def test_foldsplitter(self):
taskids = np.array([0 for _ in range(6)] + [1 for _ in range(6)])
times = np.array(range(6) + range(6))
X = np.transpose(np.vstack((times, taskids)))
np.testing.assert_array_equal(list(foldsplitter(X, -1, [1, 2])), [
(np.array([
True, False, False, False, False, False, True, True, True,
True, True, True
],
dtype=bool),
np.array([
False, True, True, True, True, True, False, False, False,
False, False, False
],
dtype=bool)),
(np.array([
True, True, False, False, False, False, True, True, True, True,
True, True
],
dtype=bool),
np.array([
False, False, True, True, True, True, False, False, False,
False, False, False
],
dtype=bool)),
(np.array([
True, True, True, True, True, True, True, False, False, False,
False, False
],
dtype=bool),
np.array([
False, False, False, False, False, False, False, True, True,
True, True, True
],
dtype=bool)),
(np.array([
True, True, True, True, True, True, True, True, False, False,
False, False
],
dtype=bool),
np.array([
False, False, False, False, False, False, False, False, True,
True, True, True
],
dtype=bool))
])
def test_foldsplitter(self):
taskids=np.array([0 for _ in range(6)]+[1 for _ in range(6)])
times=np.array(range(6)+range(6))
X=np.transpose(np.vstack((times, taskids)))
np.testing.assert_array_equal(list(foldsplitter(X, -1, [1, 2])),
[(np.array([ True, False, False, False, False, False, True, True, True,
True, True, True], dtype=bool),
np.array([False, True, True, True, True, True, False, False, False,
False, False, False], dtype=bool)),
(np.array([ True, True, False, False, False, False, True, True, True,
True, True, True], dtype=bool),
np.array([False, False, True, True, True, True, False, False, False,
False, False, False], dtype=bool)),
(np.array([ True, True, True, True, True, True, True, False, False,
False, False, False], dtype=bool),
np.array([False, False, False, False, False, False, False, True, True,
True, True, True], dtype=bool)),
(np.array([ True, True, True, True, True, True, True, True, False,
False, False, False], dtype=bool),
np.array([False, False, False, False, False, False, False, False, True,
True, True, True], dtype=bool))])
methodname=sys.argv[2]
train_set_ratios=[int(sys.argv[3])]
fname=sys.argv[4]
random_restarts=int(sys.argv[5])
filter_retweets=bool(int(sys.argv[6]))
if len(sys.argv)>=8:
#if random number generator seed has been passed
seed=int(sys.argv[7])
import numpy as np
np.random.seed(seed)
else:
initialize_seed_with_currtime()
X, y, header = load_data(fname, labels_to_keep=LABELS)
_, _, postprocessed_task_column_id, _=extract_feature_indices(header)
splitter = foldsplitter(X, postprocessed_task_column_id, train_set_ratios)
evaluation_measures = [sklearn.metrics.accuracy_score]
tasks_number=len(set(X[:, postprocessed_task_column_id]))
methodsmultitask, methodnamesmultitask = get_methods_multitask(tasks_number, header, random_restarts=random_restarts)
methodssingletask, methodnamessingletask = get_methods_singletask(header, random_restarts=random_restarts)
if methodname != None:
#if we are interested in keeping only one method
methodnamesmultitask, methodsmultitask = filter_methods(methodnamesmultitask, methodsmultitask, methodname)
methodnamessingletask, methodssingletask = filter_methods(methodnamessingletask, methodssingletask, methodname)
experiment = Experiment(X, y, train_set_ratios, foldtorun, splitter, evaluation_measures, methodnamesmultitask, methodsmultitask,
methodnamessingletask, methodssingletask, print_metrics=print_metrics_multiclass,
random_restarts=random_restarts, results={}, header=header, filter_retweets=filter_retweets)
experiment.run()
methodname = sys.argv[2]
train_set_ratios = [int(sys.argv[3])]
fname = sys.argv[4]
random_restarts = int(sys.argv[5])
filter_retweets = bool(int(sys.argv[6]))
if len(sys.argv) >= 8:
#if random number generator seed has been passed
seed = int(sys.argv[7])
import numpy as np
np.random.seed(seed)
else:
initialize_seed_with_currtime()
X, y, header = load_data(fname, labels_to_keep=LABELS)
_, _, postprocessed_task_column_id, _ = extract_feature_indices(header)
splitter = foldsplitter(X, postprocessed_task_column_id, train_set_ratios)
evaluation_measures = [sklearn.metrics.accuracy_score]
tasks_number = len(set(X[:, postprocessed_task_column_id]))
methodsmultitask, methodnamesmultitask = get_methods_multitask(
tasks_number, header, random_restarts=random_restarts)
methodssingletask, methodnamessingletask = get_methods_singletask(
header, random_restarts=random_restarts)
if methodname != None:
#if we are interested in keeping only one method
methodnamesmultitask, methodsmultitask = filter_methods(
methodnamesmultitask, methodsmultitask, methodname)
methodnamessingletask, methodssingletask = filter_methods(
methodnamessingletask, methodssingletask, methodname)
