ikoghoemmanuell commited on
Commit
c02fdf2
1 Parent(s): 6a8724c

Delete app

Browse files
Files changed (1) hide show
  1. app/app.py +0 -66
app/app.py DELETED
@@ -1,66 +0,0 @@
1
- import streamlit as st
2
- import transformers
3
- import torch
4
-
5
- # Load the model and tokenizer
6
- model = transformers.AutoModelForSequenceClassification.from_pretrained("ikoghoemmanuell/finetuned_sentiment_model")
7
- tokenizer = transformers.AutoTokenizer.from_pretrained("ikoghoemmanuell/finetuned_sentiment_tokenizer")
8
-
9
- # Define the function for sentiment analysis
10
- @st.cache_resource
11
- def predict_sentiment(text):
12
- # Load the pipeline.
13
- pipeline = transformers.pipeline("sentiment-analysis")
14
-
15
- # Predict the sentiment.
16
- prediction = pipeline(text)
17
- sentiment = prediction[0]["label"]
18
- score = prediction[0]["score"]
19
-
20
- return sentiment, score
21
-
22
- # Setting the page configurations
23
- st.set_page_config(
24
- page_title="Sentiment Analysis App",
25
- page_icon=":smile:",
26
- layout="wide",
27
- initial_sidebar_state="auto",
28
- )
29
-
30
- # Add description and title
31
- st.write("""
32
- # How Positive or Negative is your Text?
33
- Enter some text and we'll tell you if it has a positive, negative, or neutral sentiment!
34
- """)
35
-
36
-
37
- # Add image
38
- image = st.image("https://i0.wp.com/thedatascientist.com/wp-content/uploads/2018/10/sentiment-analysis.png", width=400)
39
-
40
- # Get user input
41
- text = st.text_input("Enter some text here:")
42
-
43
- # Define the CSS style for the app
44
- st.markdown(
45
- """
46
- <style>
47
- body {
48
- background-color: #f5f5f5;
49
- }
50
- h1 {
51
- color: #4e79a7;
52
- }
53
- </style>
54
- """,
55
- unsafe_allow_html=True
56
- )
57
-
58
- # Show sentiment output
59
- if text:
60
- sentiment, score = predict_sentiment(text)
61
- if sentiment == "Positive":
62
- st.success(f"The sentiment is {sentiment} with a score of {score*100:.2f}%!")
63
- elif sentiment == "Negative":
64
- st.error(f"The sentiment is {sentiment} with a score of {score*100:.2f}%!")
65
- else:
66
- st.warning(f"The sentiment is {sentiment} with a score of {score*100:.2f}%!")