From c62d1213b859e229dd90a5a6cbcf36d2f961fadb Mon Sep 17 00:00:00 2001
From: coolneng <akasroua@gmail.com>
Date: Tue, 22 Jun 2021 03:35:59 +0200
Subject: [PATCH] Add modules from other labs

---
 src/local_search.py  | 75 ++++++++++++++++++++++++++++++++++++++++++++
 src/main.py          | 58 ++++++++++++++++++++++++++++++++++
 src/preprocessing.py | 16 ++++++++++
 3 files changed, 149 insertions(+)
 create mode 100644 src/local_search.py
 create mode 100755 src/main.py
 create mode 100644 src/preprocessing.py

diff --git a/src/local_search.py b/src/local_search.py
new file mode 100644
index 0000000..06f6834
--- /dev/null
+++ b/src/local_search.py
@@ -0,0 +1,75 @@
+from numpy.random import choice, seed, randint
+from pandas import DataFrame
+
+
+def get_row_distance(source, destination, data):
+    row = data.query(
+        """(source == @source and destination == @destination) or \
+        (source == @destination and destination == @source)"""
+    )
+    return row["distance"].values[0]
+
+
+def compute_distance(element, solution, data):
+    accumulator = 0
+    distinct_elements = solution.query(f"point != {element}")
+    for _, item in distinct_elements.iterrows():
+        accumulator += get_row_distance(
+            source=element,
+            destination=item.point,
+            data=data,
+        )
+    return accumulator
+
+
+def get_first_random_solution(n, m, data):
+    solution = DataFrame(columns=["point", "distance"])
+    seed(42)
+    solution["point"] = choice(n, size=m, replace=False)
+    solution["distance"] = solution["point"].apply(
+        func=compute_distance, solution=solution, data=data
+    )
+    return solution
+
+
+def element_in_dataframe(solution, element):
+    duplicates = solution.query(f"point == {element}")
+    return not duplicates.empty
+
+
+def replace_worst_element(previous, n, data):
+    solution = previous.copy()
+    worst_index = solution["distance"].astype(float).idxmin()
+    random_element = randint(n)
+    while element_in_dataframe(solution=solution, element=random_element):
+        random_element = randint(n)
+    solution["point"].loc[worst_index] = random_element
+    solution["distance"].loc[worst_index] = compute_distance(
+        element=solution["point"].loc[worst_index], solution=solution, data=data
+    )
+    return solution
+
+
+def get_random_solution(previous, n, data):
+    solution = replace_worst_element(previous, n, data)
+    while solution["distance"].sum() <= previous["distance"].sum():
+        solution = replace_worst_element(previous=solution, n=n, data=data)
+    return solution
+
+
+def explore_neighbourhood(element, n, data, max_iterations=100000):
+    neighbourhood = []
+    neighbourhood.append(element)
+    for _ in range(max_iterations):
+        previous_solution = neighbourhood[-1]
+        neighbour = get_random_solution(previous=previous_solution, n=n, data=data)
+        neighbourhood.append(neighbour)
+    return neighbour
+
+
+def local_search(n, m, data):
+    first_solution = get_first_random_solution(n, m, data)
+    best_solution = explore_neighbourhood(
+        element=first_solution, n=n, data=data, max_iterations=100
+    )
+    return best_solution
diff --git a/src/main.py b/src/main.py
new file mode 100755
index 0000000..887484b
--- /dev/null
+++ b/src/main.py
@@ -0,0 +1,58 @@
+from preprocessing import parse_file
+from genetic_algorithm import genetic_algorithm
+from memetic_algorithm import memetic_algorithm
+from time import time
+from argparse import ArgumentParser
+
+
+def execute_algorithm(args, n, m, data):
+    if args.algorithm == "genetic":
+        return genetic_algorithm(
+            n,
+            m,
+            data,
+            select_mode=args.selection,
+            crossover_mode=args.crossover,
+            max_iterations=100,
+        )
+    return memetic_algorithm(
+        n,
+        m,
+        data,
+        hybridation=args.hybridation,
+        max_iterations=100,
+    )
+
+
+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 parse_arguments():
+    parser = ArgumentParser()
+    parser.add_argument("file", help="dataset of choice")
+    subparsers = parser.add_subparsers(dest="algorithm")
+    parser_genetic = subparsers.add_parser("genetic")
+    parser_memetic = subparsers.add_parser("memetic")
+    parser_genetic.add_argument("crossover", choices=["uniform", "position"])
+    parser_genetic.add_argument("selection", choices=["generational", "stationary"])
+    parser_memetic.add_argument("hybridation", choices=["all", "random", "best"])
+    return parser.parse_args()
+
+
+def main():
+    args = parse_arguments()
+    n, m, data = parse_file(args.file)
+    start_time = time()
+    solutions = execute_algorithm(args, n, m, data)
+    end_time = time()
+    show_results(solutions, time_delta=end_time - start_time)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/src/preprocessing.py b/src/preprocessing.py
new file mode 100644
index 0000000..56a3543
--- /dev/null
+++ b/src/preprocessing.py
@@ -0,0 +1,16 @@
+from pandas import read_table
+
+
+def read_header(filename):
+    with open(filename, "r") as f:
+        header = f.readline().split()
+    return int(header[0])
+
+
+def parse_file(filename):
+    n = read_header(filename)
+    m = 50
+    df = read_table(
+        filename, names=["source", "destination", "distance"], sep=" ", skiprows=[0]
+    )
+    return n, m, df