def update(individual_classifications):
#start by removing all temp files
try:
os.remove("/home/greg/Databases/condor_ibcc.out")
except OSError:
pass
try:
os.remove("/home/greg/Databases/condor_ibcc.mat")
except OSError:
pass
try:
os.remove("/home/greg/Databases/condor_ibcc.csv.dat")
except OSError:
pass
with open("/home/greg/Databases/condor_ibcc.csv","a") as f:
for u, s, b in individual_classifications:
f.write(str(u)+","+str(s)+","+str(b)+"\n")
print datetime.datetime.time(datetime.datetime.now())
ibcc.runIbcc("/home/greg/Databases/condor_ibcc.py")
print datetime.datetime.time(datetime.datetime.now())
def __ibcc__2(results_dict,users_per_subject):
# results needs to be a dictionary which maps from a subject ID to a list of found clusters
# users_per_subject needs to be different, just in case someone clicked on nothing
# get a list of all of the users
assert type(users_per_subject) == dict
global_users = []
for u_list in users_per_subject.values():
for u in u_list:
if not(u in global_users):
global_users.append(u)
things_in_subject = {}
off_by_one_clusters = []
things_list = []
thing_index = 0
for zooinverse_id in results_dict:
things_in_subject[zooinverse_id] = []
centers,clusters,users = results_dict[zooinverse_id]
pairs = __find_closest__(centers,clusters,users,user_threshold=1,offset=thing_index)
off_by_one_clusters.extend(list(pairs))
for users_per_marking in users:
things_in_subject[zooinverse_id].append(thing_index)
# find out who saw or did not see this "thing" - out of everyone who viewed this subject
t = []
for u in users_per_subject[zooinverse_id]:
if u in users_per_marking:
t.append((global_users.index(u),1))
else:
t.append((global_users.index(u),0))
things_list.append(t[:])
thing_index += 1
# run ibcc with out combining any of the clusters
with open(base_directory+"/Databases/base_ibcc.csv","wb") as f:
f.write("a,b,c\n")
for thing_index in range(len(things_list)):
for user_index, marked in things_list[thing_index]:
f.write(str(user_index)+","+str(thing_index)+","+str(marked)+"\n")
__ibcc_init__("base")
ibcc.runIbcc(base_directory+"/Databases/base_ibcc.py")
confusions = []
with open(base_directory+"/Databases/base_ibcc.mat") as f:
for user_index, l in enumerate(f.readlines()):
confusions.append([float(f) for f in l[:-1].split(" ")])
for count,(c1,c2,overlap) in enumerate(off_by_one_clusters):
print things_list[c1]
print things_list[c2]
users = zip(*things_list[c1])[0]
for u in users:
print confusions[u][2],confusions[u][3]
break
def __ibcc__(self):
for species in self.speciesList:
#check to see whether or not this file exists
if not(os.path.isfile(self.baseDir+"ibcc/"+species+"_ibcc.out"+str(self.cutOff))):
ibcc.runIbcc(self.baseDir+"ibcc/"+str(species)+str(self.cutOff)+"config.py")
#i = IBCCsetup()
#i.__createConfigs__()
#i.__filterUserClassifications__()
#i.__ibcc__()
def __classify__(self):
userNames = self.userDict.keys()
subjectNames = self.subjectDict.keys()
f = open(self.baseDir+"ibcc/input",'wb')
for u in self.userDict:
classifications = self.userDict[u].__getClassifications__()
for (s,r) in classifications:
f.write(str(userNames.index(u)) + "," + str(subjectNames.index(s)) + "," + str(r) + "\n")
f.close()
#now - write the config file
f = open(self.baseDir+"ibcc/config.py",'wb')
f.write("import numpy as np\nscores = np.array([0,1])\n")
f.write("nScores = len(scores)\n")
f.write("nClasses = 2\n")
f.write("inputFile = '"+self.baseDir+"ibcc/input'\n")
f.write("outputFile = '"+self.baseDir+"ibcc/output'\n")
f.write("confMatFile = '"+self.baseDir+"ibcc/confusion'\n")
#f.write("nu0 = np.array([45.0,55.0])\n")
f.close()
ibcc.runIbcc(self.baseDir+"ibcc/config.py")
pass
try:
os.remove(data_directory + "/galaxy_zoo_ibcc.mat")
except OSError:
pass
try:
os.remove(data_directory + "/galaxy_zoo_ibcc.csv.dat")
except OSError:
pass
import datetime
print datetime.datetime.time(datetime.datetime.now())
print base_directory + "/Databases/galaxy_zoo_ibcc.py"
ibcc.runIbcc(data_directory + "/galaxy_zoo_ibcc.py")
print datetime.datetime.time(datetime.datetime.now())
#read in gold standard data
pos0 = []
pos1 = []
pos2 = []
with open(data_directory + "/candels_t01_a00_positive.dat", "rb") as f:
for l in f.readlines():
pos0.append(l[:-1])
with open(data_directory + "/candels_t01_a01_positive.dat", "rb") as f:
for l in f.readlines():
pos1.append(l[:-1])
with open(data_directory + "/candels_t01_a02_positive.dat", "rb") as f:
for l in f.readlines():
pos2.append(l[:-1])
def __signal_ibcc_majority__(self,split_ip_address=True):
"""
run ibcc to determine which clusters are signal or noise
use majority voting to determine priors
:param split_ip_address: for user ids which are ip addresses - when people are not logged in - should be
treat each subject completely separate. That is if ip address X marked subjects A and B should we treat
X as being two completely different people for those two classifications. There is no guarantee that they
are the same person but seems like a lot of information to throw away. The param is to allow exploring the
options and results.
:return:
"""
# todo: implement a middle ground for split_ip_address where we treat the same ip address as the same person
# todo: as long as the classifications are close enough together time wise
# get all users who have viewed any subjects which are processing - also get the list of those who
# did so while not logged in
all_users = list(self.project_api.__all_users__())
all_ips = list(self.project_api.__all_ips__())
# global cluster count - across all images/subjects
cluster_count = -1
# need to give the ip addresses unique indices, so update ip_offset after every subject
ip_offset = 0
# needed for determining priors for IBCC
real_animals = 0
fake_animals = 0
# needed for prior confusion matrix
true_pos = []
true_neg = []
# intermediate holder variable
# because ibcc needs indices to be nice and ordered with no gaps, we have to make two passes through the data
to_ibcc = []
# for each global cluster index, store what image/subject it is from and what its local index is
# wrt to that subject
self.global_to_local = []
# print out the classifications and set up the priors using majority voting
for zooniverse_id in self.clusterResults:
if self.clusterResults[zooniverse_id] is None:
continue
# get the list of all the users who viewed this subject
# and the ip addresses of every user who was not logged in while viewing the subjects
users_per_subject = self.project_api.__users__(zooniverse_id)
ips_per_subject = self.project_api.__ips__(zooniverse_id)
# process each cluster (possible animal), one at a time
# only the names of users who marked this cluster matter - the specific x,y points are irrelevant right now
for local_index,user_per_cluster in enumerate(self.clusterResults[zooniverse_id][2]):
# moving on to the next animal so increase counter
# universal counter over all images
cluster_count += 1
# needed for determining priors for IBCC
pos = 0
neg = 0
# note that the cluster with index cluster_count is from subject zooniverse_id
self.global_to_local.append((zooniverse_id,local_index))
# for this cluster, go through each user and see if they marked this cluster
# check whether or not each user marked this cluster
for user_id in users_per_subject:
# if the user was not logged in
if user_id in ips_per_subject:
# if we are considering the ip addresses of each user (i.e. those that were not logged in)
# separately for each image - assign a user index based only this image
# use negative indices to differentiate ip addresses and users
# +1 assures that we don't have 0 - which is "both" positive and negative
if split_ip_address:
user_index = -(ips_per_subject.index(user_id)+ip_offset+1)
else:
# we are treating all occurances of this ip address as being from the same user
user_index = -all_ips.index(user_id)-1
else:
# user was logged in
# todo: use bisect to increase speed
user_index = all_users.index(user_id)
