incrementalClassificationNaiveBayes
Naive Bayes classification model for incremental learning
Description
TheincrementalClassificationNaiveBayes
function creates anincrementalClassificationNaiveBayes
model object, which represents a naive Bayes multiclass classification model for incremental learning.
Unlike other Statistics and Machine Learning Toolbox™ model objects,incrementalClassificationNaiveBayes
can be called directly. Also, you can specify learning options, such as performance metrics configurations and prior class probabilities, before fitting the model to data. After you create anincrementalClassificationNaiveBayes
object, it is prepared forincremental learning。
incrementalClassificationNaiveBayes
is best suited for incremental learning. For a traditional approach to training a naive Bayes model for multiclass classification (such as creating a model by fitting it to data, performing cross-validation, tuning hyperparameters, and so on), seefitcnb
。
创建
You can create anincrementalClassificationNaiveBayes
model object in several ways:
Call the function directly— Configure incremental learning options, or specify learner-specific options, by calling
incrementalClassificationNaiveBayes
directly. This approach is best when you do not have data yet or you want to start incremental learning immediately. You must specify the maximum number of classes or all class names expected in the response data during incremental learning.Convert a traditionally trained model— To initialize a naive Bayes classification model for incremental learning using the model parameters of a trained model object (
ClassificationNaiveBayes
), you can convert the traditionally trained model to anincrementalClassificationNaiveBayes
model object by passing it to theincrementalLearner
function.Call an incremental learning function—
fit
,updateMetrics
, andupdateMetricsAndFit
accept a configuredincrementalClassificationNaiveBayes
model object and data as input, and return anincrementalClassificationNaiveBayes
model object updated with information learned from the input model and data.
Syntax
Description
returns a default incremental learning model object for naive Bayes classification,Mdl
= incrementalClassificationNaiveBayes('MaxNumClasses',MaxNumClasses
)Mdl
, whereMaxNumClasses
is the maximum number of classes expected in the response data during incremental learning. Properties of a default model contain placeholders for unknown model parameters. You must train a default model before you can track its performance or generate predictions from it.
specifies all class namesMdl
= incrementalClassificationNaiveBayes('ClassNames',ClassNames
)ClassNames
expected in the response data during incremental learning, and sets theClassNames
property.
uses either of the previous syntaxes to setpropertiesand additional options using name-value arguments. Enclose each name in quotes. For example,Mdl
= incrementalClassificationNaiveBayes(___,Name,Value
)incrementalClassificationNaiveBayes('DistributionNames','mn','MaxNumClasses',5,'MetricsWarmupPeriod',100)
specifies that the joint conditional distribution of the predictor variables is multinomial, sets the maximum number of classes expected in the response data to5
, and sets the metrics warm-up period to100
。
Input Arguments
MaxNumClasses
—Maximum number of classes
positive integer
Maximum number of classes expected in the response data during incremental learning, specified as a positive integer.
MaxNumClasses
sets the number of class names in theClassNames
property.
If you do not specifyMaxNumClasses
, you must specify theClassNames
argument.
Example:'MaxNumClasses',5
Data Types:single
|double
ClassNames
—All unique class labels
categorical array|character array|string array|logical vector|numeric vector|cell array of character vectors
All unique class labels expected in the response data during incremental learning, specified as a categorical, character, or string array; logical or numeric vector; or cell array of character vectors.ClassNames
and the response data must have the same data type. This argument sets theClassNames
property.
ClassNames
specifies the order of any input or output argument dimension that corresponds to the class order. For example, set'ClassNames'
to specify the order of the dimensions ofCost
or the column order of classification scores returned bypredict
If you do not specifyClassNames
, you must specify theMaxNumClasses
argument. In that case, the software infers theClassNames
property from the data during incremental learning.
Example:'ClassNames',["virginica" "setosa" "versicolor"]
Data Types:single
|double
|logical
|string
|char
|cell
|categorical
Specify optional pairs of arguments asName1=Value1,...,NameN=ValueN
, whereName
is the argument name andValue
is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.
Before R2021a, use commas to separate each name and value, and encloseName
in quotes.
Example:'NumPredictors',4,'Prior',[0.3 0.3 0.4]
specifies4
variables in the predictor data and the prior class probability distribution of[0.3 0.3 0.4]
。
Cost
—Cost of misclassifying observation
square matrix|structure array
Cost of misclassifying an observation, specified as a value in this table, wherecis the number of classes in theClassNames
property:
Value | Description |
---|---|
c-by-cnumeric matrix |
|
Structure array | A structure array having two fields:
|
If you specifyCost
, you must also specify theClassNames
argument.Cost
sets theCost
property.
The default is one of the following alternatives:
An empty array
[]
when you specifyMaxNumClasses
Ac-by-cmatrix when you specify
ClassNames
, whereCost(
for alli
,j
) = 1
≠i
, andj
Cost(
for alli
,j
) = 0
=i
j
Example:'Cost',struct('ClassNames',{'b','g'},'ClassificationCosts',[0 2; 1 0])
Data Types:single
|double
|struct
Metrics
—Model performance metrics to track during incremental learning
"mincost"
(default) |"classiferror"
|string vector|function handle|cell vector|structure array|"binodeviance"
|"exponential"
|"hinge"
|"logit"
|"quadratic"
Model performance metrics to track during incremental learning, in addition to minimal expected misclassification cost, specified as a built-in loss function name, string vector of names, function handle (for example,@metricName
), structure array of function handles, or cell vector of names, function handles, or structure arrays.
WhenMdl
is温暖的(seeIsWarm),updateMetrics
andupdateMetricsAndFit
track performance metrics in theMetricsproperty ofMdl
。
The following table lists the built-in loss function names. You can specify more than one by using a string vector.
