Create new prediction, becasue forgot about another in.tsv

This commit is contained in:
Bartusiak 2020-03-31 17:09:32 +02:00
parent 02b281edc8
commit caca661287
3 changed files with 10346 additions and 30 deletions

View File

@ -2,19 +2,37 @@ from collections import defaultdict
import math
import pickle
open_file=open('naive_base_model.pkl','rb')
write_file_test=open('test-A/out.tsv','w')
write_file_dev=open('dev-0/out.tsv','w')
pickle_loaded=pickle.load(open_file)
open_file = open('naive_base_model.pkl', 'rb')
pickle_loaded = pickle.load(open_file)
paranomal_class_logprob, skeptic_class_logprob, word_logprobs = pickle_loaded
#pickle_loaded=pickle.load(open_file)
#paranomal_class_logprob, skeptic_class_logprob, word_logprobs = pickle_loaded
#Niektórych słów nie bezie w zbiorze treningowym dev-0 i dev-A
for i in word_logprobs.keys():
for token, tokens in word_logprobs[i].items():
try:
if (word_logprobs['skeptic'][token] > word_logprobs['paranormal'][token]):
write_file_test.write("S\n")
write_file_dev.write("S\n")
def prediction(input,output):
output_file = open(output,'w')
with open(input,encoding='utf-8') as in_file:
for line in in_file:
temp_paranormal_logprob = paranomal_class_logprob
temp_skeptic_logprob = skeptic_class_logprob
text, timestamp = line.rstrip('\n').split('\t')
tokens = text.lower().split(' ')
for token in tokens:
if token not in word_logprobs['paranormal']:
word_logprobs['paranormal'][token] = 0
if token not in word_logprobs['skeptic']:
word_logprobs['skeptic'][token] = 0
temp_paranormal_logprob += paranomal_class_logprob + word_logprobs['paranormal'][token]
temp_skeptic_logprob += skeptic_class_logprob + word_logprobs['skeptic'][token]
if temp_paranormal_logprob > temp_skeptic_logprob:
output_file.write('P\n')
else:
write_file_test.write("P\n")
write_file_dev.write("P\n")
except KeyError:break
output_file.write('S\n')
def main():
prediction('dev-0/in.tsv','dev-0/out.tsv')
prediction('test-A/in.tsv/in.tsv','test-A/out.tsv')
main()

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff