def randomisation_test4bigrmas_inSequences(seqOfSeqs,
df_obsStat,
Nsh,
condsLi,
sampsLi,
testStat=teStat_proportions_diff):
"""DEPRECATED: use randtest4bigrmas_inSequences
"""
## define array to slice superSequences back into the sequences
seq_slicer = superSequenceSlicer(
seqOfSeqs) #np.cumsum(np.array([len(item) for item in seqOfSeqs]))
## define super sequence vector
superSequence = np.array(flattenList(seqOfSeqs))
## randomisations test
nr, nc = np.shape(df_obsStat)
shuffle_tests = np.zeros((Nsh, nr, nc))
N_values_r = np.zeros_like(df_obsStat)
for i in np.arange(Nsh):
## randomise supersequence
np.random.shuffle(superSequence)
## define sequences: slice supersequence and put in str format for nltk
sequences_str = aa.seqsLi2iniEndSeq(
sliceBackSuperSequence(superSequence, seq_slicer))
## split sequences into bigrams
my_bigrams = list(nltk.bigrams(sequences_str))
## count bigrams
cfd_sh0 = ngr.bigrams2cfd(my_bigrams)
## fill cfd_sh0 with empty valued keys of the missing values
cfd_sh = ngr.fill2KyDict(cfd_sh0, kySet=set(sampsLi) | set(condsLi))
## transform cfd into matrix form
Mp_sh = ngr.condFreqDict2condProbMatrix(
cfd_sh, condsLi, sampsLi)[0] # normalised matrix
shTest_i = testStat(Mp_sh) # compute satat variable
shuffle_tests[i] = shTest_i # save distribution for later
N_values_r[shTest_i >= df_obsStat] += 1 # test right
# compute p-value
p_r = 1.0 * N_values_r / Nsh
return p_r, shuffle_tests
def cfd(self):
return ngr.bigrams2cfd(self.bigrams)