Name | Description |
---|---|
"binodeviance" |
Binomial deviance |
"classiferror" |
Misclassification error rate |
"exponential" |
Exponential |
"hinge" |
Hinge |
"logit" |
Logistic |
"mincost" |
Minimal expected misclassification cost (for classification scores that are posterior probabilities). |
"quadratic" |
Quadratic |
For more details on the built-in loss functions, seeloss
。
Example:'Metrics',["classiferror" "logit"]
To specify a custom function that returns a performance metric, use function handle notation. The function must have this form.
metric = customMetric(C,S,Cost)
The output argument
metric
is ann-by-1 numeric vector, where each element is the loss of the corresponding observation in the data processed by the incremental learning functions during a learning cycle.You specify the function name (here,
customMetric
).C
is ann-by-Klogical matrix with rows indicating the class to which the corresponding observation belongs, whereKis the number of classes. The column order corresponds to the class order in theClassNames
property. CreateC
by settingC(
=p
,q
)1
, if observation
is in classp
, for each observation in the specified data. Set the other element in rowq
top
0
。S
is ann-by-Knumeric matrix of predicted classification scores.S
is similar to thePosterior
output ofpredict
, where rows correspond to observations in the data and the column order corresponds to the class order in theClassNames
property.S(
is the classification score of observationp
,q
)
being classified in classp
。q
Cost
is aK-by-Knumeric matrix of misclassification costs. See the'Cost'
name-value argument.
To specify multiple custom metrics and assign a custom name to each, use a structure array. To specify a combination of built-in and custom metrics, use a cell vector.
Example:'Metrics',struct('Metric1',@customMetric1,'Metric2',@customMetric2)
Example:'Metrics',{@customMetric1 @customMetric2 'logit' struct('Metric3',@customMetric3)}
updateMetrics
andupdateMetricsAndFit
store specified metrics in a table in theMetrics
property. The data type ofMetrics
determines the row names of the table.
'Metrics' Value Data Type |
Description ofMetrics Property Row Name |
Example |
---|---|---|
String or character vector | Name of corresponding built-in metric | Row name for"classiferror" is"ClassificationError" |
Structure array | Field name | Row name forstruct('Metric1',@customMetric1) is"Metric1" |
Function handle to function stored in a program file | Name of function | Row name for@customMetric is"customMetric" |
Anonymous function | CustomMetric_ , where is metric inMetrics |
Row name for@ (C、S、成本)customMetric (C、S、成本)… isCustomMetric_1 |
For more details on performance metrics options, seePerformance Metrics。
Data Types:char
|string
|struct
|cell
|function_handle
Properties
You can set most properties by using name-value pair argument syntax only when you callincrementalClassificationNaiveBayes
directly. You can set some properties when you callincrementalLearner
to convert a traditionally trained model. You cannot set the propertiesDistributionParameters
,IsWarm
, andNumTrainingObservations
。
Classification Model Parameters
CategoricalPredictors
—Categorical predictors list
vector of positive integers|logical vector|"all"
This property is read-only.
Categorical predictors list, specified as one of the values in this table.
Value | Description |
---|---|
Vector of positive integers | Each entry in the vector is an index value corresponding to the column of the predictor data that contains a categorical variable. The index values are between 1 and |
Logical vector | Atrue entry means that the corresponding column of predictor data is a categorical variable. The length of the vector isNumPredictors 。 |
"all" |
All predictors are categorical. |
For the identified categorical predictors,incrementalClassificationNaiveBayes
uses multivariate multinomial distributions. For more details, seeDistributionNames
。
By default, if you specify theDistributionNames
option, all predictor variables corresponding to'mvmn'
are categorical. Otherwise, none of the predictor variables are categorical.
Example:'CategoricalPredictors',[1 2 4]
and'CategoricalPredictors',[true true false true]
specify that the first, second, and fourth of four predictor variables are categorical.
Data Types:single
|double
|logical
CategoricalLevels
—Levels of multivariate multinomial predictor variables
cell vector
Levels of multivariate multinomial predictor variables, specified as a cell vector. The length ofCategoricalLevels
is equal toNumPredictors
。
Incremental fitting functionsfit
andupdateMetricsAndFit
populate cells with the learned numeric categorical levels of each categorical predictor variable, while cells corresponding to other predictor variables contain an empty array[]
。Specifically, if predictorjis multivariate multinomial,CategoricalLevels{
j}
is a list of all distinct values of predictorjexperienced during incremental fitting. For more details, see theDistributionNames
property.
Note
Unlikefitcnb
, incremental fitting functions order the levels of a predictor as the functions experience them during training. For example, suppose predictorjis categorical with multivariate multinomial distribution. The order of the levels inCategoricalLevels{j}
and, consequently, the order of the level probabilities in each cell ofDistributionParameters{:,j}
returned by incremental fitting functions can differ from the order returned byfitcnb
for the same training data set.
Cost
—Cost of misclassifying observation
square numeric matrix|empty array[]
This property is read-only.
Cost of misclassifying an observation, specified as an array.
If you specify the'Cost'
name-value argument, its value setsCost
。If you specify a structure array,Cost
is the value of theClassificationCosts
field.
If you convert a traditionally trained model to createMdl
,Cost
is theCost
property of the traditionally trained model.
Data Types:single
|double
ClassNames
—All unique class labels
categorical array|character array|string array|logical vector|numeric vector|cell array of character vectors
This property is read-only.
All unique class labels expected in the response data during incremental learning, specified as a categorical or character array, a logical or numeric vector, or a cell array of character vectors.
