Spaces:
Runtime error
Runtime error
Upload 2 files
Browse files- book_train.csv +0 -0
- stri.py +65 -0
book_train.csv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
stri.py
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import torch
|
3 |
+
import numpy as np
|
4 |
+
import pandas as pd
|
5 |
+
from transformers import AutoTokenizer, AutoModel
|
6 |
+
|
7 |
+
st.title("Книжные рекомендации")
|
8 |
+
|
9 |
+
# Загрузка модели и токенизатора
|
10 |
+
model_name = "cointegrated/rubert-tiny2"
|
11 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
12 |
+
model = AutoModel.from_pretrained(model_name, output_hidden_states=True)
|
13 |
+
|
14 |
+
# Загрузка датасета и аннотаций к книгам
|
15 |
+
books = pd.read_csv('book_train.csv')
|
16 |
+
annot = books['annotation']
|
17 |
+
|
18 |
+
# Предобработка аннотаций и получение эмбеддингов
|
19 |
+
embeddings = []
|
20 |
+
for annotation in annot:
|
21 |
+
annotation_tokens = tokenizer.encode_plus(
|
22 |
+
annotation,
|
23 |
+
add_special_tokens=True,
|
24 |
+
max_length=128,
|
25 |
+
pad_to_max_length=True,
|
26 |
+
return_tensors='pt'
|
27 |
+
)
|
28 |
+
|
29 |
+
with torch.no_grad():
|
30 |
+
outputs = model(**annotation_tokens)
|
31 |
+
hidden_states = outputs.hidden_states
|
32 |
+
last_hidden_state = hidden_states[-2]
|
33 |
+
embeddings.append(torch.mean(last_hidden_state, dim=1).squeeze())
|
34 |
+
|
35 |
+
# Получение эмбеддинга запроса от пользователя
|
36 |
+
query = st.text_input("Введите запрос")
|
37 |
+
query_tokens = tokenizer.encode_plus(
|
38 |
+
query,
|
39 |
+
add_special_tokens=True,
|
40 |
+
max_length=128,
|
41 |
+
pad_to_max_length=True,
|
42 |
+
return_tensors='pt'
|
43 |
+
)
|
44 |
+
|
45 |
+
# Проверка, был ли введен запрос
|
46 |
+
if query:
|
47 |
+
with torch.no_grad():
|
48 |
+
query_outputs = model(**query_tokens)
|
49 |
+
query_hidden_states = query_outputs.hidden_states
|
50 |
+
query_last_hidden_state = query_hidden_states[-2]
|
51 |
+
query_embedding = torch.mean(query_last_hidden_state, dim=1).squeeze()
|
52 |
+
|
53 |
+
# Вычисление косинусного расстояния между эмбеддингом запроса и каждой аннотацией
|
54 |
+
cosine_similarities = torch.nn.functional.cosine_similarity(
|
55 |
+
query_embedding.unsqueeze(0),
|
56 |
+
torch.stack(embeddings)
|
57 |
+
)
|
58 |
+
|
59 |
+
cosine_similarities = cosine_similarities.numpy()
|
60 |
+
|
61 |
+
indices = np.argsort(cosine_similarities)[::-1]
|
62 |
+
|
63 |
+
st.header("Рекомендации")
|
64 |
+
for i in indices[:10]:
|
65 |
+
st.write(books['title'][i])
|