included book information

app.py

@@ -13,6 +13,22 @@ dataset = load_dataset("FDSRashid/embed_matn", token = Secret_token)
 df = dataset["train"].to_pandas()
 taraf_max = np.max(df['taraf_ID'].unique())
 
+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['Book'] = matn_info['bookid_hadithid'].apply(lambda x: books[books['Book_ID'] == int(x.split('_')[0])]['Book_Name'].to_list()[0])
+matn_info['Author'] = matn_info['bookid_hadithid'].apply(lambda x: books[books['Book_ID'] == int(x.split('_')[0])]['Author'].to_list()[0])
+matn_info['Hadith Number'] = matn_info['bookid_hadithid'].apply(lambda x: x.split('_')[1])
+
+
+
+joined_df = matn_info.merge(df, left_index=True, right_on='__index_level_0__')
+df = joined_df.copy()
+
+
 def plot_similarity_score(taraf_num):
     taraf_df = df[df['taraf_ID']== taraf_num]
     taraf_df['Number'] = np.arange(len(taraf_df))
@@ -25,7 +41,7 @@ def plot_similarity_score(taraf_num):
     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']]
+    return fig, fig_dis, taraf_df[['matn', 'Number', 'Book', 'Author', 'Hadith Number']]
 
 with gr.Blocks() as demo: 
   taraf_number = gr.Slider(1,taraf_max , value=10000, label="Taraf", info="Choose the Taraf to Input", step = 1)