File size: 3,172 Bytes
18ef847
8c483b2
18ef847
8c483b2
18ef847
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eb7cf2b
 
 
087fa98
 
18ef847
087fa98
e5238cb
de68813
 
 
 
 
 
 
 
18ef847
 
 
 
 
 
 
23b9d9a
73e88e8
 
 
 
 
 
 
 
 
 
 
 
 
18ef847
 
 
 
 
 
 
73e88e8
 
 
 
 
 
 
 
 
 
 
 
 
 
18ef847
 
 
 
 
73e88e8
 
 
 
 
 
18ef847
 
 
 
 
 
 
 
 
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
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
import streamlit as st

import transformers

import torch

from transformers import AutoTokenizer, AutoModelForSequenceClassification




# Define the paths of the pre-trained models

model1_path = "saisi/finetuned-Sentiment-classfication-ROBERTA-Base-model"

model2_path = "saisi/finetuned-Sentiment-classfication-DISTILBERT-model"




# Initialize the tokenizer and models for sentiment analysis

tokenizer1 = AutoTokenizer.from_pretrained(model1_path)

model1 = AutoModelForSequenceClassification.from_pretrained(model1_path)

tokenizer2 = AutoTokenizer.from_pretrained(model2_path)

model2 = AutoModelForSequenceClassification.from_pretrained(model2_path)




# Define a function to preprocess the text data

def preprocess(text):
    new_text = []
    for t in text.split(" "):
        t = '@user' if t.startswith('@') and len(t) > 1 else t
         # Replace links with 'http'
        t = 'http' if t.startswith('http') else t
        new_text.append(t)
         # Join the preprocessed text

        return " ".join(new_text)




# Define a function to perform sentiment analysis on the input text using model 1

def sentiment_analysis_model1(text):
    text = preprocess(text)
    # Tokenize the input text using the pre-trained tokenizer
    encoded_input = tokenizer1(text, return_tensors='pt')
    # Feed the tokenized input to the pre-trained model and obtain output
    output = model1(**encoded_input)
    # Obtain the prediction scores for the output
    scores_ = output[0][0].detach().numpy()
    # Apply softmax activation function to obtain probability distribution over the labels
    scores_ = torch.nn.functional.softmax(torch.from_numpy(scores_), dim=0).numpy()
    # Format the output dictionary with the predicted scores
    labels = ['Negative', 'Positive']
    scores = {l:float(s) for (l,s) in zip(labels, scores_) }
     # Return the scores
    return scores




# Define a function to perform sentiment analysis on the input text using model 2

def sentiment_analysis_model2(text):
    text = preprocess(text)
    # Tokenize the input text using the pre-trained tokenizer
    encoded_input = tokenizer1(text, return_tensors='pt')
    # Feed the tokenized input to the pre-trained model and obtain output
    output = model1(**encoded_input)
    # Obtain the prediction scores for the output
    scores_ = output[0][0].detach().numpy()
    # Apply softmax activation function to obtain probability distribution over the labels
    scores_ = torch.nn.functional.softmax(torch.from_numpy(scores_), dim=0).numpy()
    # Format the output dictionary with the predicted scores
    labels = ['Negative', 'Positive']
    scores = {l:float(s) for (l,s) in zip(labels, scores_) }
     # Return the scores
    return scores


# Define the Streamlit app

def app():
       # Define the app title
    st.title("Sentiment Analysis")
# Define the input field
    text_input = st.text_input("Enter text:")
     # Define the model selection dropdown
    model_selection = st.selectbox("Select a model:", ["Model 1", "Model 2"])




    # Perform sentiment analysis when the submit button is clicked

    if st.button("Submit"):

        if text_input