tumourkit.segmentation.evaluate

Evaluating script for cell predictions.

Input format

Centroids in a csv with columns X,Y and class. Both for prediction and GT.

Output

F1-score (binary, macro and weighted), accuracy, ROC AUC and error percentage between the prediction and the GT at cell-level.

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_matrices`	Adds two matrices even if their shapes are different.
`compute_f1_score_from_matrix`	Computes the F1 score of a given class against the rest.
`compute_metrics_from_matrix`	Computes various evaluation metrics from a confusion matrix.
`compute_perc_error_bkgr`	Computes absolute difference in percentages of the classes.
`get_confusion_matrix`	Calculates the confusion matrix based on the ground truth and predicted centroids.
`get_pairs`	Retrieves true and predicted labels ordered by their correspondences.
`main`
`main_with_args`
`save_csv`	Saves metrics in CSV format for later use.
`save_debug_matrix`	Saves a confusion matrix in CSV format for debug purposes.