dsa-helpers 0.3__tar.gz → 0.3.dev1__tar.gz

{dsa_helpers-0.3/dsa_helpers.egg-info → dsa_helpers-0.3.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dsa_helpers
-Version: 0.3
+Version: 0.3.dev1
 Summary: Utility functions for working with the DSA girder client.
 Author-email: "Juan C. Vizcarra" <jvizcar@emory.edu>
 Maintainer-email: "Juan C. Vizcarra" <jvizcar@emory.edu>
@@ -20,8 +20,6 @@ Requires-Dist: pymongo
 Requires-Dist: pillow
 Requires-Dist: dash
 Requires-Dist: dash_bootstrap_components
-Requires-Dist: shapely
-Requires-Dist: geopandas
 
 # Digital Slide Archive (DSA) Helpers
 Digital Slide Archive Python utility library.

{dsa_helpers-0.3 → dsa_helpers-0.3.dev1}/dsa_helpers/__init__.py

@@ -1,8 +1,7 @@
 # Shadow imports.
+from .login import login
 from .imread import imread
 from .imwrite import imwrite
 
 # Modules that should be available.
-# from . import girder_utils, image_utils, dash
-
-__all__ = ["girder_utils", "image_utils", "dash"]
+from . import girder_utils, image_utils, dash

{dsa_helpers-0.3 → dsa_helpers-0.3.dev1}/dsa_helpers/girder_utils.py

@@ -285,37 +285,3 @@ def get_rectangle_element_coords(element):
     corner_coords = np.array(corner_coords, dtype=np.int32)
 
     return corner_coords
-
-
-def login(
-    api_url: str,
-    login_or_email: str | None = None,
-    password: str | None = None,
-    api_key: str | None = None,
-) -> GirderClient:
-    """Authenticate a girder client with the given credentials or interactively
-    if none is given.
-
-    Args:
-        api_url (str): The DSA girder API url.
-        login_or_email (str | None): The login or email. Defaults to None.
-        password (str | None): Password for login / email. Defaults to None.
-        api_key (str | None): The api key to authenticate with. Defaults to None.
-
-    Returns:
-        girder_client.GirderClient: The authenticated girder client.
-
-    """
-    gc = GirderClient(apiUrl=api_url)
-
-    if api_key is None:
-        if login_or_email is None:
-            _ = gc.authenticate(interactive=True)
-        elif password is None:
-            _ = gc.authenticate(username=login_or_email, interactive=True)
-        else:
-            _ = gc.authenticate(username=login_or_email, password=password)
-    else:
-        _ = gc.authenticate(apiKey=api_key)
-
-    return gc

{dsa_helpers-0.3 → dsa_helpers-0.3.dev1/dsa_helpers.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dsa_helpers
-Version: 0.3
+Version: 0.3.dev1
 Summary: Utility functions for working with the DSA girder client.
 Author-email: "Juan C. Vizcarra" <jvizcar@emory.edu>
 Maintainer-email: "Juan C. Vizcarra" <jvizcar@emory.edu>
@@ -20,8 +20,6 @@ Requires-Dist: pymongo
 Requires-Dist: pillow
 Requires-Dist: dash
 Requires-Dist: dash_bootstrap_components
-Requires-Dist: shapely
-Requires-Dist: geopandas
 
 # Digital Slide Archive (DSA) Helpers
 Digital Slide Archive Python utility library.

{dsa_helpers-0.3 → dsa_helpers-0.3.dev1}/dsa_helpers.egg-info/SOURCES.txt

@@ -1,11 +1,9 @@
 .gitignore
 LICENSE
 README.md
-app.py
 pyproject.toml
 readthedocs.yaml
 requirements.txt
-test.ipynb
 dsa_helpers/__init__.py
 dsa_helpers/girder_utils.py
 dsa_helpers/image_utils.py
@@ -13,6 +11,7 @@ dsa_helpers/imread.py
 dsa_helpers/imwrite.py
 dsa_helpers/login.py
 dsa_helpers/mongo_utils.py
+dsa_helpers/object_detection.py
 dsa_helpers.egg-info/PKG-INFO
 dsa_helpers.egg-info/SOURCES.txt
 dsa_helpers.egg-info/dependency_links.txt
@@ -20,9 +19,4 @@ dsa_helpers.egg-info/requires.txt
 dsa_helpers.egg-info/top_level.txt
 dsa_helpers/dash/__init__.py
 dsa_helpers/dash/header.py
-dsa_helpers/dash/header_callbacks.py
-dsa_helpers/ml/__init__.py
-dsa_helpers/ml/object_detection/__init__.py
-dsa_helpers/ml/object_detection/get_pearce_roi_images.py
-dsa_helpers/ml/object_detection/tile_image.py
-dsa_helpers/ml/object_detection/utils.py
+dsa_helpers/dash/header_callbacks.py

