Fix pseudorandom solution generation

src/processing.py

@@ -1,6 +1,8 @@
 from preprocessing import parse_file
-from pandas import DataFrame
+from pandas import DataFrame, Series
 from sys import argv
+from random import seed, randint
+from time import time
 
 
 def get_first_solution(n, data):
@@ -11,7 +13,7 @@ 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
@@ -25,11 +27,14 @@ 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
+    return Series(data={"point": furthest_point, "distance": furthest_row["distance"]})
+
+
+def remove_solution_dataset(data, solution):
+    return data.query(f"source != {solution} and destination != {solution}")
 
 
 def greedy_algorithm(n, m, data):
@@ -37,29 +42,64 @@ 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 = solutions["point"].tail(n=1)
-        centroid, index = get_furthest_element(element=int(last_solution), data=data)
-        solutions = solutions.append(dict(centroid), ignore_index=True)
-        data = data.drop(index)
+        last_solution = int(solutions["point"].tail(n=1))
+        centroid = get_furthest_element(element=last_solution, data=data)
+        solutions = solutions.append(centroid, ignore_index=True)
+        data = remove_solution_dataset(data=data, solution=last_solution)
     return solutions
 
 
-# NOTE In each step, switch to the element that gives the least amount
-def local_search():
-    pass
+def get_pseudorandom_solution(n, data):
+    seed(42)
+    solution = data.iloc[randint(a=0, b=n)]
+    return Series(data={"point": solution["destination"], "distance": 0})
+
+
+def local_search(n, m, data):
+    solutions = DataFrame(columns=["point", "distance"])
+    first_solution = get_pseudorandom_solution(n=n, data=data)
+    solutions = solutions.append(first_solution, ignore_index=True)
+    for _ in range(m):
+        pass
+    return solutions
+
+
+def execute_algorithm(choice, n, m, data):
+    if choice == "greedy":
+        return greedy_algorithm(n, m, data)
+    elif choice == "local":
+        return local_search(n, m, data)
+    else:
+        print("The valid algorithm choices are 'greedy' and 'local'")
+        exit(1)
+
+
+def show_results(solutions, time_delta):
+    distance_sum = solutions["distance"].sum()
+    duplicates = solutions.duplicated()
+    print(solutions)
+    print("Total distance: " + str(distance_sum))
+    if solutions[duplicates].empty:
+        print("No duplicates found")
+    print("Execution time: " + str(time_delta))
 
 
 def usage(argv):
-    print(f"Usage: python {argv[0]} <file>")
+    print(f"Usage: python {argv[0]} <file> <algorithm choice>")
+    print("algorithm choices:")
+    print("greedy: greedy algorithm")
+    print("local: local search algorithm")
     exit(1)
 
 
 def main():
-    if len(argv) != 2:
+    if len(argv) != 3:
         usage(argv)
     n, m, data = parse_file(argv[1])
-    solutions = greedy_algorithm(n, m, data)
-    print(solutions)
+    start_time = time()
+    solutions = execute_algorithm(choice=argv[2], n=n, m=m, data=data)
+    end_time = time()
+    show_results(solutions, time_delta=end_time - start_time)
 
 
 if __name__ == "__main__":