test

functions/single_similar.py

@@ -2,13 +2,27 @@ import pandas as pd
 import numpy as np
 
 def find_similar(p_index, similarity_matrix, filtered_df, top_x):
-    selected_row = similarity_matrix[p_index]
+
+    # filter out just projects from filtered df
     filtered_indices = filtered_df.index.tolist()
     print(filtered_indices)
 
-    index_position_mapping = {index: position for position, index in enumerate(filtered_indices)}
+    index_position_mapping = {position: index for position, index in enumerate(filtered_indices)}
     print(index_position_mapping)
 
-    return "top_projects_df"
+    filtered_column_sim_matrix = similarity_matrix[:, filtered_indices]
+
+    # filter out the row of the selected poject
+    project_row = filtered_column_sim_matrix[p_index]
+    sorted_indices = np.argsort(project_row)
+    top_10_indices_descending = sorted_indices[-10:][::-1]
+    top_10_original_indices = [index_position_mapping[position] for position in top_10_indices_descending]
+
+    top_10_values_descending = project_row[top_10_indices_descending]
+
+    result_df = filtered_df.iloc[top_10_original_indices]
+    result_df["similarity"] = top_10_values_descending
+
+    return result_df
 
 

similarity_page.py

@@ -351,5 +351,6 @@ def show_single_matching_page():
         if isinstance(filtered_df_s, pd.DataFrame) and len(filtered_df_s) != 0:
 
             top_projects_df = find_similar(selected_project_index, sim_matrix, filtered_df_s, 10)
+            st.dataframe(top_projects_df)
             #show_single_table(top_projects_df)