def train_dir(directory, cls, bool_model, bool_feat, ntf_model, ntf_feat):
for f in NBmodel.get_files(directory):
bool_ex = NBmodel.munge_Boolean(f, bool_feat)
ntf_ex = NBmodel.munge_NTF(f, ntf_feat)
bool_model.train(bool_ex, cls)
ntf_model.train(ntf_ex, cls)
def _get_features_list(spam_dir, ham_dir):
def process_email(freq, filename, cls):
email = open(filename, "r")
for line in email:
tok = line.rstrip("\n").rstrip("\r").strip(" ").split(" ")
for t in tok:
freq[(cls, t)] = [freq[(cls, t)][0] + 1, freq[(cls, t)][0] + float(1 / len(tok))]
email.close()
freq = defaultdict(lambda: list([0, 0]))
for email_file in NBmodel.get_files(spam_dir):
process_email(freq, email_file, "SPAM")
for email_file in NBmodel.get_files(ham_dir):
process_email(freq, email_file, "HAM")
return freq
def train_dir(directory, cls, model):
exs = []
for f in NBmodel.get_files(directory):
exs.append(model.munge(f))
if len(exs) > 500:
for ex in exs:
model.train(ex, cls)
exs = []
def train_dir(directory, cls, model):
exs = []
for f in NBmodel.get_files(directory):
exs.append(model.munge(f))
if len(exs) > 500:
for ex in exs:
model.train(ex, cls)
exs = []
def _get_features_list(spam_dir, ham_dir):
def process_email(freq, filename, cls):
email = open(filename, 'r')
for line in email:
tok = line.rstrip("\n").rstrip("\r").strip(" ").split(" ")
for t in tok:
freq[(cls,t)] = [freq[(cls,t)][0]+1,
freq[(cls,t)][0]+float(1/len(tok))]
email.close()
freq = defaultdict(lambda: list([0,0]))
for email_file in NBmodel.get_files(spam_dir):
process_email(freq, email_file, 'SPAM')
for email_file in NBmodel.get_files(ham_dir):
process_email(freq, email_file, 'HAM')
return freq
