conn = connect('buses.db')
curs = conn.cursor()
curs.execute("select * from stops")
stops = []
for row in curs:
code = row[0]
name = row[1]
x = row[2]
y = row[3]
stops.append(((x, y), code, name))
tree = kdtree(stops)
#tree.dump(3)
#searchrange(tree,(55.9014167786,-4),(55.916,-3.224),2)
#testloc=(55.952545,-3.200546)
#nearest = searchnearest(tree,testloc)
#print "The nearest is ",nearest, distance(nearest.location[0],testloc)
# Snap route points to stops
curs.execute("select * from points")
for row in curs:
route, chain, x, y, stop, dist = row
pointloc = (x, y)
stop = searchnearest(tree, pointloc)
stoploc, code, name = stop.location
conn = connect('buses.db')
curs = conn.cursor()
curs.execute("select * from stops")
stops=[]
for row in curs:
code=row[0]
name=row[1]
x=row[2]
y=row[3]
stops.append(((x,y),code,name))
tree=kdtree(stops)
def recordnumgenerator():
num=0
while 1:
yield num
num+=1
# Header - 8 bytes - 'bus1', integer root pos
f=file("stops.dat","wb")
f.seek(8,os.SEEK_SET)
recordnumgen=recordnumgenerator()
rootpos=tree.write(f,recordnumgen)
f.seek(0,os.SEEK_SET)
print rootpos ," root"
first mapping
For each column not in the mapping the nearest neighbor that IS in the mapping
is identified and a new mapping is printed in which such columns are mapped to
the same symbol as said nearest neighbor.
"""
import sys
from math import *
from kdtree import *
inf = float( "inf" )
k = kdtree()
points = []
points_to_labels = dict()
# Read the mapping
mapping = {}
for line in open( sys.argv[1] ):
fields = line.split()
mapping[ fields[0] ] = fields[1]
# Read the ancestral distributions associated with that mapping
for line in open( sys.argv[2] ):
if line.startswith( '#' ):
continue
fields = line.split()
label = fields[0]
def result(string, empty):
_input = []
query = string.split(',')
for i in range(8):
_input.append(int(query[i]))
start_time = time.time()
result = empty.search_nn([
_input[0], _input[1], _input[2], _input[3], _input[4], _input[5],
_input[6], _input[7]
])
T = "%s seconds" % (time.time() - start_time)
a = str(result)
b = a.split('(')
distance = b[2].split(',')[9].split(')')[0]
d = b[2].split(')')[0].split(',')[0:8]
coordinate = "" + d[0] + ',' + d[1] + ',' + d[2] + ',' + d[3] + ',' + d[
4] + ',' + d[5] + ',' + d[6] + ',' + d[7]
index = b[2].split(')')[0].split(',')[8]
str1 = "The nearest neighbor point's coordinate is : " + coordinate
str2 = "The time cost of kdtree is : " + T
str3 = "The distance between query point and neareast point is : " + distance
return [str1, str2, str3]
kdtree('itemset.txt')
result('1,2,3,4,5,6,7,8')
