def find_route(n, matrix, time_limit):
good = []
for i in range(1, 2**(n - 1)):
bin = binary(i, n - 1) + "1"
iArr = []
posArr = []
for j in range(n - 1):
if (bin[j] == '1'):
iArr.append(j)
posArr.append(locations[j])
if (len(iArr) > 1):
new_mat = getMat(iArr, matrix)
dist_list = []
for j in range(len(iArr)):
for k in range(j + 1, len(iArr)):
dist_list.append((j, k, new_mat[j][k]))
fitness_dists = mlrose.TravellingSales(distances=dist_list)
problem_fit = mlrose.TSPOpt(length=len(iArr),
fitness_fn=fitness_dists,
maximize=False)
best_state, best_fitness = mlrose.genetic_alg(problem_fit,
random_state=2)
best_state_fr = []
for k in range(len(iArr)):
best_state_fr.append(iArr[best_state[k]])
if (best_fitness < time_limit):
good.append(best_state_fr)
return good
def rank(fnames, save=True):
dist_mat = np.load(fnames['dmat'])
dist_list = mat2tuples(dist_mat)
# define fitness function object
fitness_dists = mlrose.TravellingSales(distances=dist_list)
# define optimization problem object
n = dist_mat.shape[0]
problem_fit = mlrose.TSPOpt(length=n,
fitness_fn=fitness_dists,
maximize=False)
# solve problem using the genetic algorithm
best_state, best_fitness = mlrose.genetic_alg(problem_fit,
mutation_prob=0.2,
max_attempts=100,
random_state=2)
# retrieve ranked list
cand = load(fnames['cand'])
ranked_cand = cand.loc[best_state]
# save the output
fname_ranked = None
if save:
fname, ext = os.path.splitext(fnames['cand'])
fname_ranked = fname + '_ranked' + ext
write(fname_ranked, ranked_cand)
print('Ordered candidates saved to {}'.format(fname_ranked))
return fname_ranked
def main():
name_of_exp = "One Max"
# Create list of city coordinates
coords_list = [(1, 1), (4, 2), (5, 2), (6, 4), (4, 4), (3, 6), (1, 5), (2, 3)]
mimic = []
# Initialize fitness function object using coords_list
fitness_coords = mlrose.TravellingSales(coords=coords_list)
problem = mlrose.TSPOpt(length=8, fitness_fn=fitness_coords,
maximize=False)
z_s = ['RHC', 'SA', 'GA', 'MIMIC']
for i in [0.1,0.2,0.3,0.4,0.5]:
best_state, best_fitness, learning_curve, timing_curve = mlrose.genetic_alg(problem, pop_size=100,
mutation_prob=i,
max_attempts=100,
max_iters=100, curve=True,
random_state=1)
mimic.append(learning_curve)
print(i)
print(best_fitness)
for x, z in zip([0.1,0.2,0.3,0.4,0.5], mimic):
plt.plot(z, label=str(x))
plt.legend()
plt.title('GA Randomized Optimization MutationProb vs Fitness Curve (TSP)')
plt.xlabel('Function iteration count')
plt.ylabel('Fitness function value')
plt.show()
def gera_grafo(df) -> Grafo:
global grafo
grafo = Grafo(df)
for i in range(len(colunas)):
# Pega o nome da cidade pelo índice
cidade_origem = colunas[i]
for j in range(len(colunas)):
# Pega o peso e o destino da aresta e adiciona no objeto Grafo
destino = df.index[j]
peso = df.iloc[j][cidade_origem]
#aresta = dict(rota=(cidade_origem, destino), peso=peso)
if peso != '-':
aresta = (int(cidade_origem), int(destino), int(peso))
grafo.adiciona_arestas(aresta)
fitness = mlrose.TravellingSales(distances=grafo.arestas)
# Define optimization problem object
problem_fit = mlrose.TSPOpt(length=8, fitness_fn=fitness, maximize=False)
best_state, best_fitness = mlrose.genetic_alg(problem_fit,
mutation_prob=0.2,
max_attempts=100,
random_state=2)
print(fitness)
return grafo
def tsp_factory(length=10, min_nodeval=1, max_nodeval=20):
coords = []
for i in range(length):
node = (
np.random.randint(min_nodeval, max_nodeval),
np.random.randint(min_nodeval, max_nodeval),
)
while node in coords:
node = (
np.random.randint(min_nodeval, max_nodeval),
np.random.randint(min_nodeval, max_nodeval),
)
coords.append(node)
fitness = count_evaluations(mlrose.TravellingSales, coords)
fitness_final = mlrose.CustomFitness(fitness)
fitness_final.get_prob_type = (
lambda: "tsp"
) # Just a hack to make it work with a custom function.
