Upload 4 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+dataset_all.csv filter=lfs diff=lfs merge=lfs -text

book_embeddings6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c63b66f5dfb711ac7f2cb043620a29c5f3ec32bb69e61828caea3098648ef8f9
+size 36412873

dataset_all.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2c7bebcb0c5efe1685f50870fda789ea2572c782e2e661f2045abbbfbbc550
+size 46342847

requirements.txt

@@ -0,0 +1,64 @@
+altair==5.2.0
+attrs==23.2.0
+blinker==1.7.0
+cachetools==5.3.2
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+filelock==3.13.1
+fsspec==2024.2.0
+gitdb==4.0.11
+GitPython==3.1.41
+huggingface-hub==0.20.3
+idna==3.6
+importlib-metadata==7.0.1
+Jinja2==3.1.3
+joblib==1.3.2
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.2.1
+nltk==3.8.1
+numpy==1.26.4
+packaging==23.2
+pandas==2.2.0
+pillow==10.2.0
+protobuf==4.25.2
+pyarrow==15.0.0
+pydeck==0.8.1b0
+Pygments==2.17.2
+python-dateutil==2.8.2
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.33.0
+regex==2023.12.25
+requests==2.31.0
+rich==13.7.0
+rpds-py==0.17.1
+safetensors==0.4.2
+scikit-learn==1.4.0
+scipy==1.12.0
+sentence-transformers==2.3.1
+sentencepiece==0.1.99
+six==1.16.0
+smmap==5.0.1
+streamlit==1.31.0
+sympy==1.12
+tenacity==8.2.3
+threadpoolctl==3.2.0
+tokenizers==0.15.1
+toml==0.10.2
+toolz==0.12.1
+torch==2.2.0
+tornado==6.4
+tqdm==4.66.1
+transformers==4.37.2
+typing_extensions==4.9.0
+tzdata==2023.4
+tzlocal==5.2
+urllib3==2.2.0
+validators==0.22.0
+zipp==3.17.0

stream_5.py

@@ -0,0 +1,67 @@
+import streamlit as st
+import numpy as np
+import pandas as pd
+from sentence_transformers import SentenceTransformer, util
+from PIL import Image
+import requests
+import torch
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Load BERT model
+model = SentenceTransformer('cointegrated/rubert-tiny2')
+
+# Load dataset
+databook = pd.read_csv('/Users/idaklimanova/ds_bootcamp/ds-phase-2/project4/dataset_all.csv')
+
+# Load saved embeddings
+embeddings = torch.load('book_embeddings3.pth')
+
+# Function to get most similar books
+def get_most_similar_books(user_query, embeddings):
+    # Encode user query
+    query_embedding = model.encode(user_query, convert_to_tensor=True)
+    user_query = util.normalize_embeddings(query_embedding.unsqueeze(0))  # Add unsqueeze to add batch dimension
+    
+    # Convert torch tensors to numpy arrays
+    user_query_np = user_query.cpu().detach().numpy()
+    embeddings_np = embeddings.cpu().detach().numpy()
+    
+    # Calculate similarity using cosine similarity
+    similarities = cosine_similarity(user_query_np, embeddings_np)
+    
+    # Get indices of most similar books
+    indices = np.argsort(similarities[0])[::-1][:5]  # Get top 5 indices with highest cosine similarity
+    return indices
+
+
+def main():
+    st.title("Рекомендации книг")
+
+    # Get user query
+    user_query = st.text_input("Введите описание книги:")
+
+    button = st.button('Отправить запрос', type="primary")
+
+    # Show recommended books
+    if user_query:
+        st.write("Наиболее подходящие книги для вас:")
+        similar_books_indices = get_most_similar_books(user_query, embeddings)
+        for idx in similar_books_indices:
+            book = databook.iloc[idx]
+
+            # Display book cover image and description side by side
+            col1, col2 = st.columns([1, 4])  # Layout ratio 1:4
+            with col1:
+                if pd.notna(book['image_url']):
+                    try:
+                        image = Image.open(requests.get(book['image_url'], stream=True).raw)
+                        st.image(image, caption='Обложка книги', width=130)
+                    except Exception as e:
+                        st.write("Ошибка при загрузке изображения:", e)
+            with col2:
+                st.subheader(book['title'])
+                st.write(f"Автор: {book['author']}")
+                st.write(f"Описание: {book['annotation']}")
+
+if __name__ == "__main__":
+    main()