The Origin Forum
File Exchange
Try Origin for Free
The Origin Forum
Home | Profile | Register | Active Topics | Members | Search | FAQ | Send File to Tech support
 All Forums
 Origin Forum for Programming
 LabTalk Forum
 LabTalk command curve fitting

Note: You must be registered in order to post a reply.
To register, click here. Registration is FREE!

Screensize:
UserName:
Password:
Anti-Spam Code:
Format Mode:
Format: BoldItalicizedUnderlineStrikethrough Align LeftCenteredAlign Right Horizontal Rule Insert HyperlinkUpload FileInsert Image Insert CodeInsert QuoteInsert List
   
Message:

* HTML is OFF
* Forum Code is ON
Smilies
Smile [:)] Big Smile [:D] Cool [8D] Blush [:I]
Tongue [:P] Evil [):] Wink [;)] Clown [:o)]
Black Eye [B)] Eight Ball [8] Frown [:(] Shy [8)]
Shocked [:0] Angry [:(!] Dead [xx(] Sleepy [|)]
Kisses [:X] Approve [^] Disapprove [V] Question [?]

 
Check here to subscribe to this topic.
   

T O P I C    R E V I E W
Sprenger Posted - 02/20/2019 : 06:42:25 AM
Origin Ver. and Service Release (Select Help-->About Origin): Orign2018 b9.5.1.195
Operating System:Windows 10

I am looking for the labtalk command to perform a curve fitting with weigthing

So far this works for the basic curve:
nlbegin iy:=(2,1) func:=boltzmann nltree:=tt;

now I want to add the following Weigths method (an option in the Dialog theme):
"Variance ~ y2"

how can I add this in a labtalk script?
Many thanks
Frank
4   L A T E S T    R E P L I E S    (Newest First)
yuki_wu Posted - 02/25/2019 : 02:44:55 AM
Hi Frank,

I am sorry that it seems a bug. We have added this issue to our bug tracking database(ID: ORG-19744) and it is targeted to be fixed in the next version.

Sorry for the inconvenience.

Thanks,
Yuki

OriginLab

Sprenger Posted - 02/22/2019 : 07:24:57 AM
Orign 2018 SR1
b9.5.1.195
Windows 10

Dear Yuki,
I tried the same commands on the older Orign 2018 version:
Now the weight is used, but (different results when weihgt:=stat is used) but the weight:=5 does not work and gives an error.

The Problem with Origin 2019 seems to be a but that does not recognize the weight et al.

Best
Frank

>>nlbegin iy:=(1,2) func:=boltzmann weight:=stat nltree:=tt;
nlfit;
>>tt.dx=
tt.dx=790.98729516533

>>nlbegin iy:=(1,2) func:=boltzmann nltree:=tt;
nlfit;
>>tt.dx=
tt.dx=618.24890090712

>>nlbegin iy:=(1,2) func:=boltzmann nltree:=tt weight:=5;
nlfit;
Variable value is not in predefined list, VarName = weight, VarValue = 5
#Command Error!
>>
Sprenger Posted - 02/22/2019 : 05:39:04 AM
OriginVer. 9.6.0.172
Operating System: Windows 10 (1803)

Dear Yuki, many thanks for your suggestion.
I have tried several weight settings, but they seem to be ignored totally, I am always getting the results as if no weight is selected.
With (manual) weight setting (by the interface in fitting window) the results are different. Here are my labtalk commands:


nlbegin iy:=(1,2) func:=boltzmann nltree:=tt weight:=stat;
nlfit;
tt.A1=3.1890203237919
tt.dx=618.24890090712


nlbegin iy:=(1,2) func:=boltzmann nltree:=tt weight:=5;
nlfit;
tt.A1=3.1890203237919
tt.dx=618.24890090712


nlbegin iy:=(1,2) func:=boltzmann nltree:=tt;
nlfit;
tt.A1=3.1890203237919
tt.dx=618.24890090712
yuki_wu Posted - 02/21/2019 : 9:53:44 PM
Hi Frank,

Try to set weight:=5. As usual, we define No Weight= 0, Instrumental = 1, Statistical = 2…

Regards,
Yuki

OriginLab

The Origin Forum © 2020 Originlab Corporation Go To Top Of Page
Snitz Forums 2000