def create_best_segment_image(list_file, segment_dir, corpus_meta, prob_topic_doc, n_topic, n_segment, output_dir):
for name_file in list_file:
print name_file
buff_segment = []
ind_segment = [int(item_corpus[0]) for item_corpus in corpus_meta if name_file == item_corpus[1].split('-')[0]]
val_segment = [(ind, prob_topic_doc[ind][topic]) for ind in ind_segment for topic in range(n_topic)]
val_segment = sorted(val_segment,key=itemgetter(1), reverse=True)
bag_of_best_segment = val_segment[0:n_segment]
fig = plt.figure()
index_plt = 1
for index, prob in bag_of_best_segment:
print 'jogie'
img = img_as_float(io.imread(img_dir+name_file+'.ppm'))
n_col = len(img[0])
list_of_segment = csvToListOfSegment(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
no_segment = int(corpus_meta[index][2])
buff_segment.append([row*n_col+col for row, col in list_of_segment[no_segment]])
segments_res = csv2Array(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
img[segments_res != no_segment] = (0.0,0.0,0.9)
ax1 = fig.add_subplot(6,5, index_plt, axisbg='grey')
ax1.set_xticks(()), ax1.set_yticks(())
ax1.imshow(img)
index_plt += 1
plt.savefig('coba/'+name_file)
plt.clf()
plt.close()
def create_best_segment_image(list_file, segment_dir, corpus_meta, prob_topic_doc, n_topic, n_segment, output_dir):
for name_file in list_file:
print name_file
buff_segment = []
ind_segment = [int(item_corpus[0]) for item_corpus in corpus_meta if name_file == item_corpus[1].split('-')[0]]
val_segment = [(ind, prob_topic_doc[ind][topic]) for ind in ind_segment for topic in range(n_topic)]
val_segment = sorted(val_segment,key=itemgetter(1), reverse=True)
bag_of_best_segment = val_segment[0:n_segment]
fig = plt.figure()
index_plt = 1
for index, prob in bag_of_best_segment:
print 'jogie'
img = img_as_float(io.imread(img_dir+name_file+'.ppm'))
n_col = len(img[0])
list_of_segment = csvToListOfSegment(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
no_segment = int(corpus_meta[index][2])
buff_segment.append([row*n_col+col for row, col in list_of_segment[no_segment]])
segments_res = csv2Array(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
img[segments_res != no_segment] = (0.0,0.0,0.9)
ax1 = fig.add_subplot(6,5, index_plt, axisbg='grey')
ax1.set_xticks(()), ax1.set_yticks(())
ax1.imshow(img)
index_plt += 1
plt.savefig('coba/'+name_file)
plt.clf()
plt.close()
def generate_map_segment(name_file, param):
global cache_list_segment
map_segment_init = {}
map_segment_for_GA = {}
segment_in_image = [
int(item_corpus[0]) for item_corpus in param['corpus_meta']
if name_file == item_corpus[1].split('-')[0]
]
cache = ('key', 'list_of_segment') #remember 1 before
for i in range(len(segment_in_image)):
index = segment_in_image[i]
n_col = len(
img_as_float(io.imread(param['img_dir'] + name_file + '.ppm'))[0])
if param['corpus_meta'][index][1] == cache[0]:
list_of_segment = cache[1]
else:
list_of_segment = csvToListOfSegment(
param['segment_dir'] + '/' + name_file + '/' +
param['corpus_meta'][index][1])
cache = (param['corpus_meta'][index][1], list_of_segment)
no_segment = int(param['corpus_meta'][index][2])
pixel_in_segment = [
row * n_col + col for row, col in list_of_segment[no_segment]
]
max_prob_topic = max(
[prob_topic for prob_topic in param['prob_topic_doc'][index]])
if len(pixel_in_segment) >= 1000:
map_segment_init[index] = (max_prob_topic, pixel_in_segment)
map_segment_for_GA[name_file] = map_segment_init
return map_segment_for_GA
def create_segmentfile_from_binary_string(name_file, segment_dir, corpus_meta, output_dir, img_dir, ind_segment):
buff_segment = []
for index in ind_segment:
img = img_as_float(io.imread(img_dir+name_file+'.ppm'))
n_col = len(img[0])
segments_res = csv2Array(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
list_of_segment = csvToListOfSegment(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
no_segment = int(corpus_meta[index][2])
img[segments_res != no_segment] = (0.0,0.0,0.9)
buff_segment.append([row*n_col+col for row, col in list_of_segment[no_segment]])
ensure_path(output_dir+'/image/'+name_file+'/')
io.imsave(output_dir+'/image/'+name_file+'/'+str(index)+'.png', img)
writeCsv(buff_segment, output_dir+'/'+name_file+'.sup')
def create_segmentfile_from_binary_string(name_file, segment_dir, corpus_meta, output_dir, img_dir, ind_segment):
buff_segment = []
for index in ind_segment:
img = img_as_float(io.imread(img_dir+name_file+'.ppm'))
n_col = len(img[0])
segments_res = csv2Array(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
list_of_segment = csvToListOfSegment(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
no_segment = int(corpus_meta[index][2])
img[segments_res != no_segment] = (0.0,0.0,0.9)
buff_segment.append([row*n_col+col for row, col in list_of_segment[no_segment]])
ensure_path(output_dir+'/image/'+name_file+'/')
io.imsave(output_dir+'/image/'+name_file+'/'+str(index)+'.png', img)
writeCsv(buff_segment, output_dir+'/'+name_file+'.sup')
def create_best_n_segment_image(name_file, segment_dir, corpus_meta, prob_topic_doc, n_topic, n_segment, output_dir, img_dir):
buff_segment = []
ind_segment = [int(item_corpus[0]) for item_corpus in corpus_meta if name_file == item_corpus[1].split('-')[0]]
val_segment = [(ind, prob_topic_doc[ind][topic]) for ind in ind_segment for topic in range(n_topic)]
val_segment = sorted(val_segment,key=itemgetter(1), reverse=True)
bag_of_best_segment = val_segment[0:n_segment]
for index, prob in bag_of_best_segment:
img = img_as_float(io.imread(img_dir+name_file+'.ppm'))
n_col = len(img[0])
list_of_segment = csvToListOfSegment(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
no_segment = int(corpus_meta[index][2])
buff_segment.append([row*n_col+col for row, col in list_of_segment[no_segment]])
writeCsv(buff_segment, output_dir+'/'+name_file+'.sup')
def create_best_n_segment_image(name_file, segment_dir, corpus_meta, prob_topic_doc, n_topic, n_segment, output_dir, img_dir):
buff_segment = []
ind_segment = [int(item_corpus[0]) for item_corpus in corpus_meta if name_file == item_corpus[1].split('-')[0]]
val_segment = [(ind, prob_topic_doc[ind][topic]) for ind in ind_segment for topic in range(n_topic)]
val_segment = sorted(val_segment,key=itemgetter(1), reverse=True)
bag_of_best_segment = val_segment[0:n_segment]
for index, prob in bag_of_best_segment:
img = img_as_float(io.imread(img_dir+name_file+'.ppm'))
n_col = len(img[0])
list_of_segment = csvToListOfSegment(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
no_segment = int(corpus_meta[index][2])
buff_segment.append([row*n_col+col for row, col in list_of_segment[no_segment]])
writeCsv(buff_segment, output_dir+'/'+name_file+'.sup')
def generate_map_segment(name_file, param):
global cache_list_segment
map_segment_init = {}
map_segment_for_GA = {}
segment_in_image = [int(item_corpus[0]) for item_corpus in param['corpus_meta'] if name_file == item_corpus[1].split('-')[0]]
cache = ('key','list_of_segment') #remember 1 before
for i in range(len(segment_in_image)):
index = segment_in_image[i]
n_col = len(img_as_float(io.imread(param['img_dir']+name_file+'.ppm'))[0])
if param['corpus_meta'][index][1] == cache[0]:
list_of_segment = cache[1]
else:
list_of_segment = csvToListOfSegment(param['segment_dir']+'/'+name_file+'/'+ param['corpus_meta'][index][1])
cache = (param['corpus_meta'][index][1], list_of_segment)
no_segment = int(param['corpus_meta'][index][2])
pixel_in_segment = [row*n_col+col for row, col in list_of_segment[no_segment]]
max_prob_topic = max([prob_topic for prob_topic in param['prob_topic_doc'][index]])
if len(pixel_in_segment) >= 1000:
map_segment_init[index] = (max_prob_topic, pixel_in_segment)
map_segment_for_GA[name_file] = map_segment_init
return map_segment_for_GA
def sort_segment_cross_topic(name_file, segment_dir, corpus_meta, prob_topic_doc, n_topic, n_segment, output_dir, img_dir):
buff_segment = []
ind_segment = [int(item_corpus[0]) for item_corpus in corpus_meta if name_file == item_corpus[1].split('-')[0]]
val_per_topic = []
for topic in range(n_topic):
val = [(ind, prob_topic_doc[ind][topic]) for ind in ind_segment]
sort_val = sorted(val, key=itemgetter(1), reverse=True)
val_per_topic.append(sort_val)
sort_val_per_topic = sorted(val_per_topic, key=lambda x: x[0][1], reverse=True)
candidate_segment = []
for i in range(4):