# did the user mark this cluster or not?
if user_id in user_per_cluster:
to_ibcc.append((user_id,user_index,cluster_count,1))
pos += 1
else:
to_ibcc.append((user_id,user_index,cluster_count,0))
neg += 1
# if a majority of people say that there is an animal - use this for prior values
if pos > neg:
real_animals += 1
# for estimating the confusion matrix
true_pos.append(pos/float(pos+neg))
else:
fake_animals += 1
true_neg.append(neg/float(pos+neg))
ip_offset += len(ips_per_subject)
# now run through again - this will make sure that all of the indices are ordered with no gaps
# since the user list is created by reading through all the users, even those which haven't annotated
# of the specific images we are currently looking at
ibcc_user_list = []
# this is also for other functions to be able to interpret the results
self.ibcc_users = []
for user,user_index,animal_index,found in to_ibcc:
# can't use bisect or the indices will be out of order
if not(user_index in ibcc_user_list):
ibcc_user_list.append(user_index)
self.ibcc_users.append(user)
# write out the input file for IBCC
with open(self.base_directory+"/Databases/"+self.alg+"_ibcc.csv","wb") as f:
f.write("a,b,c\n")
for marking_count,(user,user_index,animal_index,found) in enumerate(to_ibcc):
if marking_count == 200:
break
i = ibcc_user_list.index(user_index)
f.write(str(i)+","+str(animal_index)+","+str(found)+"\n")
# create the prior estimate and the default confusion matrix
prior = real_animals/float(real_animals + fake_animals)
t = np.mean(true_pos)
f = np.mean(true_neg)
# what the weight should be
# todo: should this be hard coded or set as a param?
weight = 10
# the confusion matrix cannot have any zero values
confusion = [[max(int(t*weight),1),max(int((1-t)*weight),1)],[max(int((1-f)*weight),1),max(int(f*weight),1)]]
# create the config file
with open(self.base_directory+"/Databases/"+self.alg+"_ibcc.py","wb") as f:
f.write("import numpy as np\n")
f.write("scores = np.array([0,1])\n")
f.write("nScores = len(scores)\n")
f.write("nClasses = 2\n")
f.write("inputFile = \""+self.base_directory+"/Databases/"+self.alg+"_ibcc.csv\"\n")
f.write("outputFile = \""+self.base_directory+"/Databases/"+self.alg+"_signal.out\"\n")
f.write("confMatFile = \""+self.base_directory+"/Databases/"+self.alg+"_ibcc.mat\"\n")
f.write("nu0 = np.array(["+str(max(int((1-prior)*100),1))+","+str(max(int(prior*100),1))+"])\n")
f.write("alpha0 = np.array("+str(confusion)+")\n")
# start by removing all temp files
try:
os.remove(self.base_directory+"/Databases/"+self.alg+"_signal.out")
except OSError:
pass
try:
os.remove(self.base_directory+"/Databases/"+self.alg+"_ibcc.mat")
except OSError:
pass
try:
os.remove(self.base_directory+"/Databases/"+self.alg+"_ibcc.csv.dat")
except OSError:
pass
# pickle.dump((big_subjectList,big_userList),open(base_directory+"/Databases/tempOut.pickle","wb"))
ibcc.runIbcc(self.base_directory+"/Databases/"+self.alg+"_ibcc.py")
def __signal_ibcc_gold__(self,global_indices,gold_standard_pts,split_ip_address=True):
"""
uses gold standard from experts instead of priors based on majority voting
:param global_indices:
:param split_ip_address:
:param gold_standard_pts: the list of global indices for which we are going to provide gold standard data
using a negative index is a way of giving a false positive
:return:
"""
# intermediate holder variable
# because ibcc needs indices to be nice and ordered with no gaps, we have to make two passes through the data
to_ibcc = []
# there will be some redundancy reading in the subject list - so keep track of the current subject_id
# and only update when necessary
users_per_subject = None
ips_per_subject = None
current_subject = None