You can setClassNames
in one of three ways:
If you specify the
MaxNumClasses
argument, the software infers theClassNames
property during incremental learning.If you specify the
ClassNames
argument,incrementalClassificationNaiveBayes
stores your specification in theClassNames
property.(The software treats string arrays as cell arrays of character vectors.)If you convert a traditionally trained model to create
Mdl
, theClassNames
property is specified by the corresponding property of the traditionally trained model.
Data Types:single
|double
|logical
|char
|string
|cell
|categorical
NumPredictors
—Number of predictor variables
nonnegative numeric scalar
This property is read-only.
Number of predictor variables, specified as a nonnegative numeric scalar.
The defaultNumPredictors
value depends on how you create the model:
If you convert a traditionally trained model to create
Mdl
,NumPredictors
is specified by the corresponding property of the traditionally trained model.If you create
Mdl
by callingincrementalClassificationNaiveBayes
directly, you can specifyNumPredictors
by using name-value argument syntax. If you do not specify the value, then the default value is0
, and incremental fitting functions inferNumPredictors
from the predictor data during training.
Data Types:double
NumTrainingObservations
—Number of observations fit to incremental model
0
(default) |nonnegative numeric scalar
This property is read-only.
Number of observations fit to the incremental modelMdl
, specified as a nonnegative numeric scalar.NumTrainingObservations
increases when you passMdl
and training data tofit
orupdateMetricsAndFit
。
Note
If you convert a traditionally trained model to createMdl
,incrementalClassificationNaiveBayes
does not add the number of observations fit to the traditionally trained model toNumTrainingObservations
。
Data Types:double
Prior
—Prior class probabilities
numeric vector|'empirical'
|'uniform'
This property is read-only.
Prior class probabilities, specified as'empirical'
,'uniform'
, or a numeric vector.incrementalClassificationNaiveBayes
stores thePrior
value as a numeric vector.
Value | Description |
---|---|
'empirical' |
Incremental learning functions infer prior class probabilities from the observed class relative frequencies in the response data during incremental training. |
'uniform' |
For each class, the prior probability is 1/K, whereKis the number of classes. |
numeric vector | Custom, normalized prior probabilities. The order of the elements ofPrior corresponds to the elements of theClassNames property. |
The defaultPrior
value depends on how you create the model:
If you convert a traditionally trained model to create
Mdl
,Prior
is specified by the corresponding property of the traditionally trained model.Otherwise, the default value of
Prior
is'empirical'
。
Data Types:single
|double
|char
|string
ScoreTransform
—Score transformation function
'none'
(default) |string scalar|character vector|function handle
This property is read-only.
Score transformation function describing how incremental learning functions transform raw response values, specified as a character vector, string scalar, or function handle.incrementalClassificationNaiveBayes
stores the specified value as a character vector or function handle.
This table describes the available built-in functions for score transformation.
Value | Description |
---|---|
"doublelogit" |
1/(1 +e–2x) |
"invlogit" |
log(x/ (1 –x)) |
"ismax" |
Sets the score for the class with the largest score to 1, and sets the scores for all other classes to 0 |
"logit" |
1/(1 +e–x) |
"none" or"identity" |
x(no transformation) |
"sign" |
–1 forx< 0 0 forx= 0 1 forx> 0 |
"symmetric" |
2x– 1 |
"symmetricismax" |
Sets the score for the class with the largest score to 1, and sets the scores for all other classes to –1 |
"symmetriclogit" |
2/(1 +e–x) – 1 |
For a MATLAB®function or a function that you define, enter its function handle; for example,@function
, where:
function
accepts ann-by-Kmatrix (the original scores) and returns a matrix of the same size (the transformed scores).nis the number of observations, and rowjof the matrix contains the class scores of observationj。
Kis the number of classes, and columnkis class
ClassNames(
。k
)
The defaultScoreTransform
value depends on how you create the model:
If you convert a traditionally trained model to create
Mdl
,ScoreTransform
is specified by the corresponding property of the traditionally trained model.The default
'none'
specifies returning posterior class probabilities.
Data Types:char
|function_handle
|string
Training Parameters
DistributionNames
—Predictor distributions
"mn"
|"mvmn"
|"normal"
|string vector|cell vector of character vectors
Predictor distributions P(x|ck), whereckis classClassNames(
, specified as a character vector or string scalar, or a 1-by-k
)NumPredictors
string vector or cell vector of character vectors with values from the table.
Value | Description |
---|---|
"mn" |
Multinomial distribution. If you specify"mn" , then all features are components of a multinomial distribution (for example, abag-of-tokensmodel). Therefore, you cannot include"mn" as an element of a string array or a cell array of character vectors. For details, seeEstimated Probability for Multinomial Distribution。 |
"mvmn" |
Multivariate multinomial distribution. For details, seeEstimated Probability for Multivariate Multinomial Distribution。 |
"normal" |
Normal distribution. For details, seeNormal Distribution Estimators |
If you specify a character vector or string scalar, then the software models all the features using that distribution. If you specify a 1-by-NumPredictors
string vector or cell vector of character vectors, the software models featurejusing the distribution in elementjof the vector.
By default, the software sets all predictors specified as categorical predictors (see theCategoricalPredictors
property) to'mvmn'
。Otherwise, the default distribution is'normal'
。
incrementalClassificationNaiveBayes
stores the value as a character vector or cell vector of character vectors.
Example:“DistributionNames”、“锰”
specifies that the joint conditional distribution of all predictor variables is multinomial.
Example:'DistributionNames',["normal" "mvmn" "normal"]
specifies that the first and third predictor variables are normally distributed and the second variable is categorical with a multivariate multinomial distribution.