problem = mlrose.TSPOpt(length=length,
fitness_fn=fitness_final,
maximize=False)
dists = generate_distances(coords)
optimum, _ = held_karp(dists)
return problem, optimum
def encuentra_circuito(ls_basicas):
n_bas = [i for i in range(len(ls_basicas))]
comb = itertools.combinations(n_bas, 2)
dist_list = []
for i in comb:
costo = aptitud2(ls_basicas[i[0]], ls_basicas[i[1]])
dist_list.append((i[0], i[1], costo))
#print(ls_basicas[i[0]], ls_basicas[i[1]], costo)
# Initialize fitness function object using dist_list
fitness_dists = mlrose.TravellingSales(distances=dist_list)
problem_fit = mlrose.TSPOpt(length=len(ls_basicas),
fitness_fn=fitness_dists,
maximize=True)
best_state, best_fitness = mlrose.genetic_alg(problem_fit, random_state=2)
#print(best_state)
#print(best_fitness)
# =============================================================================
# for i in best_state:
# print(ls_basicas[i])
# =============================================================================
return list(best_state), best_fitness / 2
def calculate_route(super_matrix, shopping_list):
shopping_list.append("0") # go through enterance
bfs, routes = calc_distance_between_all_list(super_matrix, shopping_list)
bfs = sorted(bfs)
(new_input, input_converter_dict) = input_converter(bfs)
# Initialize fitness function object using dist_list
fitness_dists = mlrose.TravellingSales(distances=new_input)
# Define optimization problem object
problem_fit = mlrose.TSPOpt(length=len(shopping_list),
fitness_fn=fitness_dists,
maximize=False)
# Solve problem using the genetic algorithm
# best_state, best_fitness = mlrose.genetic_alg(problem_fit, random_state = 2)
best_state, best_fitness = mlrose.genetic_alg(problem_fit,
mutation_prob=0.2,
max_attempts=200,
pop_size=200,
random_state=0)
output_converter_dict = dict(
(v, k) for k, v in input_converter_dict.items())
final_result = [output_converter_dict[x] for x in best_state]
register_index = final_result.index("0")
final_result = final_result[register_index:] + final_result[:register_index]
final_route = []
for (k, v) in zip(final_result, final_result[1:] + final_result[:1]):
for (x, y, z) in routes:
if k == x and v == y:
final_route += z
elif k == y and v == x:
final_route += z[::-1]
return final_route, items_coor(super_matrix, shopping_list)
def tsp(dd,l):
state=[]
for i in range(0,len(dd)):
fitness_dists = mlrose.TravellingSales(distances = dd[i])
problem_fit = mlrose.TSPOpt(length = len(l[i]), fitness_fn = fitness_dists, maximize=False)
best_state, best_fitness = mlrose.genetic_alg(problem_fit, random_state = 2)
state.append(best_state.tolist())
return(state)
def api_tsp():
# Check if an ID was provided as part of the URL.
# If ID is provided, assign it to a variable.
# If no ID is provided, display an error in the browser.
places_to_visit = []
if 'places' in request.args:
temp = request.args['places']
splitItems = temp.split(",")
# listTemp = [int(i) for i in splitItems]
print(request.args['places'])
places_to_visit = splitItems
# id = int(request.args['id'])
else:
return "Error: No id field provided. Please specify an id."
# Create an empty list for our results
results = []
distance_matrix=[]
for i in range(len(places_to_visit)):
for j in range(i+1,len(places_to_visit)):
origin=places_to_visit[i]
dest=places_to_visit[j]
key=(origin,dest)
req='https://maps.googleapis.com/maps/api/distancematrix/json?origins=place_id:'+origin+'&destinations=place_id:'+dest+'&key='+my_API_key
Response = requests.get(req)
Response=Response.json()
#pprint.pprint(Response["rows"][0]["elements"][0]["duration"]["value"])
value=Response["rows"][0]["elements"][0]["duration"]["value"] #We get the time duration is seconds
new_element=(i,j,value)
distance_matrix.append(new_element)
fitness = mlrose.TravellingSales(distances = distance_matrix)
# We want to visit all the places of our list "places_to_visit"
problem = mlrose.TSPOpt(length = len(places_to_visit), fitness_fn = fitness,
maximize=False)
best_state, best_fitness = mlrose.genetic_alg(problem, random_state = 0)
ordered_places_to_visit=[]
for i in best_state:
ordered_places_to_visit.append(places_to_visit[i])
print(places_to_visit)
temp = {}
temp['results'] = ordered_places_to_visit
results.append(temp)
# Loop through the data and match results that fit the requested ID.
# IDs are unique, but other fields might return many results
# for book in books:
# if book['id'] in listTemp:
# results.append(book)
# Use the jsonify function from Flask to convert our list of
# Python dictionaries to the JSON format.
return jsonify(results)
def genetic(self):
problem_no_fit = mlrose.TSPOpt(length=len(self.coord),
coords=self.coord,
maximize=False)
best_state, best_fitness = mlrose.genetic_alg(problem_no_fit,
mutation_prob=0.2,
max_attempts=100,
random_state=2)
return best_state
def metaheuristic(dist, meta=None, nnodes=None, **kwargs):
# fit data
fit_dist = mr.TravellingSales(distances=dist)
# define TSP
fit_problem = mr.TSPOpt(length=nnodes, fitness_fn=fit_dist, maximize=False)
# define optmization metaheuristic
# kwargs are parameters to the metaheuristic
best_state, best_fit = meta(fit_problem, **kwargs)
return (best_state, best_fit)
def _cal_route(self):
""" based on TSP solver """
dist_list = self._build_dist_list()
fitness_dists = mlrose.TravellingSales(distances=dist_list)
problem_fit = mlrose.TSPOpt(length=len(self._places),
fitness_fn=fitness_dists,
maximize=False)
best_state, best_fitness = mlrose.genetic_alg(problem_fit,
random_state=2)
return best_state
def calc_shortest_route_mlrose(
systems: Iterable[Dict]) -> Tuple[List[Dict], float]:
# See https://mlrose.readthedocs.io/en/stable/source/tutorial2.html#
fitness_distances = mlrose.TravellingSales(
distances=calc_distances(systems))
problem_fit = mlrose.TSPOpt(length=len(systems),
fitness_fn=fitness_distances,
maximize=False)
best_state, best_fitness = mlrose.genetic_alg(problem_fit,
random_state=20,
max_attempts=20)
return ([systems[index] for index in best_state], best_fitness)
def _do_tsp(self, dist_list):
"""Do the actual travelling salesperson."""
dist_list.sort(key=lambda x: x[0])
length = int(self._get_max_index_value_in_dists(dist_list) + 1)
try:
fitness_dists = mlrose.TravellingSales(distances=dist_list)
problem_fit = mlrose.TSPOpt(
length=length, fitness_fn=fitness_dists, maximize=False)
best_state, best_fitness = mlrose.genetic_alg(
problem_fit, mutation_prob=0.2, max_attempts=50)
except Exception:
print(f"tsp failed. dist_list: {dist_list}")
raise
return best_state
def findSolution():
fitness_coords = mlrose.TravellingSales(coords=coords_list)
problem_fit = mlrose.TSPOpt(length=48,
fitness_fn=fitness_coords,
maximize=False)
best_state, best_fitness = mlrose.genetic_alg(problem_fit,
mutation_prob=0.2,
max_attempts=100,
random_state=2)
json_response = json.dumps({
"bestState": best_state.tolist(),
"bestFitness": best_fitness.tolist()
})
print(json_response)
return json_response
def shortest_path(coords, start, end):
tsp_fitness = mlrose.TravellingSales(coords=coords)
def filter_endpoints(state):
if state[0] == start and state[-1] == end:
return tsp_fitness.evaluate(state)
else:
return math.inf
fitness = mlrose.CustomFitness(filter_endpoints, 'tsp')
problem = mlrose.TSPOpt(length=len(coords),
fitness_fn=fitness,
maximize=False)
path, length = mlrose.genetic_alg(problem, random_state=2)
return [coords[i] for i in path]
def __init__(self, my_map):
self.my_map = my_map
self.my_map_np = np.asarray(self.my_map)
# analysis the map
self.bound_cells = mark_boundaries(self.my_map_np)
print('Find Minimal Set Cover')
start = datetime.datetime.now()
self.key_points, self.key_pt_dirs, self.key_pt_cover_bd_idx = find_min_set_cover(
self.bound_cells)
self.state_dist, self.state_space = gen_solution_space(
self.bound_cells, self.key_points, self.key_pt_dirs, 0.1, 50)
print("Time for Minimal Set Cover is ",
datetime.datetime.now() - start)
