Spaces:
Running
Running
File size: 5,974 Bytes
ad12f7d cd3cab0 ad12f7d cd3cab0 ad12f7d cd3cab0 ad12f7d cd3cab0 ad12f7d cd3cab0 ad12f7d cd3cab0 ad12f7d 53feba4 ad12f7d 5a1cec5 53feba4 ad12f7d 53feba4 ad12f7d cd3cab0 ad12f7d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 |
import pandas as pd
from sklearn.model_selection import train_test_split
import torch
from torch.utils.data import DataLoader, Dataset
from transformers import BertTokenizer, BertForSequenceClassification, AdamW
from transformers import get_linear_schedule_with_warmup
import numpy as np
from sklearn.metrics import accuracy_score, classification_report
import streamlit as st
# Load and preprocess the IMDb dataset
data_url = "https://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz"
df = pd.read_csv(data_url)
df['label'] = df['sentiment'].map({'positive': 1, 'negative': 0})
train_df, test_df = train_test_split(df, test_size=0.2, random_state=42)
train_df.to_csv('train.csv', index=False)
test_df.to_csv('test.csv', index=False)
class SentimentDataset(Dataset):
def __init__(self, dataframe, tokenizer, max_len):
self.tokenizer = tokenizer
self.data = dataframe
self.max_len = max_len
def __len__(self):
return len(self.data)
def __getitem__(self, index):
review = str(self.data.iloc[index, 0])
label = self.data.iloc[index, 1]
encoding = self.tokenizer.encode_plus(
review,
add_special_tokens=True,
max_length=self.max_len,
return_token_type_ids=False,
pad_to_max_length=True,
return_attention_mask=True,
return_tensors='pt',
)
return {
'review_text': review,
'input_ids': encoding['input_ids'].flatten(),
'attention_mask': encoding['attention_mask'].flatten(),
'labels': torch.tensor(label, dtype=torch.long)
}
def train_epoch(model, data_loader, loss_fn, optimizer, device, scheduler, n_examples):
model = model.train()
losses = []
correct_predictions = 0
for d in data_loader:
input_ids = d["input_ids"].to(device)
attention_mask = d["attention_mask"].to(device)
labels = d["labels"].to(device)
outputs = model(
input_ids=input_ids,
attention_mask=attention_mask
)
loss = loss_fn(outputs.logits, labels)
correct_predictions += torch.sum(torch.argmax(outputs.logits, dim=1) == labels)
losses.append(loss.item())
loss.backward()
optimizer.step()
scheduler.step()
optimizer.zero_grad()
return correct_predictions.double() / n_examples, np.mean(losses)
def eval_model(model, data_loader, loss_fn, device, n_examples):
model = model.eval()
losses = []
correct_predictions = 0
with torch.no_grad():
for d in data_loader:
input_ids = d["input_ids"].to(device)
attention_mask = d["attention_mask"].to(device)
labels = d["labels"].to(device)
outputs = model(
input_ids=input_ids,
attention_mask=attention_mask
)
loss = loss_fn(outputs.logits, labels)
correct_predictions += torch.sum(torch.argmax(outputs.logits, dim=1) == labels)
losses.append(loss.item())
return correct_predictions.double() / n_examples, np.mean(losses)
def create_data_loader(df, tokenizer, max_len, batch_size):
ds = SentimentDataset(
dataframe=df,
tokenizer=tokenizer,
max_len=max_len
)
return DataLoader(
ds,
batch_size=batch_size,
num_workers=4
)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
# Load data
train_df = pd.read_csv('train.csv')
test_df = pd.read_csv('test.csv')
# Create data loaders
BATCH_SIZE = 16
MAX_LEN = 128
train_data_loader = create_data_loader(train_df, tokenizer, MAX_LEN, BATCH_SIZE)
test_data_loader = create_data_loader(test_df, tokenizer, MAX_LEN, BATCH_SIZE)
EPOCHS = 2
optimizer = AdamW(model.parameters(), lr=2e-5, correct_bias=False)
total_steps = len(train_data_loader) * EPOCHS
scheduler = get_linear_schedule_with_warmup(
optimizer,
num_warmup_steps=0,
num_training_steps=total_steps
)
loss_fn = torch.nn.CrossEntropyLoss().to(device)
model = model.to(device)
# Training loop
for epoch in range(EPOCHS):
train_acc, train_loss = train_epoch(
model,
train_data_loader,
loss_fn,
optimizer,
device,
scheduler,
len(train_df)
)
print(f'Epoch {epoch + 1}/{EPOCHS}')
print(f'Train loss {train_loss} accuracy {train_acc}')
val_acc, val_loss = eval_model(
model,
test_data_loader,
loss_fn,
device,
len(test_df)
)
print(f'Val loss {val_loss} accuracy {val_acc}')
# Save the model
model.save_pretrained('bert-sentiment-model')
tokenizer.save_pretrained('bert-sentiment-model')
# Streamlit app
model = BertForSequenceClassification.from_pretrained('bert-sentiment-model')
tokenizer = BertTokenizer.from_pretrained('bert-sentiment-model')
model = model.eval()
def predict_sentiment(text):
encoding = tokenizer.encode_plus(
text,
add_special_tokens=True,
max_length=128,
return_token_type_ids=False,
pad_to_max_length=True,
return_attention_mask=True,
return_tensors='pt',
)
input_ids = encoding['input_ids']
attention_mask = encoding['attention_mask']
with torch.no_grad():
outputs = model(input_ids, attention_mask=attention_mask)
probabilities = torch.nn.functional.softmax(outputs.logits, dim=1)
predicted_class = torch.argmax(probabilities, dim=1).item()
return 'positive' if predicted_class == 1 else 'negative'
st.title("Sentiment Analysis with BERT")
user_input = st.text_area("Enter a movie review:")
if st.button("Analyze"):
sentiment = predict_sentiment(user_input)
st.write(f'The sentiment of the review is: **{sentiment}**')
|