JMP Wish List

What inspired this wish list request?  The Parallel Plot (Sankey Plot) option in Graph builder is great! It provides you a very intuitive way to compare a multitude of columns. You can even flip a scale to align columns which anticorrelate.   But there is one big problem which makes the parallel plot less useful than it could be: There is no possibility to adjust the individual scales, like. e.g. in this Add-In: Parallel Plot with Axis Scaling   by @txnelson . Therefore, a single outlier point can ruin a whole "column".   there are some option to solve the issue - with their own drawbacks: - Nuke the outlier data point. - Switch to log (x+1) scale,  as @julian showed @ Discovery summit Europe 2023.     What is the improvement you would like to see?  Please provide an functionality to adjust the scales in Parallel Plot.  Nice: an option to choose ranges in order of MAD (median absolute deviation), e.g. +/-3MAD, +/-6MAD.     Why is this idea important?  With the new functionality, Parallel Plot will be much more useful than it is now.         more wishes submitted by   ... View more

☑ cool new feature ☑ could help many users! ☐ removes a „bug“ ☐ nice to have ☐ nobody needs it   #myTop10_2023 ➜ Jmp18 :)   What inspired this wish list request?  Many of the plot types in Graph Builder have the option to apply a summary statistics before displaying the data, but Smoother doesn't have this feature. Therefore, the Smoother data can deviate a lot from what is plotted as Points or Line.   What is the improvement you would like to see Please add the functionality of Summary Statistics also to Smoother.   Why is this idea important? With the possibility to use a summary statistics for Smoother, it will be much easier to plot such curves and to get the smoother aligned to what the other plot types display. At the moment, the user has to re-program the functionality of Summary Statistics via Column formulas to preprocess the data to use it with Smoother.     Names Default To Here( 1 ); dt = Open( "$SAMPLE_DATA/Big Class.jmp" ); Graph Builder( Size( 535, 458 ), Show Control Panel( 0 ), Summary Statistic( "Median" ), Graph Spacing( 4 ), Variables( X( :age ), Y( :height ) ), Elements( Points( X, Y, Legend( 5 ), Summary Statistic( "Min" ) ), Smoother( X, Y, Legend( 6 ) ), Line( X, Y, Legend( 7 ), Summary Statistic( "Min" ) ) ) ) ;         more wishes submitted by   ... View more

What inspired this wish list request?  Graph Builder has a lot of possibilities to specify the markers, marker sizes and colors for each legend entry which is specified via Overlay and Color. Sometimes, the user wants to "overwrite" some settings for a specific subset which could be not explicitly listed in the legend (e.g. special color for exluded data points).   At the moment, this is already possible by storing color and marker settings for some specific rows. Unfortunately, the settings from Graph Builder overwrite the . In the example below, the selected data points keep their special markers because there is no specific marker setting defined in Graph Builder, but the color settings of the rows is just overruled by the color setting from Graph Builder. Another disadvantage of storing the settings as : the settings stick to the specific row. If the table changes, wrong data points will be highlighted.   What is the improvement you would like to see?  As discussed in the DataViz Session @ DiscoverySummit 2023, an additional Overwrite Dropzone would be cool. It can be used to overwrite the settings by Overlay and Color.   Why is this idea important?  The Overwrite Dropzone will give the users additional freedom in formatting their GraphBuilder Plots. e.g. if excluded rows are switched on to be displayed in the plot, one could give the data points a faint grey color - to make then distinguishable from other data points which are not excluded.   Names Default to Here(1); dt = Open( "$SAMPLE_DATA/Big Class.jmp" ); dt << Clear Select << Select Rows( [5, 12, 15] ) << Colors( "Black" ) << Markers( "Star" ); gb = dt << Graph Builder( Size( 437, 413 ), Graph Spacing( 4 ), Variables( X( :height ), Y( :weight ), Overlay( :sex ) ), Elements( Points( X, Y, Legend( 1 ) ), Smoother( X, Y, Legend( 2 ) ) ) );       more wishes submitted by   ... View more

Hello,   I would like to request the option to do a Fit All for Discrete Fit in the Distribution Platform, similar to what's available for Continuous Fit. Regards Mehul Shroff ... View more

What inspired this wish list request?      What is the improvement you would like to see?  Allow Graph Builder to create error bars/confidence bands using model based estimates.   Why is this idea important?        ... View more

Since long I'm observing that row states Hide, Exclude and Hide&Exclude are not always working as expected. I made a demo case for Exclude and Hide. I would expect that an excluded row is not part of an analysis but it is shown in graphs. It works like this - sometimes. Just run the attached script. The behavior is the same in JMP16 and 17.     Interacting with the data is the core of JMP's analytical promise. It must be consistent across platforms  otherwise the user can't trust results.     ... View more

What inspired this wish list request?  I have come across few types of issues with data filters when working with large datasets which make filtering data very slow and unresponsive (conditional data filters getting unfiltered and using Find). Issues with Find can be related to few (bugs? or features) how Find works with local data filters, but Run would still be nice option to have.   What is the improvement you would like to see?  I would like to see an option in Filter red triangle menu to create Run button for a filter. This would allow me to filter the data to the level I want to before filtering it all.   Why is this idea important?  Using filters with data having a lot of data can get quite unresponsive from time to time, especially if there is any calculations involved. ... View more

In semiconductor and semiconductor-adjacent data, we often have multiple sources of variation in our data. For example, lot-to-lot variation, wafer-to-wafer variation, and site-to-site variation. In creating control charts, one point is often one lot. That one lot is usually an average, with the multiple points measured from that single lot average being across multiple wafers and/or sites. In traditional Xbar control limits calculations, the within-subgroup variation is used to calculate the limits for the Xbar chart. But wafer-to-wafer and site-to-site variation can be utterly unrelated to the lot-to-lot variation. So control limits calculate from wafer-to-wafer plus site-to-site variation can look absolutely ridiculous on an Xbar control chart where each point is 1 lot. I have seen real data examples using traditional Xbar limit calculations with almost all of the points being marked as OOC because the limits were so tight.   It would be much better if the limits on the Xbar control chart in this example situation were based on the lot-to-lot variation.   As far as I know, this is only currently possible in JMP17 using Analyze>Quality and Process>Legacy Control Charts>Presummarize. I am afraid that the Presummarize is on the chopping block ("Legacy") for a future version of JMP. Either keep it as a platform in JMP, or create a new platform that has the same capability of calculating control limits from the variation on the same chart.     ... View more

What inspired this wish list request?  Desire to see simultaneously peaks on a histogram that are orders of magnitude different on the Count axis. A linear scale will flatten the smaller peak, whereas a log10 scale would reveal all peaks, large and small.   What is the improvement you would like to see?  Add an option to switch to log scale of the Count axis in histograms in Distribution platform, just like Graph Builder offers it. If a count is zero, do not show a bar.   Why is this idea important?  For my job as a defect metrologist I need to be able to see both large and small (sometimes several orders of magnitude apart on the count axis) subpopulations on a histogram. The count axis in log scale is the only way I know to achieve this. @PatrickGiuliano  ... View more

What inspired this wish list request?          What is the improvement you would like to see?      Why is this idea important? It is important to show that there is data at a zero bar and all chart elements should change independently in graph builder (these also aligns with what a user is expecting)   ... View more

The current summary of a smoothing spline shows the lambda parameter which is hard to connect to the smoothness of the fit when introducing this methodology.   To offer a more interpretable measure of the smoothing spline, the output could add the trace of the projection matrix, aka, the equivalent degrees of freedom (EDF).  With the EDF, it would then be simpler to contrast the fit of a smoothing spline to, for example, the fit of a polynomial with an equal number of parameters.  The EDF is a component of the output for a smoothing spline in R.     ... View more

What inspired this wish list request?  I'm using JMP Pro 17 and really happy with the introduction of Design Space Profiler. However, I was surprised to see that inside some models' platforms that can use Profiler, the Design Space Profiler was not directly accessible/available (example here with SVM, not having the possibility to directly use Design Space Profiler feature, but this "bug" is also present for Bootstrap Forest, Boosted Tree, and perhaps some other modeling platforms) :  For some other models' platforms, the Design Space Profiler is directly accessible/available (here with Neural Networks) :    What is the improvement you would like to see?  There is still a workaround for this situation, by saving the formulas in the datatable and create a Profiler based on these formulas. The Design Space Profiler is then always available :  But it would be easier if the Design Space Profiler was available "by default" in all modeling platforms that have access to the Profiler.   Why is this idea important? The Design Space Profiler is a very informative and interesting feature. JMP beginners may not be aware of the possible workaround, and may miss some very interesting informations because of the "non-native" presence of this feature in all modeling platforms. ... View more

☑ cool new feature ☑ could help many users! ☐ removes a „bug“ ☐ nice to have ☐ nobody needs it   What inspired this wish list request?  The Recall buttons in the GUIs of the standard platforms are great. Such a help to work efficiently!   Sometimes, I have to toggle between two settings or need to trigger an action that is similar to a step that I did some while ago: Total Recall - or Back to the Future? how to travel further into the past    What is the improvement you would like to see? Please add a history to the recall function. If the current implementation of the save and recall function saves recalls settings to/from an associative array of settings, the new version should save and recall the settings to/from a list of associative arrays. With a mouse click on the button, the user can trigger the standard recall of the last setting. By right clicking (or shift/CTRL ...anything) clicking a context menu should show up with numbers - 1 to -N. Clicking on Number -M should trigger a recall of setting # -M.       Why is this idea important? A history will make the recall function even more versatile :)         more wishes submitted by   ... View more

What inspired this wish list request? Here is a sample tabulate.  The header makes sense. But if I scroll down, the top row of the header is lost.  I can see Mean and N, but I don't know what they are for.     What is the improvement you would like to see? I would like the entire header to be shown as the user scrolls down the tabulate table.   Why is this idea important?      ... View more

What inspired this wish list request? I would like to be able to visualize an additional variable     What is the improvement you would like to see? I would like to create a graph where the symbols or points can be substituted with numbers or letters from a column I select.  See example attached generated in Sigmaplot.     Why is this idea important? This allows display of additional variable without having to hover.     ... View more

What inspired this wish list request? I have done a number of experiments using DOE and am a novice at the process. We had a demo of the easy DOE with our company representative and it looks amazing! However, it doesn't help us with      What is the improvement you would like to see? It would be super helpful if we could take a previous design and put it into the easy DOE interface to help with the analysis on the back end. I know it wouldn't help with the design, but it would give valuable insights on how to look at our outputs     Why is this idea important? THis would make the easy DOE an even more powerful tool. Experiments take a lot of time and energy so if we could get more/better information out of them rather than redoing them to get the benefit of easy DOE we would be really happy.   ... View more

