long1104 commited on
Commit
283d652
1 Parent(s): 93aa755

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +61 -36
app.py CHANGED
@@ -1,46 +1,71 @@
1
- import streamlit as st
2
- import transformers
3
 
4
- # Load the pre-trained language model
5
- model_name = "bert-base-uncased"
6
- model = transformers.pipeline("text-classification", model=model_name)
7
 
8
- # Streamlit App
9
- def main():
10
- st.title("Sentence Category Classifier")
11
 
12
- # Input search sentence
13
- search_query = st.text_input("Enter a sentence:")
14
 
15
- result = ""
16
 
17
- # Process the search sentence when the user clicks the Search button
18
- if st.button("Search"):
19
- if search_query:
20
- # Classify the sentence using the pre-trained model
21
- categories = classify_sentence(search_query)
22
 
23
- # Display the categories as output
24
- if categories:
25
- result = f"The sentence belongs to the following categories:\n\n"
26
- for category in categories:
27
- result += f"• {category}\n"
28
- else:
29
- result = "No categories found for the sentence."
30
 
31
- # Display the result
32
- st.text(result)
33
-
34
- # Function to classify the sentence using the pre-trained language model
35
- @st.cache(allow_output_mutation=True)
36
- def classify_sentence(query):
37
- # Classify the sentence using the pre-trained model
38
- categories = model(query)
39
 
40
- # Extract the category labels from the model's output
41
- category_labels = [category['label'] for category in categories]
42
 
43
- return category_labels
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
 
45
- if __name__ == "__main__":
46
- main()
 
 
 
 
 
1
+ # import streamlit as st
2
+ # import transformers
3
 
4
+ # # Load the pre-trained language model
5
+ # model_name = "bert-base-uncased"
6
+ # model = transformers.pipeline("text-classification", model=model_name)
7
 
8
+ # # Streamlit App
9
+ # def main():
10
+ # st.title("Sentence Category Classifier")
11
 
12
+ # # Input search sentence
13
+ # search_query = st.text_input("Enter a sentence:")
14
 
15
+ # result = ""
16
 
17
+ # # Process the search sentence when the user clicks the Search button
18
+ # if st.button("Search"):
19
+ # if search_query:
20
+ # # Classify the sentence using the pre-trained model
21
+ # categories = classify_sentence(search_query)
22
 
23
+ # # Display the categories as output
24
+ # if categories:
25
+ # result = f"The sentence belongs to the following categories:\n\n"
26
+ # for category in categories:
27
+ # result += f"• {category}\n"
28
+ # else:
29
+ # result = "No categories found for the sentence."
30
 
31
+ # # Display the result
32
+ # st.text(result)
33
+
34
+ # # Function to classify the sentence using the pre-trained language model
35
+ # @st.cache(allow_output_mutation=True)
36
+ # def classify_sentence(query):
37
+ # # Classify the sentence using the pre-trained model
38
+ # categories = model(query)
39
 
40
+ # # Extract the category labels from the model's output
41
+ # category_labels = [category['label'] for category in categories]
42
 
43
+ # return category_labels
44
+
45
+ # if __name__ == "__main__":
46
+ # main()
47
+
48
+ import streamlit as st
49
+
50
+ # Function to categorize input sentences
51
+ def categorize_sentence(sentence):
52
+ # Replace this function with your own logic to categorize sentences
53
+ categories = ['Restaurants', 'Food', 'Travel', 'New York City']
54
+ return categories
55
+
56
+ # Configure Streamlit layout
57
+ st.set_page_config(page_title='Sentence Categorizer', layout='wide')
58
+
59
+ # Add title and description
60
+ st.title('Welcome to Sentence Categorizer')
61
+ st.write('Enter a sentence and discover relevant categories!')
62
+
63
+ # Create input box
64
+ sentence = st.text_input('Enter a sentence')
65
 
66
+ # Create button to trigger categorization
67
+ if st.button('Categorize'):
68
+ st.write('Categories:')
69
+ categories = categorize_sentence(sentence)
70
+ for category in categories:
71
+ st.success(category)