test_model: Test trained Hidden Markov Model with test data

In githerbert/HMM:

Description

This function tests a Hidden Markov Model for Music Information retriaval by predicting the last genre of each sequence in the testdata set. Based on the result of this function the accuracy of a model can be calculated with the function calcAccuracy().

Usage

test_model(trained_MIR_hmm, testdata)

Arguments

trained_MIR_hmm	An object of the class MIR_hmm as returned by MIR_hmm().
testdata	Testdata as returned by the function split_data().

Value

A matrix that contains the following two values for each row in the testdata:

ACTUAL	The actual last value of the sequence.
PREDICTED	The predicted last value by the Hidden Markov Model.

Examples

# Example for the case that all datasets are located in S:/

# Prepare data
jams <- load_jams("S:/", loadExample = TRUE)
jams_with_genre <- add_genres_to_jams(jams, "S:/", loadExample = TRUE)
jam_sequence <- create_time_sequence(jams_with_genre)
splitted_data <- split_data(jam_sequence)
training_dataset <- splitted_data[[1]]
test_dataset <- splitted_data[[2]]

# Train model
hmm <- MIR_hmm(training_dataset)
test_results <- test_model(hmm,test_dataset)

githerbert/HMM documentation built on May 30, 2019, 12:46 p.m.