About RVhydrA

RVhydrA

I am trying to script a fit X by Y with a by variable, then fit each with a polynomial (degree = 2) and then extract the "summary of fit" data (specifically the R Square and number of observations) to a data table. As an example I was working with the Car Physical Data sample set. For example use Weight as the Y, Horsepower as the X, and Type as the By. Then fit with each group with a 2nd order poly. extract all summary of fit diagnostics using make combined data table. I know how to do it with the gui but need to script it to perform much larger operation.

RVhydrA

Does anyone know how to calculate a moving minimum (or for that matter how to iteratively select X number of lag rows and do anything to them such as calculate a min, max, range, etc. In this specific example i want to look back over say the last 100 rows and get the minimum value, then move to the next row down and do the same again (over and over).

RVhydrA · ‎04-03-2020

paste this entire script into the formula editor to = Row(); If( to - 5 < 0, t from = 1, from = to - 5 ); Quantile( 0.5, :Column[Index( From, To )] ); :Column and From need to be changed. So column is obviously the column you want to calculate the median, From is the number of rows you want to look backwards. so if I want the median between the current row and the previous 10, i'd type -10 for From. Hope that helps

RVhydrA · ‎02-12-2020

Thanks to both of you. Dan, I tried your method but found it hard to interpret the results or replicate my previous results. Though I agree, that is how I also thought to conduct this analysis. Ultimately, I went about it the slow stupid way and was able to repeat my result. I ran a fit model with Y: Streamflow, By: Period, and Effects with Full Factorial: Precipitation, Station, Precip X Station. Then on the results for each period I ran Estimates - Multiple Comparisons - All Pairwise. This gave me the analysis of slopes between stations for each period. Then I went back and reran the fit model switching the By variable with Station and the effect variable Period. Ran that test and performed one-way ANCOVAs on each station. I was able to repeat my original results. I know the way I originally did it was much smoother than that, If only I wrote these things down! Thanks again.

RVhydrA · ‎02-12-2020

I am trying to run an ANCOVA on a dataset with a continuous Y variable (streamflow) and a continuous X variable (Precipitation), additionally I have two categorical variables "Period" (A and B) and "Station" (1, 2, 3, 4, and 5). My goal is to explore the relation between streamflow and precipitation within each period - comparing the slopes of those relations across stations, and then compare the slopes of those relations within each station across the periods. The kicker is that I already successfully did this over a year ago, I have the results, but now I need to rerun it and I have no idea how I did it. I assume its in fit model but I've got a brain block at the moment.

RVhydrA · ‎01-16-2020

I ended up figuring this out on my own, it is a simple summation function. Figured i'd post it in case anyone else needs to do something like this. If( :Precipitation Station == Lag( :Precipitation Station, 1 ), Summation( i = 1, 24, Lag( :Precipitation, i ) ), :Precipitation );

RVhydrA · ‎01-15-2020

I'm not actually trying to compute the total precip for a given station/date, but rather station/previous 24 hour period. so for example if the DateTime for a given for is 1/3/2020 09:00:00 AM I would want to take the previous 24 values in the precip column and sum those. So starting with 1/3/2020 08:00:00AM and going all the way back to 1/2/2020 09:00:00 AM. Essentially a moving 24 hour window of time. This column would thus give me the previous rain over the prior 24 hours for each row in my data table.

RVhydrA · ‎01-15-2020

I am trying to create a column that calculates the sum of the lag 24 rows. In this instance I have a column "Precip" that contains hourly precipitation totals. There is a second column "precipitation station" denoting from which location each value was recorded. I have sorted the columns based on "DateTime" and the "Precipitation Station". I am looking for an efficient way to sum the previous 24 values in the Precip column thus creating a new column that tells me how much it rained in the previous 24 hours. This 24 hour total is station specific so it cannot calculate the lag 24 values if the lag 24 precipitations do not match.

RVhydrA · ‎05-01-2018

How do I unlock a column that contains a formula? I have a binary column which is computed based on a formula. I have allowed the formula to evaluate, then suppresed the formulas evaluation and would like to edit some of the rows to change form 0 to 1 or vice versa (essentially there is no good way for me to get my formula to give me the perfect result 100% of the time due to variablity in my data so i'd like to edit a few) however the column is locked and greyed out so I cannot change any of the rows.

RVhydrA · ‎04-27-2018

I am trying to calculate a moving median. I have used the moving average function before as well as the Summation function to calculate moving averages but can't figure out how to calculate a moving median based on a set number of lag rows. For example, for every row in my column, i'd like to query the previous 650 rows and calculate the median. I'm working in the GUI right now so any thoughts on how to do this in the column formula?

RVhydrA · ‎03-15-2017

I can't find the defaults that I specified in my orginial post in preferences. I have looked through every possible category in preferences under platforms and have had no luck. In terms of selecting plot residuals by predicted, durbin-watson test, etc.. I know how to find those under the red triangle. My question was how do I set those to plot as a default so I dont have to navigate through all of those things 50 times a day each time I run a new model. Thanks!

RVhydrA · ‎03-01-2017

I am doing a lot of model building (using fit model - stepwise/best subsets regression) right now and am tired of having to manually choose certain output display items such as to show the VIF in my paremeter estimates. How to I set the VIF to default appear each time I run a new model. Also, I am largely using mallows cp to begin my model selection. each time I open up a new fit model and run it I have to right click to display mallows cp as a column, and then sort the columns based on cp values in an ascending order to view the lowest at the top. I am then repeatedly having to chose to open several row diagnostic reports such as residuals by predicted plots, actual by predicted, and durbin watson test. Doing this once, twice, or even ten times isn't a problem but for the number of models I am running is there any way to set these all at defaults in the report? I have looked in preferences where I normally go to set defaults but do not see it. Thanks!