Data Types:char
|string
|cell
DistributionParameters
—Distribution parameter estimates
cell array
This property is read-only.
Distribution parameter estimates, specified as a cell array.DistributionParameters
is aK-by-NumPredictors
cell array, whereKis the number of classes and cell (k
,j
) contains the distribution parameter estimates for instances of predictorj
in classk
。The order of the rows corresponds to the order of the classes in the propertyClassNames
, and the order of the columns corresponds to the order of the predictors in the predictor data.
If classk
has no observations for predictorj
, thenDistributionParameters{
is empty (k
,j
}[]
).
The elements ofDistributionParameters
depend on the distributions of the predictors. This table describes the values inDistributionParameters{
。k
,j
}
Distribution of Predictorj | Value of Cell Array for Predictorj and Classk |
---|---|
'mn' |
A scalar representing the probability that tokenjappears in classk。为依据ails, seeEstimated Probability for Multinomial Distribution。 |
'mvmn' |
A numeric vector containing the probabilities for each possible level of predictorjin classk。The software orders the probabilities by the sorted order of all unique levels of predictorj(stored in the propertyCategoricalLevels ). For more details, seeEstimated Probability for Multivariate Multinomial Distribution。 |
'normal' |
A 2-by-1 numeric vector. The first element is the weighted sample mean and the second element is the weighted sample standard deviation. For more details, seeNormal Distribution Estimators。 |
Note
Unlikefitcnb
, incremental fitting functions order the levels of a predictor as the functions experience them during training. For example, suppose predictorjis categorical with multivariate multinomial distribution. The order of the levels inCategoricalLevels{j}
and, consequently, the order of the level probabilities in each cell ofDistributionParameters{:,j}
returned by incremental fitting functions can differ from the order returned byfitcnb
for the same training data set.
Data Types:cell
性能指标参数
IsWarm
—Flag indicating whether model tracks performance metrics
false
or0
|true
or1
Flag indicating whether the incremental model tracks performance metrics, specified as logical0
(false
) or1
(true
).
The incremental modelMdl
is温暖的(IsWarm
becomestrue
) when incremental fitting functions perform both of these actions:
Fit the incremental model to
MetricsWarmupPeriod
observations.Process
MaxNumClasses
classes or all class names specified by theClassNames
name-value argument.
Value | Description |
---|---|
true or1 |
The incremental modelMdl is warm. Consequently,updateMetrics andupdateMetricsAndFit track performance metrics in theMetrics property ofMdl 。 |
false or0 |
updateMetrics andupdateMetricsAndFit do not track performance metrics. |
Data Types:logical
Metrics
—Model performance metrics
table
This property is read-only.
Model performance metrics updated during incremental learning byupdateMetrics
andupdateMetricsAndFit
, specified as a table with two columns andmrows, wheremis the number of metrics specified by theMetrics
name-value argument.
The columns ofMetrics
are labeledCumulative
andWindow
。
Cumulative
: Elementj
is the model performance, as measured by metricj
, from the time the model became warm (IsWarm
is1
).Window
: Elementj
is the model performance, as measured by metricj
, evaluated over all observations within the window specified by theMetricsWindowSize
property. The software updatesWindow
after it processesMetricsWindowSize
observations.
行标记指定的指标。为依据ails, see theMetrics
name-value argument ofincrementalLearner
orincrementalClassificationNaiveBayes
。
Data Types:table
MetricsWarmupPeriod
—Number of observations fit before tracking performance metrics
nonnegative integer
This property is read-only.
Number of observations the incremental model must be fit to before it tracks performance metrics in itsMetrics
property, specified as a nonnegative integer.
The defaultMetricsWarmupPeriod
value depends on how you create the model:
If you convert a traditionally trained model to create
Mdl
, theMetricsWarmupPeriod
name-value argument of theincrementalLearner
function sets this property. The default value of the argument is0
。Otherwise, the default value is
1000
。
For more details, seePerformance Metrics。
Data Types:single
|double
MetricsWindowSize
—Number of observations to use to compute window performance metrics
positive integer
This property is read-only.
Number of observations to use to compute window performance metrics, specified as a positive integer.
The defaultMetricsWindowSize
value depends on how you create the model:
If you convert a traditionally trained model to create
Mdl
, theMetricsWindowSize
name-value argument of theincrementalLearner
function sets this property. The default value of the argument is200
。Otherwise, the default value is
200
。
For more details on performance metrics options, seePerformance Metrics。
Data Types:single
|double
Object Functions
fit |
Train naive Bayes classification model for incremental learning |
updateMetricsAndFit |
Update performance metrics in naive Bayes incremental learning classification model given new data and train model |
updateMetrics |
Update performance metrics in naive Bayes incremental learning classification model given new data |
logp |
Log unconditional probability density of naive Bayes classification model for incremental learning |
loss |
Loss of naive Bayes incremental learning classification model on batch of data |
predict |
Predict responses for new observations from naive Bayes incremental learning classification model |
perObservationLoss |
Per observation classification error of model for incremental learning |
reset |
Reset incremental classification model |
Examples
Create Incremental Learner with Little Prior Information
To create a naive Bayes classification model for incremental learning, you must specify the maximum number of classes that you expect the model to process ('MaxNumClasses'
name-value argument). As you fit the model to incoming batches of data by using an incremental fitting function, the model collects new classes in itsClassNames
property. If the specified maximum number of classes is inaccurate, one of the following occurs:
Before an incremental fitting function processes the expected maximum number of classes, the model is cold. Consequently, the
updateMetrics
andupdateMetricsAndFit
functions do not measure performance metrics.If the number of classes exceeds the maximum expected, the incremental fitting function issues an error.