candidate_segment += sort_val_per_topic[i]
candidate_segment = sorted(candidate_segment,key=itemgetter(1), reverse=True)
bag_of_best_segment = candidate_segment[0:n_segment]
for index, prob in bag_of_best_segment:
img = img_as_float(io.imread(img_dir+name_file+'.ppm'))
n_col = len(img[0])
list_of_segment = csvToListOfSegment(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
no_segment = int(corpus_meta[index][2])
buff_segment.append([row*n_col+col for row, col in list_of_segment[no_segment]])
writeCsv(buff_segment, output_dir+'/'+name_file+'.sup')
def sort_segment_based_topic(name_file, segment_dir, corpus_meta, prob_topic_doc, n_topic, n_segment, output_dir, img_dir):
buff_segment = []
ind_segment = [int(item_corpus[0]) for item_corpus in corpus_meta if name_file == item_corpus[1].split('-')[0]]
val_per_topic = []
for topic in range(n_topic):
val = [(ind, prob_topic_doc[ind][topic]) for ind in ind_segment]
sort_val = sorted(val, key=itemgetter(1), reverse=True)
val_per_topic.append(sort_val)
sort_val_per_topic = sorted(val_per_topic, key=lambda x: x[0][1], reverse=True)
first_val = [fi[0][1] for fi in sort_val_per_topic[0:4]]
quota_per_topic = [int(math.floor(fi/sum(first_val) * n_segment)) for fi in first_val]
print quota_per_topic
bag_of_best_segment = [sort_val_per_topic[ind][0:quota] for quota, ind in zip(quota_per_topic, range(len(quota_per_topic)))]
for row in bag_of_best_segment:
for index, prob in row:
img = img_as_float(io.imread(img_dir+name_file+'.ppm'))
n_col = len(img[0])
list_of_segment = csvToListOfSegment(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
no_segment = int(corpus_meta[index][2])
buff_segment.append([row*n_col+col for row, col in list_of_segment[no_segment]])
writeCsv(buff_segment, output_dir+'/'+name_file+'.sup')
def sort_segment_cross_topic(name_file, segment_dir, corpus_meta, prob_topic_doc, n_topic, n_segment, output_dir, img_dir):
buff_segment = []
ind_segment = [int(item_corpus[0]) for item_corpus in corpus_meta if name_file == item_corpus[1].split('-')[0]]
val_per_topic = []
for topic in range(n_topic):
val = [(ind, prob_topic_doc[ind][topic]) for ind in ind_segment]
sort_val = sorted(val, key=itemgetter(1), reverse=True)
val_per_topic.append(sort_val)
sort_val_per_topic = sorted(val_per_topic, key=lambda x: x[0][1], reverse=True)
candidate_segment = []
for i in range(4):
candidate_segment += sort_val_per_topic[i]
candidate_segment = sorted(candidate_segment,key=itemgetter(1), reverse=True)
bag_of_best_segment = candidate_segment[0:n_segment]
for index, prob in bag_of_best_segment:
img = img_as_float(io.imread(img_dir+name_file+'.ppm'))
n_col = len(img[0])
list_of_segment = csvToListOfSegment(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
no_segment = int(corpus_meta[index][2])
buff_segment.append([row*n_col+col for row, col in list_of_segment[no_segment]])
writeCsv(buff_segment, output_dir+'/'+name_file+'.sup')
def sort_segment_based_topic(name_file, segment_dir, corpus_meta, prob_topic_doc, n_topic, n_segment, output_dir, img_dir):
buff_segment = []
ind_segment = [int(item_corpus[0]) for item_corpus in corpus_meta if name_file == item_corpus[1].split('-')[0]]
val_per_topic = []
for topic in range(n_topic):
val = [(ind, prob_topic_doc[ind][topic]) for ind in ind_segment]
sort_val = sorted(val, key=itemgetter(1), reverse=True)
val_per_topic.append(sort_val)
sort_val_per_topic = sorted(val_per_topic, key=lambda x: x[0][1], reverse=True)
first_val = [fi[0][1] for fi in sort_val_per_topic[0:4]]
quota_per_topic = [int(math.floor(fi/sum(first_val) * n_segment)) for fi in first_val]
print quota_per_topic
bag_of_best_segment = [sort_val_per_topic[ind][0:quota] for quota, ind in zip(quota_per_topic, range(len(quota_per_topic)))]
for row in bag_of_best_segment:
for index, prob in row:
img = img_as_float(io.imread(img_dir+name_file+'.ppm'))
n_col = len(img[0])
list_of_segment = csvToListOfSegment(segment_dir+'/'+name_file+'/'+ corpus_meta[index][1])
no_segment = int(corpus_meta[index][2])
buff_segment.append([row*n_col+col for row, col in list_of_segment[no_segment]])
writeCsv(buff_segment, output_dir+'/'+name_file+'.sup')