def main(self, args=None):
self.data = self.parser.parse_args(args=args)
assert not self.data.update_klass
logging.basicConfig(level=self.data.verbose)
logger = logging.getLogger('b4msa')
logger.setLevel(self.data.verbose)
best = load_json(self.data.params_fname)[0]
print(self.data.params_fname, self.data.training_set)
corpus, labels = read_data_labels(self.data.training_set)
le = LabelEncoder()
le.fit(labels)
y = le.transform(labels)
t = TextModel(corpus, **best)
X = [t[x] for x in corpus]
hy = [None for x in y]
for tr, ts in KFold(n_splits=self.data.kratio,
shuffle=True,
random_state=self.data.seed).split(X):
c = SVC(model=t)
c.fit([X[x] for x in tr], [y[x] for x in tr])
_ = c.decision_function([X[x] for x in ts])
[hy.__setitem__(k, v) for k, v in zip(ts, _)]
i = 0
with open(self.get_output(), 'w') as fpt:
for tweet in tweet_iterator(self.data.training_set):
tweet['decision_function'] = hy[i].tolist()
i += 1
fpt.write(json.dumps(tweet) + "\n")
return hy
def main(self, args=None):
self.data = self.parser.parse_args(args=args)
assert not self.data.update_klass
best = load_json(self.data.params_fname)
if isinstance(best, list):
best = best[0]
best = clean_params(best)
print(self.data.params_fname, self.data.training_set)
corpus, labels = read_data_labels(self.data.training_set)
le = LabelEncoder()
le.fit(labels)
y = le.transform(labels)
t = TextModel(corpus, **best)
X = [t[x] for x in corpus]
hy = [None for x in y]
for tr, ts in KFold(n_splits=self.data.kratio,
shuffle=True, random_state=self.data.seed).split(X):
c = SVC(model=t)
c.fit([X[x] for x in tr], [y[x] for x in tr])
_ = c.decision_function([X[x] for x in ts])
[hy.__setitem__(k, v) for k, v in zip(ts, _)]
i = 0
with open(self.get_output(), 'w') as fpt:
for tweet in tweet_iterator(self.data.training_set):
tweet['decision_function'] = hy[i].tolist()
i += 1
fpt.write(json.dumps(tweet)+"\n")
return hy
def test_SVC_predict():
from b4msa.classifier import SVC
from b4msa.textmodel import TextModel
from b4msa.utils import read_data_labels
import os
fname = os.path.dirname(__file__) + '/text.json'
X, y = read_data_labels(fname)
t = TextModel(X)
c = SVC(t)
c.fit_file(fname)
y = c.predict_text('Excelente dia b4msa')
assert y == 'POS'
def test_SVC_predict_from_file():
from b4msa.classifier import SVC
from b4msa.textmodel import TextModel
from b4msa.utils import read_data_labels
import os
fname = os.path.dirname(__file__) + '/text.json'
X, y = read_data_labels(fname)
t = TextModel(X)
c = SVC(t)
c.fit_file(fname)
y = c.predict_file(fname)
for i in y:
assert i in ['POS', 'NEU', 'NEG']
def test_SVC_predict_from_file():
from b4msa.classifier import SVC
from b4msa.textmodel import TextModel
from b4msa.utils import read_data_labels
import os
#fname = os.path.dirname(__file__) + '/text.json'
fname = 'text.json'
#fname = 'test_text.json'
X, y = read_data_labels(fname)
t = TextModel(X)
c = SVC(t)
c.fit_file(fname)
y = c.predict_file("test_text.json")
print "Final Labels"
print y
def main(self):
self.data = self.parser.parse_args()
if self.data.numprocs == 1:
numprocs = None
elif self.data.numprocs == 0:
numprocs = cpu_count()
else:
numprocs = self.data.numprocs
n_folds = self.data.n_folds
n_folds = n_folds if n_folds is not None else 5
assert self.data.score.split(":")[0] in ('macrorecall', 'macrof1', 'microf1', 'weightedf1', 'accuracy', 'avgf1', 'avgf1f0'), "Unknown score {0}".format(self.data.score)
best_list = SVC.predict_kfold_params(
self.data.training_set,
n_folds=n_folds,
score=self.data.score,
numprocs=numprocs,
seed=self.data.seed,
param_kwargs=dict(
bsize=self.data.samplesize,
hill_climbing=self.data.hill_climbing,
# qsize=self.data.qsize,
lang=self.data.lang
)
)
output = self.get_output()
if output.endswith('.gz'):
with gzip.open(output, 'wb') as fpt:
cdn = json.dumps(best_list, indent=2, sort_keys=True)
fpt.write(bytes(cdn, encoding='utf-8'))
else:
with open(output, 'w') as fpt:
fpt.write(json.dumps(best_list, indent=2, sort_keys=True))
def test_kfold():
import os
from b4msa.classifier import SVC
from b4msa.utils import read_data_labels
fname = os.path.dirname(__file__) + '/text.json'
X, y = read_data_labels(fname, get_klass='klass', get_tweet='text')
hy = SVC.predict_kfold(X, y, n_folds=10)
for x in hy:
assert x in ['POS', 'NEU', 'NEG']
def main(self):
self.data = self.parser.parse_args()
logging.basicConfig(level=self.data.verbose)
logger = logging.getLogger('b4msa')
logger.setLevel(self.data.verbose)
params_fname = self.data.params_fname
param_list = load_json(params_fname)
best = param_list[0]
svc = SVC.fit_from_file(self.data.training_set, best)
with open(self.get_output(), 'wb') as fpt:
pickle.dump(svc, fpt)
def test_kfold_pool():
import os
from b4msa.classifier import SVC
from b4msa.utils import read_data_labels
from multiprocessing import Pool
fname = os.path.dirname(__file__) + '/text.json'
X, y = read_data_labels(fname, get_klass='klass', get_tweet='text')
pool = Pool(2)
hy = SVC.predict_kfold(X, y, n_folds=2, pool=pool)
for x in hy:
assert x in ['POS', 'NEU', 'NEG']
pool.close()
def main(self):
self.data = self.parser.parse_args()
params_fname = self.data.params_fname
if params_fname is not None:
best = load_json(params_fname)
if isinstance(best, list):
best = best[0]
else:
best = dict()
best = clean_params(best)
kw = json.loads(self.data.kwargs) if self.data.kwargs is not None else dict()
best.update(kw)
svc = SVC.fit_from_file(self.data.training_set, best)
save_model(svc, self.get_output())
def main(self):
self.data = self.parser.parse_args()
logging.basicConfig(level=self.data.verbose)
params_fname = self.data.params_fname
if params_fname.endswith('.gz'):
with gzip.open(params_fname) as fpt:
cdn = fpt.read()
param_list = json.loads(str(cdn, encoding='utf-8'))
else:
with open(params_fname) as fpt:
param_list = json.loads(fpt.read())
best = param_list[0]
svc = SVC.fit_from_file(self.data.training_set, best)
with open(self.get_output(), 'wb') as fpt:
pickle.dump(svc, fpt)