# we may skip over some indices if they correspond to gold standard points which no one marked and
# are not being used as provided gold standard data
actually_used_clusters = []
for global_cluster_index,(subject_id,local_index) in enumerate(global_indices):
# only update when necessary - when we have moved on to a new subject
if subject_id != current_subject:
# get the list of all the users who viewed this subject
# and the ip addresses of every user who was not logged in while viewing the subjects
users_per_subject = self.project_api.__users__(subject_id)
# ips_per_subject = self.project_api.__ips__(subject_id)
current_subject = subject_id
if local_index is None:
# in this case, we know that no user marked this animal
# this is either provided gold standard data, or a test - in which case we should ignore
# this data
if not(global_cluster_index in gold_standard_pts):
continue
else:
user_per_cluster = []
else:
user_per_cluster = self.clusterResults[subject_id][2][local_index]
actually_used_clusters.append(global_cluster_index)
for user_id in list(users_per_subject):
# check to see if this user was logged in - if not, the user_id should be an ip address
# if not logged in, we just need to decide whether to add the subject_name on to the user_id
# which as a result treats the same ip address for different subjects as completely different
# users
try:
socket.inet_aton(user_id)
if split_ip_address:
user_id += subject_id
except (socket.error,UnicodeEncodeError) as e:
# logged in user, nothing to do
pass
if user_id in user_per_cluster:
to_ibcc.append((user_id,global_cluster_index,1))
else:
to_ibcc.append((user_id,global_cluster_index,0))
# gives each user an index with no gaps in the list
user_indices = []
# write out the input file for IBCC
with open(self.base_directory+"/Databases/"+self.alg+"_ibcc.csv","wb") as f:
f.write("a,b,c\n")
for user,cluster_index,found in to_ibcc:
if not(user in user_indices):
user_indices.append(user)
i = user_indices.index(user)
j = actually_used_clusters.index(cluster_index)
f.write(str(i)+","+str(j)+","+str(found)+"\n")
#return user_indices,actually_used_clusters
# write out the input file for IBCC
# create the config file
with open(self.base_directory+"/Databases/"+self.alg+"_ibcc.py","wb") as f:
f.write("import numpy as np\n")
f.write("scores = np.array([0,1])\n")
f.write("nScores = len(scores)\n")
f.write("nClasses = 2\n")
f.write("inputFile = \""+self.base_directory+"/Databases/"+self.alg+"_ibcc.csv\"\n")
f.write("outputFile = \""+self.base_directory+"/Databases/"+self.alg+"_signal.out\"\n")
f.write("confMatFile = \""+self.base_directory+"/Databases/"+self.alg+"_ibcc.mat\"\n")
f.write("goldFile= \""+self.base_directory+"/Databases/"+self.alg+"_gold.csv\"\n")
# start by removing all temp files
try:
os.remove(self.base_directory+"/Databases/"+self.alg+"_signal.out")
except OSError:
pass
try:
os.remove(self.base_directory+"/Databases/"+self.alg+"_ibcc.mat")
except OSError:
pass
try:
os.remove(self.base_directory+"/Databases/"+self.alg+"_ibcc.csv.dat")
except OSError:
pass
# pickle.dump((big_subjectList,big_userList),open(base_directory+"/Databases/tempOut.pickle","wb"))
ibcc.runIbcc(self.base_directory+"/Databases/"+self.alg+"_ibcc.py")
return self.base_directory+"/Databases/"+self.alg+"_signal.out", user_indices,actually_used_clusters
os.remove(base_directory+"/Databases/condor_ibcc.out")
except OSError:
pass
try:
os.remove(base_directory+"/Databases/condor_ibcc.mat")
except OSError:
pass
try:
os.remove(base_directory+"/Databases/condor_ibcc.csv.dat")
except OSError:
pass
#pickle.dump((big_subjectList,big_userList),open(base_directory+"/Databases/tempOut.pickle","wb"))
ibcc.runIbcc(base_directory+"/Databases/condor_ibcc.py")
ibcc_v = []
with open(base_directory+"/Databases/condor_ibcc.out","rb") as f:
