def train(self, emails, val_data, w2v, epochs=10, save_model=True):
optimizer = optim.RMSprop(self.parameters(),
lr=1e-3,
alpha=0.99,
momentum=0.0)
for epoch in range(epochs):
epoch_loss = 0.0
start = time.time()
# loop over each mail
for i in range(len(emails)):
optimizer.zero_grad()
loss, valid = self.predict(emails[i, :], w2v)
if valid:
# propagate the loss backward and compute the gradient
loss.backward()
# change weights based on gradient value
optimizer.step()
epoch_loss += loss.data.numpy()
end = time.time()
print 'time taken for epoch:', (end - start)
print 'loss in epoch ' + str(epoch) + ' = ' + str(epoch_loss)
if save_model:
file_name = constants.RUN_ID + '_model.pth'
self.save(file_name)
email_ids, embs = self.extract_user_embeddings()
utils.save_user_embeddings(email_ids, embs)
plots.plot_with_tsne(email_ids, embs, display_hover=False)
def train(self, emails, w2v, epochs=10, save_model=True):
loss_criteria = nn.MSELoss()
optimizer = optim.RMSprop(self.parameters(),
lr=0.0001,
alpha=0.99,
momentum=0.0)
# optimizer = optim.Adam(self.parameters(), lr=0.001, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)
email_reps = w2v.get_email_reps(emails, average=True)
for epoch in range(epochs):
print 'running epoch ', epoch
start = time.time()
epoch_loss = 0.0
for i in range(len(emails)):
sender_id = utils.get_userid(emails[i, constants.SENDER_EMAIL])
# if no word_rep was found for any of the words in the emails, ignore this case
if type(email_reps[i]) == type(None):
continue
# gets the average email embedding based on word embeddings of all the words in the mail
email_rep = email_reps[i]
recv_list = emails[i, constants.RECEIVER_EMAILS].split('|')
for recv in recv_list:
optimizer.zero_grad()
recv_id = utils.get_userid(recv)
# if sender or receiver is not an enron email id, we ignore this data point
if sender_id is None or recv_id is None:
continue
# if valid sender and receiver pairs have been found update their frequencies
self.emailid_train_freq[emails[
i,
constants.SENDER_EMAIL]] = self.emailid_train_freq.get(
emails[i, constants.SENDER_EMAIL], 0) + 1
self.emailid_train_freq[
recv] = self.emailid_train_freq.get(recv, 0) + 1
# do the forward pass
pred_email_rep = self.forward(
autograd.Variable(torch.LongTensor([sender_id])),
autograd.Variable(torch.LongTensor([recv_id])))
# compute the loss
loss = loss_criteria(
pred_email_rep,
autograd.Variable(torch.from_numpy(email_rep)))
# propagate the loss backward and compute the gradient
loss.backward()
# change weights based on gradient value
optimizer.step()
epoch_loss += loss.data.numpy()
end = time.time()
print 'time taken ', (end - start)
print 'loss in epoch ' + str(epoch) + ' = ' + str(epoch_loss)
if save_model:
file_name = constants.RUN_ID + '_model.pth'
self.save(file_name)
email_ids, embs = self.extract_user_embeddings()
utils.save_user_embeddings(email_ids, embs)
# utils.get_similar_users(email_ids, embs)
plots.plot_with_tsne(email_ids, embs, display_hover=False)
def train(self, emails, val_data, w2v, epochs=10, save_model=True):
optimizer = optim.RMSprop(self.parameters(),
lr=0.001,
alpha=0.99,
momentum=0.0)
pos_label = autograd.Variable(torch.LongTensor(
[1])) # labels for correct mails
neg_label = autograd.Variable(torch.LongTensor(
[0])) # labels for incorrect mails
neg_emails = dal.get_negative_emails(emails, fraction=1.0)
for epoch in range(epochs):
epoch_loss = 0.0
start = time.time()
for i in range(len(emails)):
optimizer.zero_grad()
loss, valid = self.predict(emails[i, :],
w2v,
label=pos_label,
training_mode=True)
if valid:
# propagate the loss backward and compute the gradient
loss.backward()
# change weights based on gradient value
optimizer.step()
epoch_loss += loss.data.numpy()
optimizer.zero_grad()
loss, valid = self.predict(neg_emails[i, :],
w2v,
label=neg_label,
training_mode=True)
if valid:
# propagate the loss backward and compute the gradient
loss.backward()
# change weights based on gradient value
optimizer.step()
epoch_loss += loss.data.numpy()
end = time.time()
print 'time taken for epoch : ', (end - start)
print 'loss in epoch ' + str(epoch) + ' = ' + str(epoch_loss)
if save_model:
file_name = constants.RUN_ID + '_model.pth'
self.save(file_name)
email_ids, embs = self.extract_user_embeddings()
utils.save_user_embeddings(email_ids, embs)
# utils.get_similar_users(email_ids, embs)
plots.plot_with_tsne(email_ids, embs, display_hover=False)