|
<?xml version='1.0' encoding='ISO-8859-1' ?>
<!ENTITY % A-PMML-MODEL '(TreeModel | NeuralNetwork | ClusteringModel | RegressionModel
| GeneralRegressionModel | AssociationModel )' >
<!ELEMENT PMML ( Header, DataDictionary, (%A-PMML-MODEL;)+, Extension* ) >
<!ATTLIST PMML
version CDATA #REQUIRED
>
<!ELEMENT Extension ANY >
<!ATTLIST Extension
extender CDATA #IMPLIED
name CDATA #IMPLIED
value CDATA #IMPLIED
>
<!ENTITY % NUMBER "CDATA">
<!ENTITY % INT-NUMBER "CDATA">
<!-- content must be an integer, no fractions or exponent -->
<!ENTITY % REAL-NUMBER "CDATA">
<!-- content can be any number- 'float','long','double' '1.23e4' -->
<!ENTITY % PROB-NUMBER "CDATA">
<!-- a REAL-NUMBER between 0.0 and 1.0 usually describing a probability -->
<!ENTITY % PERCENTAGE-NUMBER "CDATA">
<!-- a REAL-NUMBER between 0.0 and 100.0 -->
<!ENTITY % FIELD-NAME "CDATA">
<!ELEMENT Array (#PCDATA) >
<!ATTLIST Array
n %INT-NUMBER; #IMPLIED
type ( int| real| string ) #IMPLIED
>
<!ENTITY % NUM-ARRAY "Array">
<!-- an array of numbers -->
<!ENTITY % INT-ARRAY "Array">
<!-- an array of integers -->
<!ENTITY % REAL-ARRAY "Array">
<!-- an array of reals -->
<!ENTITY % STRING-ARRAY "Array">
<!-- an array of strings -->
<!-- ========= Header ================================== -->
<!ELEMENT Header (Application?, Annotation*, Timestamp?)>
<!ATTLIST Header
copyright CDATA #REQUIRED
description CDATA #IMPLIED
>
<!-- describes the software application that generated the PMML-->
<!ELEMENT Application EMPTY>
<!ATTLIST Application
name CDATA #REQUIRED
version CDATA #IMPLIED
>
<!ELEMENT Annotation (#PCDATA)>
<!ELEMENT Timestamp (#PCDATA)>
<!-- a timestamp in the format YYYY-MM-DD hh:mm:ss GMT +/- xx:xx -->
<!-- ========= Data Dictionary =========================== -->
<!ELEMENT DataDictionary (Extension*, DataField+) >
<!ATTLIST DataDictionary
numberOfFields %INT-NUMBER; #IMPLIED
>
<!ELEMENT DataField ( Extension*, (Interval*| Value*) )>
<!ATTLIST DataField
name %FIELD-NAME; #REQUIRED
displayName CDATA #IMPLIED
optype ( categorical | ordinal | continous ) #REQUIRED
isCyclic ( 0 | 1 ) "0"
>
<!ELEMENT Value (Extension* )>
<!ATTLIST Value
value CDATA #REQUIRED
displayValue CDATA #IMPLIED
property (valid | invalid | missing ) "valid"
>
<!ELEMENT Interval EMPTY>
<!ATTLIST Interval
closure (openClosed | openOpen | closedOpen | closedClosed) #REQUIRED
leftMargin %NUMBER; #IMPLIED
rightMargin %NUMBER; #IMPLIED
>
<!-- ========= Mining Schema =========================== -->
<!ELEMENT MiningSchema (Extension*, MiningField+) >
<!ENTITY % FIELD-USAGE-TYPE "(active | predicted | supplementary)">
<!ENTITY % OUTLIER-TREATMENT-METHOD "( asIs | asMissingValues | asExtremeValues)">
<!ELEMENT MiningField (Extension*)>
<!ATTLIST MiningField
name %FIELD-NAME; #REQUIRED
usageType %FIELD-USAGE-TYPE; "active"
outliers %OUTLIER-TREATMENT-METHOD; "asIs"
lowValue %NUMBER; #IMPLIED
highValue %NUMBER; #IMPLIED
>
<!-- ========= Statistics =========================== -->
<!ELEMENT ModelStats (UnivariateStats+)>
<!ENTITY % AGGREGATE "(Counts?, NumericInfo?)">
