Remove duplicates from the solutions

src/processing.py

@@ -27,7 +27,8 @@ def get_furthest_element(element, data):
     furthest_index = element_df["distance"].idxmax()
     furthest_row = data.iloc[furthest_index]
     furthest_point = get_different_element(original=element, row=furthest_row)
-    return {"point": furthest_point, "distance": furthest_row["distance"]}
+    furthest_element = {"point": furthest_point, "distance": furthest_row["distance"]}
+    return furthest_element, furthest_index
 
 
 def greedy_algorithm(n, m, data):
@@ -36,10 +37,12 @@ def greedy_algorithm(n, m, data):
     solutions = solutions.append(first_solution, ignore_index=True)
     for _ in range(m):
         last_solution = solutions["point"].tail(n=1)
-        centroid = get_furthest_element(element=int(last_solution), data=data)
+        centroid, furthest_index = get_furthest_element(
+            element=int(last_solution), data=data
+        )
         solutions = solutions.append(dict(centroid), ignore_index=True)
-        data = data.drop(centroid["point"], columns=["source", "destination"])
+        data = data.drop(furthest_index)
-    print(solutions)
+    return solutions
 
 
 # NOTE In each step, switch to the element that gives the least amount
@@ -56,7 +59,8 @@ def main():
     if len(argv) != 2:
         usage(argv)
     n, m, data = parse_file(argv[1])
-    greedy_algorithm(n, m, data)
+    solutions = greedy_algorithm(n, m, data)
+    print(solutions)
 
 
 if __name__ == "__main__":