    What inspired this wish list request? Currently, outliers detection techniques are available in different menus : Some univariate and multivariate outliers detection techniques are available in "Screening" -> "Explore Outliers", Some multivariate techniques are available in "Multivariate Methods" -> "Multivariate" and different from the other detection techniques from the Screening platforms.   Finally, some techniques or models used in litterature (Isolation Tree/Forest, One-Class SVM, k-Nearest Neigbors...) are not directly available in JMP.   What is the improvement you would like to see?  Following the idea of the Python library pyOD (pyod 1.0.7 documentation) and other libraries/packages, it would be great to have only one single JMP menu dedicated to outliers detection, using several methods combined like in the "Model Screening" platform, where several options would be available : If a response is present in the dataset and used in the "Y, column" dialog, the emphasis and techniques used would be supervised (semi or fully supervised). If no response is added in the "Y, column" dialog menu, then the techniques used could be unsupervised. In the same way as "Model Screening" platform is proposing several models in a auto-ML way, it would be great if JMP user could choose all, several or only one methods among those proposed. In order to help the user have more visibility on the different techniques, it could be perhaps helpful to group some techniques behind group, like for the type of anomaly there could be several groups of methods for local, global, dependency and clustered types of anomalies. Under each group, the user could select or deselect any of the techniques, to have more freedom and flexibility. Finally, when the different outliers detection techniques are used, it could be great to have results in a "macro" and "micro" view : "Micro" view : For each detection techniques, being able to know which points were detected as outliers, in order to compare the techniques and see the agreements/disagreements between the methods, "Macro" view : For the ensemble of detection techniques, instead of "hard voting" or binary result like outlier vs. normal, it could be great to have instead a continuous "anomaly score" from ensembling the different models (ranging from 0: never detected as outlier with all selected techniques to 1: always detected as outlier), in order to use it in a transformed way (perhaps in a "reciprocal" transformation: 1/anomaly score) in other modeling platforms as a "Frequency" or "Weight" variable, in order to create "weighted models" that take into account outliers, but reduce their importance.     Why is this idea important?  Two points are motivating this request : Unify and group the different outliers detection techniques in a single platform could help user be aware of the different techniques proposed, It could be a great starting point to add new models to the JMP platform focused on this outlier detection aspect. ... View more

similar wish: Add CDFs to Graph Builder    ☑ cool new feature ☑ could help many users! - especially in semiconductor industry. ☐ removes a bug ☐ nice to have ☐ nobody needs it   What inspired this wish list request? Short: The summary statistics option in GraphBuilder are amazingly useful. Unfortunately, there is no setting for Cumulative Probability,  CDF, Normal Quantile Plots. to generate a plot like this one:       What is the improvement you would like to see?  Please add Cumulative Probability as an option for Summary Statistics in Graph Builder.   Why is this idea important?  In Graph Builder, there is a setting: Cumulative Percent An innocent user might fall into this trap and use Cumulative Percent instead of Cumulative Probability. BUT: Cumulative PERCENT is NOT Cumulative PROBABILITY  it is: -> Save us from falling into this trap!!! ... View more

1) What inspired this wish list request?  ☑ cool new feature ☐ could help many users! ☐ removes a „bug“ ☐ nice to have ☐ nobody needs it   #myTop10_2023   In GraphBuilder, one can drag a column onto the Color drop zone to use different colors for the individual items in the column - or to apply a color gradient depending on the values of this column.   By dragging 2 columns into the color drop zone, one can provide 2 columns -and then later specify via the variables list which of the two columns to choose. This makes it possible to apply independent color settings to different subplots, like in Graph Builder - subplot with different color settings?    Unfortunately, it's not possible to use more than 2 colors :(   2) What is the improvement you would like to see?  Please allow Jmp to use more than 2 columns in the Color drop zone.   3) Why is this idea important? It's possible to get up to 3 colors into the color drop zone, but the 3rd color doesn't work. It's there, it seems to work, but it doesn't do what it should do. The below code intentionally uses sex twice as color (1. and 3. entry). This is not the reason why it doesn't work - it just helps to illustrate the issue.   A comparison of the top and bottom plot shows that the top plot (which uses the third color column) has wrong colors (no blue points, the points are red) :( In different examples, the second color column was used instead of the third one.           Names Default to Here(1); dt = Open( "$SAMPLE_DATA/Big Class.jmp" ); Graph Builder( Show Control Panel( 0 ), Variables( X( :height ), Y( :weight ), Y( :weight ), Y( :weight ), Color( :sex ), Color( :weight ), Color( :sex ) ), Elements( Position( 1, 1 ), Points( X, Y, Color( 3 ) ) ), Elements( Position( 1, 2 ), Points( X, Y, Color( 2 ) ) ), Elements( Position( 1, 3 ), Points( X, Y, Color( 1 ) ) ) )         more wishes submitted by   ... View more