tsmp (version 0.3.1)

mass_pre: Precomputes several values used on MASS

Description

Precomputes several values used on MASS

Usage

mass_pre(data, data_size, query = NULL, query_size = NULL, window_size)

Arguments

data

a vector or a matrix of numeric. Reference Time Series.

data_size

an int. Reference Time Series size.

query

a vector or a matrix of numeric. Query Time Series (default is NULL).

query_size

an int. Query Time Series size (default is NULL).

window_size

an int. Sliding window size.

Value

Returns data_fft, data_mean, data_sd, query_mean and query_sd.

References

• Abdullah Mueen, Yan Zhu, Michael Yeh, Kaveh Kamgar, Krishnamurthy Viswanathan, Chetan Kumar Gupta and Eamonn Keogh (2015), The Fastest Similarity Search Algorithm for Time Series Subsequences under Euclidean Distance.

Website: https://www.cs.unm.edu/~mueen/FastestSimilaritySearch.html

See Also

mass() for using precomputed values.

Examples

# NOT RUN {
w <- mp_toy_data$sub_len
ref_data <- mp_toy_data$data[,1]
query_data <- mp_toy_data$data[,1]
d_size <- length(ref_data)
q_size <- length(query_data)

pre <- mass_pre(ref_data, d_size, query_data, q_size, w)

dp <- list()
for(i in 1:(d_size - w + 1)) {
  dp[[i]] <- mass(pre$data_fft, query_data[i:(i-1+w)], d_size, w, pre$data_mean, pre$data_sd,
          pre$query_mean[i], pre$query_sd[i])
}
# }