29 lines
913 B
Python
29 lines
913 B
Python
|
#!/usr/bin/env python3
|
||
|
|
import math
|
||
|
|
import pickle
|
||
|
|
import sys
|
||
|
|
from tokenize import tokenize
|
||
|
|
|
||
|
|
model = pickle.load(open("model.pkl", "rb"))
|
||
|
|
word_to_index, vocabulary, weights, words_count = model
|
||
|
|
lines = sys.stdin.readlines()
|
||
|
|
for line2 in lines:
|
||
|
|
line2 = line2.rstrip()
|
||
|
|
fields2 = line2.split('\t') ##rozdzielamy linie na tablice oddzielonymi tabami
|
||
|
|
label2 = fields2[0].strip() ##to etykiety
|
||
|
|
document2 = fields2[1] ##to posty
|
||
|
|
terms2 = document2.split(' ') ##to rozdziel posty na słowa
|
||
|
|
for term2 in terms2: ##dla każdego słowa w poście
|
||
|
|
if term2 in words_count:
|
||
|
|
words_count[term2] += 1 ##robimy słownik dla danego słowa ile razy występuje
|
||
|
|
else:
|
||
|
|
words_count[term2] = 1
|
||
|
|
expected=weights[0]
|
||
|
|
for t in terms2:
|
||
|
|
if(t in vocabulary):
|
||
|
|
expected=expected+(words_count[t]/len(words_count)*(weights[word_to_index[t]]))
|
||
|
|
if(expected>0.65):
|
||
|
|
print(1)
|
||
|
|
else:
|
||
|
|
print(0)
|