--- title: Project10thweek emoji: 👁 colorFrom: pink colorTo: purple sdk: streamlit sdk_version: 1.31.0 app_file: app.py pinned: false license: mit --- ## cv_project # Natural language processing🙂 Elbrus Bootcamp | Phase-2 | Team Project ## Team🧑🏻‍💻 1. [Baidildin Yerlan ](https://github.com/YerlanBaidildin) 2. [Timofeeva Ekaterina](https://github.com/katyyyyyas) 3. [Shatalova Oksana](https://github.com/datascientist23) ## Task 📌 Build a text classification application using different machine learning models🗂️ ## Contents 📝 1.Classification of restaurant reviews 🍱 🤖Classic ML algorithm trained on the BagOfWords/TF-IDF representation 🤖RNN or LSTM model (preferably use the attention option) 🤖BERT based [Dataset](https://drive.google.com/file/d/1WYabAzbgvqTGIMJodx8nkc4C1ZDL9nVU/view) 2.Classification of news topics from telegram channels🗞️ 🤖Rubert-tiny2 [Dataset](https://github.com/Elbrus-DataScience/nlp_gpt_team/blob/master/tg_channels.feather) ## Deployment 🎈 The service is implemented on [Huggingface](https://huggingface.co/spaces/katyyyyyas/project10thweek)🤗 ## Libraries 📖 ```python import streamlit as st import torch from transformers import AutoTokenizer, AutoModel import joblib import numpy as np import json import pandas as pd from gensim.models import Word2Vec import time from typing import Tuple from torch.utils.data import DataLoader, TensorDataset import torch.nn.functional as F import torch.nn as nn from torchmetrics import Accuracy from torchmetrics.functional import f1_score from string import punctuation import sklearn as sk import os from sklearn.linear_model import LogisticRegression ``` ## Guide 📜 #### How to run locally? 1. To create a Python virtual environment for running the code, enter: ``python3 -m venv myvenv`` 2. Activate the new environment: * Windows: ```myvenv\Scripts\activate.bat``` * macOS and Linux: ```source myvenv/bin/activate``` 3. Install all dependencies from the *requirements.txt* file: ``pip install -r requirements.txt`` Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference