Table of Contents
Shortcuts

slideflow.util

This module contains a variety of utility functions used throughout the package.

class slideflow.util.FileFormatter(fmt=None, datefmt=None, style='%')
format(record)

Format the specified record as text.

The record’s attribute dictionary is used as the operand to a string formatting operation which yields the returned string. Before formatting the dictionary, a couple of preparatory steps are carried out. The message attribute of the record is computed using LogRecord.getMessage(). If the formatting string uses the time (as determined by a call to usesTime(), formatTime() is called to format the event time. If there is exception information, it is formatted using formatException() and appended to the message.

class slideflow.util.LogFormatter(fmt=None, datefmt=None, style='%')
format(record)

Format the specified record as text.

The record’s attribute dictionary is used as the operand to a string formatting operation which yields the returned string. Before formatting the dictionary, a couple of preparatory steps are carried out. The message attribute of the record is computed using LogRecord.getMessage(). If the formatting string uses the time (as determined by a call to usesTime(), formatTime() is called to format the event time. If there is exception information, it is formatted using formatException() and appended to the message.

class slideflow.util.ProgressBar(ending_val, starting_val=0, bar_length=20, endtext='', show_eta=False, show_counter=False, counter_text='', leadtext='', mp_counter=None, mp_lock=None)

Flexible progress bar with dynamic ETA monitoring and multiprocessing support.

__init__(ending_val, starting_val=0, bar_length=20, endtext='', show_eta=False, show_counter=False, counter_text='', leadtext='', mp_counter=None, mp_lock=None)
class slideflow.util.TqdmLoggingHandler(*args, **kwargs)

Avoid tqdm progress bar interruption by logger’s output to console

__init__(*args, **kwargs)

Initialize the handler.

If stream is not specified, sys.stderr is used.

emit(record)

Emit a record.

If a formatter is specified, it is used to format the record. The record is then written to the stream with a trailing newline. If exception information is present, it is formatted using traceback.print_exception and appended to the stream. If the stream has an ‘encoding’ attribute, it is used to determine how to do the output to the stream.

slideflow.util.choice_input(prompt, valid_choices, default=None, multi_choice=False, input_type=<class 'str'>)

Prompts user for multi-choice input.

slideflow.util.float_input(prompt, default=None, valid_range=None)

Prompts user for float input.

slideflow.util.get_model_config(model_path)

Loads model configuration JSON file.

slideflow.util.get_relative_tfrecord_paths(root, directory='')

Returns relative tfrecord paths with respect to the given directory.

slideflow.util.get_slide_paths(slides_dir)

Get all slide paths from a given directory containing slides.

slideflow.util.get_slides_from_model_manifest(model_path, dataset=None)

Get list of slides from a model manifest.

Parameters

  • model_path (str) – Path to model from which to load the model manifest.

  • dataset (str) – ‘training’ or ‘validation’. Will return only slides from this dataset. Defaults to None (all).

Returns

List of slide names.

Return type

list(str)

slideflow.util.global_path(root, path_string)

Returns global path from a local path.

slideflow.util.int_input(prompt, default=None)

Prompts user for int input.

slideflow.util.load_json(filename)

Reads JSON data from file.

slideflow.util.make_dir(_dir)

Makes a directory if one does not already exist, in a manner compatible with multithreading.

slideflow.util.multi_warn(arr, compare, msg)

Logs multiple warnings.

slideflow.util.path_input(prompt, root, default=None, create_on_invalid=False, filetype=None, verify=True)

Prompts user for directory input.

slideflow.util.path_to_ext(path)

Returns extension of a file path string.

slideflow.util.path_to_name(path)

Returns name of a file, without extension, from a given full path string.

slideflow.util.read_annotations(annotations_file)

Read an annotations file.

slideflow.util.relative_path(path, root)

Returns a relative path, from a given root directory.

slideflow.util.tfrecord_heatmap(tfrecord, slide, tile_px, tile_um, tile_dict, outdir)

Creates a tfrecord-based WSI heatmap using a dictionary of tile values for heatmap display.

Parameters

  • tfrecord (str) – Path to tfrecord.

  • slide (str) – Path to whole-slide image.

  • tile_dict (dict) – Dictionary mapping tfrecord indices to a tile-level value for display in heatmap format.

  • tile_px (int) – Tile width in pixels.

  • tile_um (int) – Tile width in microns.

  • outdir (str) – Path to directory in which to save images.

Returns

Dictionary mapping slide names to dict of statistics (mean, median, above_0, and above_1)

slideflow.util.to_onehot(val, max)

Converts value to one-hot encoding

Parameters

  • val (int) – Value to encode

  • max (int) – Maximum value (length of onehot encoding)

slideflow.util.update_results_log(results_log_path, model_name, results_dict)

Dynamically update results_log when recording training metrics.

slideflow.util.write_json(data, filename)

Writes data to JSON file.

slideflow.util.yes_no_input(prompt, default='no')

Prompts user for yes/no input.