header = row
for idx, colhead in enumerate(header):
columns[colhead] = idx
else:
htid = row[columns['htid']]
genrecounts = int(row[columns['genrecounts']])
# This is the number of pages *in the genre.*
title = row[columns['title']]
author = row[columns['author']]
datetype = row[columns['datetype']]
startdate = row[columns['startdate']]
enddate = row[columns['enddate']]
imprintdate = row[columns['imprintdate']]
date = utils.infer_date(datetype, startdate, enddate, imprintdate)
if date > 1699 and date < 1800:
centuries['18c'].append(
(date, author, title, genrecounts, htid))
elif date < 1900:
centuries['19c'].append(
(date, author, title, genrecounts, htid))
elif date < 1923:
centuries['20c'].append(
(date, author, title, genrecounts, htid))
pagecenturies = dict()
totallength = 0
for century, voltuples in centuries.items():
# Each voltuple represent a volume.
header = row
for idx, colhead in enumerate(header):
columns[colhead] = idx
else:
htid = row[columns['htid']]
genrecounts = int(row[columns['genrecounts']])
# This is the number of pages *in the genre.*
title = row[columns['title']]
author = row[columns['author']]
datetype = row[columns['datetype']]
startdate = row[columns['startdate']]
enddate = row[columns['enddate']]
imprintdate = row[columns['imprintdate']]
date = utils.infer_date(datetype, startdate, enddate, imprintdate)
if date > 1699 and date < 1800:
centuries['18c'].append((date, author, title, genrecounts, htid))
elif date < 1900:
centuries['19c'].append((date, author, title, genrecounts, htid))
elif date < 1923:
centuries['20c'].append((date, author, title, genrecounts, htid))
pagecenturies = dict()
for century, voltuples in centuries.items():
# Each voltuple represent a volume.
pagecenturies[century] = list()
# For each list of volumes associated with a century, we construct an associated
line = line.rstrip()
fields = line.split('\t')
volid = fields[0]
word = fields[1]
count = int(fields[2])
if volid in datedict:
date = datedict[volid]
elif volid in rows:
datetype = table["datetype"][volid]
firstdate = table["startdate"][volid]
seconddate = table["enddate"][volid]
textdate = table["textdate"][volid]
date = utils.infer_date(datetype, firstdate, seconddate, textdate)
datedict[volid] = date
else:
print(volid + " missing in metadata.")
date = 0
if date > 1699 and date < 1924:
add_counts(wordcounts, date, word, count)
else:
undated.add(volid)
with open('/Volumes/TARDIS/work/forandrew/colors.tsv', mode = 'w', encoding = 'utf-8') as f:
for year, subdictionary in wordcounts.items():
for word, count in subdictionary.items():
outline = str(year) + '\t' + word + '\t' + str(count) + '\n'
f.write(outline)
line = line.rstrip()
fields = line.split('\t')
volid = fields[0]
word = fields[1]
count = int(fields[2])
if volid in datedict:
date = datedict[volid]
elif volid in rows:
datetype = table["datetype"][volid]
firstdate = table["startdate"][volid]
seconddate = table["enddate"][volid]
textdate = table["textdate"][volid]
date = utils.infer_date(datetype, firstdate, seconddate, textdate)
datedict[volid] = date
else:
print(volid + " missing in metadata.")
date = 0
if date > 1699 and date < 1924:
add_counts(wordcounts, date, word, count)
else:
undated.add(volid)
with open('/Volumes/TARDIS/work/forandrew/colors.tsv',
mode='w',
encoding='utf-8') as f:
for year, subdictionary in wordcounts.items():
for word, count in subdictionary.items():
