60 lines
2.1 KiB
Python
Executable File
60 lines
2.1 KiB
Python
Executable File
#!/usr/bin/python3
|
||
|
||
import pickle
|
||
import math
|
||
import re
|
||
|
||
def clear_tokens(tokens):
|
||
tokens = tokens.replace('\\n', ' ')
|
||
tokens = re.sub(r'\(((http)|(https)).*((\.com)|(\.net)|(\.jpg)|(\.html))\)'," ", tokens)
|
||
tokens = re.sub(r'[\n\&\"\?\\\'\*\[\]\,\;\.\=\+\(\)\!\/\:\`\~\%\^\$\#\@\’\＞\″\±]+', ' ', tokens)
|
||
tokens = re.sub(r'[\.\-][\.\-]+', ' ', tokens)
|
||
tokens = re.sub(r'œ|·', '', tokens)
|
||
tokens = re.sub(r' +', ' ', tokens)
|
||
return tokens
|
||
|
||
def calc_post_prob(post, paranormal_class_logprob, sceptic_class_logprob, word_logprobs):
|
||
# dla kazdego tokenu z danego posta
|
||
text, timestap = post.rstrip('\n').split('\t')
|
||
text = clear_tokens(text)
|
||
tokens = text.lower().split(' ')
|
||
probs = {0.0 : 'sceptic', 0.0 : 'paranormal'}
|
||
for class_ in word_logprobs.keys():
|
||
product = 1
|
||
for token in tokens:
|
||
try:
|
||
product += word_logprobs[class_][token]
|
||
except KeyError:
|
||
pass
|
||
# tu wzoru uzyj
|
||
if class_ == 'sceptic':
|
||
product += sceptic_class_logprob
|
||
elif class_ == 'paranormal':
|
||
product += paranormal_class_logprob
|
||
probs[abs(product)] = class_
|
||
#print(probs)
|
||
# mozna jeszcze zrobic aby bralo kluczowe slowa i wtedy decydowalo ze paranormal
|
||
return probs[max(probs.keys())]
|
||
|
||
|
||
def main():
|
||
with open('naive_base_model.pkl', 'rb') as f:
|
||
pickle_list = pickle.load(f)
|
||
paranormal_class_logprob = pickle_list[0]
|
||
sceptic_class_logprob = pickle_list[1]
|
||
word_logprobs = pickle_list[2]
|
||
#in_file = "test-A/in.tsv"
|
||
in_file = "dev-0/in.tsv"
|
||
#out_file = "test-A/out.tsv"
|
||
out_file = "dev-0/out.tsv"
|
||
print (f"in {in_file}")
|
||
print (f"out {out_file}")
|
||
with open(in_file) as in_f, open(out_file, 'w') as out_f:
|
||
for line in in_f:
|
||
hyp = calc_post_prob(line, paranormal_class_logprob, sceptic_class_logprob, word_logprobs)
|
||
if hyp == 'sceptic':
|
||
out_f.write(" S\n")
|
||
elif hyp == 'paranormal':
|
||
out_f.write(' P\n')
|
||
main()
|