Spaces:
Runtime error
Runtime error
| import streamlit as st | |
| import pandas as pd | |
| import json | |
| import numpy as np | |
| from fuzzywuzzy import fuzz | |
| import pinecone | |
| from sentence_transformers import SentenceTransformer | |
| pinecone.init(api_key='72677043-918a-4a15-9077-9c5b3cc40df9', environment='us-west4-gcp') | |
| model = SentenceTransformer('all-mpnet-base-v2',device='cpu') | |
| def process_string(s): | |
| return s.lower().replace('&', 'and') | |
| def levenshtein_distance(s1, s2): | |
| return fuzz.ratio(s1, s2) | |
| def compare_string_all(string, df): | |
| string = string.lower().replace('&', 'and') | |
| df['distance'] = df['cleaned_text'].apply(lambda x: levenshtein_distance(string, x.lower())) | |
| top_5_df = df.sort_values('distance', ascending=False).head(5) | |
| top_5_df = top_5_df[['label','Ingredients', 'distance']] | |
| return top_5_df | |
| def compare_string_label(string, df): | |
| string = string.lower().replace('&', 'and') | |
| df['distance'] = df['cleaned_label'].apply(lambda x: levenshtein_distance(string, x.lower())) | |
| top_5_df = df.sort_values('distance', ascending=False).head(5) | |
| top_5_df = top_5_df[['label','Ingredients', 'distance']] | |
| return top_5_df | |
| df= pd.read_json('cleaned.json') | |
| df['label+ingradient'] = df['label'] + ' : ' + df['Ingredients'] | |
| df['cleaned_text']= df['label+ingradient'].apply(process_string) | |
| df['cleaned_label'] = df['label'].apply(process_string) | |
| index = pinecone.Index('companiessearch') | |
| # Create a Streamlit app | |
| def main(): | |
| st.set_page_config(page_title="String Matching App", page_icon=":smiley:", layout="wide") | |
| st.title("Company name matching App :smiley:") | |
| # Define pages | |
| pages = ["Semantic search"] | |
| # Add radio buttons to toggle between pages | |
| page = st.sidebar.radio("Select a page", pages) | |
| # if page == pages[0]: | |
| # st.header("Matches using levenshtein_distance") | |
| # st.write("Enter a menu along with its ingredients:") | |
| # st.write("e.g. Pita & HUMMUS Garlic Hummus, crispy seasoned pita") | |
| # input_string = st.text_input("") | |
| # input_string= process_string(input_string) | |
| # if input_string: | |
| # st.write("Top 5 matches:") | |
| # if len(input_string.split())>4: | |
| # top_matches = compare_string_all(input_string, df) | |
| # else: | |
| # top_matches= compare_string_label(input_string, df) | |
| # st.dataframe(top_matches) | |
| if page == pages[0]: | |
| st.header("Matches using embeddings (semantic search)") | |
| st.write("Enter a company name:") | |
| st.write("e.g. Airtel Africa Plc") | |
| input_string = st.text_input("") | |
| input_string = process_string(input_string) | |
| if st.button("Enter"): | |
| st.write("Top 5 matches using semantic search:") | |
| # if len(input_string.split()) > 4: | |
| # top_matches = compare_string_all(input_string, df) | |
| # else: | |
| # top_matches = compare_string_label(input_string, df) | |
| xq = model.encode([input_string]).tolist() | |
| result = index.query(xq, top_k=10, includeMetadata=True) | |
| Name=[] | |
| Country=[] | |
| score=[] | |
| for matches in result['matches']: | |
| Name.append(matches['metadata']['name']) | |
| Country.append(matches['metadata']['Country']) | |
| score.append(matches['score']) | |
| final_result= pd.DataFrame(list(zip(Name, Country, score)), | |
| columns =['Company_name', 'Country','score' ]) | |
| st.dataframe(final_result) | |
| if __name__ == "__main__": | |
| main() | |