cts.train. Returns labels for
each of the input documents in the same order as the input document.
cts.train, either run directly or saved in
a JSON document in the database.
An options
object. The options for classification
are passed automatically from
cts.train to the
cts.classifier
specification as part of the classifier
object so that they are
consistent with the parameters used in training. The following
options
may be separately passed to
cts.classify
.
These options override the options present in the classifier item-by-item.
defaultThreshold,
classThresholds
classThresholds specify per-class values
(as computed from cts.thresholds).
defaultThreshold
will apply to any classes for which a per-class value is not specified.
For example:
{
...
defaultThreshold: -1.0,
classThresholds: {"Example 1": -2.42, "Example 2": 0.41}
...
}
supports form of the classifier is used;
ignored if the weights form of the classifier is used.
cts.classify classifies
an array of nodes using the output from cts.train.
The dataNodes and classifier parameters
are respectively the nodes to
be classified and the specification output from cts.train.
cts.classify can use either supports or
weights forms of the classifier output
from cts.train (see Output
Formats). If the supports form is used, the training
nodes must be passed as the 4th parameter. The options
parameter is an options object.
The output is an array of label objects of the form:
Each label corresponds to the data node in the corresponding
position in the input sequence. There will be an
object for each class where the document passed the class
threshold. The val
property gives the
class membership value for the data node in the given class. Values
greater than zero indicate likely class membership, values less than
zero indicate likely non-membership. Adjusting thresholds can give
more or less selective classification. Increasing the threshold
leads to a more selective classification (that is, decreases the
likelihood of classification in the class). Decreasing the threshold
gives less selective classification.
var firsthalf = fn.subsequence(
xdmp.directory("/shakespeare/plays/", "1"), 1, 19);
var plays1 = firsthalf.clone();
var secondhalf = fn.subsequence(
xdmp.directory("/shakespeare/plays/", "1"), 20, 37);
var plays2 = secondhalf.clone();
var labels = [];
for (var x of firsthalf) {
var singleClass = [{"name": xdmp.documentProperties(xdmp.nodeUri(x)).next().value.
xpath("//playtype/fn:string()")
}];
labels.push({"classes": singleClass});
}
var classifier = cts.train(plays1.toArray(), labels,
{"classifierType": "supports",
"useDbConfig": true,
"epsilon": 0.00001
});
cts.classify(plays2.toArray(), classifier, {}, plays1.toArray());
=>
[
{
"classes": [
{ "name": "HISTORY",
"val": 4.29498338699341
},
{ "name": "COMEDY",
"val": 2.83974766731262
},
{ "name": "TRAGEDY",
"val": -0.454397678375244
}
]
},
{
"classes": [
{ "name": "HISTORY",
"val": 3.70210886001587
},
{ "name": "COMEDY",
"val": 2.59831714630127
},
{ "name": "TRAGEDY",
"val": -0.404506534337997
}
]
},
...
]