def visualise_digits_count(self):
points = []
for el in self.db['clust_values'].find():
x = el['_id']
y = el['value']['count']
points.append({'x':x,'y':y})
visualise(points,x_title='digit',y_title='count in usernames')
def visualise_entropy(self):
#todo visualise without normal values
points = []
for el in self.clust.find({'entropy':{'$exists':True}}):
x = len(el['value'])
y = el['entropy']
points.append({'x':x,'y':y})
visualise(points,x_title='count of variable digits',y_title='entropy')
def visualise_clust(self, max):
points = []
for i in range(max):
x = i
y = self.clust.find({'value': {'$size': i}}).count()
if (y < 100):
continue
points.append({'x': x, 'y': y})
print x, y
visualise(points, header='count of names and', x_title='count of variable digits',
y_title='count of cluster names')
def big_differences():
log.info('extract messages')
users = main_db.get_not_loaded_users()
model_main = markov_chain('main', booster)
result = []
log.info('---------users to find is %s-------------------------------' % len(users))
loaded_users = []
for user in users:
log.info('load user %s' % user)
loaded_user = engine.scrap(user, neighbourhood=0)
if not loaded_user:
continue
main_db.set_user_loaded(user)
model_main = create_model(loaded_user, mc=model_main)
create_model(loaded_user)
loaded_users.append(loaded_user)
log.info('---------start process differences of models--------------')
for user in loaded_users:
model_current = markov_chain.create(user.name_, booster)
diff_element = diff_markov_chains(model_main, model_current)
result.append({'name': user.name_, 'x': diff_element['content'], 'y': user.timeline_count})
log.info('create difference... %s' % diff_element['content'])
diff_main = diff_markov_chains(model_main, model_main)
nodes, edges = model_main.get_unique_nodes_edges()
model_diffs = [
{'x': diff_main['content'], 'y': float(edges) / nodes},
]
vis.visualise(result,
header='diff and tweets count',
x_title='difference between this and main',
y_title='count tweets',
spec_symbols=model_diffs)
model_main.visualise(100)
