m (Text replacement - "www.c-motion.com/download" to "www.has-motion.com/download")
(13 intermediate revisions by one other user not shown)
Line 5:
Line 5:
|}
|}
This tutorial will show you how to export the results of your analysis. This option is useful for reporting specific signals, metrics, or events from a data set.
This tutorial will show you how to export the results of your analysis. This allows users to report specific signals, metrics, or events from a data set and to share results from analysis conducted within Inspect3D.
There is also a video tutorial to go along with this available [https://www.youtube.com/watch?v=woofjJYryCQ| here]
==Data==
This tutorial uses overground walking data from four subjects. The subjects walked at three different speeds: slow, normal and fast. The data was processed using a pipeline with automatic event detection and link model based item calculations (most notably the knee joint angles). [[https://www.has-motion.com/download/examples/inspect3d_samples.zip Four Subjects Walking Data Set]].
This tutorial also uses query definitions that have been previously saved in a [[Q3D Query File|.q3d file]]. [[https://www.has-motion.com/download/examples/AnkleAngles.q3d AnkleAngles.q3d]].
==Load the library==
==Data==
As with previous tutorials, we begin by loading the library and defining the queries relevant to our question.
This tutorial uses overground walking data from four subjects. The subjects walked at three different speeds: slow, normal and fast. The data was processed using a pipeline with automatic event detection and link model based item calculations (most notably the knee joint angles).
1. Click [[Image:I3DLoadLibrary.png|20px]] <b>Load Library</b> in the [[Inspect3D_Documentation_ToolBar|toolbar]] to open the Load Library dialog.
2. Click <b>Browse</b> and select the folder where the data is stored.
==Load and query the CMO library==
3. Click <b>Load</b> button to import the data.
1. As always, the library must first be loaded and our queries defined.
==Load queries and compute groups==
For this tutorial we will load previously saved query definitions and use them to calculate our specific groups.
1.1 A thorough explanation of loading a library and defining data can be found in [[Inspect3D_Tutorial_1|Tutorial 1]].
1. Click on the [[Image:I3DGroups.png|20px]] <b>Query Definitions</b> icon on the [[Inspect3D_Documentation_ToolBar|toolbar]] and then click on [[Image:I3DOpenGroupDef.png|20px]] <b>Load Query Def & Compute Groups</b>.
1.2 This tutorial uses a library with overground walking data at several speeds and six queries. These queries extract the knee flexion angle for the right and left sides for each of the three walking speeds throughout a complete gait cycle.
2. Select the AnkleAngles.q3d file with the saved query definitions and <b>Open</b> them.
2.To export data to a text file, click [[Image:I3DExportPCAResults.png|30px]] <b>Export</b> to open the Export Results dialog.
Three groups will now appear in the <b>Groups</b> list: ANKLE_ANGLE_X, ANKLE_ANGLE_Y, and ANKLE_ANGLE_Z. Clicking on any of the groups will show that each of the four workspaces is associated with that group.
==Customize the export==
==Visualize the groups==
<div style="overflow: hidden">
<div style="overflow: hidden">
The Export Results dialog contains two sections.[[Image:I3DExportDialogueBlankAnotated3.png|right]]
[[Image:Inspect3D_Ankle_Angles_(Four_Subjects_Walking).png|600px|right]] We can visualize the groups individually and collectively in different plots in the Queried Data area. For a full overview of how to visualize data, see the [[Inspect3D Tutorial: Load and View Data|tutorial]].
1. The 'Definition' section (see 1) is used to define which results are to be exported. The options here are Signals, Metrics, or PCA Results.
1. To start, click on [[Image:I3DShowOptions.png|20px]] <b>Show Options</b>.
2. The "Options' section (see 2) is used to specify how the results will be exported. The format for the text file and the precision with which to export numerical quantities can both be set and a preview of the export generated.
2. Under <b>Plotting options</b> choose 2 <b>Graph Rows</b> and 2 <b>Graph Columns</b> to create a 2x2 set of plots in the Queried Data area.
</div>
==Definition==
3. Close the Show Options dialog.
<div style="overflow: hidden">
1. Set the drop down menu to either Signals, Metrics or PCA results. [[Image:ExportTypeAnotated2.png|300px|right]]
1.1 In the definition section, the user selects which signals to export. Data are only available from queries, metrics and events found in queries, or results from any PCA calculations. If the user wishes to export a certain signal from the CMO library they must first define that signal using a query (See [[Inspect3D_Tutorial_1|Tutorial 1]] for explanation of signal definitions) or perform PCA on multiple pre-defined signals.
