Update README.md
Browse files
README.md
CHANGED
@@ -10,3 +10,82 @@ pinned: false
|
|
10 |
---
|
11 |
|
12 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
13 |
+
|
14 |
+
## NLP App Hugging Face's logo
|
15 |
+
Hugging Face
|
16 |
+
# Streamlit app with computer vision 💡
|
17 |
+
Elbrus Bootcamp | Phase-2 | Team Project
|
18 |
+
|
19 |
+
## Team🧑🏻💻
|
20 |
+
1. [Awlly](https://github.com/Awlly)
|
21 |
+
2. [sakoser](https://github.com/sakoser)
|
22 |
+
3. [whoisida]https://github.com/whoisida
|
23 |
+
|
24 |
+
## Task 📌lassifi
|
25 |
+
Create a service that classifies movie reviews into good, neutral and bad categories, a service that classifies user input as toxic or non-toxic, as well as a GPT 2 based text generation service that was trained to emulate a certain author’s writing.
|
26 |
+
|
27 |
+
## Contents 📝
|
28 |
+
1. Classifies movie reviewsusing LSTM,ruBert,BOW 💨 [Dataset](https://drive.google.com/file/d/1c92sz81bEfOw-rutglKpmKGm6rySmYbt/view?usp=sharing)
|
29 |
+
2. classifies user input as toxic or non-toxi using ruBert-tiny-toxicity 📑 [Dataset](https://drive.google.com/file/d/1O7orH9CrNEhnbnA5KjXji8sgrn6iD5n-/view?usp=drive_link)
|
30 |
+
3. GPT 2 based text generation service
|
31 |
+
|
32 |
+
## Deployment 🎈
|
33 |
+
The service is implemented on [Hugging Face](https://huggingface.co/spaces/Awlly/NLP_app)
|
34 |
+
|
35 |
+
## Libraries 📖
|
36 |
+
```python
|
37 |
+
import os
|
38 |
+
import unicodedata
|
39 |
+
import nltk
|
40 |
+
from dataclasses import dataclass
|
41 |
+
import joblib
|
42 |
+
import numpy as np
|
43 |
+
import matplotlib.pyplot as plt
|
44 |
+
import torch
|
45 |
+
import torch.nn as nn
|
46 |
+
import torch.nn.functional as F
|
47 |
+
import torch.optim as optim
|
48 |
+
from torch.utils.data import DataLoader, TensorDataset
|
49 |
+
from torchvision.datasets import ImageFolder
|
50 |
+
from torchvision import datasets
|
51 |
+
from torchvision import transforms as T
|
52 |
+
from torchvision.io import read_image
|
53 |
+
from torch.utils.data import Dataset, random_split
|
54 |
+
import torchutils as tu
|
55 |
+
from transformers import GPT2LMHeadModel, GPT2Tokenizer
|
56 |
+
from typing import Tuple
|
57 |
+
from tqdm import tqdm
|
58 |
+
from transformers import AutoModel, AutoTokenizer
|
59 |
+
from transformers import AutoModelForSequenceClassification
|
60 |
+
import pydensecrf.densecrf as dcrf
|
61 |
+
import pydensecrf.utils as dcrf_utils
|
62 |
+
from preprocessing import data_preprocessing
|
63 |
+
import streamlit as st
|
64 |
+
import string
|
65 |
+
from sklearn.linear_model import LogisticRegression
|
66 |
+
import re
|
67 |
+
|
68 |
+
|
69 |
+
|
70 |
+
|
71 |
+
from preprocessing import preprocess_single_string
|
72 |
+
```
|
73 |
+
|
74 |
+
|
75 |
+
from preprocessing import data_preprocessing
|
76 |
+
|
77 |
+
|
78 |
+
|
79 |
+
|
80 |
+
## Guide 📜
|
81 |
+
#### How to run locally?
|
82 |
+
|
83 |
+
1. To create a Python virtual environment for running the code, enter:
|
84 |
+
|
85 |
+
``python3 -m venv my-env``
|
86 |
+
|
87 |
+
2. Activate the new environment:
|
88 |
+
|
89 |
+
* Windows: ```my-env\Scripts\activate.bat```
|
90 |
+
* macOS and Linux: ```source my-env/bin/activate```
|
91 |
+
|