pyFTS.probabilistic package¶

Module contents¶

Probability Distribution objects

Submodules¶

pyFTS.probabilistic.ProbabilityDistribution module¶

class pyFTS.probabilistic.ProbabilityDistribution.ProbabilityDistribution(type='KDE', **kwargs)[source]¶

Bases: object

Represents a discrete or continous probability distribution If type is histogram, the PDF is discrete If type is KDE the PDF is continuous

append(values)[source]¶

append_interval(intervals)[source]¶

averageloglikelihood(data)[source]¶

bins = None¶: Number of bins on a discrete PDF

build_cdf_qtl()[source]¶

crossentropy(q)[source]¶

cummulative(values)[source]¶

density(values)[source]¶

differential_offset(value)[source]¶

empiricalloglikelihood()[source]¶

entropy()[source]¶

expected_value()[source]¶

kullbackleiblerdivergence(q)[source]¶

labels = None¶: Bins labels on a discrete PDF

plot(axis=None, color='black', tam=[10, 6], title=None)[source]¶

pseudologlikelihood(data)[source]¶

quantile(values)[source]¶

set(value, density)[source]¶

type = None¶: If type is histogram, the PDF is discrete If type is KDE the PDF is continuous

uod = None¶: Universe of discourse

pyFTS.probabilistic.kde module¶

Kernel Density Estimation

class pyFTS.probabilistic.kde.KernelSmoothing(h, kernel='epanechnikov')[source]¶

Bases: object

Kernel Density Estimation

h = None¶: Width parameter

kernel = None¶: Kernel function

kernel_function(u)[source]¶

probability(x, data)[source]¶

Probability of the point x on data

Parameters:	x – data –
Returns: