# tSVMModel Generates an SVM-based classifier model that can be used by tPredict to classify given elements. tSVMModel applies the SVM algorithm to analyze feature vectors typically prepared and provided by tModelEncoder. It generates a binary classification model out of this analysis and writes this model in memory or in a file system supported by this component, such as HDFS or S3. In local mode, Apache Spark 3.0.x and later versions are supported. This component is not shipped with your Talend Studio by default. You need to install it using the Feature Manager. For more information, see [Installing features using the Feature Manager](https://help.qlik.com/talend/r/en-US/8.0/studio-user-guide/install-features-to-talend-studio). ## tSVMModel properties for Apache Spark Batch These properties are used to configure tSVMModel running in the Spark Batch Job framework. The Spark Batch tSVMModel component belongs to the Machine Learning family. This component is available in Talend Platform products with Big Data and in Talend Data Fabric. ## Basic settings | Properties | Description | | --- | --- | | Schema and Edit schema | A schema is a row description. It defines the number of fields
(columns) to be processed and passed on to the next component. When you create a Spark
Job, avoid the reserved word line when naming the
fields.

Click Edit
schema to make changes to the schema. If the current schema is of the Repository type, three options are available:

| | Label | Select the input column used to provide classification labels. The records of this column
are used as the class names (Target in terms of classification) of the elements to be
classified.

Since a SVM model is a binary classification model, only two classes are expected, that is to
say, only two distinct values are expected from this column. | | Vector to process | Select the input column used to provide features. Very often, this column is the output of
the feature engineering computations performed by tModelEncoder. | | Save the model on file
system | Select this check box to store the model in a given file system. Otherwise, the model is
stored in memory. The button for browsing does not work with the Spark Local mode; if you are using the Spark Yarn
or the Spark Standalone mode, ensure that you have properly
configured the connection in a configuration component in the same Job, such as tHDFSConfiguration. | | Step size | Enter the size (numerical value) of the initial step of the gradient
descent calculation. The default value *1.0* means that the whole data set is taken.

Selecting the best step size is often delicate in practice.

Generally speaking, when the feature points to be analyzed are very
muddled, it is recommended to increase the step size in order to cover
enough number of points in each iteration; however, bear in mind that
too large a step size can improperly increase the time of each
iteration.

On the other hand, the smaller the step size is, the more slowly the
convergence occurs and a more accurate model you can expect. | | Number of iterations | Enter the number of iterations you want the Job to perform to train the model. | | Fraction of data to be used per
iteration | Enter the fraction (expressed in decimal) of the input data to be used
in each iteration to calculate the gradient.

The default value 1.0 means that the whole dataset is
taken. | | Regularization parameter | Enter the regularization number to used by the Updater
function in order to avoid overfitting in learning. | | Updater function | Select the function to calculate the form of the hyperplane that
separates the two classes.

This function updates the weights of every point in each iteration so
as to perform the gradient step in a given direction to form the
hyperplane.

For example, in a 2-dimension space, this hyperplane can be a line or
a set of lines if the points to be classified are linearly
separable.

The available functions are:

| | Gradient function | Select the loss function to calculate the margin between the
hyperplane and the nearest point of either class.

For further information about the loss functions available on this
drop-down list, see [Loss function for classification](https://en.wikipedia.org/wiki/Loss_functions_for_classification). | ## Advanced settings | Properties | Description | | --- | --- | | Use feature scaling | If your training data cannot converge, select this check box to make
tSVMModel reduce the condition numbers
heuristically by scaling the feature data.

Reducing the condition numbers can often improve the convergence
rate. | | Intercept | Select this check box to allow the tSVMModel to automatically calculate the intercept constants
and include them in the computation.

In general, intercept can guarantee that the residuals of your model
have a mean of zero. | | Validate data before
training | Select this check box to check whether the vectors of the training
data are well formatted before starting the training. | ## Usage | Usage guidance | Description | | --- | --- | | **Usage rule** | This component is used as an end component and requires an input link.

You can accelerate the training process by adjusting the stopping conditions such as the
maximum number of iterations or the step size but note that the training
that stops too early could impact its accuracy. | | Model evaluation | The parameters you need to set are free parameters and so their values may be provided by
previous experiments, empirical guesses or the like. They do not have any optimal values
applicable for all datasets.

Therefore, you need to train the classifier model you are generating with different sets
of parameter values until you can obtain the best confusion matrix. But note that you need
to write the evaluation code yourself to rank your model with scores.

You need to select the scores to be used depending on the algorithm you want to use to
train your classifier model. This allows you to build the most relevant confusion
matrix.

For examples about how the confusion matrix is used in a
Talend
Job for classification, see [Creating a classification model to filter spam](https://help.qlik.com/talend/r/en-US/8.0/components/machine-learning/classification-model).

For a general explanation about confusion matrix, see https://en.wikipedia.org/wiki/Confusion\_matrix from Wikipedia. | | Spark Connection | In the Spark
Configuration tab in the Run
view, define the connection to a given Spark cluster for the whole Job. In
addition, since the Job expects its dependent jar files for execution, you must
specify the directory in the file system to which these jar files are
transferred so that Spark can access these files:



This connection is effective on a per-Job basis. |