def getCorpusFilePath():
r'''Get the stored music21 directory that contains the corpus metadata cache.
>>> fp = common.getCorpusFilePath()
>>> fp.endswith('music21/corpus') or fp.endswith(r'music21\corpus')
True
'''
from music21 import corpus
coreCorpus = corpus.CoreCorpus()
if coreCorpus.manualCoreCorpusPath is None:
return os.path.join(getSourceFilePath(), 'corpus')
return coreCorpus.manualCoreCorpusPath
nGrams.append(tuple(nGram))
return nGrams
def hashNGrams(self, nGrams):
import collections
nGramDict = collections.Counter()
for nGram in nGrams:
nGramDict[nGram] += 1
sortedDict = tuple(nGramDict.most_common())
return sortedDict
if __name__ == '__main__':
import os
import json
coreCorpus = corpus.CoreCorpus()
paths = [x for x in coreCorpus.getPaths() if 'trecento' in x]
#paths = paths[:2]
paths = [os.path.join('trecento', os.path.split(x)[-1]) for x in paths]
jobs = []
jobTotal = len(paths)
for i, path in enumerate(paths):
job = NGramJob(
path,
jobNumber=i,
jobTotal=jobTotal,
)
jobs.append(job)
processedJobs = NGramJobHandler.execute(jobs)
processedJobs.sort(key=lambda x: x.filename)
result = {}