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
+kino_mail_proc.csv filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

kino_mail_proc.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d48eb99ce42b1f541b2e3bba541738ad9c86a12de0058cf2a4354d468ab965
+size 20173069

requirements.txt

@@ -0,0 +1,101 @@
+altair==5.2.0
+asttokens==2.4.1
+attrs==23.2.0
+blinker==1.7.0
+cachetools==5.3.3
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+comm==0.2.1
+contourpy==1.2.0
+cycler==0.12.1
+debugpy==1.8.1
+decorator==5.1.1
+executing==2.0.1
+filelock==3.13.1
+fonttools==4.49.0
+fsspec==2024.2.0
+gitdb==4.0.11
+GitPython==3.1.42
+idna==3.6
+importlib-metadata==7.0.1
+ipykernel==6.29.3
+jedi==0.19.1
+Jinja2==3.1.3
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+jupyter_client==8.6.0
+jupyter_core==5.7.1
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.8.3
+matplotlib-inline==0.1.6
+mdurl==0.1.2
+mpmath==1.3.0
+nest-asyncio==1.6.0
+networkx==3.2.1
+numpy==1.26.4
+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==2.19.3
+nvidia-nvjitlink-cu12==12.3.101
+nvidia-nvtx-cu12==12.1.105
+opencv-python==4.9.0.80
+packaging==23.2
+pandas==2.2.1
+parso==0.8.3
+pexpect==4.9.0
+pillow==10.2.0
+platformdirs==4.2.0
+prompt-toolkit==3.0.43
+protobuf==4.25.3
+psutil==5.9.8
+ptyprocess==0.7.0
+pure-eval==0.2.2
+py-cpuinfo==9.0.0
+pyarrow==15.0.0
+pydeck==0.8.1b0
+Pygments==2.17.2
+pyparsing==3.1.1
+python-dateutil==2.8.2
+pytz==2024.1
+PyYAML==6.0.1
+pyzmq==25.1.2
+referencing==0.33.0
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.0
+scipy==1.12.0
+seaborn==0.13.2
+six==1.16.0
+smmap==5.0.1
+stack-data==0.6.3
+streamlit==1.31.1
+sympy==1.12
+tenacity==8.2.3
+thop==0.1.1.post2209072238
+toml==0.10.2
+toolz==0.12.1
+torch==2.2.1
+torchvision==0.17.1
+tornado==6.4
+tqdm==4.66.2
+traitlets==5.14.1
+triton==2.2.0
+typing_extensions==4.10.0
+tzdata==2024.1
+tzlocal==5.2
+ultralytics==8.1.19
+urllib3==2.2.1
+validators==0.22.0
+watchdog==4.0.0
+wcwidth==0.2.13
+zipp==3.17.0

stream_temp.py

@@ -0,0 +1,89 @@
+import streamlit as st 
+import numpy as np
+import pandas as pd
+
+
+from PIL import Image
+import base64
+from io import BytesIO
+
+from sentence_transformers import SentenceTransformer, util
+import faiss
+
+df = pd.read_csv('/home/valera/ds_bootcamp/ds-phase-2/11-nn-ext/progect/movies.csv')
+
+@st.cache_resource
+def load_model():
+    return SentenceTransformer("cointegrated/rubert-tiny2")
+model = load_model()
+        
+@st.cache_resource
+def load_vector():
+    return model.encode(df["description"])
+embeddings = load_vector()
+
+index = faiss.IndexFlatIP(embeddings.shape[1])
+index.add(embeddings)
+
+# Функция для поиска фильмов по сходству
+def find_similar_movies(user_input, top_n=5):
+    user_input = model.encode(user_input)
+    user_input = user_input.reshape(1,-1)
+    distances, indices = index.search(user_input, top_n)
+    return list(indices[0])
+
+# Загрузить изображение из файла
+img = Image.open('/home/valera/ds_bootcamp/ds-phase-2/11-nn-ext/progect/_-fotor.jpg')
+buffered = BytesIO()
+img.save(buffered, format="JPEG")
+img_str = base64.b64encode(buffered.getvalue()).decode()
+
+st.markdown(f"""
+    <style>
+    .stApp {{
+        background-image: url(data:image/jpg;base64,{img_str});
+        background-size: cover;
+    }}
+    </style>
+    """, unsafe_allow_html=True)
+
+
+random_digits = np.random.choice(len(df), size=5, replace=False)
+
+# Создать текстовое поле для ввода названия фильма
+title = st.text_input('Что хотите посмотреть сегодня?')
+if st.button('Подобрать фильм'):
+    # Использование функции
+    similar_movies = find_similar_movies(title)
+    for i in similar_movies:
+        st.title('Название фильма:')
+        st.header(df['movie_title'][i])
+        st.image('http://'+ df['img_url'][i])
+        st.title('Описание:')
+        st.write(df['description'][i])
+        st.title('Жанр:')
+        st.write("Нет данных" if pd.isna(df['genres'].iloc[i]) else df['genres'][i] ) 
+        st.title('Оценка')
+        imb = 'Нет оценки' if df['imdb'][i] == 0 else str(df['imdb'][i])
+        kinopoisk = 'Нет оценки' if df['kinopoisk'][i] == 0 else str(df['kinopoisk'][i])
+        st.write(f'Рейтинг imdb: {imb}')
+        st.write(f'Рейтинг кинопоиск: {kinopoisk}')
+        st.title('-'*45)
+
+if st.button('Выбрать случайно'):
+    for i in random_digits:
+        st.title('Название фильма:')
+        st.header(df['movie_title'][i])
+        st.image('http://'+ df['img_url'][i])
+        st.title('Описание:')
+        st.write(df['description'][i])
+        st.title('Жанр:')
+        st.write("Нет данных" if pd.isna(df['genres'].iloc[i]) else df['genres'][i] ) 
+        st.title('Оценка')
+        imb = 'Нет оценки' if df['imdb'][i] == 0 else str(df['imdb'][i])
+        kinopoisk = 'Нет оценки' if df['kinopoisk'][i] == 0 else str(df['kinopoisk'][i])
+        st.write(f'Рейтинг imdb: {imb}')
+        st.write(f'Рейтинг кинопоиск: {kinopoisk}')
+        st.title('-'*45)
+
+