Quantization¶

The documentation of the quantization module.

The pyts.quantization module includes quantization algorithms.

class pyts.quantization.SAX(n_bins=4, quantiles=u'gaussian')[source]¶

Symbolic Aggregate approXimation.

Parameters:	n_bins : int (default = 4) Number of bins (also known as the size of the alphabet). quantiles : {‘gaussian’, ‘empirical’} (default = ‘gaussian’) The way to compute quantiles. If ‘gaussian’, quantiles from a gaussian distribution N(0,1) are used. If ‘empirical’, empirical quantiles are used.

Methods

`fit`([X, y])	Pass.
`fit_transform`(X[, y])	Fit to data, then transform it.
`get_params`([deep])	Get parameters for this estimator.
`set_params`(**params)	Set the parameters of this estimator.
`transform`(X)	Quantize the time series.

fit(X=None, y=None)[source]¶

Pass.

Parameters:	X Ignored y Ignored

transform(X)[source]¶

Quantize the time series.

Parameters:	X : array-like, shape = [n_samples, n_features]
Returns:	X_new : array-like, shape = [n_samples, n_features] Transformed data.

class pyts.quantization.MCB(n_bins=4, quantiles=u'gaussian')[source]¶

Multiple Coefficient Binning.

Parameters:

n_bins : int (default = 4): The number of bins. Ignored if quantiles='entropy'.
quantiles : {‘gaussian’, ‘empirical’, ‘entropy’} (default = ‘gaussian’): The way to compute quantiles. If ‘gaussian’, quantiles from a gaussian distribution N(0,1) are used. If ‘empirical’, empirical quantiles are used. If ‘entropy’, quantiles are computed using the breakpoints leading to the maximum information gain.

Methods

`fit`(X[, y])	Fit the model according to the given training data.
`fit_transform`(X[, y])	Fit to data, then transform it.
`get_params`([deep])	Get parameters for this estimator.
`set_params`(**params)	Set the parameters of this estimator.
`transform`(X)	Transform the provided data.

fit(X, y=None)[source]¶

Fit the model according to the given training data.

Parameters:	X : array-like, shape = [n_samples, n_features] Training vector, where n_samples in the number of samples and n_features is the number of features. y : None or array-like, shape = [n_samples] (default = None) Class labels for each data sample.
Returns:	self : object

transform(X)[source]¶

Transform the provided data.

Parameters:	X : array-like, shape [n_samples, n_features] The data used to scale along the features axis.
Returns:	X_new : array-like, shape [n_samples, n_features]

class pyts.quantization.SFA(n_coefs=None, anova=True, norm_mean=True, norm_std=True, n_bins=4, quantiles=u'entropy', variance_selection=False, variance_threshold=0.0)[source]¶

Symbolic Fourier Approximation.

Parameters:

n_coefs : None or int (default = None): The number of Fourier coefficients to keep. If n_coefs=None, all Fourier coefficients are returned. If n_coefs is an integer, the n_coefs most significant Fourier coefficients are returned if anova=True, otherwise the first n_coefs Fourier coefficients are returned. A even number is required (for real and imaginary values) if anova=False.
anova : bool (default = False): If True, the Fourier coefficients selection is done via a one-way ANOVA test. If False, the first Fourier coefficients are selected.
norm_mean : bool (default = True): If True, center the data before scaling. If norm_mean=True and anova=False, the first Fourier coefficient will be dropped.
norm_std : bool (default = True): If True, scale the data to unit variance.
n_bins : int (default = 4): The number of bins. Ignored if quantiles='entropy'.
quantiles : {‘gaussian’, ‘empirical’, ‘entropy’} (default = ‘gaussian’): The way to compute quantiles. If ‘gaussian’, quantiles from a gaussian distribution N(0,1) are used. If ‘empirical’, empirical quantiles are used. If ‘entropy’, quantiles are computed using the breakpoints leading to the maximum information gain.
variance_selection : bool (default = False): If True, the Fourier coefficients with low variance are removed.
variance_threshold : float (default = 0.): Fourier coefficients with a training-set variance lower than this threshold will be removed. Ignored if variance_selection=False.

Methods

`fit`(X[, y])	Fit the model according to the given training data.
`fit_transform`(X[, y])	Fit to data, then transform it.
`get_params`([deep])	Get parameters for this estimator.
`set_params`(**params)	Set the parameters of this estimator.
`transform`(X)	Transform the provided data.

fit(X, y=None)[source]¶

Fit the model according to the given training data.

Parameters:	X : array-like, shape = [n_samples, n_features] Training vector, where n_samples in the number of samples and n_features is the number of features. y : None or array-like, shape = [n_samples] (default = None) Class labels for each data sample.
Returns:	self : object

transform(X)[source]¶

Transform the provided data.

Parameters:	X : array-like, shape [n_samples, n_features] The data used to scale along the features axis.
Returns:	X_new : array-like, shape [n_samples]