def main():
global POPULATION_COUNT, ITERATIONS, MAX_FUNC_DEPTH
file = open('data.txt', 'w')
if len(sys.argv) == 3: ITERATIONS = int(sys.argv[1])
if len(sys.argv) == 3: POPULATION_COUNT = int(sys.argv[2])
f, data = create_test_data()
write_init_data(file, f, data)
population = create_population(POPULATION_COUNT, MAX_FUNC_DEPTH)
normalizator = Normalizator(data, mistake)
functions = FunctoionContainer(choose_parent_pairs2, choose_to_kill,
create_children)
options = Options(0.4)
mutator = Mutator(population, normalizator, options, functions)
print 'population: '
#for s in population: print 'm: ', mistake(s.f, data), '\t\ts.f: ', s.f
for i in range(ITERATIONS):
print 'population ' + str(i) + ' : '
for j in range(5):
s = population[(j + 1) * (-1)]
print 'm: ', mistake(s.f, data), '\t\ts.f: ', s.f
if j == 1: # ITERATION_NUMBER:MISTAKE:FUNCTION
write_population_data(file, i, s, mistake(s.f, data))
mutator.make_children()
mutator.kill_unused()
# mutator.change_random()
mutator.change_age()
mutator.mutate()
normalizator.compute_distribuante(population)
population.sort()
file.close()
def main():
global POPULATION_COUNT, ITERATIONS, MAX_FUNC_DEPTH
file = open('data.txt', 'w')
if len(sys.argv) == 3: ITERATIONS = int(sys.argv[1])
if len(sys.argv) == 3: POPULATION_COUNT = int(sys.argv[2])
f, data = create_test_data()
write_init_data(file, f, data)
population = create_population(POPULATION_COUNT, MAX_FUNC_DEPTH)
normalizator = Normalizator(data, mistake)
functions = FunctoionContainer(choose_parent_pairs2, choose_to_kill, create_children)
options = Options(0.4)
mutator = Mutator(population, normalizator, options, functions)
print 'population: '
#for s in population: print 'm: ', mistake(s.f, data), '\t\ts.f: ', s.f
for i in range(ITERATIONS):
print 'population ' + str(i) + ' : '
for j in range(5):
s = population[(j+1)*(-1)]
print 'm: ', mistake(s.f, data), '\t\ts.f: ', s.f
if j == 1: # ITERATION_NUMBER:MISTAKE:FUNCTION
write_population_data(file, i, s, mistake(s.f, data))
mutator.make_children()
mutator.kill_unused()
# mutator.change_random()
mutator.change_age()
mutator.mutate()
normalizator.compute_distribuante(population)
population.sort()
file.close()
def saveTweetsOf(screen_name, category):
for i in range(1,4):
statuses = api.GetSearch(term=settings_local.USERTRACK, lang='es', page=i,per_page=100)
for s in statuses:
if(s.text.find('RT',0,2)==-1):
screen_name = s._user._screen_name
t = Normalizator.normalize(s.text)
em = Normalizator.usedPattern(Patterns.DUPLICATED_LETTERS)
print Normalizator.usedPattern(Patterns.SPECIALCHARS_AND_MENTIONS)
print smart_str(s.text.lower())
if (not(t.isspace())):
selected = raw_input('Es un reclamo?')
tweets = db[settings_local.CATEGORIES[int(selected)]]
tweet = {'normalized_tweet': t,
'tweet': s.text,
'screen_name': screen_name,
'emphatized': em
}
tweets.insert(tweet)
def testTweets():
for i in range(1, 8):
statuses = api.GetSearch(term=settings_local.USERTRACK, lang="es", page=i, per_page=100)
for s in statuses:
t = Normalizator.normalize(s.text)
if not (t.isspace()):
if classifier.classify(extract_features(t.split())) == "reclamo":
print "\033[91m" + t
else:
print "\033[94m" + t
import etc
from normalizator import Normalizator
normalizator = Normalizator()
candidates_attr = list(map(lambda data: {'id': data['id'], 'attributes': data['attributes'] }, etc.candidates))
candidates_attr_normalized = list()
def get_spesific_values(a_list, key):
temp = []
for d in a_list:
temp.append(d['attributes'][key])
return temp
for i in range(len(candidates_attr)):
current_salary = candidates_attr[i]['attributes']['salary']
current_gpa = candidates_attr[i]['attributes']['gpa']
current_dependant = candidates_attr[i]['attributes']['dependant']
salary_normalized = normalizator.normalize_salary(get_spesific_values(candidates_attr, 'salary'), current_salary)
gpa_normalized = normalizator.normalize_gpa(get_spesific_values(candidates_attr, 'gpa'), current_gpa)
dependant_normalized = normalizator.normalize_dependant(get_spesific_values(candidates_attr, 'dependant'), current_dependant)
candidates_attr_normalized.append([candidates_attr[i]['id'],salary_normalized, gpa_normalized, dependant_normalized])
# Create a simple weight
for s in statuses:
t = Normalizator.normalize(s.text)
if not (t.isspace()):
if classifier.classify(extract_features(t.split())) == "reclamo":
print "\033[91m" + t
else:
print "\033[94m" + t
allTweets = []
for c in settings_local.CATEGORIES:
statuses = db[c].find()
for s in statuses:
t = s["normalized_tweet"]
t = Normalizator.normalize(t)
if not (t.isspace()):
allTweets.append((t, c))
tweets = []
for (words, sentiment) in allTweets:
words_filtered = [e.lower() for e in words.split() if len(e) >= 3]
tweets.append((words_filtered, sentiment))
def get_words_in_tweets(tweets):
all_words = []
for (words, sentiment) in tweets:
all_words.extend(words)
return all_words