10 Categorical Feature Extraction
Based on the datasets extracted in the numerical feature extraction step, FLIM Playground:
- merges the datasets into a single dataset
- assigns categorical features to each cell in the merged dataset
10.1 Merging Datasets
It scans the specified folder path and finds all CSV files. It uses the cell identifier column to check for duplicates both within each dataset and across all datasets.
The FOV identifier uniquely identifies a field of view and is assumed to contain all information necessary to extract the categorical features (e.g., treatment, time point, etc.), by including segments separated by a certain delimiter (e.g., _). Categorical features are assigned from individual segments or their combinations. Example: The FOV Panc1_Cyanide_dish1 denotes that it comes from the Panc1 cell line, under the Cyanide treatment, in the 1st dish.
Therefore, it checks if all field-of-view names include the same number of segments to determine the eligibility of categorical feature assignment.
It merges the datasets that pass the checks by finding common columns and vertically concatenating them.
10.2 Assigning Categorical Features
Available categorical features to be assigned are drawn from the user-specified configuration.
Based on the assumptions, it breaks down the FOV identifier into individual fields and facilitates the assignment.
A live preview of the assignment is displayed.
And the merged dataset with categorical features is available for download.