def singleprocess_datanum(self, test_dict):
fu = file_util.FileUtil('../AmazonDataBackup/reviewsNew/reviewsNew.mP')
fu.get_structure()
for data_num in test_dict.keys():
print data_num
content_list = fu.get_content_list()[0:data_num]
content_list_2_grams = summary_plot.get_2_grams_list(content_list)
start = time.time()
jd_list = summary_plot.get_jd_list(content_list_2_grams)
summary_plot.get_reviews_similarity_relation(jd_list)
finish_time = time.time() - start
# print 'finish get relation with %s s' % finish_time
test_dict[data_num] = finish_time
# test_dict = collections.OrderedDict(sorted(test_dict.items()))
return test_dict
def singleprocess_datanum(self, test_dict):
fu = file_util.FileUtil('../AmazonDataBackup/reviewsNew/reviewsNew.mP')
fu.get_structure()
for data_num in test_dict.keys():
print data_num
content_list = fu.get_content_list()[0:data_num]
content_list_2_grams = summary_plot.get_2_grams_list(content_list)
start = time.time()
jd_list = summary_plot.get_jd_list(content_list_2_grams)
summary_plot.get_reviews_similarity_relation(jd_list)
finish_time = time.time() - start
# print 'finish get relation with %s s' % finish_time
test_dict[data_num] = finish_time
# test_dict = collections.OrderedDict(sorted(test_dict.items()))
return test_dict
def write_jd_dict_to_file(q, l, m, name):
print 'starting process %s' % name
while True:
l.acquire()
if q.empty():
l.release()
continue
else:
filename = q.get()
if filename == 'STOP':
print 'process', name, ' exit'
l.release()
break
l.release()
with open(filename) as fp:
sub_list = ast.literal_eval(fp.read())
rs_relation_dict = summary_plot.get_reviews_similarity_relation(
sub_list)
l.acquire()
print 'process ', name, str(rs_relation_dict)
for feedback, num in rs_relation_dict.iteritems():
if feedback not in m.keys():
m[feedback] = 0
m[feedback] += num
l.release()
def draw_graph(dirname, title, xlabel, ylabel):
jd_list = []
jd_dict = {}
for (dirpath, dirnames, filenames) in walk(dirname):
for filename in filenames:
if not filename.startswith("."):
print filename
with open(dirname + "/" + filename) as fp:
sub_list = ast.literal_eval(fp.read())
rs_relation_dict = summary_plot.get_reviews_similarity_relation(sub_list)
for feedback, num in rs_relation_dict.iteritems():
if feedback not in jd_dict.keys():
jd_dict[feedback] = 0
jd_dict[feedback] += num
# jd_list += sub_list
# print len(jd_list)
print jd_dict
def draw_graph(dirname, title, xlabel, ylabel):
jd_list = []
jd_dict = {}
for (dirpath, dirnames, filenames) in walk(dirname):
for filename in filenames:
if not filename.startswith('.'):
print filename
with open(dirname + '/' + filename) as fp:
sub_list = ast.literal_eval(fp.read())
rs_relation_dict = summary_plot.get_reviews_similarity_relation(
sub_list)
for feedback, num in rs_relation_dict.iteritems():
if feedback not in jd_dict.keys():
jd_dict[feedback] = 0
jd_dict[feedback] += num
# jd_list += sub_list
# print len(jd_list)
print jd_dict
def write_jd_dict_to_file(q, l, m, name):
print "starting process %s" % name
while True:
l.acquire()
if q.empty():
l.release()
continue
else:
filename = q.get()
if filename == "STOP":
print "process", name, " exit"
l.release()
break
l.release()
with open(filename) as fp:
sub_list = ast.literal_eval(fp.read())
rs_relation_dict = summary_plot.get_reviews_similarity_relation(sub_list)
l.acquire()
print "process ", name, str(rs_relation_dict)
for feedback, num in rs_relation_dict.iteritems():
if feedback not in m.keys():
m[feedback] = 0
m[feedback] += num
l.release()
