tumourkit.utils.preprocessing

Module with utility functions for preprocessing.

Copyright (C) 2023 Jose Pérez Cano

This program is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.

This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more details.

You should have received a copy of the GNU Affero General Public License along with this program. If not, see <https://www.gnu.org/licenses/>.

Contact information: joseperez2000@hotmail.es

Functions

add_node	Given a dictionary with vectorial features, converts them into one column per dimension and add them into the global dictionary.
apply_mask	Apply a binary mask to an RGB image.
compute_perimeter	Compute the perimeter of a given contour.
create_dir	Creates a directory at the specified path if it does not already exist.
create_geojson	Converts a list of contours and their labels to a list of dictionaries containing GeoJSON-formatted data.
extract_features	Extracts features from a given RGB bounding box of a cell and its mask.
format_contour	Formats a contour in cv2.findContours format to an array of shape (N,2).
get_centroid_by_id	Given an image and an id representing a component, returns the centroid of the component as a tuple (x, y).
get_mask	Given segmentation mask with indices as pixel values, returns the mask corresponding to the given index.
get_names	This function returns a list of all files in a directory located at <path> that contain the substring <pattern> in their name.
parse_path	Parses a file path and checks for a trailing slash.
read_centroids	Reads a CSV file from the specified directory containing centroids and returns their contents as a NumPy array.
read_csv	Reads a CSV file from the specified directory and returns its contents as a Pandas DataFrame.
read_graph	Reads a graph in CSV format from the specified directory and returns it as a Pandas DataFrame.
read_gson	Reads the GeoJSON file at the specified path with the given name.
read_image	Given name image (without extension) and folder path, returns array with pixel values (RGB).
read_json	Reads a Hovernet JSON file from the specified path and returns the nuclei information as a dictionary.
read_labels	Reads a PNG and CSV file from the specified directories and returns their contents as a tuple.
read_names	Returns a list of file names in the specified path that contain the given pattern.
read_png	Reads a PNG file from the specified directory and returns its image data as a NumPy array.
save_centroids	Saves the given centroids to the specified directory with the specified name and a '.centroids.csv' extension.
save_csv	Saves the given CSV file to the specified directory with the specified name and a '.class.csv' extension.
save_geojson	Save a list of geojson features to a file with the given name at the specified path.
save_graph	Saves the given graph as a CSV file to the specified path.
save_png	Saves a PNG image to a file.
save_pngcsv	Saves the given PNG and CSV files to the specified directories with the specified name.