def test_from_matrix(self):
ds = Dataset.from_matrix(
self._create_matrix(), # data
[ 0, 1, 0 ], # labels
[ 'k1', 'k2', 'k3'], # feature_names
[ 'pos', 'neg'], # label_names
)
expected_labels = ['pos', 'neg', 'pos']
expected_k1s = [1,None,4]
expected_k3s = [2,3,6]
actual_labels = []
actual_k1s = []
actual_k3s = []
for (idx, (label, d)) in ds:
actual_labels.append(label)
actual_k1s.append(dict(d.num_values).get('k1', None))
actual_k3s.append(dict(d.num_values).get('k3', None))
self.assertEqual(expected_labels, actual_labels)
self.assertEqual(expected_k1s, actual_k1s)
self.assertEqual(expected_k3s, actual_k3s)
def test_from_matrix(self):
ds = Dataset.from_matrix(
self._create_matrix(), # data
[0, 1, 0], # labels
['k1', 'k2', 'k3'], # feature_names
['pos', 'neg'], # label_names
)
expected_labels = ['pos', 'neg', 'pos']
expected_k1s = [1, None, 4]
expected_k3s = [2, 3, 6]
actual_labels = []
actual_k1s = []
actual_k3s = []
for (idx, (label, d)) in ds:
actual_labels.append(label)
actual_k1s.append(dict(d.num_values).get('k1', None))
actual_k3s.append(dict(d.num_values).get('k3', None))
self.assertEqual(expected_labels, actual_labels)
self.assertEqual(expected_k1s, actual_k1s)
self.assertEqual(expected_k3s, actual_k3s)
from sklearn.datasets import load_svmlight_files
import sklearn.metrics
import jubakit
from jubakit.classifier import Classifier, Dataset, Config
# 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.
from sklearn.datasets import load_svmlight_files
import sklearn.metrics
import jubakit
from jubakit.classifier import Classifier, Dataset, Config
# 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.