archive-com.com » COM » F » FORUMAKERS.COM

Total: 261

Choose link from "Titles, links and description words view":

Or switch to "Titles and links view".
  • Test1 (7 methods)
    Wed Mar 18 2009 1 09 pm Hi all I m still struggling with this analysis Let s say I have 2 learning files File A and File B So I start the concatenate learning files tool and choose File A as Learning File 1 and File B as Learning File 2 and choose Learning File 2 Status as Test Analysis fails Please check your selections Now I do the same as before except that I swap files File B as Learning File 1 and File A as Learning File 2 Then it works Why So how do I decide which one is Learning file and which one Test file What are the criteria And I experienced another strange behaviour By mistake I chose Learning File 2 Status as Learning So the entry in each row in the status column of the concatenated file was Learning But in this case the analysis ended successfully without error message Any ideas Jürgen Jürgen Posts 3 Join date 2009 03 18 Similar topics Similar topics Verify command when used with Java JUNIT and Eclipse selenium RC how to use these methods getAllFields getElementPositionTop and getElementPositionLeft Calling C selenium methods between classes Data Provider

    Original URL path: http://zooscan.forumakers.com/t28-test1-7-methods (2016-02-14)
    Open archived version from archive


  • New Tanagra 1.4.23 version
    import it in PkID using tools import tanagra data mining diagram This tdm requires Tanagra 1 4 23 or above 1 4 24 is now available and is still fully compatible with PkID 1 2 6 release 2 Remember that such test method only apply to pid file gathering objects with the status learning for model construction and object with the status test for model evaluation see PkID user guide for details feel free to propose your own versions Stéphane Gasparini Developper of Plankton Identifier Stéphane Posts 7 Join date 2008 05 05 Location LOV Villefranche sur mer France Complete set of tdm using PLS Stéphane on Thu Jun 05 2008 6 06 pm for interrested people please find a complete set of tdm for PkID using PLS components of tanagra 1 4 23 and above Cross validation 8 PLS DA tdm Diagram Title Plankton Identification REPORT Cross validation PLS DA Database Dataset MLClassGenerator TMLGenDataset successors 2 succ 1 Define status 1 succ 2 Define status 2 Define status 1 MLClassGenerator TMLGenFSDefStatus target count 1 illus count 0 successors 1 succ 1 Supervised Learning 1 PLS DA Supervised Learning 1 PLS DA MLClassGenerator TMLGCompOneInstance embedded spv 1 embedded section Supervised Learning 1 PLS DA PLS DA successors 1 succ 1 Cross validation 1 Supervised Learning 1 PLS DA PLS DA MLClassGenerator TMLGCompSpvPLSDA nb axis 0 rdy cut 0 025 Cross validation 1 MLClassGenerator TMLGenCompAssesCV isSaveResults 0 nb repetitions 5 nb folds 2 successors 0 Define status 2 MLClassGenerator TMLGenFSDefStatus target count 0 input count 1 input 1 Ident illus count 0 successors 1 succ 1 Univariate discrete stat 1 Univariate discrete stat 1 MLClassGenerator TMLGenCompSDUnivDisc sort result 0 sort criteria 0 successors 1 succ 1 Export dataset 1 Export dataset 1 MLClassGenerator TMLGenCompExportData SelectExamples 0 SelectAttributes 0 Filename successors 0 Cross validation 9 PLS LDA tdm Diagram Title Plankton Identification REPORT Cross validation PLS LDA Database Dataset MLClassGenerator TMLGenDataset successors 2 succ 1 Define status 1 succ 2 Define status 2 Define status 1 MLClassGenerator TMLGenFSDefStatus target count 1 illus count 0 successors 1 succ 1 Supervised Learning 1 PLS LDA Supervised Learning 1 PLS LDA MLClassGenerator TMLGCompOneInstance embedded spv 1 embedded section Supervised Learning 1 PLS LDA PLS LDA successors 1 succ 1 Cross validation 1 Supervised Learning 1 PLS LDA PLS LDA MLClassGenerator TMLGCompSpvPLSLDA nb axis 0 rdy cut 0 025 Cross validation 1 MLClassGenerator TMLGenCompAssesCV isSaveResults 0 nb repetitions 5 nb folds 2 successors 0 Define status 2 MLClassGenerator TMLGenFSDefStatus target count 0 input count 1 input 1 Ident illus count 0 successors 1 succ 1 Univariate discrete stat 1 Univariate discrete stat 1 MLClassGenerator TMLGenCompSDUnivDisc sort result 0 sort criteria 0 successors 1 succ 1 Export dataset 1 Export dataset 1 MLClassGenerator TMLGenCompExportData SelectExamples 0 SelectAttributes 0 Filename successors 0 Spv learning 8 PLS DA tdm Diagram Title Plankton Identification REPORT spv learning PLS DA Database Dataset MLClassGenerator TMLGenDataset successors 1 succ 1 Discrete select examples 1 Discrete select examples 1 MLClassGenerator TMLGenCompISAttValue attribute Status value

    Original URL path: http://zooscan.forumakers.com/t8-new-tanagra-1-4-23-version (2016-02-14)
    Open archived version from archive

