def main():
parser = argparse.ArgumentParser(
description='Train CRFSuite on data from the QCRI MySQL database',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('-k',
'--k-folds',
type=int,
default=10,
help='How many folds of the data to test on')
parser.add_argument('--max-data',
type=int,
default=10000,
help='Maximum data points to train and test on')
parser.add_argument('--include-none',
type=int,
default=0,
help='Include None in Confusion Matrix.')
parser.add_argument('-threshold',
type=int,
default=10,
help='Threshold for number of gold labels classified.')
opts = parser.parse_args()
# e.g., tokenized_label =
# <TokenizedLabel dssg_id=23346 token_start=13 token_end=16
# tweet=Tornado Kills 89 in Missouri. http://t.co/IEuBas5 token_type=i18 token= 89 id=5>
# Train and test must be iterables of objects that support CRF-ready
# .tokens and .labels attributes.
query = DBSession.query(TokenizedLabel).limit(opts.max_data)
X_y = ((featurize(item.tokens, crf_feature_functions), item.labels)
for item in query)
# unzip and flatten into static list
X, y = zip(*X_y)
# we need to read X multiple times, so make sure it's all static
X = map(flatMap, X)
categories = dict(
(label.id, label.text) for label in DBSession.query(Label))
print 'categories', categories
N = len(y)
index = 0
for train_indices, test_indices in cross_validation.KFold(N,
opts.k_folds,
shuffle=True):
# train, test = tokenized_labels[train_indices], tokenized_labels[test_indices]
train_X = [X[i] for i in train_indices]
train_y = [y[i] for i in train_indices]
test_X = [X[i] for i in test_indices]
test_y = [y[i] for i in test_indices]
classifier = CRF()
# print_gloss=True
index = index + 1
evaluateSequenceClassifier(classifier, train_X, train_y, test_X,
test_y, index, opts)
def test_tweedr_models_no_ci():
from tweedr.models import DBSession, TokenizedLabel, Label
Tables = [TokenizedLabel, Label]
for Table in Tables:
row_count = DBSession.query(Table).count()
assert row_count > 0, 'There should be more than 0 rows in the table "%s"' % Table.name
def test_tweedr_models_no_ci():
from tweedr.models import DBSession, TokenizedLabel, Label
Tables = [TokenizedLabel, Label]
for Table in Tables:
row_count = DBSession.query(Table).count()
assert row_count > 0, 'There should be more than 0 rows in the table "%s"' % Table.name
def first(limit):
print >> sys.stderr, 'First %d tweets.' % limit
for tokenized_label in DBSession.query(TokenizedLabel).limit(limit):
# print repr(tokenized_label)
tokenized_label_text = unicode(tokenized_label).translate(whitespace_unicode_translations).encode('utf8')
token_type_object = tokenized_label.token_type_object
print token_type_object.id, '\t', token_type_object.text, '\t', tokenized_label_text
def first(limit):
print >> sys.stderr, 'First %d tweets.' % limit
for tokenized_label in DBSession.query(TokenizedLabel).limit(limit):
# print repr(tokenized_label)
tokenized_label_text = unicode(tokenized_label).translate(
whitespace_unicode_translations).encode('utf8')
token_type_object = tokenized_label.token_type_object
print token_type_object.id, '\t', token_type_object.text, '\t', tokenized_label_text
def read_tweets():
'''Read labeled tweets from database'''
logger.info('Reading labeled tweets from database...')
labeled_tweets = \
np.array(DBSession.query(DamageClassification).filter(DamageClassification.mturk_code
== 'QCRI').limit(opts.max_data).all())
logger.info('Read %d tweets', len(labeled_tweets))
return labeled_tweets
def main():
parser = argparse.ArgumentParser(
description='Train CRFSuite on data from the QCRI MySQL database',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('-k',
'--k-folds',
type=int,
default=10,
help='How many folds of the data to test on')
parser.add_argument('--max-data',
type=int,
default=10000,
help='Maximum data points to train and test on')
parser.add_argument(
'--adjacent',
type=int,
default=0,
help='Set adjacent to 1 if adjacent functions want to be used')
opts = parser.parse_args()
