WOLFRAM

Wolfram Language & System Documentation Center
Wolfram Language Home Page »

PredictorFunction

✖

represents a function generated by Predict that predicts numerical values from data.

Details and Options

  • PredictorFunction works like Function.
  • PredictorFunction[…][data] attempts to predict the value associated with data.
  • PredictorFunction[…][{data1,data2,…}] attempts to predict all the datai.
  • PredictorFunction[…][data,prop] gives the specified property of the prediction associated with data.
  • Possible properties applicable to all methods include:
  • "Decision"best prediction according to the distribution and the utility function
    "Distribution"distribution of value conditioned on input
    "SHAPValues"Shapley additive feature explanations for each example
    "Properties"list of all properties available
  • "SHAPValues" assesses the contribution of features by comparing predictions with different sets of features removed and then synthesized. The option MissingValueSynthesis can be used to specify how the missing features are synthesized. SHAP explanations are given as deviation from the training output mean. "SHAPValues"n can be used to control the number of samples used for the numeric estimations of SHAP explanations.
  • PredictorFunction[…][data,…,opts] specifies that the predictor should use the options opts when applied to data.
  • Possible options are:
  • IndeterminateThreshold Automaticbelow what probability density to return Indeterminate
    PerformanceGoal Automaticwhich aspect of performance to optimize
    MissingValueSynthesis Automatichow to synthesize missing values
    RecalibrationFunction Automatichow to post-process predicted value
    TargetDevice "CPU"the target device on which to perform training
    UtilityFunction Automaticutility expressed as a function of actual and predicted value
  • A PredictorFunction[…] trained in an older version of the Wolfram Language will still work in the current version.
  • Predict[FittedModel[…]] can be used to convert a fitted model into a PredictorFunction[…].
  • Predict[PredictorFunction[…],opts] can be used to update the values of PerformanceGoal, IndeterminateThreshold, UtilityFunction or FeatureExtractor of the classifier.
  • In Predict[PredictorFunction[…],FeatureExtractorfe], the FeatureExtractorFunction[…] fe will be prepended to the existing feature extractor.
  • Information[PredictorFunction[…]] generates an information panel about the classifier and its estimated performances.
  • Information[PredictorFunction[…],prop] can be used to obtain specific properties.
  • Information of a PredictorFunction[…] may include the following properties:
  • "BatchEvaluationTime"marginal time to predict one example when a batch is given
    "EvaluationTime"time needed to predict one example
    "ExampleNumber"number of training examples
    "FeatureTypes"feature types of the predictor input
    "FunctionMemory"memory needed to store the predictor
    "FunctionProperties"all prediction properties available for this predictor
    "IndeterminateThreshold"value of IndeterminateThreshold used by the predictor
    "LearningCurve"performance as function of training set size
    "MaxTrainingMemory"maximum memory used during training
    "MeanCrossEntropy"estimated mean cross entropy of the predictor
    "Method"value of Method used by the predictor
    "MethodDescription"summary of the method
    "MethodOption"full method option to be reused in a new training
    "MethodParameters"parameter settings of the method
    "Properties"all information properties available for this predictor
    "StandardDeviation"estimated standard deviation of the predictor
    "FeatureExtractor"feature extractor as FeatureExtractorFunction
    "TrainingLabelMean"mean label value seen during training
    "TrainingTime"time used by Predict to generate the predictor
    "UtilityFunction"value of UtilityFunction used by the predictor
  • Information properties also include all method suboptions.

Examples

open allclose all

Basic Examples  (2)Summary of the most common use cases

Train a PredictorFunction:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-b9dzea
Out[1]=1

Use the trained PredictorFunction to predict an output, given some feature:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-53n8
Out[2]=2

Predict multiple examples:

In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-e7w6ph
Out[3]=3

Calculate the probability distribution of the predicted value:

In[4]:=4
✖
https://wolfram.com/xid/01yyovh5nrm-bgouui
Out[4]=4

Generate a PredictorFunction using multiple features:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-6d3z0t
Out[1]=1

Use the function on a new example:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-q87iwn
Out[2]=2

Predict an example that has missing features:

In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-pjaio8
Out[3]=3

Obtain general information about the predictor:

In[4]:=4
✖
https://wolfram.com/xid/01yyovh5nrm-8y8yu
Out[4]=4

Scope  (6)Survey of the scope of standard use cases

Train a PredictorFunction on textual data:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-spf589
Out[1]=1

Predict the values of new examples:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-sprc02
Out[2]=2

Train a PredictorFunction to recognize the frequency of SawtoothWave sounds:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-dwor9v
Out[1]=1

Predict the values of new examples:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-jad4yg
In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-d4rhlb
Out[3]=3

Train a PredictorFunction:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-vvh6kg
Out[1]=1

Generate a PredictorMeasurementsObject of the function applied to a test set:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-duh5q9
Out[2]=2

Get the standard deviation of the residuals of the function on the test set:

In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-cbhd3s
Out[3]=3

Visualize the scatter plot of the test values as a function of the predicted values:

In[4]:=4
✖
https://wolfram.com/xid/01yyovh5nrm-4pfth2
Out[4]=4

Generate a predictor function whose input is an association:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-pl8yra
Out[1]=1

Use the function on an example:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-10r04a
Out[2]=2

Predict examples containing missing features:

In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-deouc6
Out[3]=3

Construct a Dataset with a list of associations:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-lhnxnd
Out[1]=1

Train a PredictorFunction to predict the feature "age" as function of the other features:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-f4tpwu
Out[2]=2

Once the PredictorFunction is trained, any input format can be used. Predict an example formatted as an association:

In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-rae3u3
Out[3]=3

Find out the order of the features, and classify an example formatted as a list:

In[4]:=4
✖
https://wolfram.com/xid/01yyovh5nrm-ccc6wd
Out[4]=4
In[5]:=5
✖
https://wolfram.com/xid/01yyovh5nrm-q5c13d
Out[5]=5

Classify examples in a Dataset:

In[6]:=6
✖
https://wolfram.com/xid/01yyovh5nrm-cbsemz
Out[6]=6
In[7]:=7
✖
https://wolfram.com/xid/01yyovh5nrm-csehx0
Out[7]=7

Load a dataset of wine quality as a function of the wines' physical properties:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-0262ca

Train a predictor to estimate wine quality:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-ytl4j2
Out[2]=2

Examine an example bottle:

In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-8yv81b
Out[3]=3

Predict the example bottle's quality:

In[4]:=4
✖
https://wolfram.com/xid/01yyovh5nrm-rfe9mh
Out[4]=4

Calculate how much higher or lower this bottle's predicted quality is than the mean:

In[5]:=5
✖
https://wolfram.com/xid/01yyovh5nrm-lqdk3d
Out[5]=5

Get an estimation for how much each feature impacted the predictor's output for this bottle:

In[6]:=6
✖
https://wolfram.com/xid/01yyovh5nrm-m7t0n8
Out[6]=6

Visualize these feature impacts:

In[7]:=7
✖
https://wolfram.com/xid/01yyovh5nrm-7d1qat
Out[7]=7

Confirm that the Shapley values fully explain the predicted quality:

In[8]:=8
✖
https://wolfram.com/xid/01yyovh5nrm-08373t
Out[8]=8
Out[8]=8

Learn a distribution of the data that treats each feature as independent:

In[9]:=9
✖
https://wolfram.com/xid/01yyovh5nrm-ddmot3
Out[9]=9

Estimate SHAP value feature importance for 100 bottles of wine, using 5 samples for each estimation:

In[10]:=10
✖
https://wolfram.com/xid/01yyovh5nrm-euwga
Out[10]=10

Calculate how important each feature is to the model:

In[11]:=11
✖
https://wolfram.com/xid/01yyovh5nrm-otiw08
Out[11]=11

Visualize the model's feature importance:

In[12]:=12
✖
https://wolfram.com/xid/01yyovh5nrm-wsqujs
Out[12]=12

Visualize a nonlinear relationship between a feature's value and its impact on the model's prediction:

