File size: 2,918 Bytes
55bdad4
5a40ca9
55bdad4
 
03251df
 
 
55bdad4
 
 
1ce306e
ee38f19
55bdad4
 
03251df
 
 
96db83a
a8e4a85
55bdad4
 
 
 
 
 
8b71a2e
55bdad4
 
 
ee38f19
55bdad4
 
 
 
 
a8e4a85
55bdad4
a8e4a85
55bdad4
 
 
5a40ca9
55bdad4
 
1ce306e
55bdad4
 
 
 
 
 
3bf18ee
55bdad4
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
import streamlit as st
from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer, TFAutoModelForSequenceClassification

# Options for models from transformers library
MODEL_OPTS = ['finetuned', 'default', 'bertweet-base-sentiment-analysis', 'twitter-roberta-base', 'distilRoberta-financial-sentiment']
FINETUNED_OPT = MODEL_OPTS[0]
DEFAULT_OPT = MODEL_OPTS[1]

# returns loaded model and tokenizer, if any
def load_model(opt):
    if opt not in MODEL_OPTS: print("Incorrect model selection. Try again!")
    model, tokenizer = None, None

    # Load the chosen sentiment analysis model from transformers
    if opt == FINETUNED_OPT:
        tokenizer = DistilBertTokenizerFast.from_pretrained('distilbert-base-uncased')
        model = DistilBertForSequenceClassification.from_pretrained('saccharinedreams/finetuned-distilbert-base-uncased-for-hupd')
    elif opt == DEFAULT_OPT:
        return model, tokenizer
    elif opt == 'bertweet-base-sentiment-analysis':
        tokenizer = AutoTokenizer.from_pretrained("finiteautomata/bertweet-base-sentiment-analysis")
        model = AutoModelForSequenceClassification.from_pretrained("finiteautomata/bertweet-base-sentiment-analysis")
    elif opt == 'twitter-roberta-base-sentiment':
        tokenizer = AutoTokenizer.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
        model = AutoModelForSequenceClassification.from_pretrained("cardiffnlp/twitter-roberta-base-sentiment")
    elif opt == 'distilRoberta-financial-sentiment':
        tokenizer = AutoTokenizer.from_pretrained("mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis")
        model = AutoModelForSequenceClassification.from_pretrained("mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis")
    
    elif not model and not tokenizer: 
        print("Model not loaded correctly. Try again!")

    return model, tokenizer

def sentiment_analysis(model, tokenizer):
    if model and tokenizer:
        return pipeline('text-classification', model=model, tokenizer=tokenizer)
    else: return pipeline('text-classification')

# Title the Streamlit app 'Sentiment Analysis'
st.title('Sentiment Analysis')
st.markdown('Link to the app - [sentiment-analysis-app](https://huggingface.co/spaces/saccharinedreams/sentiment-analysis-app)')

# Take in user input
user_text = st.text_input('Input text to perform sentiment analysis on here.', 'I love AI!')

# The user can interact with a dropdown menu to choose a sentiment analysis model.
dropdown_value = st.selectbox('Select one of the following sentiment analysis models', MODEL_OPTS, index=MODEL_OPTS.index(DEFAULT_OPT))
model, tokenizer = load_model(dropdown_value)

# Perform sentiment analysis on the user's input
result = sentiment_analysis(model, tokenizer)(user_text)

# Display the sentiment analysis results
st.write('Sentiment:', result[0]['label'], '; Score:', result[0]['score'])