def function(params):
"""
Function to be optimized.
"""
# generate config
config = jubatus_config(params)
# create a classifier service.
classifier = Classifier.run(config)
# scoring metric (default accuracy metric)
metric = accuracy_score
# calculate cross-validation score
score = cv_score(classifier, dataset, metric=metric)
# stop the classifier
classifier.stop()
# print score and hyperparameters
print_log(score, params)
# hyperopt only minimize target function and we convert the accuracy score to be minimized.
return -1.0 * score
# 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:
train_test_indices = StratifiedKFold(labels, n_folds=10)
else:
skf = StratifiedKFold(n_splits=10)
train_test_indices = skf.split(labels, labels)
for train_idx, test_idx in train_test_indices:
# Clear the classifier (call `clear` RPC).
# Load LIBSVM files.
# Note that these example files are not included in this repository.
# You can fetch them from: https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass.html#news20
print("Loading LIBSVM files...")
(train_X, train_y, test_X, test_y) = load_svmlight_files(['news20', 'news20.t'])
# Create a Train Dataset.
print("Creating train dataset...")
train_ds = Dataset.from_matrix(train_X, train_y)
# Create a Test Dataset
print("Creating test dataset...")
test_ds = Dataset.from_matrix(test_X, test_y)
# Create a Classifier Service
classifier = Classifier.run(Config())
# Train the classifier.
print("Training...")
for (idx, _) in classifier.train(train_ds):
if idx % 1000 == 0:
print("Training... ({0} %)".format(100 * idx / len(train_ds)))
# Test the classifier.
print("Testing...")
y_true = []
y_pred = []
for (idx, label, result) in classifier.classify(test_ds):
y_true.append(label)
y_pred.append(result[0][0])
if idx % 1000 == 0:
# Load a CSV file.
loader = CSVLoader('iris.csv')
# Define a Schema that defines types for each columns of the CSV file.
schema = Schema({
'Species': Schema.LABEL,
}, Schema.NUMBER)
# Display Schema
print('Schema: {0}'.format(schema))
# Create a Dataset.
dataset = Dataset(loader, schema).shuffle()
n_samples = len(dataset)
n_train_samples = int(n_samples / 2)
# Create a Classifier configuration.
cfg = Config()
# Bulk train-test the classifier.
result = Classifier.train_and_classify(
cfg,
dataset[:n_train_samples],
dataset[n_train_samples:],
sklearn.metrics.classification_report
)
print('---- Classification Report -----------------------------------')
print(result)
'Sepal.Length': Schema.NUMBER,
'Sepal.Width': Schema.NUMBER,
'Petal.Length': Schema.NUMBER,
'Petal.Width': Schema.NUMBER,
})
# Create a Dataset, which is an abstract representation of a set of data
# that can be fed to Services like Classifier. `shuffle()` returns a new
# Dataset whose order of data is shuffled. Note that datasets are immutable
# objects.
dataset = Dataset(loader, schema).shuffle()
# Create a Classifier Service.
# Classifier process starts using a default configuration.
cfg = Config.default()
classifier = Classifier.run(cfg)
# You can also connect to an existing service instead.
#classifier = Classifier('127.0.0.1', 9199)
# Train the classifier with every data in the dataset.
for (idx, label) in classifier.train(dataset):
# You can peek the datum being trained.
print("Train: {0}".format(dataset[idx]))
# Save the trained model file.
print("Saving model file...")
classifier.save('example_snapshot')
# Classify using the same dataset.
for (idx, label, result) in classifier.classify(dataset):
def setUp(self): self._service = Classifier.run(Config())
def setUp(self): self._service = Classifier.run(Config()) self._sh = self._service._shell()
def setUp(self):
self._service = Classifier.run(Config())
def test_simple(self):
classifier = Classifier()
# 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
# Launch Jubatus server using the specified configuration.
classifier = Classifier.run(jubatus_config)
# Train with the dataset.
for _ in classifier.train(dataset):
pass
# Classify with the same dataset.
y_true = []
y_pred = []
for (idx, label, result) in classifier.classify(dataset):
y_true.append(label)
y_pred.append(result[0][0])
classifier.stop()
# Store the metrics for current configuration.
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
# Launch Jubatus server using the specified configuration.
classifier = Classifier.run(jubatus_config)
# Train with the dataset.
for _ in classifier.train(dataset):
pass
# Classify with the same dataset.
y_true = []
y_pred = []
for (idx, label, result) in classifier.classify(dataset):
y_true.append(label)
y_pred.append(result[0][0])
classifier.stop()
# Store the metrics for current configuration.
def test_embedded(self): classifier = Classifier.run(Config(), embedded=True)
# 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()
def draw_decision_surface(i):
midx = int(i / 2)
sidx = int(i / 2) + (i % 2)
# load jubatus prediction model
model_name = 'decision_surface_{}'.format(midx)
from jubakit.model import JubaDump
# Load the digits dataset.
digits = load_digits()
# Create a dataset.
dataset = Dataset.from_array(digits.data, digits.target)
n_samples = len(dataset)
n_train_samples = int(n_samples * 0.7)
train_ds = dataset[:n_train_samples]
test_ds = dataset[n_train_samples:]
# Create a classifier.
config = Config(method='AROW',
parameter={'regularization_weight': 0.1})
classifier = Classifier.run(config)
model_name = 'classifier_digits'
model_path = '/tmp/{}_{}_classifier_{}.jubatus'.format(
classifier._host, classifier._port, model_name)
# show the feature weights of the target label.
target_label = 4
# Initialize summary writer.
writer = SummaryWriter()
# train and test the classifier.
epochs = 100
for epoch in range(epochs):
# train
def setUp(self):
self._service = Classifier.run(Config())
self._sh = self._service._shell()
from jubakit.classifier import Classifier, Dataset, Config
from jubakit.model import JubaDump
# Load the digits dataset.
digits = load_digits()
# Create a dataset.
dataset = Dataset.from_array(digits.data, digits.target)
n_samples = len(dataset)
n_train_samples = int(n_samples * 0.7)
train_ds = dataset[:n_train_samples]
test_ds = dataset[n_train_samples:]
# Create a classifier.
config = Config(method='AROW', parameter={'regularization_weight': 0.1})
classifier = Classifier.run(config)
model_name = 'classifier_digits'
model_path = '/tmp/{}_{}_classifier_{}.jubatus'.format(classifier._host,
classifier._port,
model_name)
# show the feature weights of the target label.
target_label = 4
# Initialize summary writer.
writer = SummaryWriter()
# train and test the classifier.
epochs = 100
for epoch in range(epochs):
