Re: Batch file operations
Hi Steve,
Thanks for looking at this.
The problem is that forfiles drops the output files into the same folder as the source files - like this.
Thus to use the join procedure one has to go through the whole list selecting every second (-COH) files. Very tedious and not good for a large number of egonets.
?
I have tried several ways of getting around this: e.g.
- Having the forfiles output with an prefix (Coh-) - No success.
- Incorporating a wildcard in the join command, after setting all IDs to six spaces, [join(AANetSoc_??????-COH)]
it didn't work.
BTW I also checked to see if the ? wildcard would work in place of the * wildcard in the forfiles procedure. It did not. SO there is something amiss there.
?
The optimum procedure would be to have the forfiles output go into a separate folder from the source files. I do this when doing analyses in the gui. Is it possible to do in a CLI command?
?
|
Re: Batch file operations
Hi, sorry not to have seen this earlier. So, the menu option Data|Join|Columns has a browse button that lets you select multiple files at once. Does that solve your problem?
?
steve
?
|
Re: NetDraw Multiple Relations
That's probably it. ¶Ù²¹±è³ó²Ô¨¦±ð, if that is not the problem, please contact me at sborgatti@... and send me your datasets.? ?
steve
|
Re: Netdraw error: "Unable to identify file type"
It works for me, but I will investigate.
?
Meanwhile, there are alternative ways to read your data. First, in netdraw, press the ¡®Open with a U¡¯ button, second from the left (see attached png file).
?
Or, in ucinet, go to the command line interface (CLI) and type:
?
->draw campnet
?
steve
?
?
?
?
Stephen P. Borgatti
Carol Martin Gatton Chair of Management
Gatton College of Business and Economics
University of Kentucky
?
toggle quoted message
Show quoted text
From: [email protected] <[email protected]>
On Behalf Of torres.ana via groups.io
Sent: Monday, May 12, 2025 15:05
To: [email protected]
Subject: Re: [ucinet] Netdraw error: "Unable to identify file type"
?
Please, could you help me with another problem? When I do File > Open > UCINet Dataset > Network and choose "1-mode network", there is an error: "Access violation at address 006EE0AC in module 'netdraw.exe'. Read of address 00000000.".
I am using version 6.810b.
|
Re: Netdraw error: "Unable to identify file type"
Thank you!
?
Please, could you help me with another problem? When I do File > Open > UCINet Dataset > Network and choose "1-mode network", there is an error: "Access violation at address 006EE0AC in module 'netdraw.exe'. Read of address 00000000.". I am using version 6.810b.
?
Thanks in advance!
|
Re: NetDraw Multiple Relations
I'm sure someone else has a better answer, but for me that's always happened whenever the list of nodes on File 2 doesn't match the list of nodes on File 1. When it's a perfect fit, they stack. You probably already knew that, but that's my experience. Maybe double check that.
|
Re: Netdraw error: "Unable to identify file type"
Oops. That¡¯s my error. UCINET version 6.810 uses a new file format for the ##h files. I forgot to update NetDraw. If you download , it should be fine. ? Let me know if any problems. ? steve ?
toggle quoted message
Show quoted text
From: [email protected] <[email protected]> On Behalf Of torres.ana via groups.io
Sent: Friday, May 9, 2025 17:36
To: [email protected]
Subject: [ucinet] Netdraw error: "Unable to identify file type"? Please, could you help me with this error? I have created a matrix via DL editor. But when I try to open UCINET file using?Netdraw, the following error appears: "Unable to identify file type (...) was it created by a later version of UCINET?". I have just downloaded it from the website.
|
Netdraw error: "Unable to identify file type"
Please, could you help me with this error? I have created a matrix via DL editor. But when I try to open UCINET file using?Netdraw, the following error appears: "Unable to identify file type (...) was it created by a later version of UCINET?". I have just downloaded it from the website.
Thank you!
?
|
NetDraw Multiple Relations
Hello!
?