RVhydrA · ‎12-13-2016

Seems to be a glitch in JSL that forces me to save the data table before I can actually "<<journal" AND "<<save script to journal" of a plot/graph builder. I moved my save command line to the top of the for loop and it all worked. You can normally journal and then save but for whatever reason in this instance the save was required before performing the save script line. Thanks for all the help folks.

RVhydrA · ‎12-12-2016

I decided to save the script for each plot to the same journal that I was already saving the plots to. That way if I see a strange data point it is easy to just click on the script link and open up the data table and plot to interact with it. problem I am having is now when I run my script I keep being forced to manually save the data table during each iteration of the for loop. I'm guessing that I have something written incorrectly. the script works fine unitl I add the "save script to journal" If I only journal the plot, OR only journal the script, it works fine, but when I journal both it opens a file explorer window and makes me manually save as before the script moves on, which given the number of iterations in the for loop sort of defeats the purpose of a script to a degree. Its almost there but let me know if anyone has any thoughts on why this is happening I have attached the most relevant part of the script as well as two output screenshots to give you an idea of what i'm trying to do. Thanks for any advice!

RVhydrA · ‎12-09-2016

I have a script in which there is a for loop that is running through a number of "monitoring stations" and generating plots examing relations between various parameters. These are then journaled together by station., subsquently producing a data review package for later use. I use this script for reviewing the data that I get back from my laboratory. As of now these journals are static. It would be very helpful if they could be dynamic in such that I could click on a data point that looks funky and have that point/row highlighted in my associated data table. I've had trouble searching for this online, help!

RVhydrA · ‎08-17-2016

I am trying to create a new column in JSL that will be an ongoing sum of the previous rows in that column. I have a column called "Total Daily Flow" I also have a column which marks what location the data in "total daily flow came from (call that "Site"). for example, Say on Oct. 1, (which is specified in another column called "day of water year") i have a total daily flow of 1000, and this day happens to be day 1 of the year. I want a column whose first row will be = 1000. then say on day two, which will be the second row in the table, Oct. 2, there is a total daily flow of 5000, I would want the new row in the new column to be 1000 + 5000 = 6000. then say Oct. 3 has a daily flow of 3000, so the next row will be 6000+3000 = 9000. This is to go on for every row in my table that shares the same location name (Site) and is in the same "year" as specified by the column "day of water year" (1-365).

RVhydrA · ‎01-07-2016

here is a sample of what i'm working on, I changed some of the quarter designations for the purpose of this example

RVhydrA · ‎01-07-2016

I am trying to create a worksheet to keep track of sample count. I have columns for Site Name, Quarter, and several other informative stats. I want to create a column that will update each time a new sample is added(i.e. 1, 2, 3... ) I have 12 sites, each of which I want the sample counter to be exclusively linked to. Furthermore I want the counter to be futher categorized by the financial quarter (1-4). The way I hope this to work is that say that one day I get samples at 2 sites. I input a new row. In the Site Name column I input "Site A", and that the sample was collected in Quarter "2". I create another new row for the other site that I sampled "Site B" also collected in quarter "2". In this example Site A has already had 5 samples this quarter(2), and site B has had 2 samples in this quarter(2). I want my counter to automatically populate a "6" for sample count for Site A, and "3" for Site B. I then want to use this counter to populate a bar graph indicating the progression toward the 15 samples per Quarter goal for each site. Help!

RVhydrA · ‎04-03-2015

Out of the blue I have lost the ability to drag and drop into graph builder. Any thoughts? Is there a toggle for this?

Date Registered	‎04-03-2015 07:51 AM
Date Last Visited	a week ago
Total Messages Posted	19
Total Kudos Received	4

Online Status	Offline
Date Last Visited	a week ago

Fit X by Y with by group and 2-polynomial fit

Moving minimum (moving window)

Re: Calculate a moving median

Re: ANCOVA with 1 continuous X and 2 categorical X variables

ANCOVA with 1 continuous X and 2 categorical X variables

Re: calculating sum of lag x rows

Re: calculating sum of lag x rows

calculating sum of lag x rows

Unlock column with formula

Calculate a moving median

Re: Fit X by Y with by group and 2-polynomial fit

Re: Moving minimum (moving window)

Re: Moving minimum (moving window)

Re: ANCOVA with 1 continuous X and 2 categorical X variables

Re: ANCOVA with 1 continuous X and 2 categorical X variables

Re: Calculate a moving median

Re: calculating sum of lag x rows

Fit X by Y with by group and 2-polynomial fit

Moving minimum (moving window)

Re: Calculate a moving median

Re: ANCOVA with 1 continuous X and 2 categorical X variables

ANCOVA with 1 continuous X and 2 categorical X variables

Re: calculating sum of lag x rows

Re: calculating sum of lag x rows

calculating sum of lag x rows

Unlock column with formula

Calculate a moving median

Re: How to set defaults in Fit Model reports (VIF, cp, etc..)

How to set defaults in Fit Model reports (VIF, cp, etc..)

Re: Dynamic Journal

Re: Dynamic Journal

Dynamic Journal

help creating a column that is a cumulative sum based on other columns

Re: how to make an auto-updating sample count column

how to make an auto-updating sample count column

I have lost the ability to drag and drop columns in graph builder.