#!/usr/bin/env python
__author__ = 'ggdhines'
from penguinAggregation import PenguinAggregation
import random
import os
import sys
# add the paths necessary for clustering algorithm and ibcc - currently only works on Greg's computer
if os.path.exists("/home/ggdhines"):
sys.path.append("/home/ggdhines/PycharmProjects/reduction/experimental/clusteringAlg")
else:
sys.path.append("/home/greg/github/reduction/experimental/clusteringAlg")
from divisiveKmeans import DivisiveKmeans
clusterAlg = DivisiveKmeans().__fit__
penguin = PenguinAggregation()
subject_ids = penguin.__get_subjects_per_site__("APZ00035mv",complete=True,remove_blanks=True)
for i,subject in enumerate(random.sample(subject_ids,50)):
print i
penguin.__readin_subject__(subject)
blankImage = penguin.__cluster_subject__(subject, clusterAlg)
if not blankImage:
penguin.__save_raw_markings__(subject)
break
clusterAlg = DivisiveKmeans().__fit__
penguin = PenguinAggregation()
gold_subjects = penguin.__get_gold_subjects__()
gold_sample = gold_subjects[:50]
penguin.__readin_users__()
for count,zooniverse_id in enumerate(gold_sample):
if count == 50:
break
print count, zooniverse_id
penguin.__readin_subject__(zooniverse_id,read_in_gold=True)
blankImage = penguin.__cluster_subject__(zooniverse_id, clusterAlg,fix_distinct_clusters=True,correction_alg=correctionAlg)
penguin.__soy_it__(zooniverse_id)
penguin.__signal_ibcc__()
penguin.__roc__()
# one_overlap = penguin.__off_by_one__(display=True)
# last_id = None
#
# for t in one_overlap:
# if t[0] != last_id:
# print "*****"
# print "====="
# last_id = t[0]
# penguin.__relative_confusion__(t)
Y2 = []
Z1 = []
Z2 = []
nonEmpty = 0
index = -1
random.shuffle(subject_ids)
while True:
index += 1
#for i,subject in enumerate(random.sample(subject_ids,50)):
#subject = "APZ000173v"
subject = subject_ids[index]
#print nonEmpty,index
penguin.__readin_subject__(
subject, read_in_gold=True) #,users_to_skip=["caitlin.black"])
numClusters, time_to_cluster = penguin.__cluster_subject__(
subject, clusterAlg)
if numClusters == 0:
continue
print nonEmpty
nonEmpty += 1
if nonEmpty == 50:
break
accuracy1 = penguin.__accuracy__(subject)
X1.append(numClusters)
Y1.append(time_to_cluster)
Z1.append(accuracy1)
Y2 = []
Z1 = []
Z2 = []
nonEmpty = 0
index = -1
random.shuffle(subject_ids)
while True:
index += 1
#for i,subject in enumerate(random.sample(subject_ids,50)):
#subject = "APZ000173v"
subject = subject_ids[index]
#print nonEmpty,index
agglomerative.__readin_subject__(subject,read_in_gold=True)#,users_to_skip=["caitlin.black"])
dkmeans.__readin_subject__(subject,read_in_gold=True)
numClusters,time_to_cluster = agglomerative.__cluster_subject__(subject)
if numClusters == 0:
continue
print nonEmpty
nonEmpty += 1
if nonEmpty == 30:
break
accuracy1 = agglomerative.__accuracy__(subject)
X1.append(numClusters)
Y1.append(time_to_cluster)
Z1.append(accuracy1)
from penguinAggregation import PenguinAggregation
import random
import os
import sys
# add the paths necessary for clustering algorithm and ibcc - currently only works on Greg's computer
if os.path.exists("/home/ggdhines"):
sys.path.append("/home/ggdhines/PycharmProjects/reduction/experimental/clusteringAlg")
else:
sys.path.append("/home/greg/github/reduction/experimental/clusteringAlg")
from divisiveKmeans import DivisiveKmeans
clusterAlg = DivisiveKmeans().__fit__
penguin = PenguinAggregation()
zooniverse_id_list = random.sample(penguin.__get_subjects_per_site__("APZ0001x3p"),40)
for i,zooniverse_id in enumerate(zooniverse_id_list):
print i
penguin.__readin_subject__(zooniverse_id)
blankImage = penguin.__cluster_subject__(zooniverse_id, clusterAlg)
if not blankImage:
print "+--"
penguin.__find_closest_neighbour__(zooniverse_id)
#penguin.__plot_cluster_size__(zooniverse_id_list)
penguin.__find_one__(zooniverse_id_list)
Z1 = []
Z2 = []
nonEmpty = 0
index = -1
random.shuffle(subject_ids)
while True:
index += 1
#for i,subject in enumerate(random.sample(subject_ids,50)):
#subject = "APZ000173v"
subject = subject_ids[index]
#print nonEmpty,index
agglomerative.__readin_subject__(
subject, read_in_gold=True) #,users_to_skip=["caitlin.black"])
dkmeans.__readin_subject__(subject, read_in_gold=True)
numClusters, time_to_cluster = agglomerative.__cluster_subject__(subject)
if numClusters == 0:
continue
print nonEmpty
nonEmpty += 1
if nonEmpty == 20:
break
accuracy1 = agglomerative.__accuracy__(subject)
X1.append(numClusters)
Y1.append(time_to_cluster)
Z1.append(accuracy1)
import random
import os
import sys
# add the paths necessary for clustering algorithm and ibcc - currently only works on Greg's computer
if os.path.exists("/home/ggdhines"):
sys.path.append(
"/home/ggdhines/PycharmProjects/reduction/experimental/clusteringAlg")
else:
sys.path.append("/home/greg/github/reduction/experimental/clusteringAlg")
from divisiveKmeans import DivisiveKmeans
clusterAlg = DivisiveKmeans().__fit__
penguin = PenguinAggregation()
zooniverse_id_list = random.sample(
penguin.__get_subjects_per_site__("APZ0001x3p"), 40)
for i, zooniverse_id in enumerate(zooniverse_id_list):
print i
penguin.__readin_subject__(zooniverse_id)
blankImage = penguin.__cluster_subject__(zooniverse_id, clusterAlg)
if not blankImage:
print "+--"
penguin.__find_closest_neighbour__(zooniverse_id)
#penguin.__plot_cluster_size__(zooniverse_id_list)
penguin.__find_one__(zooniverse_id_list)
X2 = []
Y2 = []
Z1 = []
Z2 = []
nonEmpty = 0
index = -1
random.shuffle(subject_ids)
while True:
index += 1
# for i,subject in enumerate(random.sample(subject_ids,50)):
# subject = "APZ000173v"
subject = subject_ids[index]
# print nonEmpty,index
penguin.__readin_subject__(subject, read_in_gold=True) # ,users_to_skip=["caitlin.black"])
numClusters, time_to_cluster = penguin.__cluster_subject__(subject, clusterAlg)
if numClusters == 0:
continue
print nonEmpty
nonEmpty += 1
if nonEmpty == 50:
break
accuracy1 = penguin.__accuracy__(subject)
X1.append(numClusters)
Y1.append(time_to_cluster)
Z1.append(accuracy1)
#!/usr/bin/env python
__author__ = 'ggdhines'
from penguinAggregation import PenguinAggregation
import random
import os
import sys
# add the paths necessary for clustering algorithm and ibcc - currently only works on Greg's computer
if os.path.exists("/home/ggdhines"):
sys.path.append(
"/home/ggdhines/PycharmProjects/reduction/experimental/clusteringAlg")
else:
sys.path.append("/home/greg/github/reduction/experimental/clusteringAlg")
from divisiveKmeans import DivisiveKmeans
clusterAlg = DivisiveKmeans().__fit__
penguin = PenguinAggregation()
subject_ids = penguin.__get_subjects_per_site__("APZ00035mv",
complete=True,
remove_blanks=True)
for i, subject in enumerate(random.sample(subject_ids, 50)):
print i
penguin.__readin_subject__(subject)
blankImage = penguin.__cluster_subject__(subject, clusterAlg)
if not blankImage:
penguin.__save_raw_markings__(subject)
break
# add the paths necessary for clustering algorithm and ibcc - currently only works on Greg's computer
if os.path.exists("/home/ggdhines"):
sys.path.append(
"/home/ggdhines/PycharmProjects/reduction/experimental/clusteringAlg")
else:
sys.path.append("/home/greg/github/reduction/experimental/clusteringAlg")
from agglomerativeClustering import Ward, TooBig
clusterAlg = Ward().__fit__
penguin = PenguinAggregation()
subject_ids = pickle.load(
open(aggregation.base_directory + "/Databases/penguin_gold.pickle", "rb"))
for i, subject in enumerate(random.sample(subject_ids, 50)):
#subject = "APZ000173v"
print i, subject
penguin.__readin_subject__(subject, users_to_skip=["caitlin.black"])
try:
numClusters, time = penguin.__cluster_subject__(subject, clusterAlg)
except TooBig:
print "too big"
continue
if not blankImage:
penguin.__display_raw_markings__(subject)
penguin.__display__markings__(subject)
gold_dict[zooniverse_id] = pts[:]
zooniverse_id = s["zooniverse_id"]
width = s["metadata"]["original_size"]["width"]
height = s["metadata"]["original_size"]["height"]
pts = [(int(x) / (width / 1000.), int(y) / (height / 563.))