ibcc_results = csv.reader(f, delimiter=' ')
for row in ibcc_results:
ibcc_v.append(float(row[2]))
with open(base_directory+"/Databases/condor_ibcc.mat","rb") as f:
ibcc_results = csv.reader(f, delimiter=' ')
for row in ibcc_results:
ibcc_v.append(float(row[2]))
for ii,zooniverse_id in enumerate(results_dict):
print zooniverse_id
pass
try:
os.remove(data_directory+"/galaxy_zoo_ibcc.mat")
except OSError:
pass
try:
os.remove(data_directory+"/galaxy_zoo_ibcc.csv.dat")
except OSError:
pass
import datetime
print datetime.datetime.time(datetime.datetime.now())
print base_directory+"/Databases/galaxy_zoo_ibcc.py"
ibcc.runIbcc(data_directory+"/galaxy_zoo_ibcc.py")
print datetime.datetime.time(datetime.datetime.now())
#read in gold standard data
pos0 = []
pos1 = []
pos2 = []
with open(data_directory+"/candels_t01_a00_positive.dat","rb") as f:
for l in f.readlines():
pos0.append(l[:-1])
with open(data_directory+"/candels_t01_a01_positive.dat","rb") as f:
for l in f.readlines():
pos1.append(l[:-1])
with open(data_directory+"/candels_t01_a02_positive.dat","rb") as f:
for l in f.readlines():
pos2.append(l[:-1])
f.write(str(user_index)+","+str(subject_index)+","+str(ann)+"\n")
print "number of users " + str(len(user_ids))
print "number of gold labels " + str(len(list(gold_set)))
with open(baseDir+"Databases/supernova_ibcc.py",'wb') as f:
f.write("import numpy as np\nscores = np.array([0,1])\n")
f.write("nScores = len(scores)\n")
f.write("nClasses =2\n")
f.write("inputFile = '"+baseDir+"Databases/supernova_ibcc.csv'\n")
f.write("outputFile = '"+baseDir+"Databases/supernova_ibcc.out'\n")
f.write("confMatFile = '"+baseDir+"Databases/supernova_ibcc.mat'\n")
f.write("goldFile = '"+baseDir+"Databases/supernova_ibcc_gold.csv'\n")
os.remove(baseDir+"Databases/supernova_ibcc.csv.dat")
ibcc.runIbcc(baseDir+"Databases/supernova_ibcc.py")
print "done IBCC"
x_values = []
y_values = []
with open(baseDir+"Databases/supernova_ibcc.mat","rb") as f:
reader = csv.reader(f,delimiter=" ")
for user_index,r in enumerate(reader):
count = classification_counts[user_index]
if min(count) < 5:
continue
x = float(r[0])
y = float(r[-1])
x_values.append(x)
try:
os.remove(base_directory+"/Databases/penguins_ibcc.out")
except OSError:
pass
try:
os.remove(base_directory+"/Databases/penguins_ibcc.mat")
except OSError:
pass
try:
os.remove(base_directory+"/Databases/penguins_ibcc.in.dat")
except OSError:
pass
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
f.write("import numpy as np\n")
f.write("scores = np.array([0,1,2])\n")
f.write("nScores = len(scores)\n")
f.write("nClasses = 3\n")
f.write("inputFile = \"/home/greg/Databases/galaxy_zoo_ibcc.csv\"\n")
f.write("outputFile = \"/home/greg/Databases/galaxy_zoo_ibcc.out\"\n")
f.write("confMatFile = \"/home/greg/Databases/galaxy_zoo_ibcc.mat\"\n")
f.write("nu0 = np.array([40,40,10])\n")
f.write("alpha0 = np.array([[5, 2, 2], [2, 5, 2], [3, 3, 3]])\n")
try:
os.remove("/home/greg/Databases/galaxy_zoo_ibcc.out")
except OSError:
pass
try:
os.remove("/home/greg/Databases/galaxy_zoo_ibcc.mat")
except OSError:
pass
try:
os.remove("/home/greg/Databases/galaxy_zoo_ibcc.csv.dat")
except OSError:
pass
import datetime
print datetime.datetime.time(datetime.datetime.now())
ibcc.runIbcc("/home/greg/Databases/galaxy_zoo_ibcc.py")
print datetime.datetime.time(datetime.datetime.now())
def __ibcc__(results_dict,users_per_subject):
# create a global index of all users
global_users = []
for u_list in users_per_subject.values():
for u in u_list:
if not(u in global_users):
global_users.append(u)
things_in_subject = {}
things_list = []
thing_index = 0
off_by_one_clusters = []
for zooinverse_id in results_dict:
things_in_subject[zooinverse_id] = []
centers,clusters,users = results_dict[zooinverse_id]
