1. Summary
  2. Files
  3. Support
  4. Report Spam
  5. Create account
  6. Log in

Changes between Version 1 and Version 2 of TrainTestExtractorTutorial

Show
Ignore:
Timestamp:
09/29/09 02:03:08 (5 years ago)
Author:
linfrank (IP: 172.29.29.58)
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • TrainTestExtractorTutorial

    v1 v2  
    77== Using the GUI == 
    88 
    9 1)      To run this type of task using the gui type: 
    10  
     9 1. To run this type of task using the GUI type: 
     10{{{ 
    1111java –Xmx500M edu.cmu.minorthird.ui.TrainTestExtractor –gui 
    12  
    13 A window will appear.  The view and change the parameters of the experiment press the Edit Button located next to TrainTestExtractor.  A PropertyEditor will appear: 
    14  
    15 2)      To view what each parameter does and/or how to set it, click the “?” button next to each field.  The parameters that must be entered for the experiment to run are baseParameters (-labels) and signalParameters (-spanType or –spanProp)  All other parameters have default or are not needed for the result.  There are 5 bunches of parameters that can be modified for running a TrainTestExtractor experiment: 
    16  
    17 1.      First training data for the experiment must be entered by specifying a labelsFilename.  Since the samples are built into the code, sample1.train can simply be typed into the TextField under labelsFilename to load the data.  Note: data from a directory can be loaded by using the browse button. 
    18  
    19 2.      To save the results from the experiment, enter a file to which to write the results in the sasveAs text field.  Note: this is optional. 
    20  
    21 3.      Once labelsFilename is specified, click the “Edit” button next to signalParamters.  IMPORTANT:  labelsFilename must be specified BEFORE clicking “Edit”.  Another Property Editor will appear.  
    22  
    23                         Select the trueName from the pull down menu.  Then press the “OK” button to close the PropertyEditor for signalParameters 
    24  
    25 4.      Type sample1.test in the testFilename TextField.  Note: when a test file is specified, minorthird does not use a splitter.  To use a splitter, simply do not specify any test file.  The splitter is set to RandomSplitter by default thus does not need to be specified or changed for the experiment to run. 
    26  
    27 5.      Options for how minorthird learns from the training data are in training Parameters.  These options all have defaults, so do not need to be explicated stated for the experiment to run. Most importantly the learner can be changed by selected a learner from the pull down menu and edited by pressing the “Edit” button next to learner.  To view the javadoc documentation for the currently selected learner, press the “?” button for a link to javadocs.  The output parameter specifies how minorthird labels extracted types.  By default it is set to prediction, but it is useful to change this to something more informative such as predicted_trueName. 
     12}}} 
     13 2. A window will appear. To view and change the parameters of the experiment press the '''Edit''' button located next to '''TrainTestExtractor'''. A '''Property Editor''' will appear: 
     14[[Image(prop_editor.jpg)]] 
     15 3. To view what each parameter does and/or how to set it, click the '''?''' button next to each field. The parameters that must be entered for the experiment to run are '''baseParameters''' ('''-labels''') and '''signalParameters''' ('''-spanType''' or '''–spanProp'''). All other parameters have defaults or are not required. There are 5 bunches of parameters that can be modified for running a TrainTestExtractor experiment: 
     16  a. First training data for the experiment must be entered by specifying a '''labelsFilename'''. Since the samples are built into the code, `sample1.train` can simply be typed into the text field under '''labelsFilename''' to load the data. Note: data from a directory can be loaded by using the '''Browse''' button. 
     17  b. To save the results from the experiment, enter a file to which to write the results in the '''saveAs''' text field. Note: this is optional. 
     18  c. Once '''labelsFilename''' is specified, click the '''Edit''' button next to '''signalParamters'''. Important: '''labelsFilename''' must be specified ''BEFORE'' clicking '''Edit'''. Another '''Property Editor''' will appear. Select '''trueName''' from the pull down menu. Then press the '''OK''' button to close '''Property Editor for signalParameters''': 
     19[[Image(signal_params.jpg)]] 
     20  d. Type `sample1.test` in the '''testFilename''' text field. Note: when a test file is specified, MinorThird does not use a splitter. To use a splitter, simply do not specify any test file. The splitter is set to RandomSplitter by default thus does not need to be specified or changed for the experiment to run. 
     21  e. Options for how MinorThird learns from the training data are in '''trainingParameters'''.  These options all have defaults, so do not need to be explicated stated for the experiment to run. Most importantly the learner can be changed by selected a learner from the pull down menu and edited by pressing the “Edit” button next to learner.  To view the javadoc documentation for the currently selected learner, press the “?” button for a link to javadocs.  The output parameter specifies how minorthird labels extracted types.  By default it is set to prediction, but it is useful to change this to something more informative such as predicted_trueName. 
    2822 
    29233)      Feel free to try changing any of the other parameters including the ones in advanced options.  Click on the help buttons to get a feeling for what each parameter does and how changing it may affect your results.  Once all the parameters are set, click the “OK” button on the PropertyEditor.