def show(data, recommender, fractionTrain=0.8, highFactor=0.1, verbose=False, plot=False):
"""
Parameters:
cluster: an array of arrays
fractionTrain: a float specifying percent of data to use as train
highFactor: ratio of any given element to the largest element in the array
Returns:
the RMSE produced by removing a specific color, then adding it back
Algorithm:
Works by first finding the max value in the histogram and then trying to find the
index of the histogram that contains the value that is closest (in terms of a ration
with the max value) to highFactor. Removes this color, then passes it to recommender
to get back a value which it then adds to the histogramogram, then takes the rmse between
the original and the modified
"""
xTrain, xTest = ml.splitData(data, fractionTrain)
train_names, test_names = ml.splitData(np.array(names), fractionTrain)
assert len(train_names) == len(xTrain)
assert len(test_names) == len(xTest)
n, D = xTest.shape
indices = np.random.choice(n, SAMPLE_SIZE)
xTest = xTest[indices, :]
test_names = test_names[indices]
assert xTest.shape == (SAMPLE_SIZE, D)
assert test_names.shape == (SAMPLE_SIZE,)
n = SAMPLE_SIZE
train_colors, _, train_histograms = tester.removeColors(xTrain, highFactor=highFactor)
try:
recommender.fitWithPlot(train_histograms, train_colors, train_names)
except:
print train_colors
recommender.fit(train_histograms, train_colors)
if verbose:
print "Done fitting"
colors, quantities, histograms = tester.removeColors(xTest, highFactor=highFactor)
assert colors.shape[0] == n
assert histograms.shape[0] == n
numCorrect = 0
if plot:
colorRecommend = []
namesRecommend = []
colorRemoved = []
clusterLoc = []
# clusterIndexList = []
D = histograms.shape[1]
count = np.zeros(D)
for color in colors:
count[color] += 1
clusters = []
recommendedColors = np.zeros((n))
ignored = 0
for i in xrange(n):
if i % 100 == 1:
print "Partial %d: %f" % (i, float(numCorrect) / i)
color, amount = colors[i], quantities[i]
# Ignore colors that might bias us
if count[color] > 10:
ignored += 1
continue
hist = histograms[i]
# Ignore colors that are basically the background
if hist[color] > 0.4:
ignored += 1
continue
if verbose:
print "Testing site %s" % names[i]
print "Amount remmoved %d" % amount
# This is used for cluster recommendations
# elem, recommendedColor = recommender.recommendFromCluster(hist, xTrain)
# if verbose:
# print 'Recommended from website %s' % names[elem]
# This is used for vanilla classifiers
try:
cluster_names = recommender.clusterNames(hist)
clusters.append(cluster_names)
except:
pass
cluster = recommender.cluster(hist)
print "Incoming x"
nz = ml.maxArgs(hist, 15)
for j in nz:
print j, hist[j]
for x in cluster:
print "Another x"
nz = ml.maxArgs(x, 15)
for j in nz:
print j, x[j]
recommendedColor = recommender.predict(hist)
print recommendedColor
r1, g1, b1 = image.binToRGB(color)
r2, g2, b2 = image.binToRGB(recommendedColor)
if verbose:
print "Removed color %d %d %d. Recommended color %d %d %d." % (r1, g1, b1, r2, g2, b2)
print "Color distance: %d" % (image.binDistance(recommendedColor, color))
recommendedColors[i] = recommendedColor
# for plotting purposes
if plot:
colorRemoved.append(color)
colorRecommend.append(recommendedColor)
namesRecommend.append(test_names[i])
# clusterIndex = recommender.returnClusterTest(hist)
# clusterNames = recommender.clusterNames[clusterIndex]
# clusterIndexList.append(clusterLin)
# clusterLoc.append(clusterNames)
if verbose:
print "Recommended color %d" % (recommendedColor)
if recommendedColor == color:
numCorrect += 1
print "Ignored: %d" % ignored
print tester.colorError(colors, recommendedColors)
if plot:
plotRecommend(colorRemoved, colorRecommend, namesRecommend, clusters)
percentCorrect = float(numCorrect) / (n - ignored)
return percentCorrect
def test(data, recommender, fractionTrain=.8, highFactor=.1, verbose=False):
"""
Parameters:
cluster: an array of arrays
fractionTrain: a float specifying percent of data to use as train
highFactor: ratio of any given element to the largest element in the array
Returns:
the RMSE produced by removing a specific color, then adding it back
Algorithm:
Works by first finding the max value in the histogram and then trying to find the
index of the histogram that contains the value that is closest (in terms of a ration
with the max value) to highFactor. Removes this color, then passes it to recommender
to get back a value which it then adds to the histogramogram, then takes the rmse between
the original and the modified
"""
xTrain, xTest = ml.splitData(data, fractionTrain)
n = xTest.shape[0]
m = xTrain.shape[0]
train_colors, _, train_histograms = removeColors(xTrain, highFactor=highFactor)
recommender.fit(train_histograms, train_colors)
if verbose:
print 'Done fitting'
colors, quantities, histograms = removeColors(xTest, highFactor=highFactor)
assert(colors.shape[0] == n)
assert(histograms.shape[0] == n)
numCorrect = 0
D = histograms.shape[1]
count = np.zeros(D)
for color in colors:
count[color] += 1
tmp = count[np.where(count > 0)]
color_mean = np.mean(tmp)
color_stdev = np.std(tmp)
print 'Color mean and stdev', color_mean, color_stdev
recommendedColors = np.zeros((n))
ignored = 0
intersectionRatio = 0.
for i in xrange(n):
if i % 100 == 1:
print 'Partial %d: %f' % (i, float(numCorrect) / (i - ignored + 1))
color, amount = colors[i], quantities[i]
# Ignore colors that might bias us
if count[color] > color_mean + color_stdev:
ignored += 1
continue
hist = histograms[i]
# Ignore colors that are basically the background
if hist[color] > 0.4:
ignored += 1
continue
if verbose:
print 'Testing site %s' % names[i]
print 'Amount remmoved %d' % amount
try:
cluster = recommender.cluster(hist)
intersectionRatio += core.clusterIntersectionRatio(hist, cluster)
except:
pass
#recommender.testClusters(hist)
recommendedColor = recommender.predict(hist)
r1, g1, b1 = image.binToRGB(color)
r2, g2, b2 = image.binToRGB(recommendedColor)
if verbose:
print 'Removed color %d %d %d. Recommended color %d %d %d.' % (r1, g1, b1, r2, g2, b2)
print 'Color distance: %d' % (image.binDistance(recommendedColor, color))
recommendedColors[i] = recommendedColor
if verbose:
print 'Recommended color %d' % (recommendedColor)
if recommendedColor == color:
numCorrect += 1
print 'Ignored: %d. Used: %d' % (ignored, n - ignored)
print 'Mean cluster intersection ratio: %f' % (intersectionRatio / (n - ignored))
print colorError(colors, recommendedColors)
percentCorrect = float(numCorrect)/(n - ignored)
return percentCorrect