for (x, y) in pts]
if penguin.__get_status__(zooniverse_id) != "complete":
continue
penguin.__readin_subject__(zooniverse_id)
blankImage = penguin.__cluster_subject__(zooniverse_id,
clusterAlg,
fix_distinct_clusters=True)
penguin.__roc__()
#__ibcc__2(penguin.clusterResults,penguin.users_per_subject)
# plt.plot(Xt,Yt,'.')
# plt.xlabel("Large cluster size")
# plt.ylabel("Small cluster size")
# plt.xlim((min(Xt)-0.05,max(Xt)+0.05))
# plt.ylim((min(Yt)-0.05,max(Yt)+0.05))
# plt.show()
# for i in range(1,10):
# print sum([1 for j in Yt if i == j])
# Y = []
# yErr = []
gold_dict[zooniverse_id] = pts[:]
zooniverse_id = s["zooniverse_id"]
width = s["metadata"]["original_size"]["width"]
height = s["metadata"]["original_size"]["height"]
pts = [(int(x)/(width/1000.),int(y)/(height/563.)) for (x,y) in pts]
if penguin.__get_status__(zooniverse_id) != "complete":
continue
penguin.__readin_subject__(zooniverse_id)
blankImage = penguin.__cluster_subject__(zooniverse_id, clusterAlg,fix_distinct_clusters=True)
penguin.__roc__()
#__ibcc__2(penguin.clusterResults,penguin.users_per_subject)
# plt.plot(Xt,Yt,'.')
# plt.xlabel("Large cluster size")
# plt.ylabel("Small cluster size")
# plt.xlim((min(Xt)-0.05,max(Xt)+0.05))
# plt.ylim((min(Yt)-0.05,max(Yt)+0.05))
# plt.show()
# for i in range(1,10):
# print sum([1 for j in Yt if i == j])
# Y = []
# yErr = []
# X = []
import cPickle as pickle
import aggregation
# add the paths necessary for clustering algorithm and ibcc - currently only works on Greg's computer
if os.path.exists("/home/ggdhines"):
sys.path.append("/home/ggdhines/PycharmProjects/reduction/experimental/clusteringAlg")
else:
sys.path.append("/home/greg/github/reduction/experimental/clusteringAlg")
from agglomerativeClustering import Ward, TooBig
clusterAlg = Ward().__fit__
penguin = PenguinAggregation()
subject_ids = pickle.load(open(aggregation.base_directory + "/Databases/penguin_gold.pickle", "rb"))
for i, subject in enumerate(random.sample(subject_ids, 50)):
# subject = "APZ000173v"
print i, subject
penguin.__readin_subject__(subject, users_to_skip=["caitlin.black"])
try:
numClusters, time = penguin.__cluster_subject__(subject, clusterAlg)
except TooBig:
print "too big"
continue
if not blankImage:
penguin.__display_raw_markings__(subject)
penguin.__display__markings__(subject)