Upload 5 files

.gitattributes

@@ -33,3 +33,5 @@ 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.csv filter=lfs diff=lfs merge=lfs -text
+embeddings.txt filter=lfs diff=lfs merge=lfs -text

dataset.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c10dbf7a899fbf0553bf6cab5fd11abf35cf224e4e6e4f7843fdd19144c550
+size 19266108

embeddings.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b5b8bd90c7567e8b983efa49fe56a6f4d94406196bf6d89184d1cb46902624d
+size 292747747

func.py

@@ -0,0 +1,37 @@
+import pandas as pd
+import numpy as np
+import torch
+from transformers import BertModel, BertTokenizer
+from sklearn.metrics.pairwise import cosine_similarity
+
+
+tokenizer = BertTokenizer.from_pretrained("DeepPavlov/rubert-base-cased-sentence")
+model = BertModel.from_pretrained("DeepPavlov/rubert-base-cased-sentence", output_hidden_states = True)
+device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+
+
+def filter_by_ganre(df: pd.DataFrame, ganre_list: list):
+    filtered_df = df[df['ganres'].apply(lambda x: any(g in ganre_list for g in(x)))]
+    return filtered_df
+
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output['last_hidden_state']
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    sum_embeddings = torch.sum(token_embeddings * input_mask_expanded, 1)
+    sum_mask = torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+    return sum_embeddings / sum_mask
+
+def recommendation(df: pd.DataFrame, embeddings:np.array, user_text: str, n=10):
+    token_user_text = tokenizer(user_text, return_tensors='pt', padding='max_length', truncation=True, max_length=512)
+    user_embeddings = torch.Tensor().to(device)
+    model.to(device)
+    model.eval()
+    with torch.no_grad():
+        batch = {k: v.to(device) for k, v in token_user_text.items()}
+        outputs = model(**batch)
+        user_embeddings = torch.cat([user_embeddings, mean_pooling(outputs, batch['attention_mask'])])
+        user_embeddings = user_embeddings.cpu().numpy()
+    cosine_similarities = cosine_similarity(embeddings, user_embeddings.reshape(1, -1))
+    df_res = pd.DataFrame(cosine_similarities.ravel(), columns=['cos_sim']).sort_values('cos_sim', ascending=False)
+    dict_topn = df_res.iloc[:n, :].cos_sim.to_dict()
+    return dict_topn

requirements.txt

@@ -0,0 +1,77 @@
+altair==5.2.0
+attrs==23.1.0
+blinker==1.7.0
+cachetools==5.3.2
+certifi==2023.11.17
+charset-normalizer==3.3.2
+click==8.1.7
+filelock==3.13.1
+fsspec==2023.12.1
+gitdb==4.0.11
+GitPython==3.1.40
+huggingface-hub==0.19.4
+idna==3.6
+imageio==2.33.0
+importlib-metadata==6.11.0
+Jinja2==3.1.2
+joblib==1.3.2
+jsonschema==4.20.0
+jsonschema-specifications==2023.11.2
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.2.1
+numpy==1.26.2
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.18.1
+nvidia-nvjitlink-cu12==12.3.101
+nvidia-nvtx-cu12==12.1.105
+packaging==23.2
+pandas==2.1.3
+Pillow==10.1.0
+protobuf==4.25.1
+pyarrow==14.0.1
+pydeck==0.8.1b0
+Pygments==2.17.2
+python-dateutil==2.8.2
+pytz==2023.3.post1
+PyYAML==6.0.1
+referencing==0.32.0
+regex==2023.10.3
+requests==2.31.0
+rich==13.7.0
+rpds-py==0.13.2
+safetensors==0.4.1
+scikit-learn==1.3.2
+scipy==1.11.4
+sentencepiece==0.1.99
+six==1.16.0
+smmap==5.0.1
+streamlit==1.29.0
+sympy==1.12
+tenacity==8.2.3
+threadpoolctl==3.2.0
+tokenizers==0.15.0
+toml==0.10.2
+toolz==0.12.0
+torch==2.1.1
+tornado==6.4
+tqdm==4.66.1
+transformers==4.35.2
+triton==2.1.0
+typing_extensions==4.8.0
+tzdata==2023.3
+tzlocal==5.2
+urllib3==2.1.0
+validators==0.22.0
+watchdog==3.0.0
+zipp==3.17.0

shows.py

@@ -0,0 +1,67 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import ast
+
+from func import filter_by_ganre, recommendation
+
+
+
+"""
+# Умный поиск сериалов
+"""
+
+df = pd.read_csv('dataset.csv')
+embeddings = np.loadtxt('embeddings.txt')
+df['ganres'] = df['ganres'].apply(lambda x: ast.literal_eval(x))
+
+st.write(f'<p style="font-family: Arial, sans-serif; font-size: 24px; ">Количество сериалов, \
+         предоставляемых сервисом {len(df)}</p>', unsafe_allow_html=True)
+
+ganres_lst = sorted(['драма', 'документальный', 'биография', 'комедия', 'фэнтези', 'приключения', 'для детей', 'мультсериалы', 
+              'мелодрама', 'боевик', 'детектив', 'фантастика', 'триллер', 'семейный', 'криминал', 'исторический', 'музыкальные', 
+              'мистика', 'аниме', 'ужасы', 'спорт', 'скетч-шоу', 'военный', 'для взрослых', 'вестерн'])
+
+st.sidebar.header('Панель инструментов :gear:')
+choice_g = st.sidebar.multiselect("Выберите жанры", options=ganres_lst)
+n = st.sidebar.selectbox("Количество отображаемых элементов на странице", options=[5, 10, 15])
+
+
+# col3, col4 = st.columns([5,2])
+
+# with col3:
+text = st.text_input('Введите описание для рекомендации')
+
+# with col4:
+
+button = st.button('Отправить запрос', type="primary")
+    
+if text and button:
+    if len(choice_g) == 0:
+        choice_g = ganres_lst
+    filtered_df = filter_by_ganre(df, choice_g)
+    top_dict = recommendation(filtered_df, embeddings, text)
+    st.write(f'<p style="font-family: Arial, sans-serif; font-size: 18px; text-align: center;"><strong>Всего подобранных \
+         рекомендаций {len(top_dict)}</strong></p>', unsafe_allow_html=True)
+    st.write('\n')
+
+    # Отображение изображений и названий
+    for ind, sim in enumerate(top_dict):
+        col1, col2 = st.columns([3, 4]) 
+        with col1:
+            st.image(df['poster'][ind], width=300)
+        with col2:
+            st.write(f"***Название:*** {df['title'][ind]}")
+            st.write(f"***Жанр:*** {', '.join(df['ganres'][ind])}")
+            st.write(f"***Описание:*** {df['description'][ind]}")
+            similarity = round(sim, 4)
+            st.write(f"***Cosine Similarity : {similarity}***")
+            st.write(f"***Ссылка на фильм : {df['url'][ind]}***")
+
+        st.markdown(
+        "<hr style='border: 2px solid #000; margin-top: 10px; margin-bottom: 10px;'>",
+        unsafe_allow_html=True
+    )
+
+
+# streamlit run shows.py