def test_from_array_without_label(self):
ds = Dataset.from_array(
[[10, 20, 30], [20, 10, 50], [40, 10, 30]], # data
None, # labels
['k1', 'k2', 'k3'], # feature_names
['pos', 'neg'], # label_names
)
expected_labels = [None, None, None]
expected_k1s = [10, 20, 40]
actual_labels = []
actual_k1s = []
for (idx, (label, d)) in ds:
actual_labels.append(label)
actual_k1s.append(dict(d.num_values)['k1'])
self.assertEqual(expected_labels, actual_labels)
self.assertEqual(expected_k1s, actual_k1s)
def test_from_array(self):
ds = Dataset.from_array(
[ [10,20,30], [20,10,50], [40,10,30] ], # data
[ 0, 1, 0 ], # labels
['k1', 'k2', 'k3'], # feature_names
['pos', 'neg'], # label_names
)
expected_labels = ['pos', 'neg', 'pos']
expected_k1s = [10, 20, 40]
actual_labels = []
actual_k1s = []
for (idx, (label, d)) in ds:
actual_labels.append(label)
actual_k1s.append(dict(d.num_values)['k1'])
self.assertEqual(expected_labels, actual_labels)
self.assertEqual(expected_k1s, actual_k1s)
from jubakit.classifier import Classifier, Dataset, Config
# switch StratifiedKFold API
sklearn_version = int(sklearn.__version__.split('.')[1])
if sklearn_version < 18:
from sklearn.cross_validation import StratifiedKFold
else:
from sklearn.model_selection import StratifiedKFold
# Load built-in `iris` dataset from scikit-learn.
iris = sklearn.datasets.load_iris()
# Convert it into jubakit Dataset.
#dataset = Dataset.from_array(iris.data, iris.target)
# ... or, optionally you can assign feature/label names to improve human-readbility.
dataset = Dataset.from_array(iris.data, iris.target, iris.feature_names,
iris.target_names)
# Shuffle the dataset, as the dataset is sorted by label.
dataset = dataset.shuffle()
# Create a Classifier Service.
# Classifier process starts using a default configuration.
classifier = Classifier.run(Config())
# Prepare arrays to keep true/predicted labels to display a report later.
true_labels = []
predicted_labels = []
# Run stratified K-fold validation.
labels = list(dataset.get_labels())
if sklearn_version < 18:
# switch StratifiedKFold API
sklearn_version = int(sklearn.__version__.split('.')[1])
if sklearn_version < 18:
from sklearn.cross_validation import StratifiedKFold
else:
from sklearn.model_selection import StratifiedKFold
# Load built-in `iris` dataset from scikit-learn.
iris = sklearn.datasets.load_iris()
# Convert it into jubakit Dataset.
#dataset = Dataset.from_array(iris.data, iris.target)
# ... or, optionally you can assign feature/label names to improve human-readbility.
dataset = Dataset.from_array(iris.data, iris.target, iris.feature_names, iris.target_names)
# Shuffle the dataset, as the dataset is sorted by label.
dataset = dataset.shuffle()
# Create a Classifier Service.
# Classifier process starts using a default configuration.
classifier = Classifier.run(Config())
# Prepare arrays to keep true/predicted labels to display a report later.
true_labels = []
predicted_labels = []
# Run stratified K-fold validation.
labels = list(dataset.get_labels())
if sklearn_version < 18:
===================================================
In this example we show classification using Digits dataset.