pairs = __find_closest__(centers,clusters,users,user_threshold=1,offset=thing_index)
off_by_one_clusters.extend(list(pairs))
for users_per_marking in users:
things_in_subject[zooinverse_id].append(thing_index)
# find out who saw or did not see this "thing" - out of everyone who viewed this subject
t = []
for u in users_per_subject[zooinverse_id]:
if u in users_per_marking:
t.append((global_users.index(u),1))
else:
t.append((global_users.index(u),0))
things_list.append(t[:])
thing_index += 1
# run ibcc with out combining any of the clusters
with open(base_directory+"/Databases/base_ibcc.csv","wb") as f:
f.write("a,b,c\n")
for thing_index in range(len(things_list)):
for user_index, marked in things_list[thing_index]:
f.write(str(user_index)+","+str(thing_index)+","+str(marked)+"\n")
__ibcc_init__("base")
ibcc.runIbcc(base_directory+"/Databases/base_ibcc.py")
# now try merging each possible pair and running ibcc on the resulting set up
# yes, this is going to be tedious and time consuming - hope for a better implementation later on
for count,(c1,c2,overlap) in enumerate(off_by_one_clusters):
# most of the time, thing_index and thing_prime_index will be the same
# but can be an off by one indifference to account for that fact that we are skipping over c2
thing_prime_index = 0
print (c1,c2)
with open(base_directory+"/Databases/merged_ibcc.csv","wb") as f:
f.write("a,b,c\n")
for thing_index in range(len(things_list)):
#print (thing_index,thing_prime_index)
if thing_index == c2:
# we skipping this one
#print "skip"
pass
else:
if thing_index == c1:
# merge
assert thing_index == thing_prime_index
assert len(list(overlap)) <= 1
#print zip(*things_list[c1])[0]
#print zip(*things_list[c1])[1]
#print zip(*things_list[c2])[1]
for (user_index1,marked1),(user_index2,marked2) in zip(things_list[c1],things_list[c2]):
assert user_index1 == user_index2
f.write(str(user_index1)+","+str(thing_prime_index)+","+str(marked1 or marked2)+"\n")
else:
# proceed as normal
# continue
for user_index, marked in things_list[thing_index]:
f.write(str(user_index)+","+str(thing_prime_index)+","+str(marked)+"\n")
thing_prime_index += 1
#print thing_index
#print thing_prime_index
#assert thing_prime_index == (thing_index-1)
__ibcc_init__("merged")
ibcc.runIbcc(base_directory+"/Databases/merged_ibcc.py")
p1 = load_ibcc_probabilities("base",c1)
p2 = load_ibcc_probabilities("base",c2)
p3 = load_ibcc_probabilities("merged",c1)
print (p1,p2,p3)
if p3 < (max(p1,p2)-0.01):
break
def __runIBCC__(self):
collection = self.db['merged_classifications'+str(self.cutoff)]
self.user_list = []
self.subject_list = []
shutil.rmtree(self.baseDir+"ibcc")
os.makedirs(self.baseDir+"ibcc")
counter = -1
for speciesGroup in self.species_groups:
self.user_list = []
self.subject_list = []
count = []
required_l = list(powerset(speciesGroup))
prohibited_l = [[s for s in speciesGroup if not(s in r)] for r in required_l]
counter += 1
self.__createConfigFile(counter,len(required_l))
ibcc_input_file = open(self.baseDir+"ibcc/"+str(counter)+".in","wb")
for document in collection.find():
user_name = document["user_name"]
subject_zooniverse_id = document["subject_zooniverse_id"]
user_species_list = document["species_list"]
if not(subject_zooniverse_id in self.nonempty_list):
continue
#IBCC requires an int ID for both user and subject - so convert
if user_name in self.user_list:
userID = self.user_list.index(user_name)
count[userID] += 1
else:
self.user_list.append(user_name)
userID = len(self.user_list)-1
count.append(1)
if subject_zooniverse_id in self.subject_list:
subjectID = self.subject_list.index(subject_zooniverse_id)
else:
self.subject_list.append(subject_zooniverse_id)
subjectID = len(self.subject_list)-1
#which class does this classification count as?
