alsouse, autopars, batch, brief, comment, draw, features, help_par, ignore, info, input_pars, kfold, learn, listio, listmods, listpars, log, output, quickquit, quit, set, setmod, testset, useonly
<attributes> must be a list of one or more attribute names, or can be the word "all". This command operates on the current 'iostate' (standing for input/output state. The iostate determines which attributes are used for inputs, and which (if any) for outputs. Changing the iostate may cause the model to be relearned if the new iostate is incompatible (in terms of number and types of inputs and outputs) with the current model. The alsouse command moves all the attributes mentioned in the argument to the inputs list.
The commands are executed in just the same way as if you were to type them into the command line manually here. Note that all output is sent to this display as usual. Note too that the execution of the commands continues blindly even if there are errors along the way. The batch file should simply have one command on each line. You can leave blank lines if you like. Lines beginning with a # character will be treated as comments and ignored.
You are simply told the names and whether the attributes are symbolic or real. Each attribute is tenvscribed on one line. For more tenvtails on attributes, use the info command.
This command is almost certainly useless to you unless you
are planning on saving the text of your session to a file, and wish
to add a comment to the reader of the session.
comment on <sessionname>: This will switch on some internal flags that will
add special annotations to all output so that it can easily
be turned into a tutorial. Graphics will be saved to files
with names like andrew12.ps if andrew was given as the
session name.
comment off: Switch off the above.
comment <anything else>: Will allow the user to type in commentary about
what's going on to be used by the comment command.
Important: TO STOP ENTERING COMMENT, PUT A SINGLE . ON A LINE.
Note that many models cannot be drawn. If they can't be drawn they will explain why.
This command gives documented info about the given parameter. To find out what are the parameters of the current model, type listpars. Instead of specifying a single parameters you can choose "all" which gives you information about every parameter.
<attributes> must be a list of one or more attribute names, or can be the word "all". This command operates on the current 'iostate' (standing for input/output state. The iostate determines which attributes are used for inputs, and which (if any) for outputs. Changing the iostate may cause the model to be relearned if the new iostate is incompatible (in terms of number and types of inputs and outputs) with the current model. The ignore command moves all the attributes mentioned in the argument to the ignored list.
<attributes> may be "all" or a list of attribute names or numbers For the symbolic attributes, you are told what the symbolic values are, and how many times each value occurs in the dataset. For the real-valued attributes, you are told their means, variances, mins and maxes. In each case you are also shown the first eight values. You are also told how many values are missing.
Runs k-fold cross validation on current model and params. Does not affect the model currently stored in memory.
Note that this command is never really needed, because any of the other commands that actually need a model will learn and cache it automatically
This simply lists all parameters used by the current model, as a set of <key> <value> pairs. Notice that changing one parameter (which you can do with the autopars, input_pars or setpar command) can cause other parameters to also change, or spring into existance or to disappear. Type help_par <param_name> for more info on a specific parameter.
This command takes all text output and appends it into a file. (Note that appending allows the user to add to a log file at any time.) Typing 'log off' at any time will disable logging.
Tell learner to use the given output. If the argument is "none", uses no outputs. This is appropriate for density models only. Else the argument must be a single attribute. It should be a real-valued attribute for regression or a symbolic attribute for classification. But note that the software will do its best to convert between real and symbolic automatically for you. What happens to the previous output attribute? If it is in the ignored list then it becomes ignored. If it is not on the ignored list it is added to the set of input attributes.
Warning---please make sure you've saved any results you need before you type quit
param_name must be one of the parameter names obtained when you type listpars <param_name> must be one of the parameters mentioned by listpars
To see the available set of models, type listmods. Once you've selected a model, type listpars to see it's parameters.
<attributes> must be a list of one or more attribute names, or can be the word "all". This command operates on the current 'iostate' (standing for input/output state. The iostate determines which attributes are used for inputs, and which (if any) for outputs. Changing the iostate may cause the model to be relearned if the new iostate is incompatible (in terms of number and types of inputs and outputs) with the current model. The useonly command moves all the attributes mentioned in the argument to the inputs list and makes all attributes not mentioned into ignored attributes.