This can happen, e.g., if an input value is missing and there is no other method for treating missing values. It is used if the prediction logic itself did not produce a result. In this case, the attribute priorProbability specifies a default probability for the corresponding target category. Targets can also be used for classification tasks. Targets: allows for post-processing of the predicted value in the format of scaling if the output of the model is continuous.Missing Value Treatment (attribute missingValueTreatment): indicates how the missing value replacement was derived (e.g. Missing Value Replacement Policy (attribute missingValueReplacement): if this attribute is specified then a missing value is automatically replaced by the given values.In PMML, outliers can be treated as missing values, as extreme values (based on the definition of high and low values for a particular field), or as is. Outlier Treatment (attribute outliers): defines the outlier treatment to be use.Predicted fields are those whose values are predicted by the model. Typical values are: active, predicted, and supplementary. Usage type (attribute usageType): defines the way a field is to be used in the model.Name (attribute name): must refer to a field in the data dictionary.It contains specific information about each field, such as: This can be a subset of the fields as defined in the data dictionary. Mining Schema: a list of all fields used in the model.Besides neural networks, PMML allows for the representation of many other types of models including support vector machines, association rules, Naive Bayes classifier, clustering models, text models, decision trees, and different regression models. These attributes are NeuralInputs, NeuralLayer, and NeuralOutputs. This information is then followed by three kinds of neural layers which specify the architecture of the neural network model being represented in the PMML document. Number of Layers (attribute numberOfLayers).Activation Function (attribute activationFunction).Algorithm Name (attribute algorithmName).E.g., A multi-layered feedforward neural network is represented in PMML by a "NeuralNetwork" element which contains attributes such as: Model: contains the definition of the data mining model.Aggregation: used to summarize or collect groups of values.Functions (custom and built-in): derive a value by applying a function to one or more parameters.Value mapping: map discrete values to discrete values.Discretization: map continuous values to discrete values.Normalization: map values to numbers, the input can be continuous or discrete.PMML defines several kinds of simple data transformations. Data Transformations: transformations allow for the mapping of user data into a more desirable form to be used by the mining model.Depending on this definition, the appropriate value ranges are then defined as well as the data type (such as, string or double). It is here that a field is defined as continuous, categorical, or ordinal (attribute optype). Data Dictionary: contains definitions for all the possible fields used by the model.It also contains an attribute for a timestamp which can be used to specify the date of model creation. Header: contains general information about the PMML document, such as copyright information for the model, its description, and information about the application used to generate the model such as name and version.A PMML file can be described by the following components:
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |