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 = learn.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 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 = learn.monitors.ValidationMonitor(x_val, y_val,
early_stopping_rounds=100)
# classifier without early stopping - overfitting
classifier1 = learn.TensorFlowDNNClassifier(hidden_units=[10, 20, 10],
n_classes=3,
steps=1000)
classifier1.fit(x_train, y_train)
accuracy_score(y_test, classifier1.predict(x_test))
# classifier with early stopping - improved accuracy on testing set
classifier2 = learn.TensorFlowDNNClassifier(hidden_units=[10, 20, 10],
n_classes=3,
steps=1000)
classifier2.fit(x_train, y_train, monitors=[val_monitor])
accuracy_score(y_test, classifier2.predict(x_test))
def testIris(self):
path = tf.test.get_temp_dir() + '/tmp.saver'
random.seed(42)
iris = datasets.load_iris()
classifier = learn.TensorFlowLinearClassifier(n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
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 = learn.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 testDNNDropout0_1(self):
# Dropping only a little.
iris = datasets.load_iris()
classifier = learn.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 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(learning_rate):
return tf.train.MomentumOptimizer(learning_rate, 0.9)
cont_features = [
tf.contrib.layers.real_valued_column("", dimension=4)]
classifier = learn.TensorFlowDNNClassifier(
feature_columns=cont_features,
hidden_units=[10, 20, 10],
n_classes=3,
steps=400,
learning_rate=0.01,
optimizer=custom_optimizer)
classifier.fit(x_train, y_train)
score = accuracy_score(y_test, classifier.predict(x_test))
self.assertGreater(score, 0.65, "Failed with score = {0}".format(score))
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 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)
def custom_optimizer(learning_rate):
return tf.train.MomentumOptimizer(learning_rate, 0.9)
classifier = learn.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 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)
def custom_optimizer(learning_rate):
return tf.train.MomentumOptimizer(learning_rate, 0.9)
classifier = learn.TensorFlowDNNClassifier(hidden_units=[10, 20, 10],
n_classes=3,
steps=400,
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, 0.65, "Failed with score = {0}".format(score))
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 = learn.LinearClassifier(
feature_columns=learn.infer_real_valued_columns_from_input(iris.data),
n_classes=3)
classifier.fit(iris_data(), iris_target(), max_steps=500)
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 testIris(self): path = tf.test.get_temp_dir() + '/tmp.saver' random.seed(42) iris = datasets.load_iris() classifier = learn.TensorFlowLinearClassifier(n_classes=3) classifier.fit(iris.data, iris.target) classifier.save(path)
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 = learn.LinearClassifier(
feature_columns=learn.infer_real_valued_columns_from_input(iris.data),
n_classes=3)
classifier.fit(iris_data(), iris_target(), max_steps=500)
score1 = accuracy_score(iris.target,
list(classifier.predict(iris.data)))
score2 = accuracy_score(iris.target,
list(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 testIrisClassWeight(self):
iris = datasets.load_iris()
classifier = learn.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 testIrisClassWeight(self):
iris = datasets.load_iris()
classifier = learn.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 testIris(self):
iris = datasets.load_iris()
classifier = learn.TensorFlowLinearClassifier(
feature_columns=learn.infer_real_valued_columns_from_input(iris.data),
n_classes=3)
classifier.fit(iris.data, [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 testNoCheckpoints(self):
random.seed(42)
iris = datasets.load_iris()
cont_features = [tf.contrib.layers.real_valued_column('', dimension=4)]
classifier = learn.DNNClassifier(feature_columns=cont_features,
hidden_units=[10, 20, 10],
n_classes=3)
classifier.fit(iris.data, iris.target, max_steps=100)
def testIrisSummaries(self):
iris = datasets.load_iris()
output_dir = tempfile.mkdtemp() + "learn_tests/"
classifier = learn.TensorFlowLinearClassifier(n_classes=3,
model_dir=output_dir)
classifier.fit(iris.data, iris.target)
score = accuracy_score(iris.target, classifier.predict(iris.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 = learn.TensorFlowDNNClassifier(hidden_units=[10, 20, 10],
n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
def testNoCheckpoints(self):
path = tf.test.get_temp_dir() + '/tmp/tmp.saver4'
random.seed(42)
iris = datasets.load_iris()
classifier = learn.TensorFlowDNNClassifier(hidden_units=[10, 20, 10],
n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
def testNoCheckpoints(self):
random.seed(42)
iris = datasets.load_iris()
cont_features = [
tf.contrib.layers.real_valued_column('', dimension=4)]
classifier = learn.DNNClassifier(feature_columns=cont_features,
hidden_units=[10, 20, 10],
n_classes=3)
classifier.fit(iris.data, iris.target, max_steps=100)
def testIrisClassWeight(self):
iris = datasets.load_iris()
