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 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 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 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 testIris(self):
path = tf.test.get_temp_dir() + '/tmp.saver'
random.seed(42)
iris = datasets.load_iris()
classifier = skflow.TensorFlowLinearClassifier(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, 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 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))
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))
