def __init__(self, folder):
self.folder = folder
self.spams = []
self.hams = []
corp = Corpus(folder)
for fname, content in corp.emails():
if self.is_ham(fname):
self.hams.append(Email(fname, content))
else:
self.spams.append(Email(fname, content))
def test(self, directory):
corp = Corpus(directory)
result = {}
if self.trained:
for fname, body in corp.emails():
SpamSum = 0
HamSum = 0
examined = Email(fname, body)
for spam in self.spams:
SpamSum += Email.compare_emails(examined, spam)
for ham in self.hams:
HamSum += Email.compare_emails(examined, ham)
if SpamSum / len(self.spams) > HamSum / len(self.hams):
result[fname] = 'SPAM'
else:
result[fname] = 'OK'
write_classification_to_file(
directory + os.path.sep + '!prediction.txt', result)
else:
for fname, body in corp.emails():
counter = 0
for word in self.blacklist:
if word in body:
counter += 1
if counter > 3:
result[fname] = 'SPAM'
else:
result[fname] = 'OK'
write_classification_to_file(
directory + os.path.sep + '!prediction.txt', result)
#coding: utf-8
from my_email import Email
e = Email()
e.send_mail('윤준연', '*****@*****.**')
e.send_mail('윤준연', '*****@*****.**', 'emails.xlsx')
e.send_mail('윤준연', '*****@*****.**', 'd:\emails.xlsx')
from my_email import Email
from my_news import News
from my_excel import Excel
m_email = Email()
m_news = News()
m_excel = Excel()
news_list = m_news.find_news('fascampus')
m_email.from_email = '*****@*****.**'
m_email.to_email = '*****@*****.**'
m_email.subject = 'Dear. '
for news in news_list:
m_email.contents = m_email.contents + news + '\n'
m_email.send_mail()
m_excel.excel_file = 'result.xlsx'
m_excel.save_to_excel(news_list)
from my_email import Email
class Corpus:
def __init__(self, folder):
self.folder = folder
self.files = os.listdir(folder)
def emails(self):
# ignore some file
for file in self.files:
if file[0] == '!':
continue
filePath = self.folder + os.path.sep + file
with open(filePath, 'rt', encoding='utf-8') as f:
yield file, f.read()
if __name__ == "__main__":
path = "data\\2"
corpus = Corpus(path)
count = 0
# Go through all emails and print the filename and the message body
for fname, body in corpus.emails():
print(fname)
print(body)
print('-------------------------')
count += 1
email = Email(fname, body)
print('Finished: ', count, 'files processed.')
def detectLanguagesMails(repertory, out, LFRA, LENG, n=1, Type=False):
file_FRA = open(LFRA, "r")
learning_FRA = ""
for line in file_FRA:
learning_FRA += line
file_FRA.close()
file_ENG = open(LENG, "r")
learning_ENG = ""
for line in file_ENG:
learning_ENG += line
file_ENG.close()
detector = LangDetectorByNGrams()
detector.addDocument(learning_FRA, "french", n, Type)
detector.addDocument(learning_ENG, "english", n, Type)
SW_detect = LangDectectorStopWords()
language_mails = dict()
language_paragraphes = dict()
language_sentences = dict()
language_mails["conflicts"] = 0
globalfile = ""
nb_mails = 0
nb_paragraph = 0
GLOBAL_F = open(out + "/global.txt", 'w')
os.chdir(repertory)
for mails in glob.glob("*"):
name = re.search('(.*)', mails)
name_file = str(out + "/" + name.group(1) + ".detect")
print(name_file)
FILE = open(name_file, 'w')
e = Email(mails)
body = e.get_body()
detectN = detector.detect(body, n, Type)
if isinstance(detectN, list):
language = detectN[0][0]
else:
language = detectN
if language not in language_mails:
language_mails[language] = 0
language_mails[language] += 1
globalfile += (name.group(1) + "\t" + language)
language_by_SW = SW_detect.stopWords_detect(body)
FILE.write("Le mail \"" + name.group(1) + "\" est globalement en : " +
language)
if language != language_by_SW:
language_mails["conflicts"] += 1
FILE.write(" (conflict)")
globalfile += " (conflict)"
globalfile += "\n"
FILE.write("\n" + str(detectN) + "\n")
FILE.write("Language by Stop Words : " + language_by_SW + "\n")
FILE.write(
"\n\n+++++++++++++++++++++++++++++++++++++++++++++++++\n+++++++++++++++++++++++++++++++++++++++++++++++++\n"
)
detectN = detector.detect(e.get_subject(), n, Type)
if isinstance(detectN, list):
language = detectN[0][0]
else:
language = detectN
FILE.write("Le sujet du mail est en : " + language + "\n")
FILE.write("Subject : " + e.get_subject() + "\n")
FILE.write(
"\n\n+++++++++++++++++++++++++++++++++++++++++++++++++\n+++++++++++++++++++++++++++++++++++++++++++++++++\n"
)
i = 0
for paragraph in cuttingText.getSubsections(body):
i += 1
detectN = detector.detect(paragraph, n, Type)
if isinstance(detectN, list):
language = detectN[0][0]
else:
language = detectN
if language not in language_paragraphes:
language_paragraphes[language] = 0
language_paragraphes[language] += 1
FILE.write("Le paragraphe " + str(i) + " est en : " + language +
"\n\t" + paragraph +
"\n\n==========================================\n")
nb_paragraph += 1
j = 0
FILE.write(
"\n\n+++++++++++++++++++++++++++++++++++++++++++++++++\n+++++++++++++++++++++++++++++++++++++++++++++++++\n"
)
for sentence in cuttingText.getSentences(body):
j += 1
detectN = detector.detect(sentence, n, Type)
if isinstance(detectN, list):
language = detectN[0][0]
else:
language = detectN
if language not in language_sentences:
language_sentences[language] = 0
language_sentences[language] += 1
FILE.write("La phrase " + str(j) + " est en : " + language +
"\n\t" + sentence +
"\n==========================================\n")
FILE.close()
nb_mails += 1
GLOBAL_F.write("Nombre de mails total : " + str(nb_mails) + "\n")
for language in language_mails:
GLOBAL_F.write("\t- en " + language + " : " +
str(language_mails[language]) + "\n")
GLOBAL_F.write("Nombre de paragraphes total : " +
str(sum(language_paragraphes.values())) + " (moyenne : " +
str(sum(language_paragraphes.values()) / nb_mails) + ")\n")
for language in language_paragraphes:
GLOBAL_F.write("\t- en " + language + " : " +
str(language_paragraphes[language]) + "\n")
GLOBAL_F.write("Nombre de phrases total : " +
str(sum(language_sentences.values())) + " (moyenne : " +
str(sum(language_sentences.values()) / nb_mails) + ")\n")
for language in language_sentences:
GLOBAL_F.write("\t- en " + language + " : " +
str(language_sentences[language]) + "\n")
GLOBAL_F.write("\n" + globalfile)
GLOBAL_F.close()