4. With the top-left plot selected (this will be indicated with a light-grey border), select the ANKLE_ANGLE_X group, select all workspaces, and then plot the raw sequences.
1.2 The three types of data can be exported using this dialog are signals, metrics, or PCA results.
5. Select the top-right plot and plot the raw sequences from the ANKLE_ANGLE_Y group's workspaces.
1.3 The check boxes that allow you to decide what parts of the data to export changed based on the export type in the combo box. Regardless of the export type, the first 5 rows (or 5 columns) describe the signals being exported (header information). To preview the export format, after any signals are selected, the user can press 'Generate Preview'.
6. Select the bottom-left plot and plot the raw sequences from the ANKLE_ANGLE_Z group's workspaces.
2. Select the check boxes of the data you wish to export.
7. Select the bottom-right plot, select all groups and all workspaces, and plot the group means.
[[Image:Export ExportGraphOption.png|right]] It is possible now to export the visualizations to one of four image formats: JPG, PDF vector graphic, PNG, or BMP.
The Signals option exports previously defined waveforms. The user controls the Number of Points that will be used to normalize the data; the default setting is 101. The types of data that can be exported include both individual and group data as well as raw and processed data. The five options are: including the header information for each export type:
1. Right-click the bottom-right plot and select <b>Export Graph...</b> from the context menu.
1. <b>Group Mean:</b> Exports the normalized mean for the defined group (a group is a query). The exported file will contain the normalized mean for each group. The normalized mean for each subject is taken, and mean is taken across the subject means.
2. In the Export Graph dialog, choose your desired <b>Export Path</b>, leave <b>Use Current Size</b> checked, and set the <b>Format</b> to ".pdf (vector graphics)".
* The headers will be:
** Row 1: CMO library path
** Row 2: Signal Name_MEAN
** Row 3: P2D
** Row 4: Group Name
** Row 5: Signal Component
2. <b>Group Standard Deviation:</b> Exports the standard deviation for the group using the mean subject curves as the input data (ie. N = the number of subjects/cmo files contained within the group). The normalized mean for each subject is taken, and the standard deviation is taken across the subject means.
3. Click <b>Save</b>.
* The headers will be:
** Row 1: CMO library path
** Row 2: Signal Name_STD_DEV
** Row 3: P2D
** Row 4: Group Name
** Row 5: Signal Component
3. <b>Subject Mean:</b> Exports the normalized mean data for each subject in each of the groups.
[[Image:Inspect3D_Export_Graph_Menu.png]]
* The headers will be:
** Row 1: CMO file name
** Row 2: Signal Name
** Row 3: P2D
** Row 4: Group Name
** Row 5: Signal Component
4. <b>Subject Raw</b>: Exports the normalized data for each subject in each of the groups.
4. Alternatively, export all four graphs collectively by selecting [[Image:I3D_file_export_graphs.png|20px]] <b>Export Graphs</b> on the [[Inspect3D_Documentation_ToolBar|toolbar]].
* The headers will be:
** Row 1: CMO file name/C3D file name
** Row 2: Signal Name_StartFrame_EndFrame
** Row 3: P2D
** Row 4: Group Name
** Row 5: Signal Component
4.1 <b>Events (Normalised)</b>: This option becomes visible when the Subject Raw option is selected, and exports the normalised events that occur within this sequence (intermediate events). The data is normalized to the percentage of the signals.
* The headers will be:
** Col 1: CMO file name/C3D file name
** Col 2: Signal Name_StartFrame_EndFrame_EventName
** Col 3: EVENTS
** Col 4: Group Name
** Col 5: Signal Component.
5. <b>Subject Raw (Original)</b>: Exports the time based (un-normalized) data for each subject in each of the groups.
5. In the Export Graph dialog, choose your desired <b>Export Path</b>, uncheck <b>Use Current Size</b>, specify Height and Width to be 400 pixels each, and set the <b>Format</b> to ".jpg".