meet_required = [sorted(list(set(user_species_list).intersection(r))) == sorted(list(r)) for r in required_l]
meet_prohibited = [tuple(set(user_species_list).intersection(p)) == () for p in prohibited_l]
meet_overall = [r and p for (r, p) in zip(meet_required, meet_prohibited)]
assert(sum([1. for o in meet_overall if o]) == 1)
class_id = meet_overall.index(True)
print(str(userID) + "," + str(subjectID) + "," + str(class_id), file=ibcc_input_file)
ibcc_input_file.close()
#now run IBCC
ibcc.runIbcc(self.baseDir+"ibcc/"+str(counter)+"config.py")
print(count)
classifications.append((user_index, subject_index, blank))
print "====----"
print errorCount
try:
os.remove("/home/greg/Databases/condor_ibcc.out")
except OSError:
pass
try:
os.remove("/home/greg/Databases/condor_ibcc.mat")
except OSError:
pass
try:
os.remove("/home/greg/Databases/condor_ibcc.csv.dat")
except OSError:
pass
with open("/home/greg/Databases/condor_ibcc.csv", "wb") as f:
f.write("a,b,c\n")
for u, s, b in classifications:
f.write(str(u) + "," + str(s) + "," + str(b) + "\n")
print datetime.datetime.time(datetime.datetime.now())
ibcc.runIbcc("/home/greg/Databases/condor_ibcc.py")
print datetime.datetime.time(datetime.datetime.now())
pickle.dump(subjects, open("/home/greg/Databases/condor_ibcc.pickle", "wb"))
else:
userIndex = users.index(userName)
if not(photoName in photos):
photos.append(photoName)
photoIndex = len(photos)- 1
else:
photoIndex = photos.index(photoName)
if i in classification:
print(str(userIndex)+","+str(photoIndex)+",1", file=f)
else:
print(str(userIndex)+","+str(photoIndex)+",0", file=f)
f.close()
ibcc.runIbcc(baseDir+"ibcc/"+str(i)+"config.py")
#merge the results into the existing ones
#assume all photos are now in the list - should be
reader = csv.reader(open(baseDir+"ibcc/"+str(i)+".out","rU"), delimiter=" ")
for photoIndex, neg, pos in reader:
photoIndex = int(float(photoIndex))
pos = float(pos)
if len(ibccClassifications) < (photoIndex+1):
ibccClassifications.append([])
if pos > 0.5:
#print(photoIndex,len(ibccClassifications))
ibccClassifications[photoIndex].append(s)
try:
os.remove(base_directory + "/Databases/penguins_ibcc.out")
except OSError:
pass
try:
os.remove(base_directory + "/Databases/penguins_ibcc.mat")
except OSError:
pass
try:
os.remove(base_directory + "/Databases/penguins_ibcc.in.dat")
except OSError:
pass
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, [
else:
userIndex = users.index(userName)
if not (photoName in photos):
photos.append(photoName)
photoIndex = len(photos) - 1
else:
photoIndex = photos.index(photoName)
if i in classification:
print(str(userIndex) + "," + str(photoIndex) + ",1", file=f)
else:
print(str(userIndex) + "," + str(photoIndex) + ",0", file=f)
f.close()
ibcc.runIbcc(baseDir + "ibcc/" + str(i) + "config.py")
#merge the results into the existing ones
#assume all photos are now in the list - should be
