def test_init():
with pytest.raises(ValueError):
ToolBox(y[0:5], X, query_type='AllLabels', saving_path=None)
with pytest.raises(NotImplementedError):
ToolBox(y, X, query_type='AllLabel', saving_path=None)
with pytest.raises(Exception):
ToolBox(y, x=None, query_type='Features', saving_path=None)
def test_get_split():
with pytest.raises(Exception):
t = ToolBox(X=X, y=y, query_type='AllLabels', saving_path=None)
a, b, c, d = t.get_split()
tb.split_AL(test_ratio=0.3, initial_label_rate=0.1, split_count=split_count)
a, b, c, d = tb.get_split()
assert (check_one_to_one_correspondence(a, b, c, d))
n_features=20,
n_informative=2,
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=None)
split_count = 5
acebox = ToolBox(X=X, y=y, query_type='AllLabels', saving_path=None)
# split data
acebox.split_AL(test_ratio=0.3,
initial_label_rate=0.1,
split_count=split_count)
# use the default Logistic Regression classifier
model = acebox.get_default_model()
# query 50 times
stopping_criterion = acebox.get_stopping_criterion('num_of_queries', 50)
# use pre-defined strategy, The data matrix is a reference which will not use additional memory
randomStrategy = QueryRandom()
uncertainStrategy = QueryInstanceUncertainty(X, y)
import os
import numpy as np
from sklearn.datasets import load_iris
from acepy.experiment import State, StateIO
from acepy.toolbox import ToolBox
X, y = load_iris(return_X_y=True)
split_count = 5
cur_path = os.path.abspath('.')
toolbox = ToolBox(X=X, y=y, query_type='AllLabels', saving_path=cur_path)
# split data
toolbox.split_AL(test_ratio=0.3, initial_label_rate=0.1, split_count=split_count)
train_ind, test_ind, L_ind, U_ind = toolbox.get_split(round=0)
# -------Initialize StateIO----------
saver = StateIO(round=0, train_idx=train_ind, test_idx=test_ind, init_L=L_ind, init_U=U_ind, saving_path='.')
# or by using toolbox
# saver = toolbox.get_stateio(round=0)
saver.init_L.difference_update([0, 1, 2])
saver.init_U.update([0, 1, 2])
# -------Basic operations------------
st1_batch1 = State(select_index=[1], performance=0.89)
my_value = 'my_entry_info'
st1_batch1.add_element(key='my_entry', value=my_value)
st1_batch2 = State(select_index=[0, 1], performance=0.89)
st2_batch1 = State(select_index=[0], performance=0.89)
st3_batch1 = State(select_index=[2], performance=0.89)