Change fitness evaluation

src/genetic_algorithm.py

@@ -1,10 +1,11 @@
-from numpy import sum, append, intersect1d, array_equal
+from numpy import intersect1d, array_equal
 from numpy.random import randint, choice, shuffle
 from pandas import DataFrame
 from math import ceil
 from functools import partial
 from multiprocessing import Pool
 from copy import deepcopy
+from itertools import combinations
 
 
 def get_row_distance(source, destination, data):
@@ -35,22 +36,23 @@ def generate_individual(n, m, data):
 
 
 def evaluate_individual(individual, data):
-    fitness = []
-    genotype = individual.point.values
-    distances = data.query(f"source in @genotype and destination in @genotype")
-    for item in genotype[:-1]:
-        element_df = distances.query(f"source == {item} or destination == {item}")
-        max_distance = element_df["distance"].astype(float).max()
-        fitness = append(arr=fitness, values=max_distance)
-        distances = distances.query(f"source != {item} and destination != {item}")
-    individual["fitness"] = sum(fitness)
+    fitness = 0
+    comb = combinations(individual.index, r=2)
+    for index in list(comb):
+        elements = individual.loc[index, :]
+        fitness += get_row_distance(
+            source=elements["point"].head(n=1).values[0],
+            destination=elements["point"].tail(n=1).values[0],
+            data=data,
+        )
+    individual["fitness"] = fitness
     return individual
 
 
 def select_distinct_genes(matching_genes, parents, m):
     first_parent = parents[0].query("point not in @matching_genes")
     second_parent = parents[1].query("point not in @matching_genes")
-    cutoff = randint(m - len(matching_genes))
+    cutoff = randint(m - len(matching_genes) + 1)
     first_parent_genes = first_parent.point.values[cutoff:]
     second_parent_genes = second_parent.point.values[:cutoff]
     return first_parent_genes, second_parent_genes
@@ -137,9 +139,8 @@ def group_parents(parents):
         first = parents[i]
         second = parents[i + 1]
         if array_equal(first.point.values, second.point.values):
-            tmp = second
-            second = parents[i - 2]
-            parents[i - 2] = tmp
+            random_index = randint(i + 1)
+            second, parents[random_index] = parents[random_index], second
         parent_pairs.append([first, second])
     return parent_pairs
 

src/main.py

@@ -1,9 +1,7 @@
 from preprocessing import parse_file
 from genetic_algorithm import genetic_algorithm
 from memetic_algorithm import memetic_algorithm
-from sys import argv
 from time import time
-from itertools import combinations
 from argparse import ArgumentParser
 
 
@@ -17,54 +15,24 @@ def execute_algorithm(args, n, m, data):
             crossover_mode=args.crossover,
             max_iterations=100,
         )
-    else:
-        return memetic_algorithm(
-            n,
-            m,
-            data,
-            hybridation=args.hybridation,
-            max_iterations=100,
-        )
-
-
-def get_row_distance(source, destination, data):
-    row = data.query(
-        """(source == @source and destination == @destination) or \
-        (source == @destination and destination == @source)"""
+    return memetic_algorithm(
+        n,
+        m,
+        data,
+        hybridation=args.hybridation,
+        max_iterations=100,
     )
-    return row["distance"].values[0]
 
 
-def get_fitness(solutions, data):
-    counter = 0
-    comb = combinations(solutions.index, r=2)
-    for index in list(comb):
-        elements = solutions.loc[index, :]
-        counter += get_row_distance(
-            source=elements["point"].head(n=1).values[0],
-            destination=elements["point"].tail(n=1).values[0],
-            data=data,
-        )
-    return counter
-
-
-def show_results(solutions, fitness, time_delta):
-    duplicates = solutions.duplicated().any()
-    print(solutions)
-    print(f"Total distance: {fitness}")
+def show_results(solution, time_delta):
+    duplicates = solution.duplicated().any()
+    print(solution)
+    print(f"Total distance: {solution.fitness.values[0]}")
     if not duplicates:
         print("No duplicates found")
     print(f"Execution time: {time_delta}")
 
 
-def usage(argv):
-    print(f"Usage: python {argv[0]} <file> <algorithm choice> <")
-    print("algorithm choices:")
-    print("genetic: genetic algorithm")
-    print("memetic: memetic algorithm")
-    exit(1)
-
-
 def parse_arguments():
     parser = ArgumentParser()
     parser.add_argument("file", help="dataset of choice")
@@ -83,8 +51,7 @@ def main():
     start_time = time()
     solutions = execute_algorithm(args, n, m, data)
     end_time = time()
-    fitness = get_fitness(solutions, data)
-    show_results(solutions, fitness, time_delta=end_time - start_time)
+    show_results(solutions, time_delta=end_time - start_time)
 
 
 if __name__ == "__main__":