# FeatureTransformer

## Description

A `FeatureTransformer`

object contains information about the
feature transformations generated from a training data set. To better understand the generated
features, you can use the `describe`

object
function. To apply the same training set feature transformations to a test set, you can use
the `transform`

object
function.

## Creation

Create a `FeatureTransformer`

object by using the `gencfeatures`

or
`genrfeatures`

function.

## Properties

`Type`

— Type of model

`'classification'`

| `'regression'`

This property is read-only.

Type of model, returned as `'classification'`

or
`'regression'`

.

`TargetLearner`

— Expected learner type

`'linear'`

| `'bag'`

| `'gaussian-svm'`

This property is read-only.

Expected learner type, returned as `'linear'`

,
`'bag'`

, or `'gaussian-svm'`

. The software creates
and selects new features assuming that they will be used to train a linear model, a
bagged ensemble, or a support vector machine (SVM) model with a Gaussian kernel,
respectively.

`NumEngineeredFeatures`

— Number of engineered features

nonnegative scalar

This property is read-only.

Number of engineered features stored in `FeatureTransformer`

,
returned as a nonnegative scalar.

**Data Types: **`double`

`NumOriginalFeatures`

— Number of original features

nonnegative scalar

This property is read-only.

Number of original features stored in `FeatureTransformer`

, returned
as a nonnegative scalar.

**Data Types: **`double`

`TotalNumFeatures`

— Total number of features

nonnegative scalar

This property is read-only.

Total number of features stored in `FeatureTransformer`

, returned as
a nonnegative scalar. `TotalNumFeatures`

equals the sum of
`NumEngineeredFeatures`

and
`NumOriginalFeatures`

.

**Data Types: **`double`

## Object Functions

## Examples

### Generate and Inspect Features for Regression Problem

Generate features from a table of predictor data by using `genrfeatures`

. Inspect the generated features by using the `describe`

object function.

Read power outage data into the workspace as a table. Remove observations with missing values, and display the first few rows of the table.

```
outages = readtable("outages.csv");
Tbl = rmmissing(outages);
head(Tbl)
```

Region OutageTime Loss Customers RestorationTime Cause _____________ ____________________ ______ __________ ____________________ ___________________ {'SouthWest'} 01-Feb-2002 12:18:00 458.98 1.8202e+06 07-Feb-2002 16:50:00 {'winter storm' } {'SouthEast'} 07-Feb-2003 21:15:00 289.4 1.4294e+05 17-Feb-2003 08:14:00 {'winter storm' } {'West' } 06-Apr-2004 05:44:00 434.81 3.4037e+05 06-Apr-2004 06:10:00 {'equipment fault'} {'MidWest' } 16-Mar-2002 06:18:00 186.44 2.1275e+05 18-Mar-2002 23:23:00 {'severe storm' } {'West' } 18-Jun-2003 02:49:00 0 0 18-Jun-2003 10:54:00 {'attack' } {'NorthEast'} 16-Jul-2003 16:23:00 239.93 49434 17-Jul-2003 01:12:00 {'fire' } {'MidWest' } 27-Sep-2004 11:09:00 286.72 66104 27-Sep-2004 16:37:00 {'equipment fault'} {'SouthEast'} 05-Sep-2004 17:48:00 73.387 36073 05-Sep-2004 20:46:00 {'equipment fault'}

Some of the variables, such as `OutageTime`

and `RestorationTime`

, have data types that are not supported by regression model training functions like `fitrensemble`

.

Generate 25 features from the predictors in `Tbl`

that can be used to train a bagged ensemble. Specify the `Loss`

table variable as the response.

rng("default") % For reproducibility Transformer = genrfeatures(Tbl,"Loss",25,TargetLearner="bag")

Transformer = FeatureTransformer with properties: Type: 'regression' TargetLearner: 'bag' NumEngineeredFeatures: 22 NumOriginalFeatures: 3 TotalNumFeatures: 25

The `Transformer`

object contains the information about the generated features and the transformations used to create them.