In[13]:=13
✖
https://wolfram.com/xid/01yyovh5nrm-mmlrh3
Out[13]=13

Options  (7)Common values & functionality for each option

IndeterminateThreshold  (1)

Train a PredictorFunction:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-xir5ql
Out[1]=1

Visualize the probability density for a given example:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-d9c02p
Out[2]=2
In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-jqvr
Out[3]=3

The value with the highest probability density is predicted:

In[4]:=4
✖
https://wolfram.com/xid/01yyovh5nrm-e1alw5
Out[4]=4

No prediction is made if the maximum probability density is below a specified threshold:

In[5]:=5
✖
https://wolfram.com/xid/01yyovh5nrm-mwd55p
Out[5]=5

Update the value of the threshold permanently:

In[6]:=6
✖
https://wolfram.com/xid/01yyovh5nrm-qxqkw4
Out[6]=6
In[7]:=7
✖
https://wolfram.com/xid/01yyovh5nrm-rscqal
Out[7]=7

MissingValueSynthesis  (1)

Train a predictor with two input features:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-uarmq6
Out[1]=1

Get the prediction for an example that has a missing value:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-00e8xt
Out[2]=2

Set the missing value synthesis to replace missing variables with their most likely value given known values (which is the default behavior):

In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-e03411
Out[3]=3

Replace missing variables with random samples conditioned on known values:

In[4]:=4
✖
https://wolfram.com/xid/01yyovh5nrm-od0kq
Out[4]=4

Averaging over many random imputations is usually the best strategy and allows obtaining the uncertainty caused by the imputation:

In[5]:=5
✖
https://wolfram.com/xid/01yyovh5nrm-fqeata
Out[5]=5

Specify a learning method during training to control how the distribution of data is learned:

In[6]:=6
✖
https://wolfram.com/xid/01yyovh5nrm-lyqv3u
Out[6]=6

Predict an example with missing values using the "KernelDensityEstimation" distribution to condition values:

In[7]:=7
✖
https://wolfram.com/xid/01yyovh5nrm-hwf88u
Out[7]=7

Provide an existing LearnedDistribution at training to use it when imputing missing values during training and later evaluations:

In[8]:=8
✖
https://wolfram.com/xid/01yyovh5nrm-8ni5d
Out[8]=8
Out[8]=8

Specify an existing LearnedDistribution to synthesize missing values for an individual evaluation:

In[9]:=9
✖
https://wolfram.com/xid/01yyovh5nrm-z7m9zi
Out[9]=9

Control both the learning method and the evaluation strategy by passing an association at training:

In[10]:=10
✖
https://wolfram.com/xid/01yyovh5nrm-ktalq9
Out[10]=10

RecalibrationFunction  (2)

Train a predictor:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-ff009l
Out[1]=1

Compute the prediction:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-06cdnh
Out[2]=2

Compute the predictive distribution:

In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-544r1e
Out[3]=3

Temporarily set a recalibration function to apply to the prediction:

In[4]:=4
✖
https://wolfram.com/xid/01yyovh5nrm-db93uv
Out[4]=4

Compute the predictive distribution with this new recalibration:

In[5]:=5
✖
https://wolfram.com/xid/01yyovh5nrm-n4azvd
Out[5]=5

Load the Boston Homes dataset:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-w7tgbo

Train a predictor with model calibration:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-zudagx
Out[2]=2

Visualize the comparison plot on a test set:

In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-4mjeut
Out[3]=3

Remove the recalibration function from the predictor:

In[4]:=4
✖
https://wolfram.com/xid/01yyovh5nrm-hdakmq
Out[4]=4

Visualize the new comparison plot:

In[5]:=5
✖
https://wolfram.com/xid/01yyovh5nrm-8q81c8
Out[5]=5

TargetDevice  (1)

Train a predictor using a neural network:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-gnlysk

Evaluate the resulting predictor on system's default GPU and look at its AbsoluteTiming:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-4fgmey

Compare the previous timing with the one achieved by using the default CPU computation:

In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-g2ypu8

UtilityFunction  (1)

Train a predictor function:

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-i5mnof
In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-j1o7u
Out[2]=2

Visualize the probability density for a given example:

In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-jft9ef
Out[3]=3
In[4]:=4
✖
https://wolfram.com/xid/01yyovh5nrm-1n0gd
Out[4]=4

By default, the value with the highest probability density is predicted:

In[5]:=5
✖
https://wolfram.com/xid/01yyovh5nrm-he3t82
Out[5]=5

Define a utility function that penalizes the predicted value's being smaller than the actual value:

In[6]:=6
✖
https://wolfram.com/xid/01yyovh5nrm-0p1sgu

Plot this function for a given actual value:

In[7]:=7
✖
https://wolfram.com/xid/01yyovh5nrm-ygfxmi
Out[7]=7

The predictor decision is now changed despite the probability density's being unchanged:

In[8]:=8
✖
https://wolfram.com/xid/01yyovh5nrm-9k8mb
Out[8]=8

Update the value of the utility function permanently:

In[9]:=9
✖
https://wolfram.com/xid/01yyovh5nrm-klr3i4
Out[9]=9
In[10]:=10
✖
https://wolfram.com/xid/01yyovh5nrm-hc8qpk
Out[10]=10

PerformanceGoal  (1)

Obtain the built-in PredictorFunction "NameAge":

In[1]:=1
✖
https://wolfram.com/xid/01yyovh5nrm-2qwl8m
Out[1]=1

Set a custom utility function to use with this predictor:

In[2]:=2
✖
https://wolfram.com/xid/01yyovh5nrm-uk9vmz

Compute the time required to use an example with this utility function:

In[3]:=3
✖
https://wolfram.com/xid/01yyovh5nrm-4jrefl
Out[3]=3

Use PerformanceGoal to use a faster but less accurate result:

In[4]:=4
✖
https://wolfram.com/xid/01yyovh5nrm-2gqueu
Out[4]=4
Wolfram Research (2014), PredictorFunction, Wolfram Language function, https://reference.wolfram.com/language/ref/PredictorFunction.html (updated 2021).
✖
Wolfram Research (2014), PredictorFunction, Wolfram Language function, https://reference.wolfram.com/language/ref/PredictorFunction.html (updated 2021).

Text

Wolfram Research (2014), PredictorFunction, Wolfram Language function, https://reference.wolfram.com/language/ref/PredictorFunction.html (updated 2021).

✖
Wolfram Research (2014), PredictorFunction, Wolfram Language function, https://reference.wolfram.com/language/ref/PredictorFunction.html (updated 2021).

CMS

Wolfram Language. 2014. "PredictorFunction." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2021. https://reference.wolfram.com/language/ref/PredictorFunction.html.

✖
Wolfram Language. 2014. "PredictorFunction." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2021. https://reference.wolfram.com/language/ref/PredictorFunction.html.

APA

Wolfram Language. (2014). PredictorFunction. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/PredictorFunction.html

✖
Wolfram Language. (2014). PredictorFunction. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/PredictorFunction.html

BibTeX

@misc{reference.wolfram_2025_predictorfunction, author="Wolfram Research", title="{PredictorFunction}", year="2021", howpublished="\url{https://reference.wolfram.com/language/ref/PredictorFunction.html}", note=[Accessed: 30-May-2025 ]}

✖
@misc{reference.wolfram_2025_predictorfunction, author="Wolfram Research", title="{PredictorFunction}", year="2021", howpublished="\url{https://reference.wolfram.com/language/ref/PredictorFunction.html}", note=[Accessed: 30-May-2025 ]}

BibLaTeX

@online{reference.wolfram_2025_predictorfunction, organization={Wolfram Research}, title={PredictorFunction}, year={2021}, url={https://reference.wolfram.com/language/ref/PredictorFunction.html}, note=[Accessed: 30-May-2025 ]}

✖
@online{reference.wolfram_2025_predictorfunction, organization={Wolfram Research}, title={PredictorFunction}, year={2021}, url={https://reference.wolfram.com/language/ref/PredictorFunction.html}, note=[Accessed: 30-May-2025 ]}