* The headers will be:
</div>
** Row 1: CMO file name/C3D file name
** Row 2: Signal Name_StartFrame_EndFrame
** Row 3: P2D
** Row 4: Group Name
** Row 5: Signal Component
5.1 <b>Events (original)</b>: This option becomes visible when the Subject Raw option is selected. This options exports the normalised (to 101 points) events that occur within this sequence. The headers will be:
==Export Signals to Text==
<div style="overflow: hidden">
[[Image:Inspect3D_Export_Results_Settings.png|right]] Alternatively, we can export our signal data to a text format.
{| class="wikitable"
1. Click [[Image:I3DExportPCAResults.png|20px]] <b>Export Results</b> on the application toolbar.
|+ Export Headers for Standard ASCII Export
! Row 1:
! Group
! Subject
! "Raw"
! "Raw Events"
! "Raw Original"
! "Raw Events Original"
|-
! Row 2:
| CMO Library Path
| CMO Name
| C3D Name
| C3D Name
| C3D Name
| C3D Name
|-
! Row 3:
| Group_Mean/Std_Dev
| Subj_Mean/Std_Dev
| SignalName_Frames
| EventName
| SignalName_Frames
| EventName
|-
! Row 4:
| P2D
| P2D
| P2D/Metric
| Events
| Derived/Metric/P2D
| Event_Frames
|-
! Row 5:
| rowspan="1" colspan="6" style="text-align: center;" | Group Name
|-
! Row 6:
| rowspan="1" colspan="6" style="text-align: center;" | Signal Component(s)
|}
</div>
===Metrics===
2. In the Export Results dialog's <b>Definition</b> section, set the <b>Export Type</b> to Signals, the <b>Input Data</b> to All Queried Data, and select both <b>Workspace Mean</b> and Workspace Std. Dev.</b>.
<div style="overflow: hidden">
[[Image:ExportDialogueMetrics3.png|right]]
The second type of data that can be exported is called 'Metrics' under the Export type combo box. This export option is useful if certain aspects of a waveform, such as the minimum or the maximum, are desired and not the entire waveform. When selecting this export type certain options become available to the user.
3. In the Export Results dialog's <b>Export Result Options</b> section, leave the default <b>Export Format</b> and <b>Precision</b> and click <b>Generate Preview</b>.
The first option specifies the data to be used to calculate the results, being either queries or subjects. If 'queries' is selected, then the resulted metrics are calculated for each query, using the mean waveform for the query as the input data. If the 'subjects' option is selected, then metrics are calculated for each subject, for each query.
4. The <b>Table</b> of results will populate and you can scroll in both directions to inspect the text that will be exported. For each signal group, we can see in the table that each Workspace's Mean and Standard Deviation gets its own column and that there are 101 rows, one for each normalized time point. Note that resizing the dialog prioritizes any additional space for the table to make it easier to view large output files.
After selected which data to export from, the user can specific the desired metrics to export. Here there are three options and sub-options, which are described as follows. Included in this description are the header formats for each export option:
5. Specify a <b>Results File Name</b> and then click <b>Export Results</b> to finalize the export.
[[Image:ExportDialogueMinimumStDev.png|right]]
==Export Metrics to Text==
1. <b>Mean</b>: Calculates and exports the mean value(s). The header format for the queries are as follows: Col 1: CMO lib path, Col 2: Signal Name_MEAN, Col 3: P2D, Col 4: Group Name, Col and 5: Signal Component. The header format for the subjects are as follows: Col 1: CMO file name, Col 2: Signal Name_MEAN, Col 3: P2D, Col 4: Group Name, and Col 5: Signal Component.
We can also export metrics based on the data to a text format.
1.1 <b>Std. Dev.</b>: Calculates and exports the standard deviation about the selected metric. The header format for the queries are as follows: Col 1: CMO lib path, Col 2: Signal Name_MEAN_STD_DEV, Col 3: P2D, Col 4: Group Name, and Col 5: Signal Component. The header format for the subjects are as follows: Col 1: CMO file name, Col 2: Signal Name_MEAN_STD_DEV, Col 3: P2D, Col 4: Group Name, and Col 5: Signal Component.
1. Returning to the Export Results dialog's <b>Definition</b> section, set the <b>Export Type</b> to Metrics, set <b>Calculate results for</b> to Workspaces, and select both <b>Minimum</b> and <b>Maximum</b>.
2. <b>Min</b>: Calculates and exports the minimum value. If 'queries' is selected then the mean waveform is computed for the entire query and the minimum value for this signal is computed. If 'subjects' is selected then the mean waveform for each subject is computed, and the minimum value(s) for this waveform will be computed i.e. The minimum of each subject's mean waveform, not the average of individual waveforms minimum value.
2. In the Export Results dialog's <b>Export Result Options</b> section, click <b>Generate Preview</b>. For each signal group, we can see that the table contains each workspace's minimum mean value and maximum mean value.
2.1 <b>Std. Dev.</b>: Calculates and exports the standard deviation about the minimum point. If 'queries' is selected then the position of the minimum value in the waveform is computed. The mean waveforms for each subject are then computed. The value for each subject at the position of the minimum computed initially is then found. These data are used as the input for the standard deviation calculation (ie. N = number of subjects). If 'subjects' is selected, then the same process is followed, but rather than using the index of the minimum for the query waveform, the mean subject waveforms are used, and the position of their minimum(s) will be computed. This index is then applied to the raw data for the subject (ie. N = number of traces per subject).
3. Back in the main application window, click on the top-left plot.
2.2. <b>Event Point</b>: Calculates and exports the position (index) of the minimum value(s). If 'queries' is selected, then a single index is exported for each group. If 'subjects' is selected, then an index for each subject within each query is exported.
4. In the Export Results dialog's <b>Definition</b> section, set <b>Input Data</b> to Active Plot Data</b>
3. <b>Max</b>: Calculates and exports the maximum value. The same rules as described in the Min export option also apply here.
5. Click <b>Generate Preview</b> again. Now we can see that our selected metrics (Minimum and Maximum) will only be exported to the ANKLE_ANGLE_X traces, since this is the data on the currently active plot.
4. <b>Add Metrics Columns</b>: Adds and removes additional columns of metrics to the export.
6. Specify a <b>Results File Name</b> and then click <b>Export Results</b> to finalize the export.
</div>
</div>
===PCA Results===
==Perform PCA==
<div style="overflow: hidden">
In order to export [[Principal Component Analysis]] (PCA)results, we have to first calculate the PCA results! For a full overview of how to perform PCA and interpret some of the results, see the [[Inspect3D Tutorial: Perform Principal Component Analysis|tutorial]].
[[Image:ExportDialoguePCA.png|right]]
The final export options allows the user to export results from the PCA calculations. These export options allow all plots generated in Inspect3D to be recreated in a separate application. Effectively, this is a raw data export option for all PCA results. The header format is highlighted within the figures describing each export option.
1. Ensure that all groups and workspaces are selected in the <b>Groups</b> and <b>Workspaces</b> lists.
1. <b>Subject Scores</b>: This exports the mean subject scores for each group (query). The number of values exported is equal to the number of PCs selected.
2. Open the [[Image:I3D_PCAOptions2.png|30px]] <b>PCA Options</b> dropdown menu on the [[Inspect3D_Documentation_ToolBar|toolbar]].
2. <b>Group Scores</b>: This exports the mean group scores for each group. The number of values exported is equal to the number of PCs selected.
3. Set <b>Number PCs</b> to 4 and ensure that <b>Use Workspace Mean</b> is checked.
3. <b>Group Score Std. Dev</b>: This exports the standard error for each group. The number of points is equal to the number of PCs used in the analysis.
4. <b>Variance Explained</b>: This exports variance explained (as a percentage of the total variance) by each principle component.
5. The results of these calculations will automatically populate the PCA graphs. If these aren't already displayed, click [[Image:I3D_PCAShowGraphs.png|20px]] <b>Show PCA Graphs</b> in the [[Image:I3D_PCAOptions2.png|30px]] <b>PCA Options</b> dropdown menu. Because the traces for each signal cluster around a distinctive mean value, almost all of the variance in these groups can be captured by a single principal component.
5. <b>Eigenvectors</b>: This exports eigenvectors for each PC. The number of points exported is 101 and the number of signals depends on the number of PCs used in the analysis.
1. Set the Export Format to [[Visual3D_ASCII_Format|Standard ASCII], Transposed ASCII, SPSS ASCII, or [[P2D_Format|P2D]] and click Generate Preview.
[[Image:Inspect3D_Export_Results_Settings_PCA.png|400px|right]] Now that we have performed PCA, we have results to export.
[[Image:ExportDialogueTransposedPCA.png|right]]
1.1 The options section of the export dialog is used to determine the direction of the ASCII export and preview the export.
1. Click [[Image:I3DExportPCAResults.png|20px]] <b>Export Results</b> on the application toolbar.
1.2 The export format has three options. The Transposed ASCII option, which is seen on the right, exports the signals in a column centric format. The Standard ASCII option, which is seen in the examples used previously in this tutorial, exports the signals in a row centric format. The selection of either option depends on the analysis being performed on the exported signals. The SPSS ASCII, allows the exported file to be read by [http://www.ibm.com/analytics/us/en/technology/spss/ SPSS]. Finally the P2D format is a legacy file format from the MOVE3D software application.
2. In the Export Results dialog's <b>Definition</b> section, set the <b>Export Type</b> to PCA Results and select the <b>Group Scores</b>, <b>Group Scores Std. Dev.</b>, and <b>Variance Explained</b> options.
1.3 When the Generate Preview button is clicked the table will show a preview of the signals to be exported, which is controlled by the selections made in the Definition section. This preview is identical to the format of the file that will be exported.
3. In the Export Results dialog's <b>Export Result Options</b> section, leave <b>Export Format</b> as Standard ASCII and <b>Precision</b> as 4.
2. Click on the Browse button and select where you want to save your data. Once a path is defined click on the Export button to export the results.
4. Click <b>Generate Preview</b>. We can see that each signal's Group PC Score Mean and Standard Deviation is shown for each of the selected principal components and that the variance explained is shown for all computed principal components. Note here that each row in the export table is now a principal component and not a normalized time point as for the other export types. Also note that Inspect3D does have the ability to export information about all of the principal components that were calculated, not only the ones that were selected.
</div>
</div>
==Recap==
==Recap==
In this tutorial you learned how to export the traces visualized in Inspect3D to common image formats. You also learned how to export three types of data to text: Signals, Metrics, and PCA Results.
This tutorial provides an overview of using Inspect3D as an export tool for a .cmo library. It describes the three export options: Signals, Metrics, and PCA Results. Using these options, the user has improved flexibility to export only the desired signals from a data set to be further analyzed.
==Navigate Tutorials==
<div style='text-align: left;float:left;width:33%;'>Previous: [[Inspect3D_Tutorial:_Perform_Principal_Component_Analysis|Tutorial 3: Perform Principal Component Analysis]]</div>
<div style='text-align: center;float:left;width:33%;'><b>Inspect3D Getting Started Tutorials</b></div>
This tutorial will show you how to export the results of your analysis. This allows users to report specific signals, metrics, or events from a data set and to share results from analysis conducted within Inspect3D.
Data
This tutorial uses overground walking data from four subjects. The subjects walked at three different speeds: slow, normal and fast. The data was processed using a pipeline with automatic event detection and link model based item calculations (most notably the knee joint angles). [Four Subjects Walking Data Set].
This tutorial also uses query definitions that have been previously saved in a .q3d file. [AnkleAngles.q3d].
Load the library
As with previous tutorials, we begin by loading the library and defining the queries relevant to our question.
1. Click Load Library in the toolbar to open the Load Library dialog.
2. Click Browse and select the folder where the data is stored.
3. Click Load button to import the data.
Load queries and compute groups
For this tutorial we will load previously saved query definitions and use them to calculate our specific groups.
1. Click on the Query Definitions icon on the toolbar and then click on Load Query Def & Compute Groups.
2. Select the AnkleAngles.q3d file with the saved query definitions and Open them.
Three groups will now appear in the Groups list: ANKLE_ANGLE_X, ANKLE_ANGLE_Y, and ANKLE_ANGLE_Z. Clicking on any of the groups will show that each of the four workspaces is associated with that group.
Visualize the groups
We can visualize the groups individually and collectively in different plots in the Queried Data area. For a full overview of how to visualize data, see the tutorial.
1. To start, click on Show Options.
2. Under Plotting options choose 2 Graph Rows and 2 Graph Columns to create a 2x2 set of plots in the Queried Data area.
3. Close the Show Options dialog.
4. With the top-left plot selected (this will be indicated with a light-grey border), select the ANKLE_ANGLE_X group, select all workspaces, and then plot the raw sequences.