# e.g., tokenized_label =
# <TokenizedLabel dssg_id=23346 token_start=13 token_end=16
# tweet=Tornado Kills 89 in Missouri. http://t.co/IEuBas5 token_type=i18 token= 89 id=5>
# Train and test must be iterables of objects that support CRF-ready
# .tokens and .labels attributes.
query = DBSession.query(TokenizedLabel).\
filter(TokenizedLabel.tweet is not None).\
filter(TokenizedLabel.tweet != '').\
limit(opts.max_data)
if (opts.adjacent == 0):
X_y = ((featurize(item.tokens, crf_feature_functions), item.labels)
for item in query)
else:
X_y = ((featurize_adjacent(item.tokens,
crf_feature_functions), item.labels)
for item in query)
# unzip and flatten into static list
X, y = zip(*X_y)
# we need to read X multiple times, so make sure it's all static
X = map(flatMap, X)
N = len(y)
for train_indices, test_indices in cross_validation.KFold(N,
opts.k_folds,
shuffle=True):
# train, test = tokenized_labels[train_indices], tokenized_labels[test_indices]
train_X = [X[i] for i in train_indices]
train_y = [y[i] for i in train_indices]
test_X = [X[i] for i in test_indices]
test_y = [y[i] for i in test_indices]
classifier = CRF()
# print_gloss=True
evaluateSequenceClassifier(classifier, train_X, train_y, test_X,
test_y)
def default(cls, feature_functions, retrain=False, limit=10000):
# Is it messy to have this method here, since it depends on tweedr.models.*?
# and on a specific filepath in the local filesystem?
model_filepath = '/tmp/tweedr.ml.crf.classifier-max%d.model' % limit
if os.path.exists(model_filepath):
return cls.from_file(model_filepath)
else:
from tweedr.models import DBSession, TokenizedLabel
query = DBSession.query(TokenizedLabel).limit(10000)
crf = cls.from_data(query, feature_functions)
crf.save(model_filepath)
return crf
def default(cls, feature_functions, retrain=False, limit=10000):
# Is it messy to have this method here, since it depends on tweedr.models.*?
# and on a specific filepath in the local filesystem?
model_filepath = '/tmp/tweedr.ml.crf.classifier-max%d.model' % limit
if os.path.exists(model_filepath):
return cls.from_file(model_filepath)
else:
from tweedr.models import DBSession, TokenizedLabel
query = DBSession.query(TokenizedLabel).limit(10000)
crf = cls.from_data(query, feature_functions)
crf.save(model_filepath)
return crf
def main():
parser = argparse.ArgumentParser(
description='Train CRFSuite on data from the QCRI MySQL database',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('-k', '--k-folds',
type=int, default=10, help='How many folds of the data to test on')
parser.add_argument('--max-data',
type=int, default=10000, help='Maximum data points to train and test on')
parser.add_argument('--include-none', type=int, default=0, help='Include None in Confusion Matrix.')
parser.add_argument('-threshold', type=int, default=10, help='Threshold for number of gold labels classified.')
opts = parser.parse_args()
# e.g., tokenized_label =
# <TokenizedLabel dssg_id=23346 token_start=13 token_end=16
# tweet=Tornado Kills 89 in Missouri. http://t.co/IEuBas5 token_type=i18 token= 89 id=5>
# Train and test must be iterables of objects that support CRF-ready
# .tokens and .labels attributes.
query = DBSession.query(TokenizedLabel).limit(opts.max_data)
X_y = ((featurize(item.tokens, crf_feature_functions), item.labels) for item in query)
# unzip and flatten into static list
X, y = zip(*X_y)
# we need to read X multiple times, so make sure it's all static
X = map(flatMap, X)
categories = dict((label.id, label.text) for label in DBSession.query(Label))
print 'categories', categories
N = len(y)
index = 0
for train_indices, test_indices in cross_validation.KFold(N, opts.k_folds, shuffle=True):
# train, test = tokenized_labels[train_indices], tokenized_labels[test_indices]
train_X = [X[i] for i in train_indices]
train_y = [y[i] for i in train_indices]
test_X = [X[i] for i in test_indices]
test_y = [y[i] for i in test_indices]
classifier = CRF()
# print_gloss=True
index = index + 1
evaluateSequenceClassifier(classifier, train_X, train_y, test_X, test_y, index, opts)
def main():
parser = argparse.ArgumentParser(
description='Train CRFSuite on data from the QCRI MySQL database',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('-k', '--k-folds',
type=int, default=10, help='How many folds of the data to test on')
parser.add_argument('--max-data',
type=int, default=10000, help='Maximum data points to train and test on')
opts = parser.parse_args()
