Remove duplicates in an efficient way

src/processing.py

@@ -25,16 +25,25 @@ def get_different_element(original, row):
     return row.source
 
 
-def get_furthest_element(element, data):
+def get_closest_element(element, data):
     element_df = data.query(f"source == {element} or destination == {element}")
-    furthest_index = element_df["distance"].astype(float).idxmax()
+    closest_index = element_df["distance"].astype(float).idxmin()
-    furthest_row = data.iloc[furthest_index]
+    closest_row = data.loc[closest_index]
-    furthest_point = get_different_element(original=element, row=furthest_row)
+    closest_point = get_different_element(original=element, row=closest_row)
-    return Series(data={"point": furthest_point, "distance": furthest_row["distance"]})
+    return Series(data={"point": closest_point, "distance": closest_row["distance"]})
 
 
-def remove_solution_dataset(data, solution):
+def explore_solutions(solutions, data):
-    return data.query(f"source != {solution} and destination != {solution}")
+    closest_elements = solutions["point"].apply(func=get_closest_element, data=data)
+    furthest_index = closest_elements["distance"].astype(float).idxmax()
+    return closest_elements.iloc[furthest_index]
+
+
+def remove_duplicates(current, previous, data):
+    data = data.query(
+        f"(source != {current} or destination not in @previous) and (source not in @previous or destination != {current})"
+    )
+    return data
 
 
 def greedy_algorithm(n, m, data):
@@ -42,10 +51,11 @@ def greedy_algorithm(n, m, data):
     first_solution = get_first_solution(n, data)
     solutions = solutions.append(first_solution, ignore_index=True)
     for _ in range(m):
-        last_solution = int(solutions["point"].tail(n=1))
+        element = explore_solutions(solutions, data)
-        centroid = get_furthest_element(element=last_solution, data=data)
+        solutions = solutions.append(element)
-        solutions = solutions.append(centroid, ignore_index=True)
+        data = remove_duplicates(
-        data = remove_solution_dataset(data=data, solution=last_solution)
+            current=element["point"], previous=solutions["point"], data=data
+        )
     return solutions