def process(file_name):
print("1")
data=open(glob.glob(file_name).pop()).readlines()
print("2")
poem=data[9:]
print(poem)
century=data[2]
print("3")
p_categories=data[5].split()
print(p_categories)
os.chdir(r'/media/bryan/Work/graph_poetry/features/')
import functions
poem = functions.mutateRemoveJunk(poem)
linecount = len(poem)
metrical_stress = functions.getStress(poem)
last_words_ll = functions.get_last_words(poem)
rhyme_pattern = functions.make_rhyme_pattern(last_words_ll)
last_words_list = functions.get_last_words_list(last_words_ll)
poem_vector = []
poem_vector.append(file)
import rhyme_detection as rd
rhyme_pattern_vector = rd.get_rhyme_pattern_vector(last_words_ll)
poem_vector.append(rhyme_pattern_vector)
import poem_vector as pv
rhyme_vector = pv.get_rhyme_type_count(last_words_ll)
for item in rhyme_vector:
try:
item = float(item)/float(linecount)
except:
item = 0
poem_vector.append(item)
poem_vector.append(pv.get_ratio(last_words_ll))
n = pv.get_couplets(last_words_ll)
try:
poem_vector.append(float(n)/float(linecount))
except:
poem_vector.append("0")
n = pv.get_alternating_rhymes(last_words_ll)
try:
poem_vector.append(float(n)/float(linecount))
except:
poem_vector.append("0")
n = pv.get_rhymes_two_lines_apart(last_words_ll)
try:
poem_vector.append(float(n)/float(linecount))
except:
poem_vector.append("0")
poem_vector.append(linecount)
foot_count = pv.foot_count(metrical_stress)
total = sum(foot_count)
number_of_feet_per_line = pv.get_feet_per_line(metrical_stress)
for item in number_of_feet_per_line:
poem_vector.append(item)
for item in foot_count:
try:
poem_vector.append(float(item)/float(total))
except:
poem_vector.append("0")
try:
poem_vector.append(float(pv.get_streak(metrical_stress)))
except:
poem_vector.append("0")
try:
poem_vector.append(float(pv.get_switches(metrical_stress))/float(total))
except:
poem_vector.append("0")
import re
categories = ["Free","Rhymed","Couplet","Rhymes","Blank","Sonnet","Villanelle","Terza"]
categories_compiled = list(map(re.compile,categories))
poem_class = ""
poeticTerm ='unknown'
wekaClass = 'unknown'
for item in categories_compiled:
if re.search(free,item):
wekaClass = 'NR'
break
if re.search(rhymed,item):
wekaClass = 'R'
break
if re.search(couplet,item):
wekaClass = 'R'
break
if re.search(rhymes,item):
wekaClass = 'R'
break
if re.search(blank,item):
wekaClass = 'NR'
break
if re.search(sonnet,item):
wekaClass = 'R'
break
if re.search(villanelle,item):
wekaClass = 'R'
break
if re.search(terza,item):
wekaClass = 'R'
break
for item in poem_vector:
arff.write(str(item))
arff.write(", ")
arff.write(str(wekaClass))
arff.write('\n')
os.chdir('./output')
# this is where the results will be stored for each poem:
output = open(str(file)[:-3]+'out.txt', 'w')
output.write("Results" +'\n' +'\n')
output.write("Line Count : " +'\n')
output.write(str(linecount))
output.write('\n')
output.write('Metrical Stress : ' +'\n')
for item in metrical_stress:
output.write(str(item))
output.write('\n')
output.write('\n')
output.write("Rhyme Pattern : " +'\n')
p = last_words_ll.head
while p.nodebelow is not last_words_ll.head:
p = p.nodebelow
output.write(str(p.outer_letter))
output.write("-")
output.write(str(p.letter_designation))
output.write("----")
output.write(str(p.word))
output.write("----")
output.write(str(p.rhyme_type))
output.write('\n')
output.write('\n')
output.write("Poem : " +'\n')
for line in poem:
output.write(str(line))
os.chdir(r'/media/bryan/Work/graph_poetry/poetry_collection/test_site/')
os.rename(file, file.replace("txt", "done"))
for item in foot_count:
try:
poem_vector.append(float(item)/float(total))
except:
poem_vector.append("0")
# 28 max same feet streak
try:
# poem_vector.append(float(pv.get_streak(metrical_stress))/float(total))
poem_vector.append(float(pv.get_streak(metrical_stress)))
except:
poem_vector.append("0")
# 29 number of switches
try:
poem_vector.append(float(pv.get_switches(metrical_stress))/float(total))
except:
poem_vector.append("0")
# use regex to find these features:
# 30 date
# 31 author
# 31 title
# ord() gets the ascii number for the letter
ascii_words = []
for item in last_words_list:
for ch in item: