1. 1
2. 2
3. 3
4. 4
5. 5
6. 6
7. 7
8. 8
9. 9
10. 10
11. 11
12. 12
13. 13
14. 14
15. 15
16. 16
17. 17
18. 18
19. 19
20. 20
21. 21
22. 22
23. 23
24. 24
25. 25
26. 26
27. 27
28. 28
29. 29
30. 30
31. 31
32. 32
33. 33
34. 34
35. 35
36. 36
37. 37
38. 38
39. 39
40. 40
41. 41
42. 42
43. 43
44. 44
45. 45
46. 46
47. 47
48. 48
49. 49
50. 50
51. 51
52. 52

#!/usr/bin/python3

import re
import psycopg2
import torch
import torch.nn as nn


# Fetch messages from database since it's way faster than using the API
conn = psycopg2.connect(dbname="mastodon_production")
cur = conn.cursor()
cur.execute('SELECT * FROM statuses')
statuses = cur.fetchall()

# Get the messages as plain text
# TODO: Remove punctuation and other junk
text = [re.sub(r'<[^>]*>', '', status[2]) for status in statuses]  # Use regex to remove HTML stuff
print(text[0:100])


# https://closeheat.com/blog/pytorch-lstm-text-generation-tutorial
class Model(nn.Module):
    def __init__(self, dataset):
        super(Model, self).__init__()

        self.lstm_size = 128
        self.embedding_dim = 128
        self.num_layers = 3

        n_vocab = len(dataset.uniq_words)
        self.embedding = nn.Embedding(
            num_embeddings=n_vocab,
            embedding_dim=self.embedding_dim
        )
        self.lstm = nn.LSTM(
            input_size=self.lstm_size,
            hidden_size=self.lstm_size,
            num_layers=self.num_layers,
            dropout=0.2
        )
        self.fc = nn.Linear(self.lstm_size, n_vocab)
    
    def forward(self, x, prev_state):
        embed = self.embedding(x)
        output, state = self.lstm(embed, prev_state)
        logits = self.fc(output)

        return logits, state
    
    def init_state(self, sequence_length):
        return (torch.zeros(self.num_layers, sequence_length, self.lstm_size),
                torch.zeros(self.num_layers, sequence_length, self.lstm_size))