Appendix O — chapter4.analysis.tug_results_processing
chapter4.analysis.tug_results_processing
Provides functions to process the raw results of the TUG test obtained by the developed system and the reference method.
Functions
| Name | Description |
|---|---|
| check_status | Checks the status of the system’s generated results of a TUG execution. An execution is classified |
| compute_errors_by_subject | Computes the error in milliseconds between the measures obtained by the systems and the reference measures. |
| compute_rmse_by_subject | Computes the intra-subject RMSE between the systems’ and reference methods. |
| extract_manual_results | Extracts the TUG results generated by the reference system. |
| extract_system_results | Extracts the TUG results generated by the system. |
| invalidate_executions | Invalidates TUG executions not considered as failures by the system but that were wrongly executed due to external factors. |
check_status
chapter4.analysis.tug_results_processing.check_status(row)
Checks the status of the system’s generated results of a TUG execution. An execution is classified as success when all measures where obtained, partial_success when the duration of the test was obtained but the measure of one or more subphases is missing, failure when the duration of the test was not obtained.
Parameters
| Name | Type | Description | Default |
|---|---|---|---|
row |
pandas.Series |
Results of a TUG execution. | required |
Returns
| Type | Description |
|---|---|
| str | The status of the execution. One of success, partial_success or failure. |
compute_errors_by_subject
chapter4.analysis.tug_results_processing.compute_errors_by_subject(systems_results, man_results)
Computes the error in milliseconds between the measures obtained by the systems and the reference measures.
Parameters
| Name | Type | Description | Default |
|---|---|---|---|
systems_results |
dict | Dict containing the results (values) generated by both system’s configurations: C1 and C2 (keys). |
required |
man_results |
pandas.DataFrame |
DataFrame containing the reference measures. | required |
Returns
| Type | Description |
|---|---|
pandas.DataFrame |
DataFrame containing the errors between systems’ and reference measures. |
compute_rmse_by_subject
chapter4.analysis.tug_results_processing.compute_rmse_by_subject(errors_df)
Computes the intra-subject RMSE between the systems’ and reference methods.
Parameters
| Name | Type | Description | Default |
|---|---|---|---|
errors_df |
pandas.DataFrame |
DataFrame containing the error in ms of the system measures and the reference method for all subjects. | required |
Returns
| Type | Description |
|---|---|
pandas.DataFrame |
DataFrame containing the intra-subject RMSE for each subject, system and measure. |
extract_manual_results
chapter4.analysis.tug_results_processing.extract_manual_results(subject, results_file)
Extracts the TUG results generated by the reference system.
Parameters
| Name | Type | Description | Default |
|---|---|---|---|
subject |
str | ID of the subject whose results are extracted. | required |
results_file |
str | Path of the file containing the results. | required |
Returns
| Type | Description |
|---|---|
pandas.DataFrame |
DataFrame containing the extracted results. |
extract_system_results
chapter4.analysis.tug_results_processing.extract_system_results(subject, results_file)
Extracts the TUG results generated by the system.
Parameters
| Name | Type | Description | Default |
|---|---|---|---|
subject |
str | ID of the subject whose results are extracted. | required |
results_file |
str | Path of the file containing the results. | required |
Returns
| Type | Description |
|---|---|
pandas.DataFrame |
DataFrame containing the extracted results. |
invalidate_executions
chapter4.analysis.tug_results_processing.invalidate_executions(df, executions)
Invalidates TUG executions not considered as failures by the system but that were wrongly executed due to external factors.
Parameters
| Name | Type | Description | Default |
|---|---|---|---|
df |
pandas.DataFrame |
DataFrame containing the TUG test system’s results. | required |
executions |
dict | Dict indicating which executions (values) of which subject (key) have to be invalidated. | required |
Returns
| Type | Description |
|---|---|
pandas.DataFrame |
DataFrame with the specified samples invalidated. |