elephant.spade.test_signature_significance¶
- elephant.spade.test_signature_significance(pv_spec, concepts, alpha, winlen, corr='fdr_bh', report='spectrum', spectrum='#')[source]¶
Compute the significance spectrum of a pattern spectrum.
Given pvalue_spectrum pv_spec as a list of triplets (z,c,p), where z is pattern size, c is pattern support and p is the p-value of the signature (z,c), this routine assesses the significance of (z,c) using the confidence level alpha.
Bonferroni or FDR statistical corrections can be applied.
- Parameters:
- pv_speclist
A list of triplets (z,c,p), where z is pattern size, c is pattern support and p is the p-value of signature (z,c)
- conceptslist of tuple
Output of the concepts mining for the original data.
- alphafloat
Significance level of the statistical test
- winlenint
Size (number of bins) of the sliding window used for the analysis
- corrstr, optional
Method used for testing and adjustment of pvalues. Can be either the full name or initial letters. Available methods are:
‘bonferroni’ : one-step correction
‘sidak’ : one-step correction
‘holm-sidak’ : step down method using Sidak adjustments
‘holm’ : step-down method using Bonferroni adjustments
‘simes-hochberg’ : step-up method (independent)
‘hommel’ : closed method based on Simes tests (non-negative)
‘fdr_bh’ : Benjamini/Hochberg (non-negative)
‘fdr_by’ : Benjamini/Yekutieli (negative)
‘fdr_tsbh’ : two stage fdr correction (non-negative)
‘fdr_tsbky’ : two stage fdr correction (non-negative)
‘’ or ‘no’: no statistical correction
For further description see: https://www.statsmodels.org/stable/generated/statsmodels.stats.multitest.multipletests.html Default: ‘fdr_bh’
- report{‘spectrum’, ‘significant’, ‘non_significant’}, optional
Format to be returned for the significance spectrum:
- ‘spectrum’: list of triplets (z,c,b), where b is a boolean specifying
whether signature (z,c) is significant (True) or not (False)
- ‘significant’: list containing only the significant signatures (z,c) of
pvalue_spectrum
‘non_significant’: list containing only the non-significant signatures
- spectrum{‘#’, ‘3d#’}, optional
Defines the signature of the patterns.
- ‘#’: pattern spectrum using the as signature the pair:
(number of spikes, number of occurrence)
- ‘3d#’: pattern spectrum using the as signature the triplets:
(number of spikes, number of occurrence, difference between last and first spike of the pattern)
Default: ‘#’
- Returns:
- sig_spectrumlist
Significant signatures of pvalue_spectrum, in the format specified by report