def get_datatype_by_extension(self, ext ):
"""Returns a datatype based on an extension"""
try:
builder = self.datatypes_by_extension[ext]
except KeyError:
builder = data.Text()
return builder
def get_datatype_by_extension(ext):
"""
Returns a datatype based on an extension
"""
try:
builder = datatypes_by_extension[ext]
except KeyError:
builder = data.Text()
log.warning('unkown extension in data factory %s' % ext)
return builder
'gff3' : interval.Gff3(),
'genetrack' : tracks.GeneTrack(),
'interval' : interval.Interval(),
'laj' : images.Laj(),
'lav' : sequence.Lav(),
'maf' : sequence.Maf(),
'pileup' : tabular.Pileup(),
'qualsolid' : qualityscore.QualityScoreSOLiD(),
'qualsolexa' : qualityscore.QualityScoreSolexa(),
'qual454' : qualityscore.QualityScore454(),
'sam' : tabular.Sam(),
'scf' : binary.Scf(),
'sff' : binary.Sff(),
'tabular' : tabular.Tabular(),
'taxonomy' : tabular.Taxonomy(),
'txt' : data.Text(),
'wig' : interval.Wiggle(),
'xml' : xml.GenericXml(),
}
self.mimetypes_by_extension = {
'ab1' : 'application/octet-stream',
'axt' : 'text/plain',
'bam' : 'application/octet-stream',
'bed' : 'text/plain',
'customtrack' : 'text/plain',
'csfasta' : 'text/plain',
'eland' : 'application/octet-stream',
'fasta' : 'text/plain',
'fastq' : 'text/plain',
'fastqsanger' : 'text/plain',
'gtf' : 'text/plain',
import data
import tagger
TRAIN_DATA = 'data/train.txt'
print('Loading data...')
train_corpus = data.Text(TRAIN_DATA)
print('Done')
pos_tagger = tagger.POSTagger()
print('Training model...')
pos_tagger.fit(train_corpus)
pos_tagger.save_model('model.pickle')
print('Done')
example = 'I am God'.split(' ')
prob, tags = pos_tagger.predict(example)
print('Predict POS tag for:', example)
print('Tags:', tags, 'With probability:', prob)
