def get_distr(strlist, n_len):
alphabet = ['A', 'C', 'G', 'T', 'N']
n = NGram(N=n_len, pad_len=0)
all_ngrams = 0
grams = init_grams_dict(n_len, alphabet)
for item in strlist:
if item == '':
continue
ngram_list = list(n._split(item))
for ng in ngram_list:
if ng in grams:
grams[ng] += float(1)
all_ngrams += 1
for item in grams.keys():
grams[item] /= all_ngrams
return grams
and oases_item['top'] == trinity_item['top'] \
and oases_item['n'] == trinity_item['n']\
and oases_item['kernel'].values()[0] == trinity_item['kernel'].values()[0]:
print (oases_item, trinity_item)
#intersect = set(good_list_oases) & set(good_list_trinity)
from tr_parser import get_assemblies
(ref, oases_reads, oases_name_index, trinity_reads, trinity_name_index) = get_assemblies("data/ref_for_reads.fasta",
"data/Oases.fasta",
"data/Trinity.fasta")
from ngram import NGram
n = NGram(N=4, pad_len=0)
grams = dict()
for transcript in ref:
if transcript == '':
continue
ngram_list = list(n._split(transcript))
for ng in ngram_list:
if ng == 'TTSG':
pdb.set_trace()
if ng in grams:
grams[ng] += 1
else:
grams[ng] = 1
pp = pprint.PrettyPrinter()
pp.pprint(grams)
print len(grams)
['0', '1', '2', '3', '4', '5', '6', '7', '8', '9'], "n")
masked_domain_name = multi_replace(aux3_domain_name, ['-'], "s")
#print domain_name + " -> " + masked_domain_name
#continue
feature.append(domain_name)
feature.append(masked_domain_name)
feature.append(tag)
if len(domain_name) < 5:
continue
### ID Designation
### V4-6 1-gram (mean, variance and standard deviation)
n = NGram(N=1)
v = list(n._split(domain_name))
[f1, f2, f3] = ngram_stats(v)
feature.extend([f1, f2, f3])
### V6-9 2-gram (mean, variance and standard deviation)
n = NGram(N=2)
v = list(n._split(domain_name))
[f1, f2, f3] = ngram_stats(v)
feature.extend([f1, f2, f3])
### V10-12 3-gram (mean, variance and standard deviation)
n = NGram(N=3)
v = list(n._split(domain_name))
[f1, f2, f3] = ngram_stats(v)
feature.extend([f1, f2, f3])
