def main():
# load training files into Classifier
path_to_res = os.path.join(sys.path[0], "resources\\")
neg_classif = Classifier(path_to_res + "training_negative.txt")
neu_classif = Classifier(path_to_res + "training_neutral.txt")
pos_classif = Classifier(path_to_res + "training_positive.txt")
total_entries = neu_classif.get_entries() + neg_classif.get_entries() + pos_classif.get_entries()
# load test files
test_parser = Parser(path_to_res + "test_set.txt")
counter = 1
while(True):
word_list = test_parser.giveWordList()
if len(word_list) == 0:
break
neg_p = neg_classif.classification_probability(word_list, total_entries)
neu_p = neu_classif.classification_probability(word_list, total_entries)
pos_p = pos_classif.classification_probability(word_list, total_entries)
print("Test " + str(counter) + ":\n")
print("\tNegative: " + str(math.fabs(neg_p)) + "%\n")
print("\tNeutral: " + str(math.fabs(neu_p)) + "%\n")
print("\tPositve: " + str(math.fabs(pos_p)) + "%\n")
counter += 1
class Classifier(object):
""" Contains stastical data from training text
One Classifier object per each classifiable catagory
"""
def __init__(self, training_file_path):
self._dict = {}
self._entries = 0
self._total_words = 0
self.parser = Parser(training_file_path)
self._learn()
def _learn(self):
""" Uses Parser to get entries and build the dictionary """
while(True):
word_list = self.parser.giveWordList()
if len(word_list) == 0:
return
else:
for word in word_list:
self._add_word(word)
self._entries += 1
def _add_word(self, word):
""" adds a word to the dictionary, or increments it if already inside """
if word in self._dict:
self._dict[word] += 1
self._total_words += 1
else:
self._dict[word] = 1
self._total_words += 1
def likelihood(self, word):
""" the likelihood of a word xi occuring conditionally, p(xi | Ck) """
if word in self._dict:
return self._dict[word] / self._entries
else:
return 0
def classification_probability(self, word_list, total_entries):
""" Returns the probability that the given entry is of this classifiable catagory
word_list: List, entry from test file Parser's giveWordList()
total_entries: int, sum of all Classifier's entries
Naive Bayes Formula:
p(Ck | x1, x2, .... xi) ~
p(Ck) * SIGMA(for all i)[ log p(xi | Ck) ] =
"""
prob_c = self._entries / total_entries
total_sum = 1
for word in word_list:
likelihood = self.likelihood(word)
if likelihood == 0:
total_sum += 0
else:
total_sum += math.log(self.likelihood(word))
#if(total_sum == 1):
# return 0
return prob_c * total_sum
def get_entries(self):
""" Returns the number of entries """
return self._entries
