def cost(self, **kwargs):
y_hat = self.predict(**kwargs)
y = tensor.concatenate(
(kwargs["destination_latitude"][:, None], kwargs["destination_longitude"][:, None]), axis=1
)
return error.erdist(y_hat, y).mean()
def cost(self, **kwargs):
y_hat = self.predict(**kwargs)
y = tensor.concatenate((kwargs['destination_latitude'][:, None],
kwargs['destination_longitude'][:, None]),
axis=1)
return error.erdist(y_hat, y).mean()
def cost_matrix(self, **kwargs):
self.before_predict_all(kwargs)
res = self.predict_all(**kwargs)[0]
target = tensor.concatenate(
(kwargs['destination_latitude'].dimshuffle('x', 0, 'x'),
kwargs['destination_longitude'].dimshuffle('x', 0, 'x')),
axis=2)
target = target.repeat(kwargs['latitude'].shape[0], axis=0)
ce = error.erdist(target.reshape((-1, 2)), res.reshape((-1, 2)))
ce = ce.reshape(kwargs['latitude'].shape)
return ce * kwargs['latitude_mask']
def cost_matrix(self, latitude, longitude, latitude_mask, **kwargs):
latitude = latitude.T
longitude = longitude.T
latitude_mask = latitude_mask.T
res = self.predict_all(latitude, longitude, latitude_mask, **kwargs)[0]
target = tensor.concatenate(
(kwargs['destination_latitude'].dimshuffle('x', 0, 'x'),
kwargs['destination_longitude'].dimshuffle('x', 0, 'x')),
axis=2)
target = target.repeat(latitude.shape[0], axis=0)
ce = error.erdist(target.reshape((-1, 2)), res.reshape((-1, 2)))
ce = ce.reshape(latitude.shape)
return ce * latitude_mask
def cost_matrix(self, latitude, longitude, latitude_mask, **kwargs):
latitude = latitude.T
longitude = longitude.T
latitude_mask = latitude_mask.T
res = self.predict_all(latitude, longitude, latitude_mask, **kwargs)[0]
target = tensor.concatenate(
(kwargs['destination_latitude'].dimshuffle('x', 0, 'x'),
kwargs['destination_longitude'].dimshuffle('x', 0, 'x')),
axis=2)
target = target.repeat(latitude.shape[0], axis=0)
ce = error.erdist(target.reshape((-1, 2)), res.reshape((-1, 2)))
ce = ce.reshape(latitude.shape)
return ce * latitude_mask
def cost(self, **kwargs):
(destination_hat, time_hat) = self.predict(**kwargs)
destination = tensor.concatenate((kwargs['destination_latitude'][:, None],
kwargs['destination_longitude'][:, None]), axis=1)
time = kwargs['travel_time']
destination_cost = error.erdist(destination_hat, destination).mean()
time_cost = error.rmsle(time_hat.flatten(), time.flatten())
self.add_auxiliary_variable(destination_cost, [roles.COST], 'destination_cost')
self.add_auxiliary_variable(time_cost, [roles.COST], 'time_cost')
return destination_cost + self.config.time_cost_factor * time_cost
def cost(self, **kwargs):
(destination_hat, time_hat) = self.predict(**kwargs)
destination = tensor.concatenate(
(kwargs['destination_latitude'][:, None],
kwargs['destination_longitude'][:, None]),
axis=1)
time = kwargs['travel_time']
destination_cost = error.erdist(destination_hat, destination).mean()
time_cost = error.rmsle(time_hat.flatten(), time.flatten())
self.add_auxiliary_variable(destination_cost, [roles.COST],
'destination_cost')
self.add_auxiliary_variable(time_cost, [roles.COST], 'time_cost')
return destination_cost + self.config.time_cost_factor * time_cost