This example shows how to create a naive Bayes classification model for incremental learning when the only information you specify is the expected maximum number of classes in the data. Also, the example illustrates the consequences when incremental fitting functions process all expected classes early and late in the sample.
For this example, consider training a device to predict whether a subject is sitting, standing, walking, running, or dancing based on biometric data measured on the subject. Therefore, the device has a maximum of 5 classes from which to choose.
Process Expected Maximum Number of Classes Early in Sample
Create an incremental naive Bayes model for multiclass learning. Specify a maximum of 5 classes in the data.
MdlEarly = incrementalClassificationNaiveBayes('MaxNumClasses',5)
MdlEarly = incrementalClassificationNaiveBayes IsWarm: 0 Metrics: [1x2 table] ClassNames: [1x0 double] ScoreTransform: 'none' DistributionNames: 'normal' DistributionParameters: {} Properties, Methods
MdlEarly
is anincrementalClassificationNaiveBayes
model object. All its properties are read-only.
MdlEarly
must be fit to data before you can use it to perform any other operations.
Load the human activity data set. Randomly shuffle the data.
loadhumanactivityn = numel(actid); rng(1);% For reproducibilityidx = randsample(n,n); X = feat(idx,:); Y = actid(idx);
为依据ails on the data set, enterDescription
at the command line.
Fit the incremental model to the training data by using theupdateMetricsAndFit
function. Simulate a data stream by processing chunks of 50 observations at a time. At each iteration:
Process 50 observations.
Overwrite the previous incremental model with a new one fitted to the incoming observations.
Store the mean of the first predictor in the first class , the cumulative metrics, and the window metrics to see how they evolve during incremental learning.
% PreallocationnumObsPerChunk = 50; nchunk = floor(n/numObsPerChunk); mc = array2table(zeros(nchunk,2),'VariableNames',["Cumulative""Window"]); mu1 = zeros(nchunk,1);% Incremental learningforj = 1:nchunk ibegin = min(n,numObsPerChunk*(j-1) + 1); iend = min(n,numObsPerChunk*j); idx = ibegin:iend; MdlEarly = updateMetricsAndFit(MdlEarly,X(idx,:),Y(idx)); mc{j,:} = MdlEarly.Metrics{"MinimalCost",:}; mu1(j + 1) = MdlEarly.DistributionParameters{1,1}(1);end
MdlEarly
is anincrementalClassificationNaiveBayes
model object trained on all the data in the stream. During incremental learning and after the model is warmed up,updateMetricsAndFit
checks the performance of the model on the incoming observations, and then fits the model to those observations.
To see how the performance metrics and evolve during training, plot them on separate tiles.
t = tiledlayout(2,1); nexttile plot(mu1) ylabel('\mu_{11}') xlim([0 nchunk]) nexttile h = plot(mc.Variables); xlim([0 nchunk]) ylabel('Minimal Cost') xline(MdlEarly.MetricsWarmupPeriod/numObsPerChunk,'r-.') legend(h,mc.Properties.VariableNames) xlabel(t,'Iteration')
The plots indicate thatupdateMetricsAndFit
performs the following actions:
Fit during all incremental learning iterations.
Compute the performance metrics after the metrics warm-up period (red vertical line) only.
Compute the cumulative metrics during each iteration.
Compute the window metrics after processing 200 observations (4 iterations).
Process Expected Maximum Number of Classes Late in Sample
Create a different naive Bayes model for incremental learning for the objective.
MdlLate = incrementalClassificationNaiveBayes('MaxNumClasses',5)
MdlLate = incrementalClassificationNaiveBayes IsWarm: 0 Metrics: [1x2 table] ClassNames: [1x0 double] ScoreTransform: 'none' DistributionNames: 'normal' DistributionParameters: {} Properties, Methods
Move all observations labeled with class 5 to the end of the sample.
idx5 = Y == 5; Xnew = [X(~idx5,:); X(idx5,:)]; Ynew = [Y(~idx5) ;Y(idx5)];
Fit the incremental model and plot the results.
mcnew = array2table(zeros(nchunk,2),'VariableNames',["Cumulative""Window"]); mu1new = zeros(nchunk,1);forj = 1:nchunk ibegin = min(n,numObsPerChunk*(j-1) + 1); iend = min(n,numObsPerChunk*j); idx = ibegin:iend; MdlLate = updateMetricsAndFit(MdlLate,Xnew(idx,:),Ynew(idx)); mcnew{j,:} = MdlLate.Metrics{"MinimalCost",:}; mu1new(j + 1) = MdlLate.DistributionParameters{1,1}(1);endt = tiledlayout(2,1); nexttile plot(mu1new) ylabel('\mu_{11}') xlim([0 nchunk]) nexttile h = plot(mcnew.Variables); xlim([0 nchunk]); ylabel('Minimal Cost') xline(MdlLate.MetricsWarmupPeriod/numObsPerChunk,'r-.') xline(sum(~idx5)/numObsPerChunk,'g-.') legend(h,mcnew.Properties.VariableNames,'Location','best') xlabel(t,'Iteration')
TheupdateMetricsAndFit
function trains the model throughout incremental learning, but the function starts tracking performance metrics only after the model is fit to all expected number of classes (the green vertical line in the bottom tile).
Specify All Class Names
Create an incremental naive Bayes model when you know all the class names in the data.
Consider training a device to predict whether a subject is sitting, standing, walking, running, or dancing based on biometric data measured on the subject. The class names map 1 through 5 to an activity.