# run the TSP to initialize
print('Run TSP on finding vertices cover')
start = datetime.datetime.now()
fitness_function = mlrose.TravellingSales(distances=self.state_dist)
problem_fit = mlrose.TSPOpt(length=len(self.state_space),
fitness_fn=fitness_function,
maximize=False)
# Solve the problem using the genetic algorithm
best_state, best_fitness = mlrose.genetic_alg(problem_fit,
random_state=5)
self.best_state = best_state
# extract states
idx_2_state_spaces = {}
for key, value in self.state_space.items():
idx_2_state_spaces[value] = key
state_dict = [
idx_2_state_spaces[i].split("-") for i in self.best_state
]
self.state_dict = [(self.key_points[int(s[0])], s[1])
for s in state_dict]
if np.isinf(best_fitness):
print('Error when finding TSP')
print("Time for TSP is ", datetime.datetime.now() - start)
def tsp_problem():
coords_list = [(1, 1), (4, 2), (5, 2), (6, 4), (4, 4), (3, 6), (1, 5),
(2, 3)]
fitness_coords = mlrose.TravellingSales(coords=coords_list)
# Define optimization problem object
problem_fit = mlrose.TSPOpt(length=8,
fitness_fn=fitness_coords,
maximize=True)
best_state, best_fitness = mlrose.genetic_alg(problem_fit, random_state=2)
print(best_state)
print(best_fitness)
best_state, best_fitness = mlrose.genetic_alg(problem_fit,
mutation_prob=0.2,
max_attempts=100,
random_state=2)
def find_best_path(points_data, random_state=0, use_coords=True):
'''Find the shortest closed path (in euclidean distance)
using Elastic Net Algorithm in mlrose package.'''
# tuning curve size: (numNeruo, numBin) (might be high dimensional: numNeuro>3)
# numBin = num_pts
points_data = np.array(points_data)
if len(points_data.shape) == 1:
points_data = points_data.reshape((1, points_data.size))
num_pts = points_data.shape[1] # number of points
def euclidean_distance(x, y):
return np.sqrt(np.sum((x - y)**2))
if use_coords:
coords_list = []
for i in range(num_pts):
coords_list += [tuple(points_data[:, i])]
# Initialize fitness function object using coords_list
fitness = mlrose.TravellingSales(coords=coords_list)
else:
# use euclidean distances computed
dist_list = []
for i in range(num_pts):
for j in range(num_pts):
if i != j:
dist_list.append(
(i, j,
euclidean_distance(points_data[:, i],
points_data[:, j])))
# Initialize fitness function object using dist_list
fitness = mlrose.TravellingSales(distances=dist_list)
problem_fit = mlrose.TSPOpt(length=num_pts,
fitness_fn=fitness,
maximize=False)
# Solve problem using the genetic algorithm
best_path, best_path_len = mlrose.genetic_alg(problem_fit,
random_state=random_state)
return best_path, best_path_len # length of closed curve
def _price_routing(self) -> list:
"""Returns the best path to traverse geopoints based on
the cost between each of these pairs.
"""
triplets = self._get_price_triplets()
# Sales travelling instance
fitness_prices = mlrose.TravellingSales(distances=triplets)
# Fit problem
problem_fit = mlrose.TSPOpt(length=len(self.orders),
fitness_fn=fitness_prices,
maximize=False)
best_state, _ = mlrose.genetic_alg(problem_fit,
pop_size=200,
mutation_prob=0.2,
max_attempts=100,
max_iters=10,
random_state=2)
return best_state
def get_genetic_path(self):
"""
Return an approximate solution length to the TSP problem
"""
fitness_coords = mlrose.TravellingSales(coords=self.coords)
dist_list = list(self.G.edges.data('weight'))
fitness_dists = mlrose.TravellingSales(distances=dist_list)
problem_fit = mlrose.TSPOpt(length=self.nodes,
fitness_fn=fitness_coords,
maximize=False)
best_state, best_fitness = mlrose.genetic_alg(problem_fit,
random_state=2,
mutation_prob=0.2,
max_attempts=100)
return best_fitness
def _map_routing(self) -> list:
"""Returns the best path to traverse points given by geo-coordinates.
"""
# Lat and Lon of each order
geo_points = self._get_map_coordinates()
# Sales travelling instance
fitness_coordinates = mlrose.TravellingSales(coords=geo_points)
# Fit problem
problem_fit = mlrose.TSPOpt(length=len(self.orders),
fitness_fn=fitness_coordinates,
maximize=False)
# Best state result
best_state, _ = mlrose.genetic_alg(problem_fit,
pop_size=200,
mutation_prob=0.2,
max_attempts=100,
max_iters=10,
random_state=2)
return best_state
def generate(seed, number_of_cities, area_width=250, area_height=250):
np.random.seed(seed)
x_coords = np.random.randint(area_width, size=number_of_cities)
y_coords = np.random.randint(area_height, size=number_of_cities)
coords = list(tuple(zip(x_coords, y_coords)))
duplicates = TSPGenerator.list_duplicates_(coords)
while len(duplicates) > 0:
for d in duplicates:
x_coords = np.random.randint(area_width, size=len(d))
y_coords = np.random.randint(area_height, size=len(d))
for i in range(len(d)):
coords[d[i]] = (x_coords[i], y_coords[i])
pass
duplicates = TSPGenerator.list_duplicates_(coords)
distances = TSPGenerator.get_distances(coords, False)
return mlrose.TSPOpt(coords=coords,
distances=distances,
maximize=False)
def tsp_zone_distance(transformed_df, main_df):
zones = ["D1", "D2", "D3", "D4", "D5", "D6"]
unpivoted_df = pd.melt(transformed_df,
id_vars=['Id_Cliente'],
var_name="zones")
unpivoted_df = unpivoted_df[unpivoted_df.value > 0]
joined_df = unpivoted_df.merge(main_df[["Id_Cliente", "lat", "lon"]],
on="Id_Cliente",
how="left")
total_distance = []
for zone in zones:
fitness_coords = mlrose.TravellingSales(coords=joined_df[
joined_df["zones"] == zone][["lat", "lon"]].to_numpy())
problem_fit = mlrose.TSPOpt(
length=joined_df[joined_df["zones"] == zone].shape[0],
fitness_fn=fitness_coords,
maximize=False)
best_state, best_fitness = mlrose.genetic_alg(problem_fit,
random_state=12)
total_distance.append(best_fitness)
print(total_distance)
return (sum(total_distance))
def solve_method(self, graph, current_node):
nodes = list(graph.nodes) + [self.start]
nodes.sort(key=lambda x: x.index)
dist_list = [(node1.index, node2.index, node1.compute_distance(node2))
for node1 in nodes for node2 in nodes
if node1.index < node2.index]
fitness_coords = mlrose.TravellingSales(
coords=[node.get() for node in nodes], distances=dist_list)
problem_fit = mlrose.TSPOpt(length=len(nodes),
fitness_fn=fitness_coords,
maximize=False)
self.path, self.cost = mlrose.genetic_alg(problem_fit,
mutation_prob=0.2,
max_attempts=100,
random_state=2)
self.path = [graph.get(node) for node in self.path]
display_path(self.ax, self.path)
return time.process_time() - self.time
def distance_optim(x_coordinates, y_coordinates):
# Create the distance list for cell pairs
# Unfortunately, cell indices starts from zero for mlrose
#dist_list = [(0, 1, distance(x_coordinates,y_coordinates,0,1)), (0, 2, distance(x_coordinates,y_coordinates,0,2)),\
# (1, 3, distance(x_coordinates,y_coordinates,1,3)), (2, 3, distance(x_coordinates,y_coordinates,2,3)),\
# (3, 4, distance(x_coordinates,y_coordinates,3,4)), (3, 5, distance(x_coordinates,y_coordinates,3,5)),\
# (4, 6, distance(x_coordinates,y_coordinates,4,6)), (5, 6, distance(x_coordinates,y_coordinates,5,6)),\
# (6, 7, distance(x_coordinates,y_coordinates,6,7)), (6, 8, distance(x_coordinates,y_coordinates,6,8)),\
# (7, 9, distance(x_coordinates,y_coordinates,7,9)), (8, 9, distance(x_coordinates,y_coordinates,8,9)),\
# (9, 10, distance(x_coordinates,y_coordinates,9,10)), (9, 11, distance(x_coordinates,y_coordinates,9,11)),\
# (10, 12, distance(x_coordinates,y_coordinates,10,12)), (11, 12, distance(x_coordinates,y_coordinates,11,12))]
dist_list3 = [(0, 1, distance(x_coordinates,y_coordinates,0,1)), (0, 2, distance(x_coordinates,y_coordinates,0,2)),\
(1, 3, distance(x_coordinates,y_coordinates,1,3)), (2, 3, distance(x_coordinates,y_coordinates,2,3)),\
(3, 4, distance(x_coordinates,y_coordinates,3,4)), (3, 5, distance(x_coordinates,y_coordinates,3,5))]
# Define a fitness function object
fitness_dists = mlrose.TravellingSales(distances=dist_list3)
# Define a optimization problem object
problem_fit = mlrose.TSPOpt(length=len(y_coordinates),
fitness_fn=fitness_dists,
maximize=False)
return problem_fit
import mlrose
import numpy as np
# Create list of city coordinates
coords_list = [(0, 1), (3, 4), (6, 5), (7, 3), (15, 0), (12, 4), (14, 10),
(9, 6), (7, 9), (0, 10)]
# Initialize fitness function object using coords_list
fitness_coords = mlrose.TravellingSales(coords=coords_list)
problem_fit = mlrose.TSPOpt(length=10,
fitness_fn=fitness_coords,
maximize=False)
best_state, best_fitness = mlrose.genetic_alg(problem_fit, random_state=2)
print('The best state found is: ', best_state)
print('The fitness at the best state is: ', best_fitness)
fitness_coords = mlrose.TravellingSales(coords = coords_list)
# Create list of distances between pairs of cities
dist_list = [(0, 1, 3.1623), (0, 2, 4.1231), (0, 3, 5.8310), (0, 4, 4.2426), \
(0, 5, 5.3852), (0, 6, 4.0000), (0, 7, 2.2361), (1, 2, 1.0000), \
(1, 3, 2.8284), (1, 4, 2.0000), (1, 5, 4.1231), (1, 6, 4.2426), \
(1, 7, 2.2361), (2, 3, 2.2361), (2, 4, 2.2361), (2, 5, 4.4721), \
(2, 6, 5.0000), (2, 7, 3.1623), (3, 4, 2.0000), (3, 5, 3.6056), \
(3, 6, 5.0990), (3, 7, 4.1231), (4, 5, 2.2361), (4, 6, 3.1623), \
(4, 7, 2.2361), (5, 6, 2.2361), (5, 7, 3.1623), (6, 7, 2.2361)]
# Initialize fitness function object using dist_list
fitness_dists = mlrose.TravellingSales(distances = dist_list)
# Define optimization problem object
problem_fit = mlrose.TSPOpt(length = 8, fitness_fn = fitness_coords, maximize=False)
# Create list of city coordinates
coords_list = [(1, 1), (4, 2), (5, 2), (6, 4), (4, 4), (3, 6), (1, 5), (2, 3)]
# Define optimization problem object
problem_no_fit = mlrose.TSPOpt(length = 8, coords = coords_list, maximize=False)
# Solve problem using the genetic algorithm
#best_state, best_fitness = mlrose.genetic_alg(problem_fit, random_state = 2)
