def testIrisMomentum(self):
random.seed(42)
iris = datasets.load_iris()
x_train, x_test, y_train, y_test = train_test_split(iris.data,
iris.target,
test_size=0.2,
random_state=42)
def custom_optimizer():
return momentum_lib.MomentumOptimizer(learning_rate=0.01,
momentum=0.9)
classifier = learn.DNNClassifier(
hidden_units=[10, 20, 10],
feature_columns=learn.infer_real_valued_columns_from_input(
x_train),
n_classes=3,
optimizer=custom_optimizer,
config=learn.RunConfig(tf_random_seed=1))
classifier.fit(x_train, y_train, steps=400)
predictions = np.array(list(classifier.predict_classes(x_test)))
score = accuracy_score(y_test, predictions)
self.assertGreater(score, 0.65,
"Failed with score = {0}".format(score))
def testCustomMetrics(self):
"""Tests custom evaluation metrics."""
def _input_fn(num_epochs=None):
# Create 4 rows, one of them (y = x), three of them (y=Not(x))
labels = constant_op.constant([[1], [0], [0], [0]])
features = {
'x':
input_lib.limit_epochs(array_ops.ones(shape=[4, 1],
dtype=dtypes.float32),
num_epochs=num_epochs),
}
return features, labels
def _my_metric_op(predictions, labels):
# For the case of binary classification, the 2nd column of "predictions"
# denotes the model predictions.
labels = math_ops.cast(labels, dtypes.float32)
predictions = array_ops.strided_slice(predictions, [0, 1], [-1, 2],
end_mask=1)
labels = math_ops.cast(labels, predictions.dtype)
return math_ops.reduce_sum(math_ops.multiply(predictions, labels))
classifier = debug.DebugClassifier(config=run_config.RunConfig(
tf_random_seed=1))
classifier.fit(input_fn=_input_fn, steps=5)
scores = classifier.evaluate(
input_fn=_input_fn,
steps=5,
metrics={
'my_accuracy':
MetricSpec(metric_fn=metric_ops.streaming_accuracy,
prediction_key='classes'),
'my_precision':
MetricSpec(metric_fn=metric_ops.streaming_precision,
prediction_key='classes'),
'my_metric':
MetricSpec(metric_fn=_my_metric_op,
prediction_key='probabilities')
})
self.assertTrue(
set(['loss', 'my_accuracy', 'my_precision',
'my_metric']).issubset(set(scores.keys())))
predict_input_fn = functools.partial(_input_fn, num_epochs=1)
predictions = np.array(
list(classifier.predict_classes(input_fn=predict_input_fn)))
self.assertEqual(_sklearn.accuracy_score([1, 0, 0, 0], predictions),
scores['my_accuracy'])
# Test the case where the 2nd element of the key is neither "classes" nor
# "probabilities".
with self.assertRaisesRegexp(KeyError, 'bad_type'):
classifier.evaluate(input_fn=_input_fn,
steps=5,
metrics={
'bad_name':
MetricSpec(
metric_fn=metric_ops.streaming_auc,
prediction_key='bad_type')
})
def test_pandas_series(self):
if HAS_PANDAS:
import pandas as pd # pylint: disable=g-import-not-at-top
random.seed(42)
iris = datasets.load_iris()
data = pd.DataFrame(iris.data)
labels = pd.Series(iris.target)
classifier = learn.LinearClassifier(
feature_columns=learn.infer_real_valued_columns_from_input(
data),
n_classes=3)
classifier.fit(data, labels, steps=100)
score = accuracy_score(labels,
list(classifier.predict_classes(data)))
self.assertGreater(score, 0.5,
"Failed with score = {0}".format(score))
def test_dask_iris_classification(self):
if HAS_DASK and HAS_PANDAS:
import pandas as pd # pylint: disable=g-import-not-at-top
import dask.dataframe as dd # pylint: disable=g-import-not-at-top
random.seed(42)
iris = datasets.load_iris()
data = pd.DataFrame(iris.data)
data = dd.from_pandas(data, npartitions=2)
labels = pd.DataFrame(iris.target)
labels = dd.from_pandas(labels, npartitions=2)
classifier = learn.LinearClassifier(
feature_columns=learn.infer_real_valued_columns_from_input(
data),
n_classes=3)
classifier.fit(data, labels, steps=100)
predictions = data.map_partitions(classifier.predict).compute()
score = accuracy_score(labels.compute(), predictions)
self.assertGreater(score, 0.5,
"Failed with score = {0}".format(score))