "folium":
         import leafmap.foliumap as leafmap
 
@@ -1181,3 +1211,103 @@ def view_pc_item(
         **kwargs,
     )
     return m
+
+
+def view_pc_items(
+    urls=None,
+    collection=None,
+    items=None,
+    assets=None,
+    bands=None,
+    titiler_endpoint=None,
+    attribution="Planetary Computer",
+    opacity=1.0,
+    shown=True,
+    fit_bounds=True,
+    layer_index=None,
+    backend="folium",
+    basemap=None,
+    map_args=None,
+    **kwargs,
+):
+    """
+    Visualize multiple STAC items from the Planetary Computer on an interactive map.
+
+    This function allows users to display multiple STAC items on a map using either
+    the `folium` or `ipyleaflet` backend. It supports adding basemaps, configuring
+    map options, and customizing the visualization of the STAC items.
+
+    Args:
+        urls (list, optional): List of URLs of the STAC items to visualize. Defaults to None.
+        collection (str, optional): The collection ID of the STAC items. Defaults to None.
+        items (list or str, optional): List of STAC items or their IDs. Defaults to None.
+        assets (list, optional): List of asset keys to visualize. Defaults to None.
+        bands (list, optional): List of specific bands to visualize. Defaults to None.
+        titiler_endpoint (str, optional): URL of the Titiler endpoint for rendering. Defaults to None.
+        attribution (str, optional): Attribution text for the layers. Defaults to "Planetary Computer".
+        opacity (float, optional): Opacity of the layers (0.0 to 1.0). Defaults to 1.0.
+        shown (bool, optional): Whether the layers are visible by default. Defaults to True.
+        fit_bounds (bool, optional): Whether to fit the map bounds to the layers. Defaults to True.
+        layer_index (int, optional): Index of the layers in the map's layer stack. Defaults to None.
+        backend (str, optional): Map backend to use ('folium' or 'ipyleaflet'). Defaults to "folium".
+        basemap (str, optional): Name of the basemap to add to the map. Defaults to None.
+        map_args (dict, optional): Additional arguments for configuring the map. Defaults to None.
+        **kwargs: Additional keyword arguments passed to the `add_stac_layer` method.
+
+    Returns:
+        leafmap.Map: An interactive map with the STAC items visualized.
+
+    Raises:
+        ValueError: If an unsupported backend is specified.
+    """
+    if backend == "folium":
+        import leafmap.foliumap as leafmap
+
+    elif backend == "ipyleaflet":
+        import leafmap.leafmap as leafmap
+
+    else:
+        raise ValueError(
+            f"Unsupported backend: {backend}. Supported backends are 'folium' and 'ipyleaflet'."
+        )
+
+    if map_args is None:
+        map_args = {}
+
+    if "draw_control" not in map_args:
+        map_args["draw_control"] = False
+
+    if urls is not None:
+        items = [pystac.Item.from_file(url) for url in urls]
+
+    if isinstance(items, str):
+        items = [pystac.Item.from_file(items)]
+    m = leafmap.Map(**map_args)
+
+    if basemap is not None:
+        m.add_basemap(basemap)
+    if isinstance(items, list):
+
+        for item in items:
+
+            if isinstance(item, pystac.Item):
+                collection = item.collection_id
+                if assets is None:
+                    assets = [list(item.assets.keys())[0]]
+                item = item.id
+
+                m.add_stac_layer(
+                    collection=collection,
+                    item=item,
+                    assets=assets,
+                    bands=bands,
+                    titiler_endpoint=titiler_endpoint,
+                    name=item,
+                    attribution=attribution,
+                    opacity=opacity,
+                    shown=shown,
+                    fit_bounds=fit_bounds,
+                    layer_index=layer_index,
+                    **kwargs,
+                )
+    return m

geoai/extract.py

@@ -2,6 +2,7 @@
 
 # Standard Library
 import os
+import time
 
 # Third-Party Libraries
 import cv2
@@ -19,7 +20,6 @@ from torchvision.models.detection import (
     maskrcnn_resnet50_fpn,
 )
 from tqdm import tqdm
-import time
 
 # Local Imports
 from .utils import get_raster_stats

geoai/geoai.py

@@ -7,20 +7,21 @@ logging.getLogger("maplibre").setLevel(logging.ERROR)
 import leafmap
 import leafmap.maplibregl as maplibregl
 
+from .classify import classify_image, classify_images, train_classifier
 from .download import (
     download_naip,
     download_overture_buildings,
     download_pc_stac_item,
-    get_overture_data,
     extract_building_stats,
+    get_overture_data,
     pc_collection_list,
     pc_item_asset_list,
-    pc_stac_search,
     pc_stac_download,
+    pc_stac_search,
     read_pc_item_asset,
     view_pc_item,
+    view_pc_items,
 )
-from .classify import train_classifier, classify_image, classify_images
 from .extract import *
 from .hf import *
 from .segment import *