def detect_waiting_dependency(train1, train2, tname1, tname2):
"""
Performs algorithm 1 described in 'Mining Railway Delay Dependenies in
Large-Scale Real-World Delay Data' (Flier, Gelashvili, Graffagnino,
Nunkesser).
"""
train1, train2 = trainsorting.sort_two_non_decreasing(train1, train2)
train1 = trainsorting.append(train1, float('inf'))
train2 = trainsorting.append(train2, 0)
diff = numpy.empty(len(train1)) #pylint: disable = no-member
for i in range(len(train1)):
diff[i] = train1[i] - train2[i]
points = 0
points_star = 0
start = diff[0]
start_star = 0
lastpointindex = 0 # pylint: disable = invalid-name
end_star = 0
for i in range(len(train1)):
if diff[i] > start:
if points > points_star:
#update best solution
points_star = points
start_star = start
end_star = train1[i-1]
start = diff[i]
notdone = True
while notdone:
if (train1[lastpointindex] < start and
lastpointindex < len(train1)):
lastpointindex += 1
else:
notdone = False
points = i - lastpointindex + 1
else:
points += 1
#Write sorted list to file (Why do i do this?)
#TODO: Ponder the pointfulness of this
trainio.list_to_file(numbers_to_strings(train1[:len(train1)-1]),
tname1+'sorted'+'_offset.txt', header='OFFSET')
trainio.list_to_file(numbers_to_strings(train2[:len(train2)-1]),
tname2+'sorted'+'_offset.txt', header='OFFSET')
#plot in R:
Rtrainplot(tname1, tname2, (points_star, start_star, end_star))
print 'Number of points in optimal solution: %d'%points_star
print 'Buffer time between the trains: %d'%start_star
print 'Maximal delay: %d'%end_star
def algorithm1(train1, train2):
"""
- Performs algorithm 1 described in 'Mining Railway Delay Dependenies in
Large-Scale Real-World Delay Data' (Flier, Gelashvili, Graffagnino,
Nunkesser).
- train1 and train2 must be numpy arrays containing delay times of the trains
there can be no missing values, and train1[d], train2[d] must be delay data
from the same day d. Implicitly train1 and train2 must be of equal length.
"""
train1, train2 = trainsorting.sort_two_non_decreasing(train1, train2)
train1 = trainsorting.append(train1, float('inf'))
train2 = trainsorting.append(train2, float(0))
#Locals
diff = trainsorting.difference(train1, train2)
points = 0
points_star = 0
bft = diff[0] #buffertime
bft_star = 0
lpi = 0 #last point index
md_star = 0 # maximal delay
#The algorithm:
for i in range(len(train1)):
if diff[i] > bft:
if points > points_star:
#update best solution
points_star = points
bft_star = bft
md_star = train1[i-1]
bft = diff[i]
notdone = True
while notdone:
if (train1[lpi] < bft and
lpi < len(train1)):
lpi += 1
else:
notdone = False
points = i - lpi + 1
else:
points += 1
return (points_star, bft_star, md_star)
def detect_waiting_dependency(train1, train2,tname1,tname2):
"""
Performs algorithm 1 described in 'Mining Railway Delay Dependenies in
Large-Scale Real-World Delay Data' (Flier, Gelashvili, Graffagnino,
Nunkesser).
"""
train1, train2 = trainsorting.sort_two_non_decreasing(train1, train2)
train1 = trainsorting.append(train1, float('inf'))
train2 = trainsorting.append(train2, 0)
diff = numpy.empty(len(train1)) #pylint: disable = no-member
for i in range(len(train1)):
diff[i] = train1[i] - train2[i]
points = 0
points_star = 0
start = diff[0]
start_star = 0
lastpointindex = 0 # pylint: disable = invalid-name
end_star = 0
for i in range(len(train1)):
if diff[i] > start:
if points > points_star:
#update best solution
points_star = points
start_star = start
end_star = train1[i-1]
start = diff[i]
notdone = True
while notdone:
if (train1[lastpointindex] < start and
lastpointindex < len(train1)):
lastpointindex += 1
else:
notdone = False
points = i - lastpointindex + 1
else:
points += 1
print ('Pstar :%d %d') %(train1[points_star-1], train2[points_star-1])
#Write sorted list to file
trainio.list_to_file(numbers_to_strings(train1[:len(train1)-1]),
tname1+'sorted'+'_offset.txt', header='OFFSET')
trainio.list_to_file(numbers_to_strings(train2[:len(train2)-1]),
tname2+'sorted'+'_offset.txt', header='OFFSET')
#Do this in R instead
#Globals are evil?
plotname = "delayer"+tname1+"victim"+tname2+".pdf"
os.system('Rscript trainplotter.R' + ' ' + tname1 + 'sorted_offset.txt'
+ ' ' + tname2 + 'sorted_offset.txt'
+' %d %d %d' % (points_star, start_star, end_star)
+ ' ' + plotname)
os.system('xdg-open ' + plotname)
#os.system('rm' + ' ' + '*_offset.txt')
print 'Number of points in optimal solution: %d'%points_star
print 'Buffer time between the trains: %d'%start_star
print 'Maximal delay: %d'%end_star
