def test_extraneous_label(self):
weights = CounterMap()
weights['dog'] = Counter({'warm': 2.0, 'fuzzy': 0.5})
labels = set(weights.iterkeys())
logp = maxent.get_log_probabilities(self.features, weights, labels)
self.assertEqual(logp['cat'], float('-inf'))
def test_zero_weight(self):
weights = CounterMap()
weights['dog'] = Counter({'warm': 2.0})
labels = set(weights.iterkeys())
logp = maxent.get_log_probabilities(self.features, weights, labels)
self.assertEqual(logp['dog'], 0.0)
def test_zero_weight(self):
weights = CounterMap()
weights['dog'] = Counter({'warm' : 2.0})
labels = set(weights.iterkeys())
logp = maxent.get_log_probabilities(self.features, weights, labels)
self.assertEqual(logp['dog'], 0.0)
def test_extraneous_label(self):
weights = CounterMap()
weights['dog'] = Counter({'warm' : 2.0, 'fuzzy' : 0.5})
labels = set(weights.iterkeys())
logp = maxent.get_log_probabilities(self.features, weights, labels)
self.assertEqual(logp['cat'], float('-inf'))
def setUp(self):
self.features = Counter((key, 1.0) for key in ['warm', 'fuzzy'])
self.weights = CounterMap()
self.weights['dog'] = Counter({'warm' : 2.0, 'fuzzy' : 0.5})
self.weights['cat'] = Counter({'warm' : 0.5, 'fuzzy' : 2.0})
self.labels = set(self.weights.iterkeys())
self.logp = maxent.get_log_probabilities(self.features, self.weights, self.labels)
def setUp(self):
self.features = Counter((key, 1.0) for key in ['warm', 'fuzzy'])
self.weights = CounterMap()
self.weights['dog'] = Counter({'warm': 2.0, 'fuzzy': 0.5})
self.weights['cat'] = Counter({'warm': 0.5, 'fuzzy': 2.0})
self.labels = set(self.weights.iterkeys())
self.logp = maxent.get_log_probabilities(self.features, self.weights,
self.labels)
def test_fast_slow_equal(self):
weights = CounterMap()
weights['cat'] = Counter(
(key, 1.0)
for key in ('fuzzy', 'claws', 'small', 'medium', 'large'))
weights['bear'] = Counter(
(key, 1.0)
for key in ('fuzzy', 'claws', 'small', 'medium', 'large'))
log_probs = [
maxent.get_log_probabilities(datum[1], weights, self.labels)
for datum in self.labeled_extracted_features
]
slow_expectation = maximumentropy.slow_expected_counts(
self.labeled_extracted_features, self.labels, log_probs)
fast_expectation = maxent.get_expected_counts(
self.labeled_extracted_features, self.labels, log_probs,
CounterMap())
self.assertEqual(slow_expectation, fast_expectation)
# And try again with different weights
weights['cat'] = Counter(
(key, 1.0) for key in ('fuzzy', 'claws', 'small', 'medium'))
weights['bear'] = Counter(
(key, 1.0) for key in ('fuzzy', 'claws', 'big'))
log_probs = [
maxent.get_log_probabilities(datum[1], weights, self.labels)
for datum in self.labeled_extracted_features
]
slow_expectation = maximumentropy.slow_expected_counts(
self.labeled_extracted_features, self.labels, log_probs)
fast_expectation = maxent.get_expected_counts(
self.labeled_extracted_features, self.labels, log_probs,
CounterMap())
self.assertEqual(slow_expectation, fast_expectation)
def test_fast_slow_equal(self):
weights = CounterMap()
weights['cat'] = Counter((key, 1.0) for key in ('fuzzy', 'claws', 'small', 'medium', 'large'))
weights['bear'] = Counter((key, 1.0) for key in ('fuzzy', 'claws', 'small', 'medium', 'large'))
log_probs = [maxent.get_log_probabilities(datum[1], weights, self.labels) for datum in self.labeled_extracted_features]
slow_expectation = maximumentropy.slow_expected_counts(self.labeled_extracted_features, self.labels, log_probs)
fast_expectation = maxent.get_expected_counts(self.labeled_extracted_features, self.labels, log_probs, CounterMap())
self.assertEqual(slow_expectation, fast_expectation)
# And try again with different weights
weights['cat'] = Counter((key, 1.0) for key in ('fuzzy', 'claws', 'small', 'medium'))
weights['bear'] = Counter((key, 1.0) for key in ('fuzzy', 'claws', 'big'))
log_probs = [maxent.get_log_probabilities(datum[1], weights, self.labels) for datum in self.labeled_extracted_features]
slow_expectation = maximumentropy.slow_expected_counts(self.labeled_extracted_features, self.labels, log_probs)
fast_expectation = maxent.get_expected_counts(self.labeled_extracted_features, self.labels, log_probs, CounterMap())
self.assertEqual(slow_expectation, fast_expectation)
def test_performance(self): """ C api should be faster than python API (this is potentialy flakey, depending on system load patterns) """ start = time.time() for i in xrange(100000): test = maximumentropy.slow_log_probs(self.features, self.weights, self.labels) slow_time = time.time() - start start = time.time() for i in xrange(100000): test = maxent.get_log_probabilities(self.features, self.weights, self.labels) fast_time = time.time() - start self.assertTrue(fast_time < slow_time)
def test_performance(self):
"""
C api should be faster than python API (this is potentialy flakey, depending on system load patterns)
"""
start = time.time()
for i in xrange(100000):
test = maximumentropy.slow_log_probs(self.features, self.weights,
self.labels)
slow_time = time.time() - start
start = time.time()
for i in xrange(100000):
test = maxent.get_log_probabilities(self.features, self.weights,
self.labels)
fast_time = time.time() - start
self.assertTrue(fast_time < slow_time)
def test_uneven_weights(self):
weights = CounterMap()
weights['dog'] = Counter({'warm': 2.0, 'fuzzy': 1.0})
weights['cat'] = Counter({'warm': 1.0, 'fuzzy': 1.0})
labels = set(weights.iterkeys())
logp = maxent.get_log_probabilities(self.features, weights, labels)
# construct scores
scores = Counter()
scores['dog'] = 2.0 * 1.0 + 1.0 * 1.0
scores['cat'] = 1.0 * 1.0 + 1.0 * 1.0
scores.log_normalize()
# check scores explicitly
self.assertAlmostEqual(scores['dog'], log(0.731), 3)
self.assertAlmostEqual(scores['cat'], log(0.269), 3)
# check that log probs is correct
self.assertEqual(logp['dog'], scores['dog'])
self.assertEqual(logp['cat'], scores['cat'])
def test_uneven_weights(self):
weights = CounterMap()
weights['dog'] = Counter({'warm' : 2.0, 'fuzzy' : 1.0})
weights['cat'] = Counter({'warm' : 1.0, 'fuzzy' : 1.0})
labels = set(weights.iterkeys())
logp = maxent.get_log_probabilities(self.features, weights, labels)
# construct scores
scores = Counter()
scores['dog'] = 2.0 * 1.0 + 1.0 * 1.0
scores['cat'] = 1.0 * 1.0 + 1.0 * 1.0
scores.log_normalize()
# check scores explicitly
self.assertAlmostEqual(scores['dog'], log(0.731), 3)
self.assertAlmostEqual(scores['cat'], log(0.269), 3)
# check that log probs is correct
self.assertEqual(logp['dog'], scores['dog'])
self.assertEqual(logp['cat'], scores['cat'])
from itertools import izip, repeat, chain
from maxent import get_log_probabilities, get_expected_counts
from countermap import CounterMap
from counter import Counter
def cnter(l):
return Counter(izip(l, repeat(1.0, len(l))))
training_data = (('cat', cnter(
('fuzzy', 'claws', 'small'))), ('bear', cnter(
('fuzzy', 'claws', 'big'))), ('cat', cnter(('claws', 'medium'))))
labels = set([label for label, _ in training_data])
features = set()
for _, counter in training_data:
features.update(set(counter.keys()))
weights = CounterMap()
log_probs = list()
for pos, (label, features) in enumerate(training_data):
log_probs.append(get_log_probabilities(features, weights, labels))
test = get_expected_counts(training_data, labels, log_probs, CounterMap())
print test
from itertools import izip, repeat, chain
from maxent import get_log_probabilities, get_expected_counts
from countermap import CounterMap
from counter import Counter
def cnter(l):
return Counter(izip(l, repeat(1.0, len(l))))
training_data = (('cat', cnter(('fuzzy', 'claws', 'small'))),
('bear', cnter(('fuzzy', 'claws', 'big'))),
('cat', cnter(('claws', 'medium'))))
labels = set([label for label, _ in training_data])
features = set()
for _, counter in training_data:
features.update(set(counter.keys()))
weights = CounterMap()
log_probs = list()
for pos, (label, features) in enumerate(training_data):
log_probs.append(get_log_probabilities(features, weights, labels))
test = get_expected_counts(training_data, labels, log_probs, CounterMap())
print test