<!ELEMENT UnivariateStats ( (%AGGREGATE;)?, DiscrStats?, ContStats? ) >
<!ATTLIST UnivariateStats
field %FIELD-NAME; #IMPLIED
>
<!ELEMENT Counts EMPTY>
<!ATTLIST Counts
totalFreq %NUMBER; #REQUIRED
missingFreq %NUMBER; #IMPLIED
invalidFreq %NUMBER; #IMPLIED
>
<!ELEMENT NumericInfo (Quantile*)>
<!ATTLIST NumericInfo
minimum %NUMBER; #IMPLIED
maximum %NUMBER; #IMPLIED
mean %NUMBER; #IMPLIED
standardDeviation %NUMBER; #IMPLIED
median %NUMBER; #IMPLIED
interQuartileRange %NUMBER; #IMPLIED
>
<!ELEMENT Quantile EMPTY>
<!ATTLIST Quantile
quantileLimit %PERCENTAGE-NUMBER; #REQUIRED
quantileValue %NUMBER; #REQUIRED
>
<!ELEMENT DiscrStats (Extension*, (%STRING-ARRAY;)?, (%INT-ARRAY;)? )>
<!ATTLIST DiscrStats
modalValue CDATA #IMPLIED
>
<!ELEMENT ContStats ( Extension*, Interval*, (%INT-ARRAY;)?, (%NUM-ARRAY;)?, (%NUM-ARRAY;)? )>
<!ATTLIST ContStats
totalValuesSum %NUMBER; #IMPLIED
totalSquaresSum %NUMBER; #IMPLIED
>
<!ELEMENT Partition (PartitionFieldStats+)>
<!ATTLIST Partition
name CDATA #REQUIRED
size %NUMBER; #IMPLIED
>
<!ELEMENT PartitionFieldStats (%AGGREGATE;, (%NUM-ARRAY;)*)>
<!ATTLIST PartitionFieldStats
field %FIELD-NAME; #REQUIRED
>
<!-- ========= Normalization =========================== -->
<!ENTITY % NORM-INPUT "( NormContinuous | NormDiscrete)">
<!ELEMENT NormContinuous ( Extension*, LinearNorm* ) >
<!ATTLIST NormContinuous
field %FIELD-NAME; #REQUIRED
>
<!ELEMENT LinearNorm EMPTY >
<!ATTLIST LinearNorm
orig %NUMBER; #REQUIRED
norm %NUMBER; #REQUIRED
>
<!ELEMENT NormDiscrete ( Extension* )>
<!ATTLIST NormDiscrete
field %FIELD-NAME; #REQUIRED
method (indicator | thermometer) #FIXED "indicator"
value CDATA #REQUIRED
>
<!-- ========= Neural network =========================== -->
<!ENTITY % ACTIVATION-FUNCTION "(threshold | logistic | tanh)">
<!ELEMENT NeuralNetwork (Extension*, MiningSchema, ModelStats?,
NeuralInputs, (NeuralLayer+), NeuralOutputs?) >
<!ATTLIST NeuralNetwork
modelName CDATA #IMPLIED
activationFunction %ACTIVATION-FUNCTION; #REQUIRED
threshold %REAL-NUMBER; #IMPLIED
>
<!ELEMENT NeuralInputs ( NeuralInput+ )>
<!ELEMENT NeuralLayer ( Neuron+ )>
<!ELEMENT NeuralOutputs ( NeuralOutput+ )>
<!ENTITY % NN-NEURON-ID "CDATA">
<!ENTITY % NN-NEURON-IDREF "CDATA">
<!ELEMENT NeuralInput (Extension*, ( NormContinuous | NormDiscrete))>
<!ATTLIST NeuralInput
id %NN-NEURON-ID; #REQUIRED
>
<!ELEMENT Neuron (Extension*, Con+)>
<!ATTLIST Neuron
id %NN-NEURON-ID; #REQUIRED
bias %REAL-NUMBER; #IMPLIED
activationFunction %ACTIVATION-FUNCTION; #IMPLIED
threshold %REAL-NUMBER; #IMPLIED
>
<!ELEMENT Con (Extension*)>
<!ATTLIST Con
from %NN-NEURON-IDREF; #REQUIRED
weight %REAL-NUMBER; #REQUIRED
>
<!ELEMENT NeuralOutput ( Extension*, ( NormContinuous | NormDiscrete) )>
<!ATTLIST NeuralOutput
outputNeuron %NN-NEURON-IDREF; #REQUIRED
>
<!-- ========= Clustering Model =========================== -->
<!ELEMENT ClusteringModel ( Extension*, MiningSchema, ModelStats?, ComparisonMeasure,
ClusteringField*, CenterFields?, Cluster+)>
<!ATTLIST ClusteringModel
modelName CDATA #IMPLIED