{dsa_helpers-0.3 → dsa_helpers-0.3.dev1}/dsa_helpers.egg-info/requires.txt

@@ -7,5 +7,3 @@ pymongo
 pillow
 dash
 dash_bootstrap_components
-shapely
-geopandas

{dsa_helpers-0.3 → dsa_helpers-0.3.dev1}/pyproject.toml

@@ -12,9 +12,7 @@ dependencies = [
     'pymongo',
     'pillow',
     'dash',
-    'dash_bootstrap_components',
-    'shapely',
-    'geopandas'
+    'dash_bootstrap_components'
 ]
 name = "dsa_helpers"
 authors = [
@@ -31,7 +29,7 @@ classifiers = [
     "License :: OSI Approved :: MIT License",
 ]
 keywords = ["dsa", "girder", "girder_client"]
-version = "v0.3"
+version = "v0.3dev1"
 
 [project.urls]
 Repository = "https://github.com/Gutman-Lab/dsa-python-utils"

{dsa_helpers-0.3 → dsa_helpers-0.3.dev1}/requirements.txt

@@ -7,5 +7,4 @@ pymongo
 jupyter
 pillow
 dash
-dash_bootstrap_components
-python-dotenv
+dash_bootstrap_components

dsa_helpers-0.3/app.py

@@ -1,14 +0,0 @@
-# A test application.
-from dash import Dash, html
-import dash_bootstrap_components as dbc
-from dsa_helpers.dash.header import get_header
-import os
-
-os.environ["DSA_API_URL"] = "https://megabrain.neurology.emory.edu/api/v1"
-
-app = Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])
-
-app.layout = html.Div([get_header("Test")])
-
-if __name__ == "__main__":
-    app.run_server(debug=True)

dsa_helpers-0.3/dsa_helpers/ml/__init__.py

@@ -1,2 +0,0 @@
-# Modules that can be imported.
-__all__ = ["object_detection"]

dsa_helpers-0.3/dsa_helpers/ml/object_detection/__init__.py

@@ -1,5 +0,0 @@
-# Shadow import functions.
-from .get_pearce_roi_images import get_pearce_roi_images
-from .tile_image import tile_image
-
-__all__ = ["utils"]