reader = csv.reader(open(baseDir + "ibcc/" + str(i) + ".out", "rU"),
delimiter=" ")
for photoIndex, neg, pos in reader:
photoIndex = int(float(photoIndex))
pos = float(pos)
if len(ibccClassifications) < (photoIndex + 1):
ibccClassifications.append([])
if pos > 0.5:
#print(photoIndex,len(ibccClassifications))
ibccClassifications[photoIndex].append(s)
with open("/home/greg/Databases/galaxy_zoo_ibcc.py", "wb") as f:
f.write("import numpy as np\n")
f.write("scores = np.array([0,1,2])\n")
f.write("nScores = len(scores)\n")
f.write("nClasses = 3\n")
f.write("inputFile = \"/home/greg/Databases/galaxy_zoo_ibcc.csv\"\n")
f.write("outputFile = \"/home/greg/Databases/galaxy_zoo_ibcc.out\"\n")
f.write("confMatFile = \"/home/greg/Databases/galaxy_zoo_ibcc.mat\"\n")
f.write("nu0 = np.array([40,40,10])\n")
f.write("alpha0 = np.array([[5, 2, 2], [2, 5, 2], [3, 3, 3]])\n")
try:
os.remove("/home/greg/Databases/galaxy_zoo_ibcc.out")
except OSError:
pass
try:
os.remove("/home/greg/Databases/galaxy_zoo_ibcc.mat")
except OSError:
pass
try:
os.remove("/home/greg/Databases/galaxy_zoo_ibcc.csv.dat")
except OSError:
pass
import datetime
print datetime.datetime.time(datetime.datetime.now())
ibcc.runIbcc("/home/greg/Databases/galaxy_zoo_ibcc.py")
print datetime.datetime.time(datetime.datetime.now())
os.remove(base_directory + "/Databases/condor_ibcc.out")
except OSError:
pass
try:
os.remove(base_directory + "/Databases/condor_ibcc.mat")
except OSError:
pass
try:
os.remove(base_directory + "/Databases/condor_ibcc.csv.dat")
except OSError:
pass
# pickle.dump((big_subjectList,big_userList),open(base_directory+"/Databases/tempOut.pickle","wb"))
ibcc.runIbcc(base_directory + "/Databases/condor_ibcc.py")
# now analyze the data
# assume for starters that each image does not have a condor
X = []
Y = []
X_2 = []
Y_2 = []
contains_condor = {zooniverse_id: False for zooniverse_id in zooniverse_list}
condor_probabilities = {zooniverse_id: [] for zooniverse_id in zooniverse_list}
with open(base_directory + "/Databases/condor_ibcc.out", "rb") as f:
ibcc_results = csv.reader(f, delimiter=" ")
for row in ibcc_results:
animal_index = int(float(row[0]))
condor_p = float(row[2])
print "====----"
print errorCount
try:
os.remove("/home/greg/Databases/condor_ibcc.out")
except OSError:
pass
try:
os.remove("/home/greg/Databases/condor_ibcc.mat")
except OSError:
pass
try:
os.remove("/home/greg/Databases/condor_ibcc.csv.dat")
except OSError:
pass
with open("/home/greg/Databases/condor_ibcc.csv", "wb") as f:
f.write("a,b,c\n")
for u, s, b in classifications:
f.write(str(u) + "," + str(s) + "," + str(b) + "\n")
print datetime.datetime.time(datetime.datetime.now())
ibcc.runIbcc("/home/greg/Databases/condor_ibcc.py")
print datetime.datetime.time(datetime.datetime.now())
pickle.dump(subjects, open("/home/greg/Databases/condor_ibcc.pickle", "wb"))