Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

added comments on rnn code #1

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

added comments on rnn code #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions engagement_score_model/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ def forward(self, text, text_lengths):
packed_output, (hidden, cell) = self.rnn(packed_embedded)

#unpack sequence
# TODO: are we using this?
output, output_lengths = nn.utils.rnn.pad_packed_sequence(packed_output)

#output = [sent len, batch size, hid dim * num directions]
Expand Down
10 changes: 6 additions & 4 deletions engagement_score_model/rnn_regressor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@
tweetFile = '../twitter/data/test.csv'
userFile = '../clustering/clusters.csv'
oFile = './engagement.csv'
weight_path = 'lstm_model.pt'

torch.manual_seed(SEED)
torch.backends.cudnn.deterministic = True
Expand Down Expand Up @@ -84,6 +85,7 @@
model.embedding.weight.data[UNK_IDX] = torch.zeros(EMBEDDING_DIM)
model.embedding.weight.data[PAD_IDX] = torch.zeros(EMBEDDING_DIM)
optimizer = optim.Adam(model.parameters())
# Should we use L1Loss or SmoothL1Loss? How do we feel about outliers?
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I did not check in my latest code. Since we decided to frame this as a classification task (negative, neutral, positive), the loss should be CE loss. I didn't realize that my latest code didn't make it in.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

criterion = nn.BCEWithLogitsLoss()

criterion = nn.MSELoss()

model = model.to(device)
Expand All @@ -107,15 +109,15 @@

if valid_loss < best_valid_loss:
best_valid_loss = valid_loss
torch.save(model.state_dict(), 'lstm_model.pt')
torch.save(model.state_dict(), weight_path)

print(f'Epoch: {epoch+1:02} | Epoch Time: {epoch_mins}m {epoch_secs}s')
print(f'\tTrain Loss: {train_loss:.3f} | Train Acc: {train_acc*100:.2f}%')
print(f'\t Val. Loss: {valid_loss:.3f} | Val. Acc: {valid_acc*100:.2f}%')

model.load_state_dict(torch.load('lstm_model.pt'))
model.load_state_dict(torch.load(weight_path))
test_loss, test_acc = util.evaluate(model, test_iterator, criterion)
print(f'Test Loss: {test_loss:.3f} | Test Acc: {test_acc*100:.2f}%')

util.predict_engagement(model, "This film is terrible", TEXT, device)
util.predict_engagement(model, "This film is great", TEXT, device)
util.predict_engagement(model, "There is a climate crisis!", TEXT, device)
util.predict_engagement(model, "There is a climate issue", TEXT, device)
4 changes: 2 additions & 2 deletions engagement_score_model/util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,6 @@ def binary_accuracy(preds, y):
"""
Returns accuracy per batch, i.e. if you get 8/10 right, this returns 0.8, NOT 8
"""
#round predictions to the closest integer
rounded_preds = torch.round(torch.sigmoid(preds))
correct = (rounded_preds == y).float() #convert into float for division
acc = correct.sum() / len(correct)
Expand Down Expand Up @@ -104,7 +103,7 @@ def construct_engagement_score_ds( tweetFile, userFile ):
parentFollower = tweet['follower_count'].values[0]+1
curTweetEntry.append( tweet['clean_text'].values[0] )
replyDf = tweetDf[tweetDf[parentIdCol]==pId]
#Shifting to polarity to [0 to 2]
#Shifting to polarity to [0 to 2] TODO: why aren't we using the continous value as a feature?
replyDf.loc[:,egmtCol] = np.log((( replyDf['favorite_count'] +
replyDf['retweet_count'] + 1) * ( replyDf['polarity'] + 1 ) /
parentFollower ).values[0] + 1E-15)
Expand All @@ -114,6 +113,7 @@ def construct_engagement_score_ds( tweetFile, userFile ):
curTweetEntry.append( replyDf[replyDf[usrGrpCol]==grp]
[egmtCol].mean() )
else:
# What is this -15?
curTweetEntry.append( -15 )
engagementDf.append( curTweetEntry )

Expand Down