# Note, class_weight are not supported anymore :( Use weight_column.
with self.assertRaises(ValueError):
classifier = learn.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 testDNNAutoencoder(self):
import numpy as np
iris = datasets.load_iris()
autoencoder = learn.TensorFlowDNNAutoencoder(hidden_units=[10, 20])
transformed = autoencoder.fit_transform(iris.data[1:2])
expected = np.array([[ -3.57627869e-07, 1.17000043e+00, 1.01902664e+00, 1.19209290e-07,
0.00000000e+00, 1.19209290e-07, -5.96046448e-08, -2.38418579e-07,
9.74681854e-01, 1.19209290e-07]])
self.assertAllClose(transformed, expected)
def testDNNDropout0_1(self):
# Dropping only a little.
iris = datasets.load_iris()
classifier = learn.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(self):
path = tf.test.get_temp_dir() + '/tmp.saver'
random.seed(42)
iris = datasets.load_iris()
cont_features = [
tf.contrib.layers.real_valued_column('', dimension=4)]
classifier = learn.LinearClassifier(
feature_columns=cont_features, n_classes=3, model_dir=path)
classifier.fit(iris.data, iris.target, steps=200)
def testIris_proba(self):
# If sklearn available.
if log_loss:
random.seed(42)
iris = datasets.load_iris()
classifier = learn.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 testIrisSummaries(self):
iris = datasets.load_iris()
output_dir = tempfile.mkdtemp() + "learn_tests/"
classifier = learn.LinearClassifier(
feature_columns=learn.infer_real_valued_columns_from_input(iris.data),
n_classes=3, model_dir=output_dir)
classifier.fit(iris.data, iris.target, max_steps=100)
score = accuracy_score(iris.target, classifier.predict(iris.data))
self.assertGreater(score, 0.5, "Failed with score = {0}".format(score))
def testIris(self):
path = tf.test.get_temp_dir() + '/tmp.saver'
random.seed(42)
iris = datasets.load_iris()
cont_features = [tf.contrib.layers.real_valued_column('', dimension=4)]
classifier = learn.TensorFlowLinearClassifier(
feature_columns=cont_features, n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
def testIrisSummaries(self):
iris = datasets.load_iris()
output_dir = tempfile.mkdtemp() + "learn_tests/"
classifier = learn.LinearClassifier(
feature_columns=learn.infer_real_valued_columns_from_input(iris.data),
n_classes=3, model_dir=output_dir)
classifier.fit(iris.data, iris.target, max_steps=100)
score = accuracy_score(iris.target, list(classifier.predict(iris.data)))
self.assertGreater(score, 0.5, "Failed with score = {0}".format(score))
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 = learn.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 testIrisContinueTraining(self):
iris = datasets.load_iris()
classifier = learn.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 testNoCheckpoints(self):
path = tf.test.get_temp_dir() + '/tmp/tmp.saver4'
random.seed(42)
iris = datasets.load_iris()
classifier = learn.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):
learn.TensorFlowEstimator.restore(path)
def test_pandas_series(self):
if HAS_PANDAS:
import pandas as pd
random.seed(42)
iris = datasets.load_iris()
data = pd.DataFrame(iris.data)
labels = pd.Series(iris.target)
classifier = learn.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 testCustomModel(self):
path = tf.test.get_temp_dir() + '/tmp.saver2'
random.seed(42)
iris = datasets.load_iris()
def _custom_model(x, y):
return learn.models.logistic_regression(x, y)
classifier = learn.TensorFlowEstimator(model_fn=_custom_model, n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
def testIris(self):
path = tf.test.get_temp_dir() + '/tmp.saver'
random.seed(42)
iris = datasets.load_iris()
classifier = learn.TensorFlowLinearClassifier(n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
new_classifier = learn.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 testDNN(self):
path = tf.test.get_temp_dir() + '/tmp_saver3'
random.seed(42)
iris = datasets.load_iris()
classifier = learn.TensorFlowDNNClassifier(hidden_units=[10, 20, 10], n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
new_classifier = learn.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 testIris_proba(self):
