def test_feature_generation():
"""Compare generated features to reference values."""
this_dir = os.path.join(os.path.dirname(__file__))
test_files = [
os.path.join(this_dir, 'data/257141.dat'),
os.path.join(this_dir, 'data/245486.dat'),
os.path.join(this_dir, 'data/247327.dat'),
]
features_extracted = None
values_computed = None
for i, ts_data_file_path in enumerate(test_files):
t, m, e = data_management.parse_ts_data(ts_data_file_path)
features = sft.generate_science_features(t, m, e)
sorted_features = sorted(features.items())
if features_extracted is None:
features_extracted = [f[0] for f in sorted_features]
values_computed = np.zeros((len(test_files),
len(features_extracted)))
values_computed[i,:] = [f[1] for f in sorted_features]
def features_from_csv(filename):
with open(filename) as f:
feature_names = f.readline().strip().split(",")
feature_values = np.loadtxt(f, delimiter=',')
return feature_names, feature_values
this_dir = os.path.join(os.path.dirname(__file__))
features_expected, values_expected = features_from_csv(
os.path.join(this_dir, "data/expected_features.csv"))
npt.assert_equal(features_extracted, features_expected)
npt.assert_array_almost_equal(values_computed, values_expected)
def test_generate_custom_features():
"""Test main generate custom features function"""
t, m, e = data_management.parse_ts_data(pjoin(DATA_DIR,
"dotastro_215153.dat"))
feats = cft.generate_custom_features(pjoin(APP_DATA_DIR, "testfeature1.py"),
t, m, e, use_docker=USE_DOCKER)
npt.assert_almost_equal(feats["avg_mag"], 10.347417647058824)
def test_feature_generation():
"""Compare generated features to reference values."""
this_dir = os.path.join(os.path.dirname(__file__))
test_files = [
os.path.join(this_dir, 'data/257141.dat'),
os.path.join(this_dir, 'data/245486.dat'),
os.path.join(this_dir, 'data/247327.dat'),
]
features_extracted = None
values_computed = None
for i, ts_data_file_path in enumerate(test_files):
t, m, e = data_management.parse_ts_data(ts_data_file_path)
features = generate_features(t, m, e, SCIENCE_FEATS)
sorted_features = sorted(features.items())
if features_extracted is None:
features_extracted = [f[0] for f in sorted_features]
values_computed = np.zeros(
(len(test_files), len(features_extracted)))
values_computed[i, :] = [f[1] for f in sorted_features]
def features_from_csv(filename):
with open(filename) as f:
feature_names = f.readline().strip().split(",")
feature_values = np.loadtxt(f, delimiter=',')
return feature_names, feature_values
this_dir = os.path.join(os.path.dirname(__file__))
features_expected, values_expected = features_from_csv(
os.path.join(this_dir, "data/expected_features.csv"))
npt.assert_equal(features_extracted, features_expected)
npt.assert_array_almost_equal(values_computed, values_expected)
def test_docker_extract_features():
"""Test main Docker extract features method"""
script_fpath = pjoin(APP_DATA_DIR, "testfeature1.py")
ts_datafile = pjoin(DATA_DIR, "dotastro_215153.dat")
t, m, e = data_management.parse_ts_data(ts_datafile)
feats_known_dict = {'t': list(t), 'm': list(m), 'e': list(e)}
results = cft.docker_extract_features(script_fpath, feats_known_dict)
assert (isinstance(results, dict))
npt.assert_almost_equal(results["avg_mag"], 10.347417647058824)
def test_docker_extract_features():
"""Test main Docker extract features method"""
script_fpath = pjoin(APP_DATA_DIR, "testfeature1.py")
ts_datafile = pjoin(DATA_DIR, "dotastro_215153.dat")
t, m, e = data_management.parse_ts_data(ts_datafile)
feats_known_dict = {'t': list(t), 'm': list(m), 'e': list(e)}
results = cft.docker_extract_features(script_fpath, feats_known_dict)
assert(isinstance(results, dict))
npt.assert_almost_equal(results["avg_mag"], 10.347417647058824)
def test_generate_custom_features():
"""Test main generate custom features function"""
t, m, e = data_management.parse_ts_data(
pjoin(DATA_DIR, "dotastro_215153.dat"))
feats = cft.generate_custom_features(pjoin(APP_DATA_DIR,
"testfeature1.py"),
t,
m,
e,
use_docker=USE_DOCKER)
npt.assert_almost_equal(feats["avg_mag"], 10.347417647058824)
def test_parse_ts_data(tmpdir):
"""Test time series data file parsing."""
to_str = lambda X: StringIO('\n'.join([','.join(row)
for row in X.astype(str).tolist()]))
values = np.random.random((10, 3))
t, m, e = data_management.parse_ts_data(to_str(values))
npt.assert_allclose(t, values[:, 0])
npt.assert_allclose(m, values[:, 1])
npt.assert_allclose(e, values[:, 2])
t, m, e = data_management.parse_ts_data(to_str(values[:, :2]))
npt.assert_allclose(t, values[:, 0])
npt.assert_allclose(m, values[:, 1])
npt.assert_allclose(e[1:], e[:-1]) # constant
t, m, e = data_management.parse_ts_data(to_str(values[:, :1]))
npt.assert_allclose(np.diff(t), 1. / (len(values) - 1))
npt.assert_allclose(m, values[:, 0])
npt.assert_allclose(e[1:], e[:-1]) # constant
with pytest.raises(ValueError):
data_management.parse_ts_data(to_str(values[:, []]))
def test_parse_ts_data(tmpdir):
"""Test time series data file parsing."""
to_str = lambda X: StringIO('\n'.join(
[','.join(row) for row in X.astype(str).tolist()]))
values = np.random.random((10, 3))
t, m, e = data_management.parse_ts_data(to_str(values))
npt.assert_allclose(t, values[:, 0])
npt.assert_allclose(m, values[:, 1])
npt.assert_allclose(e, values[:, 2])
t, m, e = data_management.parse_ts_data(to_str(values[:, :2]))
npt.assert_allclose(t, values[:, 0])
npt.assert_allclose(m, values[:, 1])
npt.assert_allclose(e[1:], e[:-1]) # constant
t, m, e = data_management.parse_ts_data(to_str(values[:, :1]))
npt.assert_allclose(np.diff(t), 1. / (len(values) - 1))
npt.assert_allclose(m, values[:, 0])
npt.assert_allclose(e[1:], e[:-1]) # constant
with pytest.raises(ValueError):
data_management.parse_ts_data(to_str(values[:, []]))
def test_parse_ts_data():
"""Test time series data file parsing."""
t, m, e = data_management.parse_ts_data(pjoin(DATA_PATH,
"dotastro_215153.dat"))
assert t.ndim == 1
assert len(t) == len(m) and len(m) == len(e)
def test_parse_ts_data():
"""Test time series data file parsing."""
t, m, e = data_management.parse_ts_data(
pjoin(DATA_PATH, "dotastro_215153.dat"))
assert t.ndim == 1
assert len(t) == len(m) and len(m) == len(e)