Remove duplicates from the solutions

src/processing.py

@@ -1,16 +1,8 @@
 from preprocessing import parse_file
-from pandas import DataFrame, Series
+from pandas import DataFrame
 from sys import argv
 
 
-def get_furthest_element(element, data):
-    element_df = data.query(f"source == {element} or destination == {element}")
-    furthest_index = element_df["distance"].idxmax()
-    furthest_row = data.iloc[furthest_index]
-    print(furthest_row)
-    return furthest_row
-
-
 def get_first_solution(n, data):
     distance_sum = DataFrame(columns=["point", "distance"])
     for element in range(n):
@@ -24,16 +16,36 @@ def get_first_solution(n, data):
     return furthest_row
 
 
+def get_different_element(original, row):
+    if row.source == original:
+        return row.destination
+    return row.source
+
+
+def get_furthest_element(element, data):
+    element_df = data.query(f"source == {element} or destination == {element}")
+    furthest_index = element_df["distance"].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
+
+
 def greedy_algorithm(n, m, data):
     solutions = DataFrame(columns=["point", "distance"])
     first_solution = get_first_solution(n, data)
     solutions = solutions.append(first_solution, ignore_index=True)
     for _ in range(m):
-        centroid = solutions.apply(get_furthest_element, 1, data)
-        solutions = solutions.append(centroid)
+        last_solution = solutions["point"].tail(n=1)
+        centroid, furthest_index = get_furthest_element(
+            element=int(last_solution), data=data
+        )
+        solutions = solutions.append(dict(centroid), ignore_index=True)
+        data = data.drop(furthest_index)
+    return solutions
 
 
-# NOTE In each step, switch the element that gives the least amount
+# NOTE In each step, switch to the element that gives the least amount
 def local_search():
     pass
 
@@ -47,7 +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__":