dsa_helpers-0.3/dsa_helpers/ml/object_detection/get_pearce_roi_images.py

@@ -1,136 +0,0 @@
-from girder_client import GirderClient
-import pandas as pd
-from pathlib import Path
-
-from ...girder_utils import get_region, get_item_large_image_metadata
-from ... import imwrite
-
-
-def get_pearce_roi_images(
-    gc: GirderClient,
-    item_id: str,
-    class_map: dict[str, int],
-    save_dir: str = ".",
-    mag: float | None = None,
-) -> pd.DataFrame:
-    """Download the smallestl bounding box around an ROI annotations and its
-    accompanying object detection annotations. The format used to determine ROIs
-    and boxes is based on the convention used by Dr. Thomas Pearce in his
-    OpenSeadragon applications. Labels are saved as text files in the YOLO format.
-
-    Args:
-        gc (girder_client.GirderClient): The Girder client to use.
-        item_id (str): The item ID of the WSI.
-        class_map (dict[str, int]): A dictionary mapping class names to integers.
-        save_dir (str, optional): The directory to save the images and labels.
-            Defaults to ".".
-        mag (float | None, optional): The magnification to download the ROI at.
-            If None, the scan magnification is used. Defaults to None.
-
-    Returns:
-        pandas.DataFrame: A DataFrame containing metadata for each ROI
-
-    """
-    # Create directories to save images and labels.
-    img_dir = Path(save_dir) / "images"
-    img_dir.mkdir(parents=True, exist_ok=True)
-
-    label_dir = Path(save_dir) / "labels"
-    label_dir.mkdir(parents=True, exist_ok=True)
-
-    # Get all the annotation documents with name starting with "ROI".
-    ann_docs_ids = []
-
-    for ann_doc in gc.get(
-        f"annotation?itemId={item_id}&limit=0&offset=0&sort=lowerName&sortdir=1"
-    ):
-        if ann_doc.get("annotation", {}).get("name", "").startswith("ROI"):
-            ann_docs_ids.append(ann_doc["_id"])
-
-    if not len(ann_docs_ids):
-        # No annotation documents, return None.
-        return
-
-    # Track metadata for each ROI.
-    roi_metadata = []
-
-    # Loop through each document.
-    for ann_doc_id in ann_docs_ids:
-        # Get the full annotation document.
-        ann_doc = gc.get(f"annotation/{ann_doc_id}")
-
-        # Separate the ROI element and the other elements.
-        roi_el = None
-        other_els = []
-
-        for element in ann_doc.get("annotation", {}).get("elements", []):
-            if element.get("user", {}).get("role") == "ROI":
-                roi_el = element
-            else:
-                other_els.append(element)
-
-        if roi_el is None:
-            raise Exception("No ROI element found in annotation document.")
-
-        # Download the ROI image.
-        xc, yc = roi_el["center"][:2]
-        roi_w, roi_h = int(roi_el["width"]), int(roi_el["height"])
-
-        # Get the top left coordinate of the ROI.
-        roi_left = int(xc - roi_w / 2)
-        roi_top = int(yc - roi_h / 2)
-
-        # Get scale factor to go from scan magnification to mag.
-        scan_mag = get_item_large_image_metadata(gc, item_id)["magnification"]
-
-        if mag is None:
-            mag = scan_mag
-
-        roi_img = get_region(
-            gc, item_id, left=roi_left, top=roi_top, width=roi_w, height=roi_h, mag=mag
-        )
-
-        fn = f"itemId-{item_id}-x{roi_left}y{roi_top}x{roi_left+roi_w}y{roi_top+roi_h}"
-
-        img_fp = img_dir / f"{fn}.png"
-        imwrite(img_fp, roi_img)
-
-        # Convert the boxes to YOLO format.
-        labels = ""
-
-        for element in other_els:
-            el_class = element["user"]["class"]
-
-            if el_class not in class_map:
-                continue
-
-            xc, yc = element["center"][:2]
-            xc, yc = int(xc), int(yc)
-
-            # Subtract the left and top of the ROI to get the correct coordinates.
-            xc = xc - roi_left
-            yc = yc - roi_top
-
-            # Normalize by the ROI width and height.
-            xc /= roi_w
-            yc /= roi_h
-
-            w = element["width"] / roi_w
-            h = element["height"] / roi_h
-
-            labels += f"{class_map[el_class]} {xc:.4f} {yc:.4f} {w:.4f} {h:.4f}\n"
-
-        # Save the label to a text file.
-        label_fp = label_dir / f"{fn}.txt"
-
-        with open(label_fp, "w") as fh:
-            fh.write(labels.strip())
-
-        # Append all the metadata to the list.
-        roi_metadata.append(
-            [item_id, img_fp, roi_left, roi_top, roi_w, roi_h, mag, scan_mag]
-        )
-
-    return pd.DataFrame(
-        roi_metadata, columns=["item_id", "fp", "x", "y", "w", "h", "mag", "scan_mag"]
-    )

dsa_helpers-0.3/dsa_helpers/ml/object_detection/tile_image.py

@@ -1,137 +0,0 @@
-import pandas as pd
-from geopandas import GeoDataFrame
-from pathlib import Path
-import cv2 as cv
-import numpy as np
-
-from ... import imread, imwrite
-from .utils import read_yolo_label, corners_to_polygon
-
-
-def tile_image(
-    fp: str,
-    label_fp: str | None = None,
-    save_dir: str = ".",
-    tile_size: int = 1280,
-    stride: int = None,
-    boundary_thr: float = 0.2,
-    fill: tuple[int, int, int] = (114, 114, 114),
-    box_thr: float = 0.2,
-) -> pd.DataFrame:
-    """Tile an ROI image with labels.
-
-    Args:
-        fp: Image filepath, should be in an '/images/ directory'.
-        save_dir: Location to save images and labels.
-        tile_size: Size of tile, uses square tiles only.
-        stride: Stride to use when tiling, if None then it is set equal to
-            tile_size (no overlap between tiles).
-        boundary_thr: If ROI has a boundary (for rotated ROIs) then a tile must
-            have sufficient area in boundary to be included (0.0 - 1.0).
-        fill: RGB when padding image.
-        box_thr: Area threshold of box that must be in a tile.
-
-    Returns:
-        Metadata of tiles saved.
-
-    """
-    # Read the image.
-    img = imread(fp)
-    h, w = img.shape[:2]
-
-    # Get the name of the file.
-    name = Path(fp).stem
-
-    # Get the label if it exists.
-    labels = []
-
-    if label_fp is not None:
-        labels = read_yolo_label(label_fp, im_shape=(w, h), convert=True)
-
-    # Convert the labels into a GeoDataFrame.
-    label_df = []
-
-    for box in labels:
-        label = box[0]
-        x1, y1, x2, y2 = box[1:5].astype(int)
-
-        label_df.append([label, x1, y1, x2, y2, corners_to_polygon(x1, y1, x2, y2)])
-
-    label_df = GeoDataFrame(
-        label_df, columns=["label", "x1", "y1", "x2", "y2", "geometry"]
-    )
-    label_areas = label_df.area
-
-    # Depracated code for rotated ROIs.
-    roi = corners_to_polygon(0, 0, w, h)
-
-    # Make the directories to save images and label files.
-    img_dir = Path(save_dir) / "images"
-    img_dir.mkdir(parents=True, exist_ok=True)
-
-    label_dir = Path(save_dir) / "labels"
-    label_dir.mkdir(parents=True, exist_ok=True)
-
-    # Default stride is no-overlap.
-    if stride is None:
-        stride = tile_size  # default behavior - no overlap
-
-    # Pad the image to avoid getting tiles not of the right size.
-    img = cv.copyMakeBorder(
-        img, 0, tile_size, 0, tile_size, cv.BORDER_CONSTANT, value=fill
-    )
-
-    # Get the top left corner of each tile.
-    xys = list(((x, y) for x in range(0, w, stride) for y in range(0, h, stride)))
-
-    tile_df = []  # track tile data.
-
-    # Pre-calculate the number of pixels in tile that must be in ROI to include.
-    intersection_thr = tile_size**2 * boundary_thr
-
-    # loop through each tile coordinate
-    for xy in xys:
-        # Check if this tile is sufficiently in the boundary.
-        x1, y1 = xy
-        x2, y2 = x1 + tile_size, y1 + tile_size
-
-        tile_pol = corners_to_polygon(x1, y1, x2, y2)
-        intersection = roi.intersection(tile_pol).area
-
-        if intersection > intersection_thr:
-            # Get the tile image.
-            tile = img[y1:y2, x1:x2]
-
-            # Create a name for the tile image / label.
-            fn = f"{name}_x{x1}y{y1}x{x2}y{y2}"
-
-            img_fp = img_dir / f"{fn}.png"
-
-            tile_df.append([img_fp, x1, y1, x2, y2])
-
-            imwrite(str(img_fp), tile)
-
-            # Find all boxes that intersect
-            label_intersection = label_df.geometry.intersection(tile_pol).area
-
-            tile_boxes = label_df[label_intersection / label_areas > box_thr]
-
-            # save these as normalized labels, threshold the box edges.
-            if len(tile_boxes):
-                labels = ""
-
-                for _, r in tile_boxes.iterrows():
-                    # Shift coordinates to be relative to this tile.
-                    xx1 = np.clip(r.x1 - x1, 0, tile_size) / tile_size
-                    yy1 = np.clip(r.y1 - y1, 0, tile_size) / tile_size
-                    xx2 = np.clip(r.x2 - x1, 0, tile_size) / tile_size
-                    yy2 = np.clip(r.y2 - y1, 0, tile_size) / tile_size
-
-                    xc, yc = (xx1 + xx2) / 2, (yy1 + yy2) / 2
-                    bw, bh = xx2 - xx1, yy2 - yy1
-                    labels += f"{r.label} {xc:.4f} {yc:.4f} {bw:.4f} {bh:.4f}\n"
-
-                with open(str(label_dir / f"{fn}.txt"), "w") as fh:
-                    fh.write(labels.strip())
-
-    return pd.DataFrame(tile_df, columns=["fp", "x1", "y1", "x2", "y2"])

dsa_helpers-0.3/dsa_helpers/ml/object_detection/utils.py

@@ -1,104 +0,0 @@
-import numpy as np
-from shapely.geometry import Polygon
-
-
-def convert_box_type(box):
-    """Convert a box type from YOLO format (x-center, y-center, box-width, box-height) to (x1, y1, x2, y2) where point 1 is the
-    top left corner of box and point 2 is the bottom right corner
-
-    INPUT
-    -----
-    box : array
-        [N, 4], each row a point and the format being (x-center, y-center, box-width, box-height)
-
-    RETURN
-    ------
-    new_box : array
-        [N, 4] each row a point and the format x1, y1, x2, y2
-
-    """
-    # get half the box height and width
-    half_bw = box[:, 2] / 2
-    half_bh = box[:, 3] / 2
-
-    new_box = np.zeros(box.shape, dtype=box.dtype)
-    new_box[:, 0] = box[:, 0] - half_bw
-    new_box[:, 1] = box[:, 1] - half_bh
-    new_box[:, 2] = box[:, 0] + half_bw
-    new_box[:, 3] = box[:, 1] + half_bh
-
-    return new_box
-
-
-def read_yolo_label(filepath, im_shape=None, shift=None, convert=False):
-    """Read a yolo label text file. It may contain a confidence value for the labels or not, will handle both cases
-
-    INPUTS
-    ------
-    filepath : str
-        the path of the text file
-    im_shape : tuple or int (default: None)
-        image width and height corresponding to the label, if an int it is assumed both are the same. Will scale coordinates
-        to int values instead of normalized if given
-    shift : tuple or int (default: None)
-        shift value in the x and y direction, if int it is assumed to be the same in both. These values will be subtracted and applied
-        after scaling if needed
-    convert : bool (default: False)
-        If True, convert the output boxes from yolo format (label, x-center, y-center, width, height, conf) to (label, x1, y1, x2, y2, conf)
-        where point 1 is the top left corner of box and point 2 is the bottom corner of box
-
-    RETURN
-    ------
-    coords : array
-        coordinates array, [N, 4 or 5] depending if confidence was in input file
-
-    """
-    coords = []
-
-    with open(filepath, "r") as fh:
-        for line in fh.readlines():
-            if len(line):
-                coords.append([float(ln) for ln in line.strip().split(" ")])
-
-    coords = np.array(coords)
-
-    # scale coords if needed
-    if im_shape is not None:
-        if isinstance(im_shape, int):
-            w, h = im_shape, im_shape
-        else:
-            w, h = im_shape[:2]
-
-        coords[:, 1] *= w
-        coords[:, 3] *= w
-        coords[:, 2] *= h
-        coords[:, 4] *= h
-
-    # shift coords
-    if shift is not None:
-        if isinstance(shift, int):
-            x_shift, y_shift = shift, shift
-        else:
-            x_shift, y_shift = shift[:2]
-
-        coords[:, 1] -= x_shift
-        coords[:, 2] -= y_shift
-
-    if convert:
-        coords[:, 1:5] = convert_box_type(coords[:, 1:5])
-
-    return coords
-
-
-def corners_to_polygon(x1: int, y1: int, x2: int, y2: int) -> Polygon:
-    """Return a Polygon from shapely with the box coordinates given the top left and bottom right corners of a
-    rectangle (can be rotated).
-
-    Args:
-        x1, y1, x2, y2: Coordinates of the top left corner (point 1) and the bottom right corner (point 2) of a box.
-
-    Returns:
-        Shapely polygon object of the box.
-
-    """
-    return Polygon([(x1, y1), (x2, y1), (x2, y2), (x1, y2)])