.. _`Fit`: .. _`org.sysess.sympathy.machinelearning.fit`: Fit ``` .. image:: fit.svg :width: 48 Trains a model. Use "Ports > Input > Y" for supervised/unsupervised training Documentation ::::::::::::: Trains a machine learning model using the input data. It uses the implementation of the model class .fit method. It adjusts the internal parameters of the model based on the patterns found in the training dataset. It is recommended to first use the :ref:`org.sysess.sympathy.machinelearning.simple_split` node to separate the data before training, for unbiased verification. (Note that some advanced models will not work with this node but must be used with the Fit Dataset node from Advanced Machine Learning extension.) For unsupervised learining the input port Y can be removed. However, some models might not be defined to be trained unsupervised and need to have the Y supplied. Definition :::::::::: Input ports ........... **in-model** | Type: model | Description: Input model **X** | Type: table | Description: X **Y0** | Type: table | Description: Y | Optional number of ports: 0--1 (default: 1) **sample_weights** | Type: table | Description: Sample weights | Optional number of ports: 0--1 (default: 0) Output ports ............ **out-model** | Type: model | Description: Output model Examples ........ The node can be found in: * :download:`Custom_ParameterSearch.syx ` * :download:`Regression.syx ` * :download:`Metrics.syx ` * :download:`SampleWeights.syx ` * :download:`Text_Classification.syx ` * :download:`Eigenfaces.syx ` * :download:`Fisher_faces.syx ` * :download:`clustering.syx ` * :download:`KmeansOutlierRemoval.syx ` * :download:`agglomerative_clustering.syx ` * :download:`random_forest_regressor.syx ` * :download:`linear time invariant systems.syx ` Implementation .............. .. automodule:: node_application :noindex: .. class:: Fit :noindex: