app.py

import numpy as np
import gradio as gr
import os
import pandas as pd
from datasets import load_dataset
from sklearn.metrics.pairwise import cosine_similarity
from datasets import Features, Value
import plotly.express as px

features = Features({'matn': Value('string'), 'taraf_ID': Value('string'), 'bookid_hadithid': Value('string')})


Secret_token = os.getenv('HF_token')

dataset = load_dataset("FDSRashid/embed_matn", token = Secret_token)
books = load_dataset('FDSRashid/Hadith_info', data_files='Books.csv', token=Secret_token)['train'].to_pandas()
df = dataset["train"].to_pandas()

dataset = load_dataset("FDSRashid/hadith_info", data_files = 'All_Matns.csv',token = Secret_token, features = features)
matn_info = dataset['train'].to_pandas()
matn_info = matn_info.drop(97550)
matn_info = matn_info.drop(307206)
matn_info['taraf_ID'] = matn_info['taraf_ID'].replace('KeyAbsent', -1)
matn_info['taraf_ID'] = matn_info['taraf_ID'].astype(int)

matn_info['Book_ID'] = matn_info['bookid_hadithid'].apply(lambda x: int(x.split('_')[0]))
matn_info['Hadith Number'] = matn_info['bookid_hadithid'].apply(lambda x: int(x.split('_')[1]))
matn_info = pd.merge(matn_info, books, on='Book_ID')


matn_info = matn_info.reset_index()
df = df.reset_index()
cols_to_use = df.columns.difference(matn_info.columns)
joined_df = pd.merge(matn_info,df[cols_to_use],left_index=True, right_index=True)
df = joined_df.copy()
taraf_max = np.max(df['taraf_ID'].unique())

def plot_similarity_score(taraf_num):
    taraf_df = df[df['taraf_ID']== taraf_num]
    taraf_df['Number'] = np.arange(len(taraf_df))
    embed_taraf = taraf_df['embed'].to_list()
    cos_score = cosine_similarity(embed_taraf)
    fig = px.imshow(cos_score)
    matr = cos_score
    rows, cols = matr.shape
    mask = np.tril(np.ones((rows, cols), dtype=bool), k=-1)
    lower_triangle = matr[mask]
    data = lower_triangle.flatten()
    fig_dis = px.histogram(x = data,  title = f'Similarity Distribution for Taraf {taraf_num}', labels = {'x': 'Similarity Score'}, nbins = 20, template = 'ggplot2' )
    return fig, fig_dis, taraf_df[['matn', 'Number', 'Book_Name', 'Author', 'Hadith Number']]

with gr.Blocks() as demo: 
  gr.Markdown('# Semantic Similarity  Visualizer')
  taraf_number = gr.Slider(1,taraf_max , value=10000, label="Taraf", info="Choose the Taraf to Input", step = 1)
  btn = gr.Button('Submit')
  btn.click(fn = plot_similarity_score, inputs = [taraf_number], outputs = [gr.Plot(),gr.Plot(), gr.DataFrame(wrap=True)])
  demo.launch()