if maxmatch < 0.85:
sample.append(volid)
else:
print(maxmatch)
if len(sample) < sampleperyear:
for volid in initialsample:
population.remove(volid)
stillneeded = sampleperyear - len(sample)
print("Still needed: " + str(stillneeded) + "from population " + str(len(population)))
if stillneeded >= len(population):
secondsample = population
else:
secondsample = random.sample(population, stillneeded)
sample.extend(secondsample)
selectedids.extend(sample)
for volid in sample:
author = table["author"][volid]
title = table["title"][volid]
authtitles.append((author, title))
utils.writetsv(columns, selectedids, table, "/Users/tunder/Dropbox/GenreProject/metadata/topicmodelingsample.tsv")
if maxmatch < 0.85:
sample.append(volid)
else:
print(maxmatch)
if len(sample) < sampleperyear:
for volid in initialsample:
population.remove(volid)
stillneeded = sampleperyear - len(sample)
print("Still needed: " + str(stillneeded) +
"from population " + str(len(population)))
if stillneeded >= len(population):
secondsample = population
else:
secondsample = random.sample(population, stillneeded)
sample.extend(secondsample)
selectedids.extend(sample)
for volid in sample:
author = table["author"][volid]
title = table["title"][volid]
authtitles.append((author, title))
utils.writetsv(
columns, selectedids, table,
"/Users/tunder/Dropbox/GenreProject/metadata/topicmodelingsample.tsv")
