def filterVals(latlonvals):
includeindicies=[0]
base = 0
skip = 2
while(base+skip < len(latlonvals)):
pred = ((latlonvals[base][0]+latlonvals[base+skip][0])/2, (latlonvals[base][1]+latlonvals[base+skip][1])/2)
err = CDutils.greatCircDist(pred[0], pred[1], latlonvals[base+skip-1][0], latlonvals[base+skip-1][1])
if(err > 10):
includeindicies.append(base+skip-1)
base = base+skip-1
skip = 2
else:
skip = skip + 1
newlist = [latlonvals[item] for item in includeindicies]
if(newlist[0] != newlist[-1]):
newlist.append(newlist[0])
return newlist
def filterVals(latlonvals): includeindicies=[0] base = 0 skip = 2 while(base+skip < len(latlonvals)): mfact = (skip-1.0)/skip predlat = latlonvals[base][0]+(latlonvals[base+skip][0]-latlonvals[base][0])*mfact predlon = latlonvals[base][1]+(latlonvals[base+skip][1]-latlonvals[base][1])*mfact pred = (predlat, predlon) err = CDutils.greatCircDist(pred[0], pred[1], latlonvals[base+skip-1][0], latlonvals[base+skip-1][1]) if(err > 10): includeindicies.append(base+skip-1) base = base+skip-1 skip = 2 else: skip = skip + 1 newlist = [latlonvals[item] for item in includeindicies] if(newlist[0] != newlist[-1]): newlist.append(newlist[0]) #print "filtered from "+str(len(latlonvals))+" to "+str(len(newlist)) return newlist
for i in xrange(0, len(line)):
if line[i] == "\"":
inquote = not(inquote)
newline = newline+line[i]
elif(inquote and line[i] == ","):
newline = newline+" "
else:
newline = newline+line[i]
lines[x] = newline
#testcds = [1421501, 1421502, 1421503, 1421504, 1421505]
#load all the Sydney CD census data
#CDutils.getSomeSydneyCDs(testcds)
CDutils.getAllSydneyCDs()
#now load the specific cross-tabs that I have from the ABS
dwellbyincomelines = open('/home/peterr/data/abs_stats/sydneyhousingspecialrequest/Rickwood Table 1 190407.csv').readlines()[7:]
dwellbyhhtypelines = open('/home/peterr/data/abs_stats/sydneyhousingspecialrequest/Rickwood Table 2 190407.csv').readlines()[6:]
carsbyhhtypelines = open('/home/peterr/data/abs_stats/sydneyhousingspecialrequest/Rickwood Table 3 190407.csv').readlines()[6:]
carsbyincomelines = open('/home/peterr/data/abs_stats/sydneyhousingspecialrequest/Rickwood Table 4 190407.csv').readlines()[7:]
for x in [dwellbyincomelines, dwellbyhhtypelines, carsbyhhtypelines, carsbyincomelines]:
stripQuotedCommas(x)
#work out starting data lines for each cdnumber, to save searching each time
startlines = getStartLines(dwellbyincomelines, dwellbyhhtypelines, carsbyhhtypelines, carsbyincomelines)