To better understand the generated features, use the `describe`

object function.

Info = describe(Transformer)

`Info=`*25×4 table*
Type IsOriginal InputVariables Transformations
___________ __________ ___________________________ ___________________________________________________________________
c(Region) Categorical true Region "Variable of type categorical converted from a cell data type"
Customers Numeric true Customers ""
c(Cause) Categorical true Cause "Variable of type categorical converted from a cell data type"
kmd2 Numeric false Customers "Euclidean distance to centroid 2 (kmeans clustering with k = 10)"
kmd1 Numeric false Customers "Euclidean distance to centroid 1 (kmeans clustering with k = 10)"
kmd4 Numeric false Customers "Euclidean distance to centroid 4 (kmeans clustering with k = 10)"
kmd5 Numeric false Customers "Euclidean distance to centroid 5 (kmeans clustering with k = 10)"
kmd9 Numeric false Customers "Euclidean distance to centroid 9 (kmeans clustering with k = 10)"
cos(Customers) Numeric false Customers "cos( )"
RestorationTime-OutageTime Numeric false OutageTime, RestorationTime "Elapsed time in seconds between OutageTime and RestorationTime"
kmd6 Numeric false Customers "Euclidean distance to centroid 6 (kmeans clustering with k = 10)"
kmi Categorical false Customers "Cluster index encoding (kmeans clustering with k = 10)"
kmd7 Numeric false Customers "Euclidean distance to centroid 7 (kmeans clustering with k = 10)"
kmd3 Numeric false Customers "Euclidean distance to centroid 3 (kmeans clustering with k = 10)"
kmd10 Numeric false Customers "Euclidean distance to centroid 10 (kmeans clustering with k = 10)"
hour(RestorationTime) Numeric false RestorationTime "Hour of the day"
⋮

The first three generated features are original to `Tbl`

, although the software converts the original `Region`

and `Cause`

variables to `categorical`

variables.

`Info(1:3,:) % describe(Transformer,1:3)`

`ans=`*3×4 table*
Type IsOriginal InputVariables Transformations
___________ __________ ______________ ______________________________________________________________
c(Region) Categorical true Region "Variable of type categorical converted from a cell data type"
Customers Numeric true Customers ""
c(Cause) Categorical true Cause "Variable of type categorical converted from a cell data type"

The `OutageTime`

and `RestorationTime`

variables are not included as generated features because they are `datetime`

variables, which cannot be used to train a bagged ensemble model. However, the software derives some generated features from these variables, such as the tenth feature `RestorationTime-OutageTime`

.

`Info(10,:) % describe(Transformer,10)`

`ans=`*1×4 table*
Type IsOriginal InputVariables Transformations
_______ __________ ___________________________ ________________________________________________________________
RestorationTime-OutageTime Numeric false OutageTime, RestorationTime "Elapsed time in seconds between OutageTime and RestorationTime"

Some generated features are a combination of multiple transformations. For example, the software generates the nineteenth feature `fenc(c(Cause))`

by converting the `Cause`

variable to a categorical variable with 10 categories and then calculating the frequency of the categories.

`Info(19,:) % describe(Transformer,19)`

`ans=`*1×4 table*
Type IsOriginal InputVariables Transformations
_______ __________ ______________ ____________________________________________________________________________________________________________
fenc(c(Cause)) Numeric false Cause "Variable of type categorical converted from a cell data type -> Frequency encoding (number of levels = 10)"

### Train Model Using Subset of Generated Features

Train a linear classifier using only the numeric generated features returned by `gencfeatures`

.

Load the `patients`

data set. Create a table from a subset of the variables.

load patients Tbl = table(Age,Diastolic,Height,SelfAssessedHealthStatus, ... Smoker,Systolic,Weight,Gender);

Partition the data into training and test sets. Use approximately 70% of the observations as training data, and 30% of the observations as test data. Partition the data using `cvpartition`

.

```
rng("default")
c = cvpartition(Tbl.Gender,Holdout=0.30);
TrainTbl = Tbl(training(c),:);
TestTbl = Tbl(test(c),:);
```

Use the training data to generate 25 new features. Specify the minimum redundancy maximum relevance (MRMR) feature selection method for selecting new features.

