fABBA.ABBA

class fABBA.ABBA(tol=0.1, k=2, scl=1, verbose=1, max_len=- 1)[source]
__init__(tol=0.1, k=2, scl=1, verbose=1, max_len=- 1)[source]

This class is designed for other clustering based ABBA

tol - float

Control tolerence for compression, default as 0.1.

scl - int

Scale for length, default as 1, means 2d-digitization, otherwise implement 1d-digitization.

verbose - int

Control logs print, default as 1, print logs.

max_len - int

The max length for each segment, default as -1.

Methods

__init__([tol, k, scl, verbose, max_len])

This class is designed for other clustering based ABBA

compress(series[, fillm])

Compress time series.

digitize(pieces[, alphabet_set])

Greedy 2D clustering of pieces (a Nx2 numpy array), using tolernce tol and len/inc scaling parameter scl.

fit_transform(series[, fillm, alphabet_set])

Compress and digitize the time series together.

inverse_transform(strings[, start, parameters])

Convert ABBA symbolic representation back to numeric time series representation.

reassign_labels(labels)