# If sklearn available.
if log_loss:
random.seed(42)
iris = datasets.load_iris()
classifier = learn.LinearClassifier(
feature_columns=learn.infer_real_valued_columns_from_input(iris.data),
n_classes=3)
classifier.fit(iris.data, iris.target, max_steps=250)
score = log_loss(iris.target, classifier.predict_proba(iris.data))
self.assertLess(score, 0.8, "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()
cont_features = [
tf.contrib.layers.real_valued_column('', dimension=4)]
classifier = learn.TensorFlowDNNClassifier(feature_columns=cont_features,
hidden_units=[10, 20, 10],
n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
def testNoCheckpoints(self):
path = tf.test.get_temp_dir() + '/tmp/tmp.saver4'
random.seed(42)
iris = datasets.load_iris()
cont_features = [tf.contrib.layers.real_valued_column('', dimension=4)]
classifier = learn.TensorFlowDNNClassifier(
feature_columns=cont_features,
hidden_units=[10, 20, 10],
n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
def testIris(self):
path = tf.test.get_temp_dir() + '/tmp.saver'
random.seed(42)
iris = datasets.load_iris()
classifier = learn.TensorFlowLinearClassifier(n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
new_classifier = learn.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 testIris_proba(self):
# If sklearn available.
if log_loss:
random.seed(42)
iris = datasets.load_iris()
classifier = learn.LinearClassifier(
feature_columns=learn.infer_real_valued_columns_from_input(iris.data),
n_classes=3)
classifier.fit(iris.data, iris.target, max_steps=250)
score = log_loss(iris.target, list(classifier.predict_proba(iris.data)))
self.assertLess(score, 0.8, "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 learn.models.logistic_regression(x, y)
classifier = learn.TensorFlowEstimator(model_fn=_custom_model, n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
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 = learn.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 testIrisAllVariables(self):
iris = datasets.load_iris()
classifier = learn.TensorFlowLinearClassifier(n_classes=3)
classifier.fit(iris.data, [float(x) for x in iris.target])
self.assertEqual(
classifier.get_variable_names(),
["global_step:0", "logistic_regression/weights:0",
"logistic_regression/bias:0",
"logistic_regression/softmax_classifier/softmax_cross_entropy_loss/"
"value/avg:0",
"learning_rate:0", "logistic_regression/weights/Adagrad:0",
"logistic_regression/bias/Adagrad:0"])
def testIrisContinueTraining(self):
iris = datasets.load_iris()
classifier = learn.LinearClassifier(
feature_columns=learn.infer_real_valued_columns_from_input(iris.data),
n_classes=3)
classifier.fit(iris.data, iris.target, steps=100)
score1 = accuracy_score(iris.target, list(classifier.predict(iris.data)))
classifier.fit(iris.data, iris.target, steps=500)
score2 = accuracy_score(iris.target, list(classifier.predict(iris.data)))
self.assertGreater(
score2, score1,
"Failed with score2 {0} <= score1 {1}".format(score2, score1))
def testIrisContinueTraining(self):
iris = datasets.load_iris()
classifier = learn.LinearClassifier(
feature_columns=learn.infer_real_valued_columns_from_input(iris.data),
n_classes=3)
classifier.fit(iris.data, iris.target, steps=100)
score1 = accuracy_score(iris.target, classifier.predict(iris.data))
classifier.fit(iris.data, iris.target, steps=500)
score2 = accuracy_score(iris.target, classifier.predict(iris.data))
self.assertGreater(
score2, score1,
"Failed with score2 {0} <= score1 {1}".format(score2, score1))
def testIrisContinueTraining(self):
iris = datasets.load_iris()
classifier = learn.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 testIrisAllVariables(self):
iris = datasets.load_iris()
classifier = learn.TensorFlowLinearClassifier(n_classes=3)
classifier.fit(iris.data, [float(x) for x in iris.target])
self.assertEqual(classifier.get_variable_names(), [
"OptimizeLoss/learning_rate",
"OptimizeLoss/logistic_regression/bias/Adagrad",
"OptimizeLoss/logistic_regression/softmax_classifier/"
"softmax_cross_entropy_loss/value/avg",
"OptimizeLoss/logistic_regression/weights/Adagrad", "global_step",
"logistic_regression/bias", "logistic_regression/weights"
])
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, random_state=42)
val_monitor = learn.monitors.ValidationMonitor(
x_val,
y_val,
every_n_steps=50,
early_stopping_rounds=100,
early_stopping_metric="accuracy",
early_stopping_metric_minimize=False,
)
# classifier without early stopping - overfitting
classifier1 = learn.TensorFlowDNNClassifier(hidden_units=[10, 20, 10], n_classes=3, steps=1000)
classifier1.fit(x_train, y_train)
_ = accuracy_score(y_test, classifier1.predict(x_test))
# Full 1000 steps, 12 summaries and no evaluation summary.
# 12 summaries = global_step + first + every 100 out of 1000 steps.
self.assertEqual(12, len(_get_summary_events(classifier1.model_dir)))
with self.assertRaises(ValueError):
_get_summary_events(classifier1.model_dir + "/eval")
# classifier with early stopping - improved accuracy on testing set
classifier2 = learn.TensorFlowDNNClassifier(
hidden_units=[10, 20, 10],
n_classes=3,
steps=2000,
config=tf.contrib.learn.RunConfig(save_checkpoints_secs=1),
)
classifier2.fit(x_train, y_train, monitors=[val_monitor])
_ = accuracy_score(y_val, classifier2.predict(x_val))
_ = accuracy_score(y_test, classifier2.predict(x_test))
# Note, this test is unstable, so not checking for equality.
# See stability_test for examples of stability issues.
if val_monitor.early_stopped:
self.assertLess(val_monitor.best_step, 2000)
# Note, due to validation monitor stopping after the best score occur,
# the accuracy at current checkpoint is less.
# TODO(ipolosukhin): Time machine for restoring old checkpoints?
# flaky, still not always best_value better then score2 value.
# self.assertGreater(val_monitor.best_value, score2_val)
# Early stopped, unstable so checking only < then max.
self.assertLess(len(_get_summary_events(classifier2.model_dir)), 21)
# Eval typically has ~6 events, but it varies based on the run.
self.assertLess(len(_get_summary_events(classifier2.model_dir + "/eval")), 8)
def test_pandas_dataframe(self):
if HAS_PANDAS:
import pandas as pd
random.seed(42)
iris = datasets.load_iris()
data = pd.DataFrame(iris.data)
labels = pd.DataFrame(iris.target)
classifier = learn.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 = learn.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_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.TensorFlowLinearClassifier(
feature_columns=learn.infer_real_valued_columns_from_input(data),
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 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(data)))
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 = learn.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 learn.models.logistic_regression(X, y)
classifier = learn.TensorFlowEstimator(model_fn=custom_model,
n_classes=3)
classifier.fit(iris.data, iris.target)
classifier.save(path)
new_classifier = learn.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))