Transformer = gencfeatures(TrainTbl,"Gender",25, ... FeatureSelectionMethod="mrmr")

Transformer = FeatureTransformer with properties: Type: 'classification' TargetLearner: 'linear' NumEngineeredFeatures: 23 NumOriginalFeatures: 2 TotalNumFeatures: 25

Inspect the generated features.

Info = describe(Transformer)

`Info=`*25×4 table*
Type IsOriginal InputVariables Transformations
___________ __________ ________________________ __________________________________________________________________________________________
zsc(Weight) Numeric true Weight "Standardization with z-score (mean = 153.1571, std = 26.8229)"
eb5(Weight) Categorical false Weight "Equal-width binning (number of bins = 5)"
c(SelfAssessedHealthStatus) Categorical true SelfAssessedHealthStatus "Variable of type categorical converted from a cell data type"
zsc(sqrt(Systolic)) Numeric false Systolic "sqrt( ) -> Standardization with z-score (mean = 11.086, std = 0.29694)"
zsc(sin(Systolic)) Numeric false Systolic "sin( ) -> Standardization with z-score (mean = -0.1303, std = 0.72575)"
zsc(Systolic./Weight) Numeric false Systolic, Weight "Systolic ./ Weight -> Standardization with z-score (mean = 0.82662, std = 0.14555)"
zsc(Age+Weight) Numeric false Age, Weight "Age + Weight -> Standardization with z-score (mean = 191.1143, std = 28.6976)"
zsc(Age./Weight) Numeric false Age, Weight "Age ./ Weight -> Standardization with z-score (mean = 0.25424, std = 0.062486)"
zsc(Diastolic.*Weight) Numeric false Diastolic, Weight "Diastolic .* Weight -> Standardization with z-score (mean = 12864.6857, std = 2731.1613)"
q6(Height) Categorical false Height "Equiprobable binning (number of bins = 6)"
zsc(Systolic+Weight) Numeric false Systolic, Weight "Systolic + Weight -> Standardization with z-score (mean = 276.1429, std = 28.7111)"
zsc(Diastolic-Weight) Numeric false Diastolic, Weight "Diastolic - Weight -> Standardization with z-score (mean = -69.4286, std = 26.2411)"
zsc(Age-Weight) Numeric false Age, Weight "Age - Weight -> Standardization with z-score (mean = -115.2, std = 27.0113)"
zsc(Height./Weight) Numeric false Height, Weight "Height ./ Weight -> Standardization with z-score (mean = 0.44797, std = 0.067992)"
zsc(Height.*Weight) Numeric false Height, Weight "Height .* Weight -> Standardization with z-score (mean = 10291.0714, std = 2111.9071)"
zsc(Diastolic+Weight) Numeric false Diastolic, Weight "Diastolic + Weight -> Standardization with z-score (mean = 236.8857, std = 29.2439)"
⋮

Transform the training and test sets, but retain only the numeric predictors.

```
numericIdx = (Info.Type == "Numeric");
NewTrainTbl = transform(Transformer,TrainTbl,numericIdx);
NewTestTbl = transform(Transformer,TestTbl,numericIdx);
```

Train a linear model using the transformed training data. Visualize the accuracy of the model's test set predictions by using a confusion matrix.

Mdl = fitclinear(NewTrainTbl,TrainTbl.Gender); testLabels = predict(Mdl,NewTestTbl); confusionchart(TestTbl.Gender,testLabels)

## Version History

**Introduced in R2021a**

## MATLAB 명령

다음 MATLAB 명령에 해당하는 링크를 클릭했습니다.

명령을 실행하려면 MATLAB 명령 창에 입력하십시오. 웹 브라우저는 MATLAB 명령을 지원하지 않습니다.

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)