Create an incremental naive Bayes model for multiclass learning. Specify the class names.
classnames = 1:5; Mdl = incrementalClassificationNaiveBayes('ClassNames',classnames)
Mdl = incrementalClassificationNaiveBayes IsWarm: 0 Metrics: [1x2 table] ClassNames: [1 2 3 4 5] ScoreTransform: 'none' DistributionNames: 'normal' DistributionParameters: {5x0 cell} Properties, Methods
Mdl
is anincrementalClassificationNaiveBayes
model object. All its properties are read-only.
Mdl
must be fit to data before you can use it to perform any other operations.
Load the human activity data set. Randomly shuffle the data.
loadhumanactivityn = numel(actid); rng(1);% For reproducibilityidx = randsample(n,n); X = feat(idx,:); Y = actid(idx);
为依据ails on the data set, enterDescription
at the command line.
Fit the incremental model to the training data by using theupdateMetricsAndFit
function. Simulate a data stream by processing chunks of 50 observations at a time. At each iteration:
Process 50 observations.
Overwrite the previous incremental model with a new one fitted to the incoming observations.
% PreallocationnumObsPerChunk = 50; nchunk = floor(n/numObsPerChunk);% Incremental learningforj = 1:nchunk ibegin = min(n,numObsPerChunk*(j-1) + 1); iend = min(n,numObsPerChunk*j); idx = ibegin:iend; Mdl = updateMetricsAndFit(Mdl,X(idx,:),Y(idx));end
Configure Incremental Learning Options
In addition to specifying the maximum number of class names, prepare an incremental naive Bayes learner by specifying a metrics warm-up period, during which theupdateMetricsAndFit
function fits only the model. Specify a metrics window size of 500 observations.
Load the human activity data set. Randomly shuffle the data.
loadhumanactivityn = numel(actid); rng(1);% For reproducibilityidx = randsample(n,n); X = feat(idx,:); Y = actid(idx);
The class names map 1 through 5 to an activity—sitting, standing, walking, running, or dancing, respectively—based on biometric data measured on the subject. For details on the data set, enterDescription
at the command line.
Create an incremental naive Bayes model for multiclass learning. Configure the model as follows:
Specify a metrics warm-up period of 5000 observations.
Specify a metrics window size of 500 observations.
Double the penalty to the classifier when it mistakenly classifies class 2.
Track the classification error and minimal cost to measure the performance of the model. You do not have to specify
'mincost'
forMetrics
becauseincrementalClassificationNaiveBayes
always tracks this metric.
C =的眼睛(5)- (5);C (2,[1 3 4 5]) = 2; Mdl = incrementalClassificationNaiveBayes('ClassNames',1:5,。..'MetricsWarmupPeriod',5000,'MetricsWindowSize',500,。..'Cost',C,'Metrics','classiferror')
Mdl = incrementalClassificationNaiveBayes IsWarm: 0 Metrics: [2x2 table] ClassNames: [1 2 3 4 5] ScoreTransform: 'none' DistributionNames: 'normal' DistributionParameters: {5x0 cell} Properties, Methods
Mdl
is anincrementalClassificationNaiveBayes
model object configured for incremental learning.
适合增量模型的数据by using theupdateMetricsAndFit
function. At each iteration:
Simulate a data stream by processing a chunk of 50 observations.
Overwrite the previous incremental model with a new one fitted to the incoming observations.
Store the standard deviation of the first predictor variable in the first class , the cumulative metrics, and the window metrics to see how they evolve during incremental learning.
% PreallocationnumObsPerChunk = 50; nchunk = floor(n/numObsPerChunk); ce = array2table(zeros(nchunk,2),'VariableNames',["Cumulative""Window"]); mc = array2table(zeros(nchunk,2),'VariableNames',["Cumulative""Window"]); sigma11 = zeros(nchunk,1);% Incremental fittingforj = 1:nchunk ibegin = min(n,numObsPerChunk*(j-1) + 1); iend = min(n,numObsPerChunk*j); idx = ibegin:iend; Mdl = updateMetricsAndFit(Mdl,X(idx,:),Y(idx)); ce{j,:} = Mdl.Metrics{"ClassificationError",:}; mc{j,:} = Mdl.Metrics{"MinimalCost",:}; sigma11(j + 1) = Mdl.DistributionParameters{1,1}(2);end
Mdl
is anincrementalClassificationNaiveBayes
model object trained on all the data in the stream. During incremental learning and after the model is warmed up,updateMetricsAndFit
checks the performance of the model on the incoming observations, and then fits the model to those observations.
To see how the performance metrics and evolve during training, plot them on separate tiles.
tiledlayout(2,2) nexttile plot(sigma11) ylabel('\sigma_{11}') xlim([0 nchunk]); xline(Mdl.MetricsWarmupPeriod/numObsPerChunk,'r-.') xlabel('Iteration') nexttile h = plot(ce.Variables); xlim([0 nchunk]) ylabel('Classification Error') xline(Mdl.MetricsWarmupPeriod/numObsPerChunk,'r-.') legend(h,ce.Properties.VariableNames) xlabel('Iteration') nexttile h = plot(mc.Variables); xlim([0 nchunk]); ylabel('Minimal Cost') xline(Mdl.MetricsWarmupPeriod/numObsPerChunk,'r-.') legend(h,mc.Properties.VariableNames) xlabel('Iteration')
The plots indicate thatupdateMetricsAndFit
performs the following actions:
Fit during all incremental learning iterations.
Compute the performance metrics after the metrics warm-up period (red vertical line) only.
Compute the cumulative metrics during each iteration.
Compute the window metrics after processing 500 observations (10 iterations).
Convert Traditionally Trained Model to Incremental Learner
Train a naive Bayes model for multiclass classification by usingfitcnb
。Then, convert the model to an incremental learner, track its performance, and fit the model to streaming data. Carry over training options from traditional to incremental learning.
Load and Preprocess Data
Load the human activity data set. Randomly shuffle the data.
loadhumanactivityrng(1)% For reproducibilityn = numel(actid); idx = randsample(n,n); X = feat(idx,:); Y = actid(idx);
为依据ails on the data set, enterDescription
at the command line.
Suppose that the data collected when the subject was idle (Y
<= 2) has double the quality than when the subject was moving. Create a weight variable that attributes 2 to observations collected from an idle subject, and 1 to a moving subject.
W = ones(n,1) + (Y <= 2);
Train Naive Bayes Model
Fit a naive Bayes model for multiclass classification to a random sample of half the data.
idxtt = randsample([true false],n,true); TTMdl = fitcnb(X(idxtt,:),Y(idxtt),'Weights',W(idxtt))
TTMdl = ClassificationNaiveBayes ResponseName: 'Y' CategoricalPredictors: [] ClassNames: [1 2 3 4 5] ScoreTransform: 'none' NumObservations: 12053 DistributionNames: {1x60 cell} DistributionParameters: {5x60 cell} Properties, Methods
TTMdl
is aClassificationNaiveBayes
model object representing a traditionally trained naive Bayes model.
Convert Trained Model
Convert the traditionally trained naive Bayes model to a naive Bayes classification model for incremental learning.
IncrementalMdl = incrementalLearner(TTMdl)
IncrementalMdl = incrementalClassificationNaiveBayes IsWarm: 1 Metrics: [1x2 table] ClassNames: [1 2 3 4 5] ScoreTransform: 'none' DistributionNames: {1x60 cell} DistributionParameters: {5x60 cell} Properties, Methods
Separately Track Performance Metrics and Fit Model
Perform incremental learning on the rest of the data by using theupdateMetrics
andfit
functions. Simulate a data stream by processing 50 observations at a time. At each iteration:
Call
updateMetrics
to update the cumulative and window classification error of the model given the incoming chunk of observations. Overwrite the previous incremental model to update the losses in theMetrics
property. Note that the function does not fit the model to the chunk of data—the chunk is "new" data for the model. Specify the observation weights.Call
fit
to fit the model to the incoming chunk of observations. Overwrite the previous incremental model to update the model parameters. Specify the observation weights.Store the minimal cost and mean of the first predictor variable of the first class 。
% Preallocationidxil = ~idxtt; nil = sum(idxil); numObsPerChunk = 50; nchunk = floor(nil/numObsPerChunk); mc = array2table(zeros(nchunk,2),'VariableNames',["Cumulative""Window"]); mu11 = [IncrementalMdl.DistributionParameters{1,1}(1); zeros(nchunk,1)]; Xil = X(idxil,:); Yil = Y(idxil); Wil = W(idxil);% Incremental fittingforj = 1:nchunk ibegin = min(nil,numObsPerChunk*(j-1) + 1); iend = min(nil,numObsPerChunk*j); idx = ibegin:iend; IncrementalMdl = updateMetrics(IncrementalMdl,Xil(idx,:),Yil(idx),。..'Weights',Wil(idx)); mc{j,:} = IncrementalMdl.Metrics{"MinimalCost",:}; IncrementalMdl = fit(IncrementalMdl,Xil(idx,:),Yil(idx),'Weights',Wil(idx)); mu11(j+1) = IncrementalMdl.DistributionParameters{1,1}(1);end
IncrementalMdl
is anincrementalClassificationNaiveBayes
model object trained on all the data in the stream.
Alternatively, you can useupdateMetricsAndFit
to update the performance metrics of the model given a new chunk of data, and then fit the model to the data.
Plot a trace plot of the performance metrics and 。
t = tiledlayout(2,1); nexttile h = plot(mc.Variables); xlim([0 nchunk]) ylabel('Minimal Cost') legend(h,mc.Properties.VariableNames) nexttile plot(mu11) ylabel('\mu_{11}') xlim([0 nchunk]) xlabel(t,'Iteration')
The cumulative loss levels quickly and is stable, whereas the window loss jumps throughout the training.
changes abruptly at first, then gradually levels off asfit
processes more chunks.
More About
Bag-of-Tokens Model
In the bag-of-tokens model, the value of predictorjis the nonnegative number of occurrences of tokenjin the observation. The number of categories (bins) in the multinomial model is the number of distinct tokens (number of predictors).
Incremental Learning
Incremental learning, oronline learning,是机器学习的一个分支关心processing incoming data from a data stream, possibly given little to no knowledge of the distribution of the predictor variables, aspects of the prediction or objective function (including tuning parameter values), or whether the observations are labeled. Incremental learning differs from traditional machine learning, where enough labeled data is available to fit to a model, perform cross-validation to tune hyperparameters, and infer the predictor distribution.
Given incoming observations, an incremental learning model processes data in any of the following ways, but usually in this order:
Predict labels.
Measure the predictive performance.
Check for structural breaks or drift in the model.
Fit the model to the incoming observations.
For more details, seeIncremental Learning Overview。
Algorithms
Performance Metrics
The
updateMetrics
andupdateMetricsAndFit
functions track model performance metrics (Metrics
) from new data only when the incremental model is温暖的(IsWarm
property istrue
).If you create an incremental model by using
incrementalLearner
andMetricsWarmupPeriod
is 0 (default forincrementalLearner
), the model is warm at creation.Otherwise, an incremental model becomes warm after
fit
orupdateMetricsAndFit
performs both of these actions:Fit the incremental model to
MetricsWarmupPeriod
observations, which is themetrics warm-up period。Fit the incremental model to all expected classes (see the
MaxNumClasses
andClassNames
arguments ofincrementalClassificationNaiveBayes
).
The
Metrics
property of the incremental model stores two forms of each performance metric as variables (columns) of a table,Cumulative
andWindow
, with individual metrics in rows. When the incremental model is warm,updateMetrics
andupdateMetricsAndFit
update the metrics at the following frequencies:Cumulative
— The functions compute cumulative metrics since the start of model performance tracking. The functions update metrics every time you call the functions and base the calculation on the entire supplied data set.Window
— The functions compute metrics based on all observations within a window determined by theMetricsWindowSize
name-value argument.MetricsWindowSize
also determines the frequency at which the software updatesWindow
metrics. For example, ifMetricsWindowSize
is 20, the functions compute metrics based on the last 20 observations in the supplied data (X((end – 20 + 1):end,:)
andY((end – 20 + 1):end)
).Incremental functions that track performance metrics within a window use the following process:
Store a buffer of length
MetricsWindowSize
for each specified metric, and store a buffer of observation weights.Populate elements of the metrics buffer with the model performance based on batches of incoming observations, and store corresponding observation weights in the weights buffer.
When the buffer is full, overwrite
Mdl.Metrics.Window
with the weighted average performance in the metrics window. If the buffer overfills when the function processes a batch of observations, the latest incomingMetricsWindowSize
observations enter the buffer, and the earliest observations are removed from the buffer. For example, supposeMetricsWindowSize
is 20, the metrics buffer has 10 values from a previously processed batch, and 15 values are incoming. To compose the length 20 window, the functions use the measurements from the 15 incoming observations and the latest 5 measurements from the previous batch.
The software omits an observation with a
NaN
score when computing theCumulative
andWindow
performance metric values.
Normal Distribution Estimators
If predictor variablej
has a conditional normal distribution (see theDistributionNames
property), the software fits the distribution to the data by computing the class-specific weighted mean and the biased (maximum likelihood) estimate of the weighted standard deviation. For each classk:
The weighted mean of predictorjis
wherewiis the weight for observationi。软件可实现重量在一个类uch that they sum to the prior probability for that class.
The unbiased estimator of the weighted standard deviation of predictorjis
Estimated Probability for Multinomial Distribution
If all predictor variables compose a conditional multinomial distribution (see theDistributionNames
property), the software fits the distribution using theBag-of-Tokens Model。The software stores the probability that tokenj
appears in classk
in the propertyDistributionParameters{
。With additive smoothing[1], the estimated probability isk
,j
}
where:
which is the weighted number of occurrences of tokenjin classk。
nkis the number of observations in classk。
is the weight for observationi。软件可实现重量在一个类o that they sum to the prior probability for that class.
which is the total weighted number of occurrences of all tokens in classk。
Estimated Probability for Multivariate Multinomial Distribution
If predictor variablej
has a conditional multivariate multinomial distribution (see theDistributionNames
property), the software follows this procedure:
The software collects a list of the unique levels, stores the sorted list in
CategoricalLevels
, and considers each level a bin. Each combination of predictor and class is a separate, independent multinomial random variable.For each classk, the software counts instances of each categorical level using the list stored in
CategoricalLevels{
。j
}The software stores the probability that predictor
j
in classk
has levelLin the propertyDistributionParameters{
, for all levels ink
,j
}CategoricalLevels{
。With additive smoothing[1], the estimated probability isj
}where:
which is the weighted number of observations for which predictorjequalsLin classk。
nkis the number of observations in classk。
ifxij=L, and 0 otherwise.
is the weight for observationi。软件可实现重量在一个类o that they sum to the prior probability for that class.
mjis the number of distinct levels in predictorj。
mkis the weighted number of observations in classk。
References
[1] Manning, Christopher D., Prabhakar Raghavan, and Hinrich Schütze.Introduction to Information Retrieval, NY: Cambridge University Press, 2008.
Version History
Introduced in R2021aR2021b:Naive Bayes incremental fitting functions compute biased (maximum likelihood) standard deviations for conditionally normal predictor variables
Starting in R2021b, naive Bayes incremental fitting functionsfit
andupdateMetricsAndFit
compute biased (maximum likelihood) estimates of the weighted standard deviations for conditionally normal predictor variables during training. In other words, for each classk, incremental fitting functions normalize the sum of square weighted deviations of the conditionally normal predictorxjby the sum of the weights in classk。Before R2021b, naive Bayes incremental fitting functions computed the unbiased standard deviation, likefitcnb
。The currently returned weighted standard deviation estimates differ from those computed before R2021b by a factor of
The factor approaches 1 as the sample size increases.
See Also
Functions
Open Example
You have a modified version of this example. Do you want to open this example with your edits?
MATLAB Command
You clicked a link that corresponds to this MATLAB command:
Run the command by entering it in the MATLAB Command Window. Web browsers do not support MATLAB commands.
Select a Web Site
Choose a web site to get translated content where available and see local events and offers. Based on your location, we recommend that you select:。
You can also select a web site from the following list:
How to Get Best Site Performance
Select the China site (in Chinese or English) for best site performance. Other MathWorks country sites are not optimized for visits from your location.
Americas
- América Latina(Español)
- Canada(English)
- United States(English)
Europe
- Belgium(English)
- Denmark(English)
- Deutschland(Deutsch)
- España(Español)
- Finland(English)
- France(Français)
- Ireland(English)
- Italia(Italiano)
- Luxembourg(English)
- Netherlands(English)
- Norway(English)
- Österreich(Deutsch)
- Portugal(English)
- Sweden(English)
- Switzerland
- United Kingdom(English)