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):
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, [x for x in iris.target], max_steps=100)
score = accuracy_score(iris.target, list(classifier.predict(iris.data)))
self.assertGreater(score, 0.7, "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, list(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.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.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 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 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:
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))
def testIrisAllVariables(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, [x for x in iris.target], max_steps=100)
self.assertEqual(
classifier.get_variable_names(),
["centered_bias_weight",
"centered_bias_weight/Adagrad",
"global_step",
# Double slashes appear because the column name is empty. If it was not
# empty, the variable names would be "linear/column_name/weight" etc.
"linear//weight",
"linear//weight/Ftrl",
"linear//weight/Ftrl_1",
"linear/bias_weight",
"linear/bias_weight/Ftrl",
"linear/bias_weight/Ftrl_1"])
import tensorflow.contrib.learn.python.learn as learn
from sklearn import datasets, metrics
iris = datasets.load_iris()
feature_columns = learn.infer_real_valued_columns_from_input(iris.data)
classifier = learn.LinearClassifier(n_classes=3, feature_columns=feature_columns)
classifier.fit(iris.data, iris.target, steps=200, batch_size=32)
iris_predictions = list(classifier.predict(iris.data, as_iterable=True))
score = metrics.accuracy_score(iris.target, iris_predictions)
print("Accuracy: %f" % score)
