Override this method to define a model.
Units hiddenLayers for MLP.
Units hiddenLayers for MLP. Array of positive integers. Default is Array(40, 20, 10).
Whether to include Matrix Factorization.
Whether to include Matrix Factorization. Boolean. Default is true.
The number of items.
The number of items. Positive integer.
Units of item embedding.
Units of item embedding. Positive integer. Default is 20.
Units of matrix factorization embedding.
Units of matrix factorization embedding. Positive integer. Default is 20.
The defined model, either from buildModel() or loaded from file.
The defined model, either from buildModel() or loaded from file.
The number of classes.
The number of classes. Positive integer.
Predict for classes.
Predict for classes. By default, label predictions start from 0.
Prediction data, RDD of Sample.
Number of samples per batch. Default is 32.
Boolean. Whether result labels start from 0. Default is true. If false, result labels start from 1.
Predict for user-item pairs.
Predict for user-item pairs.
RDD of user item pair feature.
RDD of user item pair prediction.
Recommend a number of users for each item given a rdd of user item pair features.
Recommend a number of users for each item given a rdd of user item pair features.
RDD of user item pair feature.
Number of users to be recommended to each item. Positive integer.
RDD of user item pair prediction.
Recommend a number of items for each user given a rdd of user item pair features.
Recommend a number of items for each user given a rdd of user item pair features.
RDD of user item pair feature.
Number of items to be recommended to each user. Positive integer.
RDD of user item pair prediction.
Save the model to the specified path.
Save the model to the specified path.
The path to save the model. Local file system, HDFS and Amazon S3 are supported. HDFS path should be like "hdfs://[host]:[port]/xxx". Amazon S3 path should be like "s3a://bucket/xxx".
The path to save weights. Default is null.
Whether to overwrite the file if it already exists. Default is false.
Print out the summary of the model.
Print out the summary of the model.
The number of users.
The number of users. Positive integer.
Units of user embedding.
Units of user embedding. Positive integer. Default is 20.
(Since version 0.3.0) please use recommended saveModule(path, overWrite)
The neural collaborative filtering model used for recommendation.
Numeric type of parameter(e.g. weight, bias). Only support float/double now.