  • New tdm available:Test 2 (Random Forest).tdm
    know that the Random Forest method is the best method to analyse your data set and that you only want to test the consequences of some modifications of your learning file for instance if you have increase the number of vignettes in one group or if you have decided to merge two groups together Since a tdm file is basically a text file it can be created or edited using a simple text editor such as the notepad Copy the following red part in your text editor and save it as Test 2 Random Forest tdm Diagram Title Plankton Identification REPORT Test 2 Random Forest Database Dataset MLClassGenerator TMLGenDataset successors 1 succ 1 Discrete select examples 1 Discrete select examples 1 MLClassGenerator TMLGenCompISAttValue attribute Status value Learning successors 1 succ 1 Define status 1 Define status 1 MLClassGenerator TMLGenFSDefStatus target count 1 target 1 Ident illus count 0 successors 1 succ 1 Bagging 1 Rnd Tree Bagging 1 Rnd Tree MLClassGenerator TMLGCompBagging embedded spv 1 embedded section Bagging 1 Rnd Tree Rnd Tree nb classifiers 100 rnd mode 1 successors 2 succ 1 Define status 2 succ 2 Export dataset 1 Bagging 1 Rnd Tree Rnd Tree MLClassGenerator TMLGCompSpvRndTree nb att for split 1 Define status 2 MLClassGenerator TMLGenFSDefStatus target count 1 target 1 Ident input count 1 input 1 pred Bagging 1 illus count 0 successors 1 succ 1 Test 1 Test 1 MLClassGenerator TMLGenCompSpvAssesTestSet examples 1 successors 0 Export dataset 1 MLClassGenerator TMLGenCompExportData SelectExamples 0 SelectAttributes 0 Filename successors 0 Launch Plankton Identifier and select Import Tanagra Data Mining diagram in the Tools menu of the main window Select the newly created tdm file and click Open The tdm file is copied in the appropriate subfolder and is now available in the select method box of the Data

    Original URL path: http://zooscan.forumakers.com/t12-new-tdm-availabletest-2-random-forest-tdm (2016-02-14)
    Open archived version from archive

  • Future version of Plankton Identifier
    those by hand is laborious and I have realized that Tanagra has a data binning option My suggestion is therefore to integrate a function to automatically calculate biomass spectra within PkID Is that technically feasible Would you like to have such a function added Thank you and all the best for the Zooscanning community Sabine LAPS Posts 7 Join date 2008 05 06 Re Future version of Plankton Identifier Stéphane on Tue May 06 2008 3 42 pm LAPS wrote My suggestion is therefore to integrate a function to automatically calculate biomass spectra within PkID Is that technically feasible Would you like to have such a function added Dear Sabine Thank you for your suggestion Actually it can already be done at least partially with current version of PkID You can indeed build your own data treatment chain using Tanagra save this data treatment as tdm file then import this tdm in PkID In addition you can calculate any variable derived from original variables using the add custom variable tools Thus you can calculate a biomass per object using ESD for instance then use this value in a tdm including both recognition algorithm and spectra construction Unfortunately there is some restrictions to tdm that can be imported in PkID see here for details and metadata of the PID files header can not be used yet to get sample volume if not constant for instance I will try to improve these points The reason why i did not provide such tdm file until now is that there is many possibilities depending on what each user want Stéphane Gasparini Developper of Plankton Identifier Stéphane Posts 7 Join date 2008 05 05 Location LOV Villefranche sur mer France Computing biomasses Admin on Wed May 07 2008 12 10 pm We actually compute biomasses

    Original URL path: http://zooscan.forumakers.com/t3-future-version-of-plankton-identifier (2016-02-14)
    Open archived version from archive

  • PkID 1.2.6 update for Tanagra 1.4.22
    2 6 have been updated You can download the last versions on PkID web site If you are using an older version of Tanagra this update is not required However the use of the last versions of both PkID and Tanagra is recommended best regards Stéphane Gasparini Developper of Plankton Identifier Stéphane Posts 7 Join date 2008 05 05 Location LOV Villefranche sur mer France Similar topics Similar topics How

    Original URL path: http://zooscan.forumakers.com/t4-pkid-1-2-6-update-for-tanagra-1-4-22 (2016-02-14)
    Open archived version from archive

  • ** Welcome **
    post your questions about Plankton Identifier PkID You can also use this forum to discuss about plankton recognition methods to share learning set to exchange data analysis scripts tdm files or to discuss about wishes for the next version of PkID Of course updates and new versions of PkID will be announced here as well as news about Tanagra Best regards Stéphane Gasparini Developper of Plankton Identifier Stéphane Posts 7

    Original URL path: http://zooscan.forumakers.com/t2-welcome (2016-02-14)
    Open archived version from archive

  • Visitor messages - cheryl Hopcroft
    Home FAQ Search Search Query Display results as Posts Topics Advanced Search Memberlist Usergroups Register Log in Current date time is Sun Feb 14 2016 7 19 pm Viewing profile cheryl Hopcroft Visitor messages Profile Statistics Contact Visitor messages No

    Original URL path: http://zooscan.forumakers.com/u83wall (2016-02-14)
    Open archived version from archive

  • Statistics - cheryl Hopcroft
    Profile Statistics Contact Statistics Topics Number of topics 3 3 49 of total Topics per day 0 00 Latest topic Tue Apr 15 2014 3 39 am Find all topics where cheryl Hopcroft has posted in Posts Posts 3 1 53 of total Posts per day 0 00 Latest post Tue Apr 15 2014 3 39 am Find all messages posted by cheryl Hopcroft Visitor messages Visitor messages number 0

    Original URL path: http://zooscan.forumakers.com/u83stats (2016-02-14)
    Open archived version from archive



  •