diff --git a/src/processing.py b/src/processing.py
index 3dad429..b39d140 100644
--- a/src/processing.py
+++ b/src/processing.py
@@ -12,7 +12,7 @@ def get_first_solution(n, data):
         distance_sum = distance_sum.append(
             {"point": element, "distance": distance}, ignore_index=True
         )
-    furthest_index = distance_sum["distance"].idxmax()
+    furthest_index = distance_sum["distance"].astype(float).idxmax()
     furthest_row = distance_sum.iloc[furthest_index]
     furthest_row["distance"] = 0
     return furthest_row
@@ -26,13 +26,14 @@ def get_different_element(original, row):
 
 def get_furthest_element(element, data):
     element_df = data.query(f"source == {element} or destination == {element}")
-    furthest_index = element_df["distance"].idxmax()
+    furthest_index = element_df["distance"].astype(float).idxmax()
     furthest_row = data.iloc[furthest_index]
     furthest_point = get_different_element(original=element, row=furthest_row)
     furthest_element = {"point": furthest_point, "distance": furthest_row["distance"]}
     return furthest_element, furthest_index
 
 
+# FIXME Remove duplicated elements properly
 def greedy_algorithm(n, m, data):
     solutions = DataFrame(columns=["point", "distance"])
     first_solution = get_first_solution(n, data)
@@ -50,7 +51,6 @@ def get_pseudorandom_solution(n, data):
     return data.iloc[randint(a=0, b=n)]
 
 
-# NOTE In each step, switch to the element that gives the least amount
 def local_search(n, m, data):
     solutions = DataFrame(columns=["point", "distance"])
     first_solution = get_pseudorandom_solution(n=n, data=data)
@@ -74,6 +74,7 @@ def show_results(solutions):
     distance_sum = solutions["distance"].sum()
     print(solutions)
     print("Total distance: " + str(distance_sum))
+    print(solutions.duplicated())
 
 
 def usage(argv):