def testIrisES(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)
X_train, X_val, y_train, y_val = train_test_split(X_train,
y_train,
test_size=0.2)
val_monitor = skflow.monitors.ValidationMonitor(X_val,
y_val,
n_classes=3)
# classifier without early stopping - overfitting
classifier1 = skflow.TensorFlowDNNClassifier(hidden_units=[10, 20, 10],
n_classes=3,
steps=1000)
classifier1.fit(X_train, y_train)
score1 = accuracy_score(y_test, classifier1.predict(X_test))
# classifier with early stopping - improved accuracy on testing set
classifier2 = skflow.TensorFlowDNNClassifier(hidden_units=[10, 20, 10],
n_classes=3,
steps=1000)
classifier2.fit(X_train, y_train, val_monitor)
score2 = accuracy_score(y_test, classifier2.predict(X_test))
def testIrisStreaming(self):
iris = datasets.load_iris()
def iris_data():
while True:
for x in iris.data:
yield x
def iris_predict_data():
for x in iris.data:
yield x
def iris_target():
while True:
for y in iris.target:
yield y
classifier = skflow.TensorFlowLinearClassifier(n_classes=3, steps=100)
classifier.fit(iris_data(), iris_target())
score1 = accuracy_score(iris.target, classifier.predict(iris.data))
score2 = accuracy_score(iris.target, classifier.predict(iris_predict_data()))
self.assertGreater(score1, 0.5, "Failed with score = {0}".format(score1))
self.assertEqual(score2, score1, "Scores from {0} iterator doesn't "
"match score {1} from full "
"data.".format(score2, score1))
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)
# setup exponential decay function
def exp_decay(global_step):
return tf.train.exponential_decay(learning_rate=0.1,
global_step=global_step,
decay_steps=100,
decay_rate=0.001)
custom_optimizer = lambda learning_rate: tf.train.MomentumOptimizer(
learning_rate, 0.9)
classifier = skflow.TensorFlowDNNClassifier(hidden_units=[10, 20, 10],
n_classes=3,
steps=800,
learning_rate=exp_decay,
optimizer=custom_optimizer)
classifier.fit(X_train, y_train)
score = accuracy_score(y_test, classifier.predict(X_test))
self.assertGreater(score, 0.7, "Failed with score = {0}".format(score))
def testIrisClassWeight(self):
iris = datasets.load_iris()
classifier = skflow.TensorFlowLinearClassifier(
n_classes=3, class_weight=[0.1, 0.8, 0.1])
classifier.fit(iris.data, iris.target)
score = accuracy_score(iris.target, classifier.predict(iris.data))
self.assertLess(score, 0.7, "Failed with score = {0}".format(score))
def testDNNDropout0_1(self):
# Dropping only a little.
iris = datasets.load_iris()
classifier = skflow.TensorFlowDNNClassifier(
hidden_units=[10, 20, 10], n_classes=3, dropout=0.1)
classifier.fit(iris.data, iris.target)
score = accuracy_score(iris.target, classifier.predict(iris.data))
self.assertGreater(score, 0.9, "Failed with score = {0}".format(score))
def testIris_proba(self):
# If sklearn available.
if log_loss:
random.seed(42)
iris = datasets.load_iris()
classifier = skflow.TensorFlowClassifier(n_classes=3, steps=250)
classifier.fit(iris.data, iris.target)
score = log_loss(iris.target, classifier.predict_proba(iris.data))
self.assertLess(score, 0.8, "Failed with score = {0}".format(score))
def testIrisContinueTraining(self):
iris = datasets.load_iris()
classifier = skflow.TensorFlowLinearClassifier(n_classes=3,
learning_rate=0.01, continue_training=True, steps=250)
classifier.fit(iris.data, iris.target)
score1 = accuracy_score(iris.target, classifier.predict(iris.data))
classifier.fit(iris.data, iris.target)
score2 = accuracy_score(iris.target, classifier.predict(iris.data))
self.assertGreater(score2, score1,
"Failed with score = {0}".format(score2))
def test_pandas_series(self):
if HAS_PANDAS:
random.seed(42)
iris = datasets.load_iris()
data = pd.DataFrame(iris.data)
labels = pd.Series(iris.target)
classifier = skflow.TensorFlowLinearClassifier(n_classes=3)
classifier.fit(data, labels)
score = accuracy_score(labels, classifier.predict(data))
self.assertGreater(score, 0.5, "Failed with score = {0}".format(score))
def testNoCheckpoints(self):
path = tf.test.get_temp_dir() + '/tmp/tmp.saver4'
random.seed(42)
iris = datasets.load_iris()
classifier = skflow.TensorFlowDNNClassifier(hidden_units=[10, 20, 10], n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
os.remove(os.path.join(path, 'checkpoint'))
with self.assertRaises(ValueError):
skflow.TensorFlowEstimator.restore(path)
def test_pandas_series(self):
if HAS_PANDAS:
random.seed(42)
iris = datasets.load_iris()
data = pd.DataFrame(iris.data)
labels = pd.Series(iris.target)
classifier = skflow.TensorFlowLinearClassifier(n_classes=3)
classifier.fit(data, labels)
score = accuracy_score(labels, classifier.predict(data))
self.assertGreater(score, 0.5,
"Failed with score = {0}".format(score))
def testDNN(self):
path = tf.test.get_temp_dir() + '/tmp_saver3'
random.seed(42)
iris = datasets.load_iris()
classifier = skflow.TensorFlowDNNClassifier(hidden_units=[10, 20, 10], n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
new_classifier = skflow.TensorFlowEstimator.restore(path)
self.assertEqual(type(new_classifier), type(classifier))
score = accuracy_score(iris.target, new_classifier.predict(iris.data))
self.assertGreater(score, 0.5, "Failed with score = {0}".format(score))
def test_pandas_dataframe(self):
if HAS_PANDAS:
random.seed(42)
iris = datasets.load_iris()
data = pd.DataFrame(iris.data)
labels = pd.DataFrame(iris.target)
classifier = skflow.TensorFlowLinearClassifier(n_classes=3)
classifier.fit(data, labels)
score = accuracy_score(labels[0], classifier.predict(data))
self.assertGreater(score, 0.5, "Failed with score = {0}".format(score))
else:
print("No pandas installed. pandas-related tests are skipped.")
