def test_reduce_node_quantity_custom_ex():
nodes_len = 2
column_names = ["№", "neighbors", "S"]
data = [
["1", "2,3,4", 2],
["2", "1,3,5", 4],
["3", "1,2,4,5", 6],
["4", "1,3,5", 8],
["5", "2,3,4,13,16", 10],
["6", "7,8,9", 1.01],
["7", "6,8,10", 1.02],
["8", "6,7,9,11", 1.03],
["9", "6,8,12", 1.04],
["10", "7,11,13", 1.05],
["11", "8,10,12,14", 1.06],
["12", "9,11,15", 1.07],
["13", "5,10,14,17", 1.08],
["14", "11,13,15", 1.09],
["15", "12,14", 1.10],
["16", "5,17", 50],
["17", "13,16", 50],
]
dataframe = pd.DataFrame(data=data, columns=column_names)
solver = Solver(data=dataframe, given_sum=20, number_of_clusters=4)
solver._reduce_nodes_quantity(graph=solver.crop_map.graph,
nodes_quantity=nodes_len)
assert len(
solver.crop_map.graph) == nodes_len, f"{len(solver.crop_map.graph)=}"
test_cluster_connected = Cluster(
serial_num=0, nodes_belong=[x for x in solver.crop_map.graph.values()])
assert solver._check_cluster_for_connectivity(
graph=solver.crop_map.graph, cluster=test_cluster_connected)
def test_first_node_absorb_second():
column_names = ["№", "neighbors", "S"]
data = [
["1", "2,3", 1],
["2", "1", 2],
["3", "2", 5],
["4", "1", 3],
]
dataframe = pd.DataFrame(data=data, columns=column_names)
solver = Solver(data=dataframe, given_sum=20, number_of_clusters=4)
first = "1"
second = "2"
solver._first_node_absorb_second(first=first,
second=second,
graph=solver.crop_map.graph)
assert {x
for x in solver.crop_map.graph.keys()} == {
"1",
"3",
"4",
}, f"{solver.crop_map.graph.keys()=}"
adj_lists = [x.adjacent_list for x in solver.crop_map.graph.values()]
for x in adj_lists:
assert second not in x, f"{second=}, {x=}"
assert ("1" in solver.crop_map.graph["3"].adjacent_list
), f'{solver.crop_map.graph["3"].adjacent_list=}'
assert ("2" not in solver.crop_map.graph["1"].adjacent_list
), f'{solver.crop_map.graph["3"].adjacent_list=}'
def test_check_cluster_for_connectivity_basic_1():
column_names = ["№", "neighbors", "S"]
data = [
["1", "2,3", 1],
["2", "1,3", 2],
["3", "1,2, 10", 5],
["4", "5", 3],
["5", "4", 3],
]
dataframe = pd.DataFrame(data=data, columns=column_names)
solver = Solver(data=dataframe, given_sum=20, number_of_clusters=4)
test_cluster_not_connected = Cluster(
serial_num=0,
nodes_belong=[
solver.crop_map.graph[x] for x in ["1", "2", "3", "4", "5"]
],
)
assert not solver._check_cluster_for_connectivity(
graph=solver.crop_map.graph, cluster=test_cluster_not_connected)
test_cluster_connected = Cluster(
serial_num=0,
nodes_belong=[solver.crop_map.graph[x] for x in ["1", "2", "3"]],
)
assert solver._check_cluster_for_connectivity(
graph=solver.crop_map.graph, cluster=test_cluster_connected)
def test_find_pair_with_min_square():
column_names = ["№", "neighbors", "S"]
data = [
["1", "3", 1],
["2", "4", 2],
["3", "1", 5],
["4", "2", 3],
]
dataframe = pd.DataFrame(data=data, columns=column_names)
solver = Solver(data=dataframe, given_sum=20, number_of_clusters=4)
res = Solver._find_pair_with_min_square(solver.crop_map.graph)
assert set(res) == {"2", "4"}, f"{res=}"
def test_solve():
data = pd.read_excel(datapath)
solver = Solver(
data=data,
given_sum=11,
number_of_clusters=4,
)
start = time.time()
times, leaders, _ = solver.solve_new(cut_bound_max=3)
print("time ", time.time() - start)
print([(x.name, x.square) for x in leaders])
assert leaders, f"{leaders=}"
def test_reduce_node_quantity_basic():
"""
придумать реальный кейс для проверки на связность
:return:
"""
global data
nodes_len = 20
data = pd.read_excel(datapath)
solver = Solver(data=data, given_sum=20, number_of_clusters=4)
solver._reduce_nodes_quantity(graph=solver.crop_map.graph,
nodes_quantity=nodes_len)
assert len(
solver.crop_map.graph) == nodes_len, f"{len(solver.crop_map.graph)=}"
test_cluster_connected = Cluster(
serial_num=0, nodes_belong=[x for x in solver.crop_map.graph.values()])
assert solver._check_cluster_for_connectivity(
graph=solver.crop_map.graph, cluster=test_cluster_connected)
def solve():
"""
Скрипт для дополнения справочника
Если указанные границы уже были проанализирваны, справочник останется без изменений
Опции:
-b граница отсечения
-d количество точек
-p
"""
datapath = Path(__file__).resolve().parents[1] / "data"
argv = sys.argv[1:]
try:
opts, args = getopt.getopt(sys.argv[1:], "b:d:f:",
["border=", "dots=", "file="])
border = None
dots = None
for opt, arg in opts:
if opt == "-b" or opt == "--border":
border = arg
elif opt == "-d" or opt == "--dots":
dots = arg
elif opt == "-f" or opt == "--file":
datapath = datapath / arg
# TODO как ошибки обрабатываем?
if not border.isdigit():
raise
if not dots.isdigit():
raise
border = int(border)
dots = int(dots)
data = pd.read_excel(datapath)
graph_constructor.construct_graph(data)
print(data)
# err_adj_list = validate(data)
# TODO выбрасываем все это, так как учимся самостоятельно определять центры полей по координатам
# и строить граф габриэля по центрам
# if err_adj_list:
# ic(err_adj_list)
# return
# # TODO научиться исправлять ошибку отсутствия антипараллельных ребер самостоятельно
# err_double_adj = validate_double_edges(data)
# if err_double_adj:
# ic(err_double_adj)
# return
# # TODO научиться исправлять ошибку наличия имени ноды в своем же списке смежности(не критично)
# err_node_in_adj = validate_node_name_not_in_adj_list(data)
# if err_node_in_adj:
# ic(err_node_in_adj)
# return
solver = Solver(data=data, given_sum=dots, number_of_clusters=4)
cluster_for_checking_map_full_connecticity = Cluster(
serial_num=-1, nodes_belong=list(solver.crop_map.graph.values()))
if not Solver._check_cluster_for_connectivity(
solver.crop_map.graph,
cluster_for_checking_map_full_connecticity):
ic("not_connected_initial_state")
return
res_new = solver.solve_new(cut_bound_max=border)
ic(res_new)
ic([x.square for x in res_new[1]])
ic(solver.crop_map.etalon_square)
new_clusters = []
for index, cluster in enumerate(res_new[1]):
names = []
for x in cluster.nodes_belong:
names.append(x.name)
names.extend(list(name for name in x.absorbed_names))
for name in names:
new_clusters.append([name, index])
names.extend(list(name for name in x.absorbed_names))
for name in names:
new_clusters.append([name, index])
new_сlusters_data = pd.DataFrame(data=new_clusters)
new_сlusters_data.to_excel(excel_writer="kmn_21_1_new_clusters.xlsx",
index=False)
except getopt.GetoptError:
logging(
f"Запуск: script_refbook.py -b <bank> -l <lower num bound> -h <higher num bound>"
)
sys.exit(-1)