is an option for Classify and related functions that specifies explicit prior probabilities to assume for output classes, independent of anything deduced from the training set.


  • ClassPriors<|class1p1,class2p2,|> specifies that the prior probability to classify a particular input as being in class classi should be pi.
  • By default, the class priors are computed from the class frequencies of the training set.
  • In ClassPriors<|class1p1,class2p2,|>, unspecified class priors will be set to their rescaled default value to ensure normalization of the distribution.


open allclose all

Basic Examples  (1)

Train a classifier on an unbalanced training set:

Obtain class probabilities for a new example:

Set a uniform prior distribution for the classes:

Set the prior distribution of classes inside the classifier:

Priors of unspecified classes are functions of the remaining probability mass:

Applications  (3)

Restrict the built-in language classifier to only two languages:

Train a classifier to recognize if an organism is diseased on a balanced training set:

Find the probability that a new organism is diseased:

Find the probability that the same organism is diseased, incorporating prior knowledge that diseased organisms represent only 1% of the population:

Train a classifier able to predict if a website user will buy a given item based on his behavior:

Define and visualize a model for the probability of buying the item as a function of the outside temperature:

Use this model and WeatherData to increase the prediction performance for a Parisian user, without additional training:

Wolfram Research (2014), ClassPriors, Wolfram Language function,


Wolfram Research (2014), ClassPriors, Wolfram Language function,


Wolfram Language. 2014. "ClassPriors." Wolfram Language & System Documentation Center. Wolfram Research.


Wolfram Language. (2014). ClassPriors. Wolfram Language & System Documentation Center. Retrieved from


@misc{reference.wolfram_2024_classpriors, author="Wolfram Research", title="{ClassPriors}", year="2014", howpublished="\url{}", note=[Accessed: 17-June-2024 ]}


@online{reference.wolfram_2024_classpriors, organization={Wolfram Research}, title={ClassPriors}, year={2014}, url={}, note=[Accessed: 17-June-2024 ]}