def compute_quality_for_corpus(corpus_dir):
truth_dic = methods.read_classification_from_file(methods.add_slash(corpus_dir)+"!truth.txt")
pred_dic = methods.read_classification_from_file(methods.add_slash(corpus_dir)+"!prediction.txt")
bc1 = BinaryConfusionMatrix('SPAM', 'OK')
bc1.compute_from_dicts(truth_dic, pred_dic)
dict_score = bc1.as_dict()
fn=dict_score['fn']
tn=dict_score['tn']
fp=dict_score['fp']
tp=dict_score['tp']
return quality_score(tp, tn, fp, fn), tp, tn, fp, fn
def train(self,path_to_truth_dir):
corpus = Corpus(path_to_truth_dir)
#Read truth file
truth = methods.read_classification_from_file(methods.add_slash(path_to_truth_dir)+"!truth.txt")
#Make truth global
self.truth = truth
for fname, body in corpus.emails_as_string():
email_as_file = open(methods.add_slash(path_to_truth_dir) + fname,'r',encoding = 'utf-8')
#Read email with EMAIL parser
msg = email.message_from_file(email_as_file)
self.extract_senders_list(msg,fname)
self.check_subject(msg,fname)
#Generate dict's
methods.generate_file_from_dict(self.path_bl , self.black_list)
methods.generate_file_from_dict(self.path_wl ,self.white_list)
methods.generate_file_from_dict(self.path_ssl , self.spam_subject_list)
methods.generate_file_from_dict(self.path_hsl ,self.ham_subject_list)
def is_spam(self,email_name):
my_dict = methods.read_classification_from_file(self.path,'!truth.txt')
if (my_dict[email_name] == 'SPAM'):
return True
return False