File size: 4,652 Bytes
0645704
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import torch
import torch.nn as nn
import torch.optim as optim
import pandas as pd
import numpy as np
import urllib.request
import zipfile
import os

from torch.utils.data import Dataset, DataLoader
from sklearn.model_selection import train_test_split
from transformers import BertTokenizer, BertModel
from model import SentimentClassifier
# Download dataset
url = "https://archive.ics.uci.edu/ml/machine-learning-databases/00331/sentiment%20labelled%20sentences.zip"
filename = "sentiment.zip"

if not os.path.exists(filename):
    urllib.request.urlretrieve(url, filename)

# Extract dataset
with zipfile.ZipFile(filename, 'r') as zip_ref:
    zip_ref.extractall()

# Load dataset
filepath_dict = {'yelp':   'sentiment labelled sentences/yelp_labelled.txt',
                 'amazon': 'sentiment labelled sentences/amazon_cells_labelled.txt',
                 'imdb':   'sentiment labelled sentences/imdb_labelled.txt'}

df_list = []
for source, filepath in filepath_dict.items():
    df = pd.read_csv(filepath, names=['sentence', 'label'], sep='\t')
    df['source'] = source
    df_list.append(df)

df = pd.concat(df_list)

# Split dataset into train and test sets
sentences = df['sentence'].values
labels = df['label'].values
train_sentences, test_sentences, train_labels, test_labels = train_test_split(
    sentences, labels, test_size=0.25)

# Define tokenizer
tokenizer = BertTokenizer.from_pretrained(
    'bert-base-uncased', do_lower_case=True)

# Define dataset


class SentimentDataset(Dataset):
    def __init__(self, sentences, labels, tokenizer, max_len):
        self.sentences = sentences
        self.labels = labels
        self.tokenizer = tokenizer
        self.max_len = max_len

    def __len__(self):
        return len(self.sentences)

    def __getitem__(self, item):
        sentence = str(self.sentences[item])
        label = self.labels[item]

        encoding = self.tokenizer.encode_plus(
            sentence,
            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 {'sentence': sentence,
                'input_ids': encoding['input_ids'].flatten(),
                'attention_mask': encoding['attention_mask'].flatten(),
                'label': torch.tensor(label, dtype=torch.long)}

# Define model


# Set device
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# Define hyperparameters
MAX_LEN = 100
BATCH_SIZE = 16
EPOCHS = 5

# Define dataloaders
train_dataset = SentimentDataset(
    train_sentences, train_labels, tokenizer, MAX_LEN)
test_dataset = SentimentDataset(
    test_sentences, test_labels, tokenizer, MAX_LEN)
train_dataloader = DataLoader(
    train_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=4)
test_dataloader = DataLoader(
    test_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=4)

# Define model and optimizer
model = SentimentClassifier(2)
model = model.to(device)
optimizer = optim.Adam(model.parameters(), lr=2e-5)

# Define loss function
criterion = nn.CrossEntropyLoss()

# Train model
for epoch in range(EPOCHS):
    print('Epoch:', epoch+1)
    train_loss = 0
    train_acc = 0

    model.train()
    for batch in train_dataloader:
        input_ids = batch['input_ids'].to(device)
        attention_mask = batch['attention_mask'].to(device)
        labels = batch['label'].to(device)

        optimizer.zero_grad()

        outputs = model(input_ids=input_ids, attention_mask=attention_mask)

        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        train_loss += loss.item()
        train_acc += (outputs.argmax(1) == labels).sum().item()

    train_loss /= len(train_dataloader)
    train_acc /= len(train_dataset)

    print('Train loss:', train_loss, 'Train accuracy:', train_acc)

    model.eval()
    test_loss = 0
    test_acc = 0

    with torch.no_grad():
        for batch in test_dataloader:
            input_ids = batch['input_ids'].to(device)
            attention_mask = batch['attention_mask'].to(device)
            labels = batch['label'].to(device)

            outputs = model(input_ids=input_ids, attention_mask=attention_mask)

            loss = criterion(outputs, labels)

            test_loss += loss.item()
            test_acc += (outputs.argmax(1) == labels).sum().item()

    test_loss /= len(test_dataloader)
    test_acc /= len(test_dataset)

    print('Test loss:', test_loss, 'Test accuracy:', test_acc)

torch.save(model.cpu().state_dict(), 'sentiment_model.pth')