def test_pandas_dataframe(self):
if HAS_PANDAS:
random.seed(42)
iris = datasets.load_iris()
data = pd.DataFrame(iris.data)
labels = pd.DataFrame(iris.target)
classifier = skflow.TensorFlowLinearClassifier(n_classes=3)
classifier.fit(data, labels)
score = accuracy_score(labels[0], classifier.predict(data))
self.assertGreater(score, 0.5,
"Failed with score = {0}".format(score))
else:
print("No pandas installed. pandas-related tests are skipped.")
def test_dask_iris_classification(self):
if HAS_DASK and HAS_PANDAS:
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 = skflow.TensorFlowLinearClassifier(n_classes=3)
classifier.fit(data, labels)
predictions = data.map_partitions(classifier.predict).compute()
score = accuracy_score(labels.compute(), predictions)
self.assertGreater(score, 0.5, "Failed with score = {0}".format(score))
def test_dask_iris_classification(self):
if HAS_DASK and HAS_PANDAS:
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 = skflow.TensorFlowLinearClassifier(n_classes=3)
classifier.fit(data, labels)
predictions = data.map_partitions(classifier.predict).compute()
score = accuracy_score(labels.compute(), predictions)
self.assertGreater(score, 0.5,
"Failed with score = {0}".format(score))
def testCustomModel(self):
path = tf.test.get_temp_dir() + '/tmp.saver2'
random.seed(42)
iris = datasets.load_iris()
def custom_model(X, y):
return skflow.models.logistic_regression(X, y)
classifier = skflow.TensorFlowEstimator(model_fn=custom_model,
n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
new_classifier = skflow.TensorFlowEstimator.restore(path)
self.assertEqual(type(new_classifier), type(classifier))
score = accuracy_score(iris.target, new_classifier.predict(iris.data))
self.assertGreater(score, 0.5, "Failed with score = {0}".format(score))
def testIrisDNN(self):
random.seed(42)
iris = datasets.load_iris()
classifier = skflow.TensorFlowDNNClassifier(
hidden_units=[10, 20, 10], n_classes=3)
classifier.fit(iris.data, iris.target)
score = accuracy_score(iris.target, classifier.predict(iris.data))
self.assertGreater(score, 0.9, "Failed with score = {0}".format(score))
weights = classifier.weights_
self.assertEqual(weights[0].shape, (4, 10))
self.assertEqual(weights[1].shape, (10, 20))
self.assertEqual(weights[2].shape, (20, 10))
self.assertEqual(weights[3].shape, (10, 3))
biases = classifier.bias_
self.assertEqual(len(biases), 4)
def testIrisExponentialDecay(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)
# setup exponential decay function
def exp_decay(global_step):
return tf.train.exponential_decay(
learning_rate=0.1, global_step=global_step,
decay_steps=100, decay_rate=0.001)
classifier = skflow.TensorFlowDNNClassifier(hidden_units=[10, 20, 10],
n_classes=3, steps=800,
learning_rate=exp_decay)
classifier.fit(X_train, y_train)
score = accuracy_score(y_test, classifier.predict(X_test))
self.assertGreater(score, 0.7, "Failed with score = {0}".format(score))
def testIrisES(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)
X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.2)
val_monitor = skflow.monitors.ValidationMonitor(X_val, y_val, n_classes=3)
# classifier without early stopping - overfitting
classifier1 = skflow.TensorFlowDNNClassifier(hidden_units=[10, 20, 10],
n_classes=3, steps=1000)
classifier1.fit(X_train, y_train)
score1 = accuracy_score(y_test, classifier1.predict(X_test))
# classifier with early stopping - improved accuracy on testing set
classifier2 = skflow.TensorFlowDNNClassifier(hidden_units=[10, 20, 10],
n_classes=3, steps=1000)
classifier2.fit(X_train, y_train, val_monitor)
score2 = accuracy_score(y_test, classifier2.predict(X_test))
def testIris(self):
iris = datasets.load_iris()
classifier = skflow.TensorFlowLinearClassifier(n_classes=3)
classifier.fit(iris.data, [float(x) for x in iris.target])
score = accuracy_score(iris.target, classifier.predict(iris.data))
self.assertGreater(score, 0.7, "Failed with score = {0}".format(score))
def testIrisSummaries(self):
iris = datasets.load_iris()
classifier = skflow.TensorFlowLinearClassifier(n_classes=3)
classifier.fit(iris.data, iris.target, logdir='/tmp/skflow_tests/')
score = accuracy_score(iris.target, classifier.predict(iris.data))
self.assertGreater(score, 0.5, "Failed with score = {0}".format(score))