morpheus_dfp.modules.dfp_training

Functions

dfp_training(builder)[source]

This module function is used for model training.

Parameters

buildermrc.Builder

Pipeline builder instance.

Notes

Configurable Parameters:

• feature_columns (list): List of feature columns to train on; Example: [“column1”, “column2”, “column3”]

• epochs (int): Number of epochs to train for; Example: 50

• model_kwargs (dict): Keyword arguments to pass to the model; Example: {“encoder_layers”: [64, 32], “decoder_layers”: [32, 64], “activation”: “relu”, “swap_p”: 0.1, “lr”: 0.001, “lr_decay”: 0.9, “batch_size”: 32, “verbose”: 1, “optimizer”: “adam”, “scalar”: “min_max”, “min_cats”: 10, “progress_bar”: false, “device”: “cpu”}

• validation_size (float): Size of the validation set; Example: 0.1