"""
import sklearn.datasets
import sklearn.metrics
import jubakit
from jubakit.classifier import Classifier, Dataset, Config
# Load the digits dataset.
digits = sklearn.datasets.load_digits()
# Create a Dataset.
dataset = Dataset.from_array(digits.data, digits.target)
n_samples = len(dataset)
n_train_samples = int(n_samples / 2)
# Create a Classifier Service
cfg = Config(method='AROW', parameter={'regularization_weight': 0.1})
classifier = Classifier.run(cfg)
print("Started Service: {0}".format(classifier))
# Train the classifier using the first half of the dataset.
train_ds = dataset[:n_train_samples]
print("Training...: {0}".format(train_ds))
for _ in classifier.train(train_ds):
pass
n_redundant=2,
n_repeated=0,
n_classes=2,
n_clusters_per_class=2,
weights=None,
flip_y=0.01,
class_sep=1.0,
hypercube=True,
shift=0.0,
scale=1.0,
shuffle=True,
random_state=0, # fixed seed
)
# Convert arrays into jubakit Dataset.
dataset = Dataset.from_array(X, y)
# Try finding the best classifier parameter.
param2metrics = {}
for method in ['AROW', 'NHERD', 'CW']:
for rw in [0.0001, 0.001, 0.01, 0.1, 1.0, 10.0]:
print('Running ({0} / regularization_weight = {1})...'.format(method, rw))
# Create a config data structure.
jubatus_config = Config(method=method, parameter={'regularization_weight': rw})
# It is equivalent to:
#jubatus_config = Config.default()
#jubatus_config['method'] = method
#jubatus_config['parameter']['regularization_weight'] = rw
===================================================
In this example we show classification using Digits dataset.
"""
import sklearn.datasets
import sklearn.metrics
import jubakit
from jubakit.classifier import Classifier, Dataset, Config
# Load the digits dataset.
digits = sklearn.datasets.load_digits()
# Create a Dataset.
dataset = Dataset.from_array(digits.data, digits.target)
n_samples = len(dataset)
n_train_samples = int(n_samples / 2)
# Create a Classifier Service
cfg = Config(method='AROW', parameter={'regularization_weight': 0.1})
classifier = Classifier.run(cfg)
print("Started Service: {0}".format(classifier))
# Train the classifier using the first half of the dataset.
train_ds = dataset[:n_train_samples]
print("Training...: {0}".format(train_ds))
for _ in classifier.train(train_ds): pass
# Test the classifier using the last half of the dataset.
n_redundant=2,
n_repeated=0,
n_classes=2,
n_clusters_per_class=2,
weights=None,
flip_y=0.01,
class_sep=1.0,
hypercube=True,
shift=0.0,
scale=1.0,
shuffle=True,
random_state=0, # fixed seed
)
# Convert arrays into jubakit Dataset.
dataset = Dataset.from_array(X, y)
# Try finding the best classifier parameter.
param2metrics = {}
for method in ['AROW', 'NHERD', 'CW']:
for rw in [0.0001, 0.001, 0.01, 0.1, 1.0, 10.0]:
print('Running ({0} / regularization_weight = {1})...'.format(
method, rw))
# Create a config data structure.
jubatus_config = Config(method=method,
parameter={'regularization_weight': rw})
# It is equivalent to:
#jubatus_config = Config.default()
#jubatus_config['method'] = method
le.fit(labels)
c = le.transform(y)
# scale dataset with (mean, variance) = (0, 1)
scaler = StandardScaler()
X = scaler.fit_transform(X)
# calculate the domain
X_min = X.min(axis=0)
#X_min = np.ones(X.shape[1])
X_max = X.max(axis=0)
X0, X1 = np.meshgrid(np.linspace(X_min[0], X_max[0], meshsize),
np.linspace(X_min[1], X_max[1], meshsize))
# make training dataset
dataset = Dataset.from_array(X, y)
# make mesh dataset to plot decision surface
contourf_dataset = Dataset.from_array(np.c_[X0.ravel(), X1.ravel()])
# setup and run jubatus
config = Config(method=method,
parameter={'regularization_weight': regularization_weight})
classifier = Classifier.run(config, port=port)
# construct classifier prediction models and dump model weights
for i, _ in enumerate(classifier.train(dataset)):
model_name = 'decision_surface_{}'.format(i)
classifier.save(name=model_name)
# prepare figure
fig, ax = plt.subplots()