I am currently using NetDraw to map out multiplex relations. I was originally able to open and add multiple matrices to the "Relations" tab in NetDraw. For some reason, I am no longer able to do so. Now, when I do File > Open > UCINet Dataset > One-mode network (as instructed per this guide: ), the pre-existing matrix in the "Relations" tab gets replaced with the new file, instead of stacking itself like before (meaning I can only map out one set of relations at a time). Any suggestions on how to stop this from happening?
?
Thank you in advance!
?
¶Ù²¹±è³ó²Ô¨¦±ð
|
Hi Steve et al;.
I am exploring ways to use UCINET with multiple ego networks. The task is to take a set egonet datasets, calculate cohesion measures for each one, then join the (single column) output files into one dataset on which I can then run univariate statistics.
I am working with the CLI interface.
forfiles works for the cohesion measures //forfiles AANetSoc_* $$-coh = cohesion($$)
?
Joincols requires each new file name (-coh) to be entered manually (Browse and select). Not practical for any large of egonets.
?
Once the joined dataset is created one can use Univariate stats to analyse further.
?
I have tried a variety of ways to find a way to run the joincols function on the AANetSoc_* -coh files, without any success. I think my optimum procedure would be to use ? wildcards within the joincols function. (join = joincols(AANetSoc_??????-coh). The joincols function does not recognize wildcards (* or ?) however.
[Incidentally, I can't get the ? wildcard to work for forfiles procedure either.]
?
Any suggestions please. (I attach my 3 egonet datasets.)
|
Hi, I¡¯m afraid I can¡¯t understand your question. I get that you have done a number of correlations, and found that most of the negative correlations are not significant (all but the very first one). You find that suspicious, but those are also the correlations based on very small N¡¯s ¨C usually just 3 nodes. The correlations based on more nodes (eg. 12), are still not significant because the correlation coefficients themselves are small. This strikes me as normal, but is difficult to say more as I really don¡¯t understand you data. E.g., why are there 31,718 rows with no data, and another 7,629 with values of NA? ? I you would like to talk further, email me at sborgatti@.... ? steve ?
toggle quoted message
Show quoted text
From: [email protected] <[email protected]> On Behalf Of Paulo Matui via groups.io
Sent: Wednesday, April 2, 2025 13:54
To: [email protected]
Subject: [ucinet] QAP Correlation? I calculated how much type I relations correlate (QAP Correlation) with type II relations for the ego network, of course, noting that the type I egonet should contain the same nodes as the type II egonet. To do this, I performed the union of the nodes of each egonet to ensure that the same nodes would be present in both egonets.
The results are in the attached csv.
The egonets are directed and valued. I expected inverse CorrCoefs; however, all calculations related to the inverse presented a p-value > 0.05. If it had occurred with some cases, I would understand. But all? Question: It seems that QAPCorrelation may have been designed for direct correlations. And that suits me. If true, then I should have symmetrized (and perhaps dichotomized) the networks. Is that correct?
|
Hi?
?
I calculated how much type I relations correlate (QAP Correlation) with type II relations for the ego network, of course, noting that the type I egonet should contain the same nodes as the type II egonet. To do this, I performed the union of the nodes of each egonet to ensure that the same nodes would be present in both egonets.
The results are in the attached csv.
The egonets are directed and valued. I expected inverse CorrCoefs; however, all calculations related to the inverse presented a p-value > 0.05. If it had occurred with some cases, I would understand. But all?
Question: It seems that QAPCorrelation may have been designed for direct correlations. And that suits me. If true, then I should have symmetrized (and perhaps dichotomized) the networks. Is that correct?
?
matui
?
?
|
I find that E-NET does not have as much difficulty with my datasets as UCINET when doing ego analyses. It is somewhat slow but does a good job (197x205 dataset done in 80 minutes). I did a Save at the end and four E-NET Database files were created, i.e., Output.alters, Output.alterties, Output.egos, and Output.enet. My question is simple. How does one reload those files into E-NET as so far it just wants to load or import new data files? Thank you.
?
|
Re: Dichotomizing Challenge
I solved the problem. Basically I gave up. I tried k-means median cluster analysis but a few outliers in my opinion altered the dichotomization.? I chose a simpler solution. I just partitioned the continuous attributes into uniform segments which also yields more detailed attributes but of course an even larger set of attributes.
|
I need to dichotomize four attributes in larger than typical datasets that I normally utilize, i.e., 100-200 cases (rows) but now need to analyze data of 2100 x 200 with UCINET but first want to dichotomize four continuous attributes before proceeding.? So I reduced the dataset to just 2100 x 4 attributes (only the continuous ones), converted to 1-mode, and then tried Dichotomize Interactive to look at the correlations. After 18 hr of? running with the spinning wheel in UCINET I gave up and repeated with only 2 attributes with same problem. I am running Windows 10 64bit with 64GB RAM (although UCINET 32bit seldom uses more than 4GB) with AMD Ryzen CPU, dual fast SSDs,? and a good graphics card.
?
I looked to see if Pajek if could do this but did not see that option. For now I using an a priori approach which I feel is not optimal but works, i.e., forcing the creation of only 2 clusters via different methods. I find that mixing continuous data with binary gives distorting results based on the scale of the continuous data after sums-squared reduction (even with normalizing and with better scale matching).
?
Any ideas would be appreciated otherwise I will continue with the a priori method that was covered by Steve Borgatti in the excellent technical document (().? Thanks.
|
Re: Cluster Analysis forcibly suppressing dendrograms
That worked perfectly! You are the GOAT, Steve! Thank you!
|
Re: Cluster Analysis forcibly suppressing dendrograms
I think it made an aesthetic judgement based on the size of your data. After you run cluster analysis, run tools|Dendrogram and give it Part as input data --- ¡®part¡¯ is created by the clustering routine. ? steve ?
toggle quoted message
Show quoted text
From: [email protected] <[email protected]> On Behalf Of hooverrp via groups.io
Sent: Sunday, February 16, 2025 17:52
To: [email protected]
Subject: [ucinet] Cluster Analysis forcibly suppressing dendrograms? Hello! I'm trying to use 'Johnson's Cluster Analysis' from the Tools menu on my dataset in order to perform a Hierarchical Cluster Analysis. I've tried messing around with some options in the menus, also I'm using the 32-bit version, but I've not been able to get it to produce the specified dendrogram. It produces a .txt file with lots of information and results, however, at the very bottom of the file it says "Graphical dendrogram suppressed." Why would it be suppressing my graph? Are there any potential error logs I could check to see why its doing this? I have tried messing around with basically every option in the menu, to no avail. Even using different datasets has all resulted in the dendrogram being suppressed.
|
Cluster Analysis forcibly suppressing dendrograms
Hello! I'm trying to use 'Johnson's Cluster Analysis' from the Tools menu on my dataset in order to perform a Hierarchical Cluster Analysis.
?
I've tried messing around with some options in the menus, also I'm using the 32-bit version, but I've not been able to get it to produce the specified dendrogram. It produces a .txt file with lots of information and results, however, at the very bottom of the file it says "Graphical dendrogram suppressed."
?
Why would it be suppressing my graph? Are there any potential error logs I could check to see why its doing this? I have tried messing around with basically every option in the menu, to no avail. Even using different datasets has all resulted in the dendrogram being suppressed.
|
Re: Number of Ties in NETDRAW
Problem solved. I did a screen capture and saved as image.? My PDF editor could not covert it but my OCR software (ReadIRIS 17) allowed import to a text document format.
|
Re: Number of Ties in NETDRAW
Almost forgot. How does one export the dich results? When I do an export to spreadsheet of the dich file it is only the matrix and I prefer the great table output in the final window as there are some nice additional factors? Selecting the table contents does not let me copy and paste.
Thanks
|
Malcolm Alexander
Paulo Matui