Ejemplo n.º 1
0
def plot_equalize():
    X = array(sum([range(110, 121)] * 5 + [range(130, 141)] * 7, []))
    Xc = cumsum(histogram(X, bins=30)[0])
    Y = equalize(X)
    Yc = cumsum(histogram(Y, bins=30)[0])
    fig, ax = subplots()
    ax.plot(Xc, c='b')
    ax.plot(Yc, c='r')
    show()
Ejemplo n.º 2
0
def plot_equalize():
	X = array(sum([range(110, 121)] * 5 + [range(130, 141)] * 7, []))
	Xc = cumsum(histogram(X, bins = 30)[0])
	Y = equalize(X)
	Yc = cumsum(histogram(Y, bins = 30)[0])
	fig, ax = subplots()
	ax.plot(Xc, c = 'b')
	ax.plot(Yc, c = 'r')
	show()
Ejemplo n.º 3
0
def test_equalize():
	"""
		Besides basic properties, does a linearity test (that may not be mathematically sound)
	"""
	X = array(sum([range(10, 21)] * 15 + [range(130, 141)] * 4, []))
	Y = equalize(X, 255)
	assert Y.min() == 0
	assert Y.max() == 255
	C = cumsum(histogram(Y, bins = 30)[0])
	L = linspace(0, X.shape[0], 30)
	err = sqrt(sum((L - C)**2)) / X.shape[0]
	assert err < 0.5, 'equalized cdf appears to be not be linear ({0:.2f} rmse from linearity)'.format(err)
Ejemplo n.º 4
0
def test_equalize():
    """
		Besides basic properties, does a linearity test (that may not be mathematically sound)
	"""
    X = array(sum([range(10, 21)] * 15 + [range(130, 141)] * 4, []))
    Y = equalize(X, 255)
    assert Y.min() == 0
    assert Y.max() == 255
    C = cumsum(histogram(Y, bins=30)[0])
    L = linspace(0, X.shape[0], 30)
    err = sqrt(sum((L - C)**2)) / X.shape[0]
    assert err < 0.5, 'equalized cdf appears to be not be linear ({0:.2f} rmse from linearity)'.format(
        err)
Ejemplo n.º 5
0
 if 'shift' in fmt:
     print 'shifting by {0}'.format(fmt['shift'])
     column += fmt['shift']
 if 'cut_gt' in fmt and 'cut_to' in fmt:
     print 'cutting > {0:f} to {1:f} for {2:d}'.format(
         fmt['cut_gt'], fmt['cut_to'], colnr)
     cut_cnt += (column > fmt['cut_gt']).sum()
     column[column > fmt['cut_gt']] = fmt['cut_to']
 if 'cut_lt' in fmt and 'cut_to' in fmt:
     print 'cutting < {0:f} to {1:f} for {2:d}'.format(
         fmt['cut_lt'], fmt['cut_to'], colnr)
     cut_cnt += (column < fmt['cut_lt']).sum()
     column[column < fmt['cut_lt']] = fmt['cut_to']
 if 'equalize' in fmt and fmt['equalize']:
     print 'equalizing histogram'
     column = equalize(column)
 ax_after.hist(column, facecolor='blue', bins=30)
 ax_after_cdf.hist(column, cumulative=True, facecolor='green', bins=30)
 ax_frac.pie([
     column.shape[0] - columnnonnum.shape[0] - cut_cnt,
     columnnonnum.shape[0], cut_cnt
 ],
             labels=['normal', 'NaN', 'cut'])
 print 'frac', column.shape[0], [
     column.shape[0] - columnnonnum.shape[0] - cut_cnt,
     columnnonnum.shape[0], cut_cnt
 ]
 show(block=False)
 while True:
     if 'cut_gt' in fmt:
         print 'column {0:d} already has a cutoff at {1:d}'.format(
Ejemplo n.º 6
0
		else:
			fmt = copy(format['default'])
		if 'shift' in fmt:
			print 'shifting by {0}'.format(fmt['shift'])
			column += fmt['shift']
		if 'cut_gt' in fmt and 'cut_to' in fmt:
			print 'cutting > {0:f} to {1:f} for {2:d}'.format(fmt['cut_gt'], fmt['cut_to'], colnr)
			cut_cnt += (column > fmt['cut_gt']).sum()
			column[column > fmt['cut_gt']] = fmt['cut_to']
		if 'cut_lt' in fmt and 'cut_to' in fmt:
			print 'cutting < {0:f} to {1:f} for {2:d}'.format(fmt['cut_lt'], fmt['cut_to'], colnr)
			cut_cnt += (column < fmt['cut_lt']).sum()
			column[column < fmt['cut_lt']] = fmt['cut_to']
		if 'equalize' in fmt and fmt['equalize']:
			print 'equalizing histogram'
			column = equalize(column)
		ax_after.hist(column, facecolor = 'blue', bins = 30)
		ax_after_cdf.hist(column, cumulative = True, facecolor = 'green', bins = 30)
		ax_frac.pie([column.shape[0] - columnnonnum.shape[0] - cut_cnt, columnnonnum.shape[0], cut_cnt], labels = ['normal', 'NaN', 'cut'])
		print 'frac', column.shape[0], [column.shape[0] - columnnonnum.shape[0] - cut_cnt, columnnonnum.shape[0], cut_cnt]
		show(block = False)
		while True:
			if 'cut_gt' in fmt:
				print 'column {0:d} already has a cutoff at {1:d}'.format(colnr, fmt['cut_gt'])
				close()
				break
			cut = raw_input('column {0:d} cutoff point? '.format(colnr))
			if cut.strip() == '':
				print 'no cutoff'
				break
			try: