import streamlit as st
import difflib
import pandas as pd

# Assuming you have 'lpi_df' and 'similarity' defined before this point

lpi_df = pd.read_csv('https://huggingface.co/spaces/kmrmanish/LPI_Course_Recommendation_System/blob/f273238053ba214e906f36c6e31c047cf5ed6011/Learning_Pathway_Index.csv')


st.title('Course Recommendation App')

user_input = st.text_input('Enter What You Want to Learn : ')

if user_input:
    list_of_all_titles = lpi_df['Module'].tolist()
    find_close_match = difflib.get_close_matches(user_input, list_of_all_titles)

    if find_close_match:
        close_match = find_close_match[0]
        index_of_the_course = lpi_df[lpi_df.Module == close_match].index.values[0]
        similarity_score = list(enumerate(similarity[index_of_the_course]))
        sorted_similar_course = sorted(similarity_score, key=lambda x: x[1], reverse=True)

        st.write('Courses suggested for you :')

        i = 1
        for course in sorted_similar_course:
            index = course[0]
            title_from_index = lpi_df[lpi_df.index == index]['Module'].values[0]
            if i < 30:
                st.write(f"{i}. {title_from_index}")
                i += 1

        if i == 1:
            st.write('No close matches found.')
    else:
        st.write('No close matches found.')