Compute the first element for the greedy algorithm

src/processing.py

@@ -1,6 +1,5 @@
 from preprocessing import parse_file
-from pandas import DataFrame
-from secrets import randbelow
+from pandas import DataFrame, Series
 from sys import argv
 
 
@@ -8,16 +7,37 @@ 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):
+        element_df = data.query(f"source == {element} or destination == {element}")
+        distance = element_df["distance"].sum()
+        distance_sum = distance_sum.append(
+            {"point": element, "distance": distance}, ignore_index=True
+        )
+    furthest_index = distance_sum["distance"].idxmax()
+    furthest_row = distance_sum.iloc[furthest_index]
     return furthest_row
 
 
 def greedy_algorithm(n, m, data):
-    solutions = DataFrame(columns=["source", "destination", "distance"])
+    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 = get_furthest_element(element=randbelow(n), data=data)
+        centroid = solutions.apply(get_furthest_element, 1, data)
         solutions = solutions.append(centroid)
 
 
+# NOTE In each step, switch the element that gives the least amount
+def local_search():
+    pass
+
+
 def usage(argv):
     print(f"Usage: python {argv[0]} <file>")
     exit(1)
@@ -27,6 +47,7 @@ def main():
     if len(argv) != 2:
         usage(argv)
     n, m, data = parse_file(argv[1])
+    greedy_algorithm(n, m, data)
 
 
 if __name__ == "__main__":