5. Select the top-right plot and plot the raw sequences from the ANKLE_ANGLE_Y group's workspaces.
6. Select the bottom-left plot and plot the raw sequences from the ANKLE_ANGLE_Z group's workspaces.
7. Select the bottom-right plot, select all groups and all workspaces, and plot the group means.
Export Graphs
It is possible now to export the visualizations to one of four image formats: JPG, PDF vector graphic, PNG, or BMP.
1. Right-click the bottom-right plot and select Export Graph... from the context menu.
2. In the Export Graph dialog, choose your desired Export Path, leave Use Current Size checked, and set the Format to ".pdf (vector graphics)".
3. Click Save.
4. Alternatively, export all four graphs collectively by selecting Export Graphs on the toolbar.
5. In the Export Graph dialog, choose your desired Export Path, uncheck Use Current Size, specify Height and Width to be 400 pixels each, and set the Format to ".jpg".
Export Signals to Text
Alternatively, we can export our signal data to a text format.
1. Click Export Results on the application toolbar.
2. In the Export Results dialog's Definition section, set the Export Type to Signals, the Input Data to All Queried Data, and select both Workspace Mean and Workspace Std. Dev..
3. In the Export Results dialog's Export Result Options section, leave the default Export Format and Precision and click Generate Preview.
4. The Table of results will populate and you can scroll in both directions to inspect the text that will be exported. For each signal group, we can see in the table that each Workspace's Mean and Standard Deviation gets its own column and that there are 101 rows, one for each normalized time point. Note that resizing the dialog prioritizes any additional space for the table to make it easier to view large output files.
5. Specify a Results File Name and then click Export Results to finalize the export.
Export Metrics to Text
We can also export metrics based on the data to a text format.
1. Returning to the Export Results dialog's Definition section, set the Export Type to Metrics, set Calculate results for to Workspaces, and select both Minimum and Maximum.
2. In the Export Results dialog's Export Result Options section, click Generate Preview. For each signal group, we can see that the table contains each workspace's minimum mean value and maximum mean value.
3. Back in the main application window, click on the top-left plot.
4. In the Export Results dialog's Definition section, set Input Data to Active Plot Data
5. Click Generate Preview again. Now we can see that our selected metrics (Minimum and Maximum) will only be exported to the ANKLE_ANGLE_X traces, since this is the data on the currently active plot.
6. Specify a Results File Name and then click Export Results to finalize the export.
Perform PCA
In order to export Principal Component Analysis (PCA)results, we have to first calculate the PCA results! For a full overview of how to perform PCA and interpret some of the results, see the tutorial.
1. Ensure that all groups and workspaces are selected in the Groups and Workspaces lists.
2. Open the PCA Options dropdown menu on the toolbar.
3. Set Number PCs to 4 and ensure that Use Workspace Mean is checked.
4. Click Run PCA.
5. The results of these calculations will automatically populate the PCA graphs. If these aren't already displayed, click Show PCA Graphs in the PCA Options dropdown menu. Because the traces for each signal cluster around a distinctive mean value, almost all of the variance in these groups can be captured by a single principal component.
Export PCA Results
Now that we have performed PCA, we have results to export.
1. Click Export Results on the application toolbar.
2. In the Export Results dialog's Definition section, set the Export Type to PCA Results and select the Group Scores, Group Scores Std. Dev., and Variance Explained options.
3. In the Export Results dialog's Export Result Options section, leave Export Format as Standard ASCII and Precision as 4.
4. Click Generate Preview. We can see that each signal's Group PC Score Mean and Standard Deviation is shown for each of the selected principal components and that the variance explained is shown for all computed principal components. Note here that each row in the export table is now a principal component and not a normalized time point as for the other export types. Also note that Inspect3D does have the ability to export information about all of the principal components that were calculated, not only the ones that were selected.
Recap
In this tutorial you learned how to export the traces visualized in Inspect3D to common image formats. You also learned how to export three types of data to text: Signals, Metrics, and PCA Results.
Load Library in the toolbar to open the Load Library dialog.
Query Definitions icon on the toolbar and then click on 
Load Query Def & Compute Groups.
.png)
PCA Options dropdown menu on the toolbar.
Run PCA.
Show PCA Graphs in the .png)
