paranormal-or-skeptic/predict.py

#!/usr/bin/python3

import sys
import pickle
from math import log, exp
from tokenizer import tokenize

#Load model
model = pickle.load(open("model.pkl","rb"))
weights, word_to_index_mapping, word_count = model

for line in sys.stdin:
    document = line.rstrip()
    fields = document.split('\t')
    document = fields[0]
    terms = tokenize(document)

    y_predicted = weights[0]
    for word in terms:
        y_predicted += weights[word_to_index_mapping.get(word,0)] * (word_count.get(word,0) / len(word_count))

    if y_predicted <= 0.5:
        print(0)
    else:
        print(1)