def test_fs_tsv_loader_with_nlp(self):
sample_words = "sample_data/email/email.tsv"
self.tlog("loading words => " + sample_words)
nlp_eng = nlp("eng")
wordmat_train, wordlabel_train, voca, wordmat_test, wordlabel_test \
= fs.tsv_loader_with_nlp(sample_words, 0.1, nlp_eng)
self.tlog('email data voca size : ' + str(len(voca)))
self.tlog('voca sample : ' + str(voca[:5]))
def test_fs_tsv_loader_with_nlp(self):
sample_words = "sample_data/email/email.tsv"
self.tlog("loading words => " + sample_words)
nlp_eng = nlp("eng")
wordmat_train, wordlabel_train, voca, wordmat_test, wordlabel_test \
= fs.tsv_loader_with_nlp(sample_words, 0.1, nlp_eng)
self.tlog('email data voca size : ' + str(len(voca)))
self.tlog('voca sample : ' + str(voca[:5]))
def test_process(self):
nlp_eng = nlp("eng")
email_data_file = "sample_data/email/email.tsv"
emailmat_train, emaillabel_train, voca, emailmat_test, emaillabel_test = fs.tsv_loader_with_nlp(
email_data_file, 0.3, nlp_eng
)
self.tlog(voca)
email_nbayes = NaiveBayes(emailmat_train, emaillabel_train)
email_nbayes.fit()
error_rate = autotest.eval_predict(email_nbayes, emailmat_test, emaillabel_test, self.logging)
self.tlog("spam-mail predict (with NaiveBayes) error rate : " + str(error_rate))
assert error_rate <= 0.1
def test_process(self):
nlp_eng = nlp("eng_lower")
email_data_file = "sample_data/email/email.tsv"
emailmat_train, emaillabel_train, voca, emailmat_test, emaillabel_test \
= fs.tsv_loader_with_nlp(email_data_file, 0.4, nlp_eng)
self.tlog(voca)
email_nbayes = NaiveBayes(emailmat_train, emaillabel_train)
email_nbayes.fit()
error_rate = autotest.eval_predict(email_nbayes, emailmat_test,
emaillabel_test, self.logging)
self.tlog("spam-mail predict (with NaiveBayes) error rate : " +
str(error_rate))
assert error_rate <= 0.1