# This solution can potentially be improved on by tuning the parameters of the optimization algorithm.
# For example, increasing the maximum number of attempts per step to 100 and increasing the mutation probability
# to 0.2, yields a tour with a total length of 17.343 units.
# Solve problem using the genetic algorithm - Improved!
def get_object_places(table_path, graph_path, visited_places):
assert os.path.exists(table_path)
assert os.path.exists(graph_path)
df = pd.read_csv(table_path, index_col=0)
while True:
#speech to text part
# obtain audio from the microphone
r = sr.Recognizer()
with sr.Microphone() as source:
print("Quale oggetto stai cercando?\n")
#audio = r.listen(source)
# recognize speech using Google Cloud Speech
try:
object_to_search = "wallet"
#object_to_search = r.recognize_google_cloud(audio, credentials_json=GOOGLE_CLOUD_SPEECH_CREDENTIALS).strip()
#similar = check_similapr_objects(df, object_to_search)
#print(similar)
if (len(df.loc[df["object"] == object_to_search]) > 0):
break
elif (similar != None):
answer = input(
object_to_search +
" non trovato, trovata compatibilita' con " + similar +
", utilizzare la sua distribuzione?[Y/n]\n")
if (answer == "Y"):
object_to_search = similar
break
except sr.UnknownValueError:
print("Google Cloud Speech could not understand audio")
except sr.RequestError as e:
print(
"Could not request results from Google Cloud Speech service; {0}"
.format(e))
df = df.loc[df["object"] == object_to_search].drop('object', 1)
places = list(df.keys())
#dropping places already visited
for visited_place in visited_places:
df = df.drop(visited_place, 1)
places.remove(visited_place)
row = df
print(row)
for x in list(zip(row.keys(), row.values[0])):
print(str(x[0]) + " " + str(x[1]))
knowledge = row.values[0]
number_of_places = len(knowledge)
distances_dict = get_distances(graph_path,
("pose", 1.7219, 11.1261, "storage"))
distances = [distances_dict[key] for key in places]
max_distance = max(distances)
inverted_distances = list(
map(lambda x: abs(x - max_distance + 1) / 5, distances))
prior_knowledge = np.array(inverted_distances)
with pm.Model() as model:
# Parameters of the Multinomial are from a Dirichlet
parameters = pm.Dirichlet('parameters',
a=prior_knowledge,
shape=number_of_places)
# Observed data is from a Multinomial distribution
observed_data = pm.Multinomial('observed_data',
n=sum(knowledge),
p=parameters,
shape=number_of_places,
observed=knowledge)
with model:
# Sample from the posterior
trace = pm.sample(draws=1000,
chains=2,
tune=500,
discard_tuned_samples=True)
trace_df = pd.DataFrame(trace['parameters'], columns=places)
# For probabilities use samples after burn in
pvals = trace_df.iloc[:, :number_of_places].mean(axis=0)
tag_and_dist = sorted(zip(places, pvals), key=lambda x: x[1], reverse=True)
display_probs(dict(tag_and_dist))
top_4_places = [x[0] for x in tag_and_dist[:4]]
g = build_graph(graph_path)
topn_nodes = []
for label in top_4_places:
for node in g.nodes():
_, _, _, node_label = node
if (node_label == label):
topn_nodes += [node]
break
#adding the actual position to the top4 nodes
topn_nodes += [("pose", 7.3533, 0.5381, "corridor-1")]
subgraph = nx.Graph()
edges = list(itertools.combinations(g.subgraph(topn_nodes), 2))
all_distances = dict(nx.all_pairs_shortest_path_length(g))
edges_with_weight = [(topn_nodes.index(x[0]), topn_nodes.index(x[1]),
all_distances[x[0]][x[1]]) for x in edges]
print(edges_with_weight)
fitness_dists = mlrose.TravellingSales(distances=edges_with_weight)
problem_fit = mlrose.TSPOpt(length=len(topn_nodes),
fitness_fn=fitness_dists,
maximize=False)
best_state, best_fitness = mlrose.genetic_alg(problem_fit, random_state=2)
path = [topn_nodes[x][3] for x in best_state]
path = rotate(path, path.index('corridor-1'))
print(path)
'''
SAME PROBLEM USING MLROSE LIBRARY
'''
import mlrose
# create a list of triplets (u,v,d) giving distance d between nodes u and v.
'''
assume
city-0,city-1,city-2,,city-3,city-4,city-5,city-6,city-7,city-8,city-9
'''
dist_list = [(0, 1, 3.1623), (0, 2, 4.1231), (0, 3, 5.8310), (0, 4, 4.2426),
(0, 5, 5.3852), (0, 6, 4.0000), (0, 7, 2.2361), (1, 2, 1.0000),
(2, 6, 5.0000), (2, 7, 3.1623), (3, 4, 2.0000), (3, 5, 3.6056),
(3, 6, 5.0990), (3, 7, 4.1231), (4, 5, 2.2361), (4, 6, 3.1623),
(4, 7, 2.2361), (5, 6, 2.2361), (5, 7, 3.1623), (6, 7, 2.2361)]
coords_list = [(1, 1), (4, 2), (5, 2), (6, 4), (4, 4), (3, 6), (1, 5), (2, 3)]
fitness_func = mlrose.TravellingSales(distances=dist_list)
optimization_problem = mlrose.TSPOpt(length=8,
fitness_fn=fitness_func,
maximize=False,
distances=dist_list)
init_state = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9]) # Define initial state
best_state, best_fitness = mlrose.genetic_alg(optimization_problem,
pop_size=1000,
mutation_prob=0.07,
random_state=2)
print('The best state : ', best_state)
print('Fitness: ', best_fitness)