modelClass (centerBased | distributionBased ) #REQUIRED
numberOfClusters %INT-NUMBER; #REQUIRED
>
<!ELEMENT CenterFields ( (%NORM-INPUT;)+ )>
<!ELEMENT Cluster (Extension*, (%NUM-ARRAY;)?, Partition?, Covariances?)>
<!ATTLIST Cluster
name CDATA #IMPLIED
>
<!ELEMENT Covariances (Matrix)>
<!ENTITY % CMP-FCT "(absDiff | gaussSim | delta | equal | table)">
<!ELEMENT ClusteringField ( Extension*, Comparisons? )>
<!ATTLIST ClusteringField
field %FIELD-NAME; #REQUIRED
fieldWeight %REAL-NUMBER; #IMPLIED
similarityScale %REAL-NUMBER; #IMPLIED
compareFunction %CMP-FCT; #IMPLIED
>
<!ELEMENT Comparisons ( Extension*, Matrix )>
<!ELEMENT Matrix ( ((%NUM-ARRAY;)+ ) | ( MatCell+ ) )?>
<!ATTLIST Matrix
kind ( diagonal | symmetric | any ) "any"
nbRows %INT-NUMBER; #IMPLIED
nbCols %INT-NUMBER; #IMPLIED
diagDefault %REAL-NUMBER; #IMPLIED
offDiagDefault %REAL-NUMBER; #IMPLIED
>
<!ELEMENT MatCell (#PCDATA)>
<!ATTLIST MatCell
row %INT-NUMBER; #REQUIRED
col %INT-NUMBER; #REQUIRED
>
<!ELEMENT ComparisonMeasure (Extension*, ( euclidean | squaredEuclidean | chebychev
| cityBlock | minkowski | simpleMatching | jaccard | tanimoto | binarySimilarity ) )>
<!ATTLIST ComparisonMeasure
kind (distance |similarity) #REQUIRED
compareFunction %CMP-FCT; #IMPLIED
minimum %NUMBER; #IMPLIED
maximum %NUMBER; #IMPLIED
>
<!ELEMENT euclidean EMPTY>
<!ELEMENT squaredEuclidean EMPTY>
<!ELEMENT cityBlock EMPTY>
<!ELEMENT chebychev EMPTY>
<!ELEMENT minkowski EMPTY>
<!ATTLIST minkowski
p-parameter %NUMBER; #REQUIRED
>
<!ELEMENT simpleMatching EMPTY>
<!ELEMENT jaccard EMPTY>
<!ELEMENT tanimoto EMPTY>
<!ELEMENT binarySimilarity EMPTY>
<!ATTLIST binarySimilarity
c00-parameter %NUMBER; #REQUIRED
c01-parameter %NUMBER; #REQUIRED
c10-parameter %NUMBER; #REQUIRED
c11-parameter %NUMBER; #REQUIRED
d00-parameter %NUMBER; #REQUIRED
d01-parameter %NUMBER; #REQUIRED
d10-parameter %NUMBER; #REQUIRED
d11-parameter %NUMBER; #REQUIRED
>
<!-- ========= Associantion Rules =========================== -->
<!ENTITY % ELEMENT-ID "CDATA">
<!ELEMENT AssociationModel (Extension*, AssocInputStats, AssocItem+, AssocItemset+,
AssocRule+) >
<!ATTLIST AssociationModel
modelName CDATA #IMPLIED
>
<!ELEMENT AssocInputStats EMPTY>
<!ATTLIST AssocInputStats
numberOfTransactions %INT-NUMBER; #REQUIRED
maxNumberOfItemsPerTA %INT-NUMBER; #IMPLIED
avgNumberOfItemsPerTA %REAL-NUMBER; #IMPLIED
minimumSupport %PROB-NUMBER; #REQUIRED
minimumConfidence %PROB-NUMBER; #REQUIRED
lengthLimit %INT-NUMBER; #IMPLIED
numberOfItems %INT-NUMBER; #REQUIRED
numberOfItemsets %INT-NUMBER; #REQUIRED
numberOfRules %INT-NUMBER; #REQUIRED
>
<!ELEMENT AssocItem EMPTY>
<!ATTLIST AssocItem
id %ELEMENT-ID; #REQUIRED
value CDATA #REQUIRED
mappedValue CDATA #IMPLIED
weight %REAL-NUMBER; #IMPLIED
>
<!ELEMENT AssocItemset (Extension*, AssocItemRef+)>
<!ATTLIST AssocItemset
id %ELEMENT-ID; #REQUIRED
support %PROB-NUMBER; #REQUIRED
numberOfItems %INT-NUMBER; #REQUIRED
>
<!ELEMENT AssocItemRef EMPTY>
<!ATTLIST AssocItemRef
itemRef %ELEMENT-ID; #REQUIRED
>
<!ELEMENT AssocRule ( Extension* )>
<!ATTLIST AssocRule
