app.py

''' To-do

Create a side bar to compare two or upload CSV

In the second tab, allow them to compare all CSV files


'''

import streamlit as st
import pandas as pd
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity

model = SentenceTransformer('paraphrase-xlm-r-multilingual-v1')

sentences = []
     
# Streamlit interface
      
st.title("Sentence Similarity")

sidebar_selectbox = st.sidebar.selectbox(
    "What would you like to work with?",
    ("Compare two sentences", "Bulk upload and mark")
)

# Streamlit form elements (default to "Compare two sentences")

if sidebar_selectbox == "Compare two sentences":

       st.subheader("Compare the similarity between two sentences")
       
       with st.form("submission_form", clear_on_submit=False):
       
              sentence_1 = st.text_input("Sentence 1 input")
              
              sentence_2 = st.text_input("Sentence 2 input")
              
              submit_button_compare = st.form_submit_button("Compare Sentences")
              
       # If submit_button_compare clicked
       if submit_button_compare:
       
              # Perform calculations
              
              # Append input sentences to 'sentences' list
              sentences.append(sentence_1)
              sentences.append(sentence_2)
              
              # Create embeddings for both sentences
              sentence_embeddings = model.encode(sentences)
              
              cos_sim = cosine_similarity(sentence_embeddings[0].reshape(1, -1), sentence_embeddings[1].reshape(1, -1))[0][0]
              cos_sim = round(cos_sim * 100) # Convert to percentage and round-off
             
                     
              st.write('Similarity between {} and {} is {}%'.format(sentence_1,
                     sentence_2, cos_sim))



if sidebar_selectbox == "Bulk upload and mark":

       st.subheader("Bulk compare similarity of sentences")
       
       # Only allow user to upload CSV files
       data_file = st.file_uploader("Upload CSV",type=["csv"])
       
       if data_file is not None:
              file_details = {"filename":data_file.name, "filetype":data_file.type, "filesize":data_file.size}
              st.write(file_details)
              df = pd.read_csv(data_file)
              st.dataframe(df)