#print penguin_clusters
#print noise__
noise_points[s] = [x for x,u in noise__]
print str(s) + " - " + str(len(user_identified_penguins))
if len(user_identified_penguins) > 20:
break
except AssertionError:
continue
#if len(user_identified_penguins) == 0:
# continue
if len(user_identified_penguins) <= 20:
#print noise__
not_found = cluster_compare(penguins[0],penguins[-1])
#if not_found == []:
# continue
image_file = cbook.get_sample_data(base_directory + "/Databases/penguins/images/"+object_id+".JPG")
image = plt.imread(image_file)
fig, ax = plt.subplots()
im = ax.imshow(image)
try:
X,Y = zip(*penguins_center[5])
plt.plot(X,Y,'.',color="red")
except ValueError:
pass
gold_centers,gold_clusters,noise__ = DivisiveDBSCAN(num_markings).fit(user_markings[20],user_ips[20],debug=True)#,jpeg_file=base_directory + "/Databases/penguins/images/"+object_id+".JPG")
print "gold standard number " + str(len(gold_clusters))
#not_found = []
fake_penguins = {}
for s in [5,10,15]:
print "== " + str(s)
#not_found.append([])
fake_penguins[s] = []
for nn in [1,2,3,4,5]:
user_identified_penguins,penguin_clusters,noise__ = DivisiveDBSCAN(nn).fit(user_markings[s],user_ips[s],debug=True)
#missed penguins - in gold standard but not found
not_found = cluster_compare(penguin_clusters,gold_clusters)
#fake penguins - found but not actually real
fake_found = cluster_compare(gold_clusters,penguin_clusters)
print len(not_found),len(fake_found)
#not_found[-1].append(len(gold_clusters) -len(not_found))
fake_penguins[s].append(len(fake_found))
overall_found[s][nn-1].append((len(gold_clusters) - len(not_found))/float(len(gold_clusters)))
#false positives - fake penguins - can only be calculated after everything else is done
for s in [5,10,15]:
for nn in [1,2,3,4,5]:
if fake_penguins[15][0] == 0:
overall_fake[s][nn-1].append(0)
print "done that"
total = 0
true_positives = []
false_positives = []
with open(base_directory + "/Databases/penguins_ibcc.out", 'rb') as f:
for l in f.readlines():
penguin_index, neg_prob, pos_prob = l.split(" ")
penguin = penguins[max_users][image_index][1][int(
float(penguin_index))][0]
#is this penguin "real" ie. is in the gold standard?
if cluster_compare(gold_standard, [
penguin,
]) == []:
#yes - penguin is real
true_positives.append(float(pos_prob))
else:
#penguin is fake
false_positives.append(float(pos_prob))
print min(sorted(true_positives)[2:])
print max(false_positives)
print len(false_positives)
X = []
Y = []
for p in np.arange(0, 1.01, 0.001):
X.append(
ibcc.runIbcc(base_directory+"/Databases/penguins_ibcc_config.py")
print "done that"
total = 0
true_positives = []
false_positives = []
with open(base_directory+"/Databases/penguins_ibcc.out",'rb') as f:
for l in f.readlines():
penguin_index, neg_prob,pos_prob = l.split(" ")
penguin = penguins[max_users][image_index][1][int(float(penguin_index))][0]
#is this penguin "real" ie. is in the gold standard?
if cluster_compare(gold_standard,[penguin,]) == []:
#yes - penguin is real
true_positives.append(float(pos_prob))
else:
#penguin is fake
false_positives.append(float(pos_prob))
print min(sorted(true_positives)[2:])
print max(false_positives)
print len(false_positives)
X = []
Y = []
for p in np.arange(0,1.01,0.001):
X.append(len([f for f in false_positives if f >= p])/float(len(false_positives)))
Y.append(len([t for t in true_positives if t >= p])/float(37.))
print "gold standard number " + str(len(gold_clusters))
# not_found = []
fake_penguins = {}
for s in [5, 10, 15]:
print "== " + str(s)
# not_found.append([])
fake_penguins[s] = []
for nn in [1, 2, 3, 4, 5]:
user_identified_penguins, penguin_clusters, noise__ = DivisiveDBSCAN(nn).fit(
user_markings[s], user_ips[s], debug=True
)
# missed penguins - in gold standard but not found
not_found = cluster_compare(penguin_clusters, gold_clusters)
# fake penguins - found but not actually real
fake_found = cluster_compare(gold_clusters, penguin_clusters)
print len(not_found), len(fake_found)
# not_found[-1].append(len(gold_clusters) -len(not_found))
fake_penguins[s].append(len(fake_found))
overall_found[s][nn - 1].append((len(gold_clusters) - len(not_found)) / float(len(gold_clusters)))
# false positives - fake penguins - can only be calculated after everything else is done
for s in [5, 10, 15]:
for nn in [1, 2, 3, 4, 5]:
if fake_penguins[15][0] == 0:
overall_fake[s][nn - 1].append(0)
#print penguin_clusters
#print noise__
noise_points[s] = [x for x, u in noise__]
print str(s) + " - " + str(len(user_identified_penguins))
if len(user_identified_penguins) > 20:
break
except AssertionError:
continue
#if len(user_identified_penguins) == 0:
# continue
if len(user_identified_penguins) <= 20:
#print noise__
not_found = cluster_compare(penguins[0], penguins[-1])
#if not_found == []:
# continue
image_file = cbook.get_sample_data(base_directory +
"/Databases/penguins/images/" +
object_id + ".JPG")
image = plt.imread(image_file)
fig, ax = plt.subplots()
im = ax.imshow(image)
try:
X, Y = zip(*penguins_center[5])
plt.plot(X, Y, '.', color="red")
except ValueError:
pass
sys.path.append("/home/ggdhines/PycharmProjects/reduction/experimental/clusteringAlg")
else:
sys.path.append("/home/greg/github/reduction/experimental/clusteringAlg")
from clusterCompare import cluster_compare
if os.path.exists("/home/ggdhines"):
base_directory = "/home/ggdhines"
else:
base_directory = "/home/greg"
penguins,temp = pickle.load(open(base_directory+"/Databases/penguins_vote.pickle","rb"))
#does this cluster have a corresponding cluster in the gold standard data?
#ie. does this cluster represent an actual penguin?
for image_index in range(len(penguins[5])):
print len(penguins[5])
user_penguins = penguins[5][0]
gold_penguins = penguins[5][1]
print len(user_penguins)
print len(user_penguins[0])
print "==="
print len(user_penguins)
for upen in user_penguins:
print upen
print cluster_compare(gold_penguins,[upen,])
break
else:
sys.path.append("/home/greg/github/reduction/experimental/clusteringAlg")
from clusterCompare import cluster_compare
if os.path.exists("/home/ggdhines"):
base_directory = "/home/ggdhines"
else:
base_directory = "/home/greg"
penguins, temp = pickle.load(open(base_directory + "/Databases/penguins_vote.pickle", "rb"))
# does this cluster have a corresponding cluster in the gold standard data?
# ie. does this cluster represent an actual penguin?
for image_index in range(len(penguins[5])):
print len(penguins[5])
user_penguins = penguins[5][0]
gold_penguins = penguins[5][1]
print len(user_penguins)
print len(user_penguins[0])
print "==="
print len(user_penguins)
for upen in user_penguins:
print upen
print cluster_compare(gold_penguins, [upen])
break
