def test_simple(): if not os.path.exists('./noaa_data'): p = params(clevel=5, storage='./noaa_data') t = Table([], dshape='{f0: int, f1:int, f2:int, f3:float}', params=p) # TODO: chunkwise copy t.append(adapter[:]) t.commit() else: t = open('ctable://noaa_data') print '--------------------------------------' print 'mean', mean(t, 'f3') print 'std', std(t, 'f2') print '--------------------------------------' qs1 = select(t, lambda x: x > 80000, 'f0') qs2 = select2(t, lambda x,y: x > y, ['f0', 'f1']) result = t[qs1]
def test_simple(): if not os.path.exists('./noaa_data'): p = params(clevel=5, storage='./noaa_data') t = Table([], dshape='{f0: int, f1:int, f2:int, f3:float}', params=p) # TODO: chunkwise copy t.append(adapter[:]) t.commit() else: t = open('ctable://noaa_data') print '--------------------------------------' print 'mean', mean(t, 'f3') print 'std', std(t, 'f2') print '--------------------------------------' qs1 = select(t, lambda x: x > 80000, 'f0') qs2 = select2(t, lambda x, y: x > y, ['f0', 'f1']) result = t[qs1]
t = blaze.open('ctable://example1') # Using chunked blaze array we can optimize for IO doing the sum # operations chunkwise from disk. t0 = time() print blaze.mean(t, 'f0') print "Chunked mean", round(time()-t0, 6) # Using NumPy is just going to through the iterator protocol on # carray which isn't going to efficient. t0 = time() print np.mean(t.data.ca['f0']) print "NumPy mean", round(time()-t0, 6) print '===================' t0 = time() #assert blaze.std(t, 'f0') == 28867.513458037913 print blaze.std(t, 'f0') print "Chunked std", round(time()-t0, 6) print '-------------------' t0 = time() print np.std(t.data.ca['f0']) print "NumPy std", round(time()-t0, 6) #blaze.generic_loop(t, 'f0')