# e.g., tokenized_label =
# <TokenizedLabel dssg_id=23346 token_start=13 token_end=16
# tweet=Tornado Kills 89 in Missouri. http://t.co/IEuBas5 token_type=i18 token= 89 id=5>
# Train and test must be iterables of objects that support CRF-ready
# .tokens and .labels attributes.
query = DBSession.query(TokenizedLabel).limit(opts.max_data)
for L in range(0, len(crf_feature_functions) + 1):
for subset in itertools.combinations(crf_feature_functions, L):
sub = list(subset)
print sub
X_y = ((featurize(item.tokens, sub), item.labels) for item in query)
# unzip and flatten into static list
X, y = zip(*X_y)
# we need to read X multiple times, so make sure it's all static
X = map(flatMap, X)
categories = dict((label.id, label.text) for label in DBSession.query(Label))
print 'categories', categories
N = len(y)
#tests on different data sets -> k folds is set to 10 right now
for train_indices, test_indices in cross_validation.KFold(N, opts.k_folds, shuffle=True):
train_X = [X[i] for i in train_indices]
train_y = [y[i] for i in train_indices]
test_X = [X[i] for i in test_indices]
test_y = [y[i] for i in test_indices]
classifier = CRF()
evaluateSequenceClassifier(classifier, train_X, train_y, test_X, test_y)
def main():
parser = argparse.ArgumentParser(
description='Train CRFSuite on data from the QCRI MySQL database',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('-k', '--k-folds',
type=int, default=10, help='How many folds of the data to test on')
parser.add_argument('--max-data',
type=int, default=10000, help='Maximum data points to train and test on')
parser.add_argument('--adjacent',
type=int, default=0, help='Set adjacent to 1 if adjacent functions want to be used')
opts = parser.parse_args()
# e.g., tokenized_label =
# <TokenizedLabel dssg_id=23346 token_start=13 token_end=16
# tweet=Tornado Kills 89 in Missouri. http://t.co/IEuBas5 token_type=i18 token= 89 id=5>
# Train and test must be iterables of objects that support CRF-ready
# .tokens and .labels attributes.
query = DBSession.query(TokenizedLabel).\
filter(TokenizedLabel.tweet is not None).\
filter(TokenizedLabel.tweet != '').\
limit(opts.max_data)
if (opts.adjacent == 0):
X_y = ((featurize(item.tokens, crf_feature_functions), item.labels) for item in query)
else:
X_y = ((featurize_adjacent(item.tokens, crf_feature_functions), item.labels) for item in query)
# unzip and flatten into static list
X, y = zip(*X_y)
# we need to read X multiple times, so make sure it's all static
X = map(flatMap, X)
N = len(y)
for train_indices, test_indices in cross_validation.KFold(N, opts.k_folds, shuffle=True):
# train, test = tokenized_labels[train_indices], tokenized_labels[test_indices]
train_X = [X[i] for i in train_indices]
train_y = [y[i] for i in train_indices]
test_X = [X[i] for i in test_indices]
test_y = [y[i] for i in test_indices]
classifier = CRF()
# print_gloss=True
evaluateSequenceClassifier(classifier, train_X, train_y, test_X, test_y)
def tokenized_labels_sample():
total = DBSession.query(TokenizedLabel).count()
index = random.randrange(total)
logger.debug('/tokenized_labels/sample: choosing #%d out of %d', index, total)
tokenized_label = DBSession.query(TokenizedLabel).offset(index).limit(1).first()
return tokenized_label.__json__()
def tokenized_labels_sample():
total = DBSession.query(TokenizedLabel).count()
index = random.randrange(total)
logger.debug("/tokenized_labels/sample: choosing #%d out of %d", index, total)
tokenized_label = DBSession.query(TokenizedLabel).offset(index).limit(1).first()
return tokenized_label.__json__()
def count():
print >> sys.stderr, 'Tweet count started.'
print 'There are %d labels in the database.' % DBSession.query(
Label).count()
print 'There are %d tokenized labels in the database.' % DBSession.query(
TokenizedLabel).count()
def __init__(self):
labeled_tweets = \
np.array(DBSession.query(DamageClassification).filter(DamageClassification.mturk_code
== 'QCRI').limit(1000).all())
labeled_tweets = map(lambda x: (x.text, int(x.label)), labeled_tweets)
self.dataset = labeled_tweets
def count():
print >> sys.stderr, 'Tweet count started.'
print 'There are %d labels in the database.' % DBSession.query(Label).count()
print 'There are %d tokenized labels in the database.' % DBSession.query(TokenizedLabel).count()
def __init__(self):
labeled_tweets = \
np.array(DBSession.query(DamageClassification).filter(DamageClassification.mturk_code
== 'QCRI').limit(1000).all())
labeled_tweets = map(lambda x: (x.text, int(x.label)), labeled_tweets)
self.dataset = labeled_tweets