Spaces:
Runtime error
Runtime error
milestone-3
Browse files- .gitignore +1 -0
- app.py +15 -13
- milestone_3.py +103 -0
.gitignore
CHANGED
@@ -127,3 +127,4 @@ dmypy.json
|
|
127 |
|
128 |
# Pyre type checker
|
129 |
.pyre/
|
|
|
|
127 |
|
128 |
# Pyre type checker
|
129 |
.pyre/
|
130 |
+
./data
|
app.py
CHANGED
@@ -3,6 +3,7 @@ from transformers import AutoTokenizer, RobertaForSequenceClassification
|
|
3 |
import numpy as np
|
4 |
import torch
|
5 |
|
|
|
6 |
st.title("CS482 Project Sentiment Analysis")
|
7 |
|
8 |
text = st.text_area(label="Text to be analyzed", value="This sentiment analysis app is great!")
|
@@ -13,16 +14,17 @@ analyze_button = st.button(label="Analyze")
|
|
13 |
|
14 |
st.markdown("**:red[Sentiment:]**")
|
15 |
|
16 |
-
|
17 |
-
if
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
|
|
|
3 |
import numpy as np
|
4 |
import torch
|
5 |
|
6 |
+
# assignment 2
|
7 |
st.title("CS482 Project Sentiment Analysis")
|
8 |
|
9 |
text = st.text_area(label="Text to be analyzed", value="This sentiment analysis app is great!")
|
|
|
14 |
|
15 |
st.markdown("**:red[Sentiment:]**")
|
16 |
|
17 |
+
with st.spinner(text="Analyzing..."):
|
18 |
+
if analyze_button:
|
19 |
+
if selected_model=="Model 1":
|
20 |
+
tokenizer = AutoTokenizer.from_pretrained("cardiffnlp/twitter-roberta-base-emotion")
|
21 |
+
model = RobertaForSequenceClassification.from_pretrained("cardiffnlp/twitter-roberta-base-emotion")
|
22 |
+
else:
|
23 |
+
tokenizer = AutoTokenizer.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment-latest")
|
24 |
+
model = RobertaForSequenceClassification.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment-latest")
|
25 |
+
inputs = tokenizer(text, return_tensors="pt")
|
26 |
+
with torch.no_grad():
|
27 |
+
logits = model(**inputs).logits
|
28 |
+
prediction_id = logits.argmax().item()
|
29 |
+
results = model.config.id2label[prediction_id]
|
30 |
+
st.write(results)
|
milestone_3.py
ADDED
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import DistilBertTokenizerFast, DistilBertModel, AdamW
|
2 |
+
import torch
|
3 |
+
from torch.utils.data import Dataset, DataLoader
|
4 |
+
import pandas as pd
|
5 |
+
|
6 |
+
|
7 |
+
# assignment 3
|
8 |
+
model_name = "distilbert-base-uncased"
|
9 |
+
tokenizer = DistilBertTokenizerFast.from_pretrained(model_name)
|
10 |
+
|
11 |
+
print("Reading data...")
|
12 |
+
data = pd.read_csv("./data/train.csv")
|
13 |
+
toxic_data = pd.DataFrame()
|
14 |
+
toxic_data["text"] = data["comment_text"]
|
15 |
+
toxic_data["labels"] = data.iloc[:, 2:].values.tolist()
|
16 |
+
print(toxic_data.head())
|
17 |
+
|
18 |
+
class ToxicDataset(Dataset):
|
19 |
+
|
20 |
+
def __init__(self, dataframe, tokenizer):
|
21 |
+
self.tokenizer = tokenizer
|
22 |
+
self.data = dataframe
|
23 |
+
self.text = dataframe.text
|
24 |
+
self.labels = self.data.labels
|
25 |
+
|
26 |
+
def __len__(self):
|
27 |
+
return len(self.text)
|
28 |
+
|
29 |
+
def __getitem__(self, idx):
|
30 |
+
text = str(self.text[idx])
|
31 |
+
if len(text) > 12:
|
32 |
+
text = text[:12]
|
33 |
+
|
34 |
+
inputs = self.tokenizer.encode_plus(
|
35 |
+
text,
|
36 |
+
None,
|
37 |
+
max_length=12,
|
38 |
+
add_special_tokens=True,
|
39 |
+
pad_to_max_length=True,
|
40 |
+
return_token_type_ids=True
|
41 |
+
)
|
42 |
+
|
43 |
+
ids = inputs["input_ids"]
|
44 |
+
mask = inputs["attention_mask"]
|
45 |
+
token_type_ids = inputs["token_type_ids"]
|
46 |
+
|
47 |
+
return {
|
48 |
+
"ids": torch.tensor(ids, dtype=torch.long),
|
49 |
+
"mask": torch.tensor(mask, dtype=torch.long),
|
50 |
+
"token_type_ids": torch.tensor(token_type_ids, dtype=torch.long),
|
51 |
+
"targets": torch.tensor(self.labels[idx], dtype=torch.float)
|
52 |
+
}
|
53 |
+
|
54 |
+
|
55 |
+
print("Data read. Splitting data...")
|
56 |
+
train_data = toxic_data.sample(frac=.8)
|
57 |
+
test_data = toxic_data.drop(train_data.index).reset_index(drop=True)
|
58 |
+
train_data = train_data.reset_index(drop=True)
|
59 |
+
|
60 |
+
print("Data split. Tokenizing data...")
|
61 |
+
train_set = ToxicDataset(train_data, tokenizer)
|
62 |
+
test_set = ToxicDataset(test_data, tokenizer)
|
63 |
+
|
64 |
+
train_loader = DataLoader(train_set, batch_size=8, shuffle=True, num_workers=0)
|
65 |
+
test_loader = DataLoader(test_set, batch_size=8, shuffle=True, num_workers=0)
|
66 |
+
|
67 |
+
print("Data tokenized. Beginning training...")
|
68 |
+
|
69 |
+
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
|
70 |
+
|
71 |
+
model = DistilBertModel.from_pretrained(model_name)
|
72 |
+
model.to(device)
|
73 |
+
model.train()
|
74 |
+
|
75 |
+
optim = AdamW(model.parameters(), lr=5e-5)
|
76 |
+
|
77 |
+
num_train_epochs = 2
|
78 |
+
|
79 |
+
for epoch in range(num_train_epochs):
|
80 |
+
for batch in train_loader:
|
81 |
+
optim.zero_grad()
|
82 |
+
input_ids = batch["ids"].to(device)
|
83 |
+
attention_mask = batch["mask"].to(device)
|
84 |
+
token_type_ids = batch["token_type_ids"].to(device, dtype = torch.long)
|
85 |
+
targets = batch["targets"].to(device)
|
86 |
+
|
87 |
+
outputs = model(input_ids, attention_mask, token_type_ids)
|
88 |
+
|
89 |
+
loss = torch.nn.BCEWithLogitsLoss()(outputs, targets)
|
90 |
+
loss.backward()
|
91 |
+
optim.step()
|
92 |
+
|
93 |
+
model.eval()
|
94 |
+
|
95 |
+
|
96 |
+
|
97 |
+
|
98 |
+
print("Training complete. Saving model...")
|
99 |
+
|
100 |
+
save_directory = ".results/model"
|
101 |
+
model.save_pretrained(save_directory)
|
102 |
+
|
103 |
+
print("Model saved.")
|