private double[][] GetDataset(IEnumerable <Leg> legs)
{
return(legs.Select(leg => _geocodingDbSync.GetLegCoordinatesAsync(leg.LegID).Result)
.Where(coordinates => coordinates != null)
.Select(coordinates =>
{
return new double[] {
Convert.ToDouble(coordinates.StartLatitude),
Convert.ToDouble(coordinates.StartLongitude),
Convert.ToDouble(coordinates.DestLatitude),
Convert.ToDouble(coordinates.DestLongitude)
};
}).ToArray());
}
public async Task <IActionResult> Get(int id)
{
if (!User.Identity.IsAuthenticated)
{
return(Challenge());
}
var driver = (await _legRepository.Get(id)).Driver;
var authResult = await _authorizationService.AuthorizeAsync(User, driver, "DriverInfoPolicy");
if (!authResult.Succeeded)
{
return(Forbid());
}
return(Ok(await _dbSync.GetLegCoordinatesAsync(id)));
}
public async Task LearnFromDates(DateTime from, DateTime to)
{
int maxPickups = await GetMaxNumberOfPickups();
// train clustering algorithm
await _locationClustering.RetrainAsync(from, to);
// initialize storage arrays
int pickupElementSize = await GetMaxNumberOfPickups() + 1;
InitStorageArray(ref clusterFareClassRegressions, pickupElementSize - 1, NumberOfFareClassIntervals - 1);
InitStorageArray(ref clusterFareClassInputDensityKernels, pickupElementSize - 1, NumberOfFareClassIntervals);
InitStorageArray(ref clusterFareClassDistributionsUnivariate, pickupElementSize - 1, NumberOfFareClassIntervals);
InitStorageArray(ref clusterPickupFrequencies, pickupElementSize);
InitStorageArray(ref clusterPickupInputDensityKernels, pickupElementSize);
InitStorageArray(ref clusterPickupInputDensityKernelsUnivariate, pickupElementSize);
// for each cluster
for (int i = 0; i < _locationClustering.NumberOfClusters; i++)
{
// obtain data set
IEnumerable <Task <Pair <Leg, bool> > > decisionTasks = (await _legRepository.ListAsync())
.Where(leg => leg.StartTime.CompareTo(from) > 0 && leg.StartTime.CompareTo(to) < 0)
.Select(async(leg) =>
{
LegCoordinates coords = await _geocodingDbSync.GetLegCoordinatesAsync(leg.LegID);
double[] dp = (new decimal[] { coords.StartLatitude, coords.StartLongitude, coords.DestLatitude, coords.DestLongitude })
.Select(Convert.ToDouble).ToArray();
return(new Pair <Leg, bool>(leg, _locationClustering.ClusterCollection.Decide(dp) == i));
});
Pair <Leg, bool>[] decisions = await Task.WhenAll(decisionTasks);
// Data input values (pickup delay, travel time) in this cluster
IEnumerable <Leg> dataLegs = decisions.Where(pair => pair.Second).Select(pair => pair.First);
double[][] dataset = dataLegs
.Select(leg => new double[]
{
leg.PickupRequestTime.HasValue
? leg.StartTime.Subtract(leg.PickupRequestTime.Value).TotalMinutes
: 0,
leg.ArrivalTime.Subtract(leg.StartTime).TotalMinutes
}).ToArray();
// Fare classes in this cluster
int[] fareClasses = dataLegs
.Select(leg =>
{
for (int j = 0; j < FareClassIntervals.Count(); j++)
{
if (j < FareClassIntervals.Count() &&
Convert.ToDecimal(FareClassIntervals.ElementAt(j)) > leg.Fare)
{
return(j);
}
}
return(FareClassIntervals.Count());
}).ToArray();
// Pickup numbers in this cluster
int[] pickupNumbers = dataLegs.Select(leg => leg.NumOfPassengersPickedUp).ToArray();
// for each possible number of pickups
for (int n = 1; n <= maxPickups; n++)
{
double[][] dataSubset = dataset.Where((dp, k) => pickupNumbers[k] == n).ToArray();
int[] fareClassesSubset = fareClasses.Where((fc, k) => pickupNumbers[k] == n).ToArray();
if (dataSubset.Length == 0)
{
throw new ApplicationException("Insufficient data to make a reliable prediction");
}
// for each fare class interval boundary
for (int j = 0; j < NumberOfFareClassIntervals; j++)
{
// train logistic regression
if (j > 0 && clusterFareClassRegressions[i][n - 1][j - 1] == null)
{
clusterFareClassRegressions[i][n - 1][j - 1] = _logisticRegressionAnalysis
.Learn(dataSubset, fareClassesSubset.Select(fc => fc >= j ? 1.0 : 0.0).ToArray());
}
// train empirical density functions
if (fareClassesSubset.Count(fc => fc >= j) > 0.0)
{
double[][] dataSubsetSamples = dataSubset.Where((dp, k)
=> fareClassesSubset[k] >= j).ToArray();
MultivariateEmpiricalDistribution fareClassInputDistribution
= new MultivariateEmpiricalDistribution(dataSubsetSamples);
SetInputDistribution(fareClassInputDistribution, dataSubsetSamples,
out clusterFareClassInputDensityKernels[i][n - 1][j],
out clusterFareClassDistributionsUnivariate[i][n - 1][j]);
}
}
}
// compute pickup frequencies
for (int l = 0; l < pickupElementSize; l++)
{
clusterPickupFrequencies[i][l] = Convert.ToDouble(dataLegs.Count(leg => leg.NumOfPassengersPickedUp == l))
/ to.Subtract(from).TotalMinutes;
if (pickupNumbers.Any(pn => pn == l))
{
double[][] samples = dataset.Where((dp, k) => pickupNumbers[k] == l).ToArray();
MultivariateEmpiricalDistribution pickupInputDistribution
= new MultivariateEmpiricalDistribution(samples);
SetInputDistribution(pickupInputDistribution, samples,
out clusterPickupInputDensityKernels[i][l],
out clusterPickupInputDensityKernelsUnivariate[i][l]);
}
}
}
}