support %PROB-NUMBER; #REQUIRED
confidence %PROB-NUMBER; #REQUIRED
antecedent %ELEMENT-ID; #REQUIRED
consequent %ELEMENT-ID; #REQUIRED
>
<!-- ========= Tree Classifcation =========================== -->
<!ENTITY % PREDICATES
"(Predicate | CompoundPredicate | True | False)">
<!ELEMENT TreeModel (Extension*, MiningSchema, ModelStats?, Node)>
<!ATTLIST TreeModel
modelName CDATA #IMPLIED
>
<!ELEMENT Node ( Extension*, (%PREDICATES;), Node*, ScoreDistribution*)>
<!ATTLIST Node
score CDATA #REQUIRED
recordCount %NUMBER; #IMPLIED
>
<!ELEMENT Predicate EMPTY>
<!ATTLIST Predicate
field %FIELD-NAME; #REQUIRED
operator (equal | lessThan | notEqual | lessOrEqual | greaterThan
| greaterOrEqual) #REQUIRED
value CDATA #REQUIRED
>
<!ELEMENT CompoundPredicate ( %PREDICATES;, (%PREDICATES;)+ )>
<!ATTLIST CompoundPredicate
booleanOperator (or | and | xor | cascade) #REQUIRED
>
<!ELEMENT True EMPTY>
<!ELEMENT False EMPTY>
<!ELEMENT ScoreDistribution EMPTY>
<!ATTLIST ScoreDistribution
value CDATA #REQUIRED
recordCount %NUMBER; #REQUIRED
>
<!-- ========= Simple Regression =========================== -->
<!ELEMENT RegressionModel (Extension*, RegressionTable)>
<!ATTLIST RegressionModel
modelName CDATA #IMPLIED
modelType (linearRegression | stepwisePolynomialRegression) #REQUIRED
targetVariableName %FIELD-NAME; #REQUIRED
>
<!ELEMENT RegressionTable ((NumericPredictor*), (CategoricalPredictor*))>
<!ATTLIST RegressionTable
intercept %REAL-NUMBER; #REQUIRED
>
<!ELEMENT NumericPredictor EMPTY>
<!ATTLIST NumericPredictor
name %FIELD-NAME; #REQUIRED
exponent %INT-NUMBER; #REQUIRED
coefficient %REAL-NUMBER; #REQUIRED
mean %REAL-NUMBER; #IMPLIED
>
<!ELEMENT CategoricalPredictor EMPTY>
<!ATTLIST CategoricalPredictor
name %FIELD-NAME; #REQUIRED
value CDATA #REQUIRED
coefficient %REAL-NUMBER; #REQUIRED
>
<!-- ========= General Regression =========================== -->
<!ELEMENT GeneralRegressionModel ( Extension*, ParameterList, FactorList?,
CovariateList?, PPMatrix?, PCovMatrix?, ParamMatrix)>
<!ATTLIST GeneralRegressionModel
targetVariableName %FIELD-NAME; #REQUIRED
modelType (regression | generalLinear |
LogLinear | multinomialLogistic) #REQUIRED
>
<!ELEMENT ParameterList (Parameter+)>
<!ELEMENT Parameter EMPTY>
<!ATTLIST Parameter
name CDATA #REQUIRED
label CDATA #IMPLIED
>
<!ELEMENT FactorList (Predictor*)>
<!ELEMENT CovariateList (Predictor*)>
<!ELEMENT Predictor EMPTY>
<!ATTLIST Predictor
name %FIELD-NAME; #REQUIRED
>
<!ELEMENT PPMatrix (PPCell+)>
<!ATTLIST PPCell
value CDATA #REQUIRED
predictorName %FIELD-NAME; #REQUIRED
parameterName CDATA #REQUIRED
targetCategory CDATA #IMPLIED
>
<!ELEMENT PCovMatrix (PCovCell+)>
<!ELEMENT PCovCell EMPTY>
<!ATTLIST PCovCell
pRow CDATA #REQUIRED
pCol CDATA #REQUIRED
tRow CDATA #REQUIRED
tCol CDATA #REQUIRED
value %REAL-NUMBER; #REQUIRED
targetCategory CDATA #IMPLIED
>
<!ELEMENT ParamMatrix (PCell+)>
<!ELEMENT PCell EMPTY>
<!ATTLIST PCell
targetCategory CDATA #REQUIRED
parameterName CDATA #REQUIRED
beta %REAL-NUMBER; #REQUIRED
df %INT-NUMBER; #IMPLIED
>
|
|
