def do_test_set_naive_bayes_sent_hs_other(utterances, filename, lex, file,
column, sentimentfile_train,
sentimentfile_test, mode):
# annotation using naive_bayes will be saved in a new file
with open(filename, 'w') as f:
writer = csv.writer(f, delimiter=';')
writer.writerow(["Utterance", "Hate Speech"]) # header
sentimentlist = senti_strength.estimate_sentiment_probabilities_other_datasets(
sentimentfile_train, file, column, mode)
list_of_sentiments = machine_learning_processing.make_list_of_column(
sentimentfile_test, 1)
utterance_id = 0
for utterance in utterances:
class_hs = do_sentiment_naive_bayes_hs(
utterance, lex, list_of_sentiments[utterance_id], sentimentlist
) # determine class of the utterance using do_sentiment_naive_bayes_hs()
# write utterance and its assigned class into the file
utterance_string = ""
for word in utterance:
utterance_string = utterance_string + word + " "
writer.writerow([utterance_string, class_hs])
utterance_id += 1
def do_test_set_mem_sent_pos_hs_ths(utterances_test, utterances_unprocessed,
filename, lex, file, column,
sentimentfile_train, sentimentfile_test,
mode):
# annotation using maximum entropy model will be saved in a new file
with open(filename, 'w') as f:
writer = csv.writer(f, delimiter=';')
writer.writerow(["Utterance", "Hate Speech"]) # header
sentimentlist = senti_strength.estimate_sentiment_probabilities_other_datasets(
sentimentfile_train, file, column, mode)
list_of_sentiments = machine_learning_processing.make_list_of_column(
sentimentfile_test, 1)
utterance_id = 0
for utterance in utterances_test:
utterance_unprocessed = utterances_unprocessed[utterance_id]
class_hs = do_mem_sent_pos_hs_ths(
utterance, utterance_unprocessed, lex,
list_of_sentiments[utterance_id], sentimentlist
) # determine class of the utterance using do_svm()
# write utterance and its assigned class into the file
utterance_string = ""
for word in utterance:
utterance_string = utterance_string + word + " "
writer.writerow([utterance_string, class_hs])
if utterance_id == 100:
print(100)
elif utterance_id == 200:
print(200)
elif utterance_id == 300:
print(300)
elif utterance_id == 400:
print(400)
elif utterance_id == 500:
print(500)
elif utterance_id == 600:
print(600)
elif utterance_id == 700:
print(700)
elif utterance_id == 800:
print(800)
elif utterance_id == 900:
print(900)
utterance_id += 1
def do_test_set_naive_bayes_sent_pos_ld(utterances, utterances_unprocessed,
filename, lex, file, column,
sentimentfile_train,
sentimentfile_test, mode):
# annotation using naive_bayes will be saved in a new file
with open(filename, 'w') as f:
writer = csv.writer(f, delimiter=';')
writer.writerow(["Utterance", "Cyberbullying"]) # header
sentimentlist = senti_strength.estimate_sentiment_probabilities_other_datasets(
sentimentfile_train, file, column, mode)
list_of_sentiments = machine_learning_processing.make_list_of_column(
sentimentfile_test, 1)
utterance_id = 0
for utterance in utterances:
utterance_unprocessed = utterances_unprocessed[utterance_id]
class_cb = do_naive_bayes_sent_pos_ld(
utterance, utterance_unprocessed, lex,
list_of_sentiments[utterance_id], sentimentlist
) # determine class of the utterance using do_naive_bayes()
# write utterance and its assigned class into the file
utterance_string = ""
for word in utterance:
utterance_string = utterance_string + word + " "
writer.writerow([utterance_string, class_cb])
if utterance_id == 100:
print(100)
elif utterance_id == 200:
print(200)
elif utterance_id == 300:
print(300)
elif utterance_id == 400:
print(400)
elif utterance_id == 500:
print(500)
elif utterance_id == 600:
print(600)
elif utterance_id == 700:
print(700)
elif utterance_id == 800:
print(800)
elif utterance_id == 900:
print(900)
elif utterance_id == 1000:
print(1000)
elif utterance_id == 1100:
print(1100)
elif utterance_id == 1200:
print(1200)
elif utterance_id == 1300:
print(1300)
elif utterance_id == 1400:
print(1400)
elif utterance_id == 1500:
print(1500)
elif utterance_id == 1600:
print(1600)
elif utterance_id == 1700:
print(1700)
elif utterance_id == 1800:
print(1800)
elif utterance_id == 1900:
print(1900)
elif utterance_id == 2000:
print(2000)
elif utterance_id == 2100:
print(2100)
elif utterance_id == 2200:
print(2200)
utterance_id += 1