def test_altitude():
from aict_tools.configuration import AICTConfig
zd_config = AICTConfig.from_yaml("examples/config_source.yaml")
assert "source_position_zd" in zd_config.disp.columns_to_read_train
alt_config = AICTConfig.from_yaml("examples/config_source_altitude.yaml")
assert "source_position_alt" in alt_config.disp.columns_to_read_train
def test_disp():
from aict_tools.configuration import AICTConfig
c = AICTConfig.from_yaml("examples/config_source.yaml")
assert "cog_x" in c.disp.columns_to_read_apply
def test_disp():
from aict_tools.configuration import AICTConfig
c = AICTConfig.from_yaml('examples/config_source.yaml')
assert 'cog_x' in c.disp.columns_to_read_apply
def test_seperation_results():
from aict_tools.scripts.train_separation_model import main as train
from aict_tools.io import read_telescope_data
from aict_tools.apply import predict_separator
import joblib
from aict_tools.configuration import AICTConfig
configuration_path = 'examples/full_config.yaml'
expectation = pd.read_csv('tests/expected_results.csv')
with tempfile.TemporaryDirectory(prefix='aict_tools_test_') as d:
gamma_path = os.path.join(d, 'gamma.hdf5')
proton_path = os.path.join(d, 'proton.hdf5')
model_path = os.path.join(d, 'test.pkl')
shutil.copy('examples/gamma.hdf5', gamma_path)
shutil.copy('examples/proton.hdf5', proton_path)
runner = CliRunner()
result = runner.invoke(train, [
configuration_path,
gamma_path,
proton_path,
os.path.join(d, 'test.hdf5'),
model_path,
])
assert result.exit_code == 0
config = AICTConfig.from_yaml(configuration_path)
model_config = config.energy
model = joblib.load(model_path)
df = read_telescope_data(
proton_path,
config,
model_config.columns_to_read_apply,
feature_generation_config=model_config.feature_generation)
protons_prediction = predict_separator(
df[model_config.features],
model,
)
df = read_telescope_data(
gamma_path,
config,
model_config.columns_to_read_apply,
feature_generation_config=model_config.feature_generation)
gammas_prediction = predict_separator(
df[model_config.features],
model,
)
np.testing.assert_array_almost_equal(
protons_prediction, expectation['separator_prediction_on_protons'])
np.testing.assert_array_almost_equal(
gammas_prediction, expectation['separator_prediction_on_gammas'])
def test_cta():
from aict_tools.configuration import AICTConfig
cta_config = AICTConfig.from_yaml("examples/cta_full_config.yaml")
assert cta_config.data_format == "CTA"
assert cta_config.pointing_alt_column == "altitude"
assert cta_config.telescopes is not None
def test_separator():
from aict_tools.configuration import AICTConfig
c = AICTConfig.from_yaml("examples/config_separator.yaml")
assert c.energy is None
assert c.disp is None
assert c.separator is not None
def test_full():
from aict_tools.configuration import AICTConfig
c = AICTConfig.from_yaml('examples/full_config.yaml')
assert c.energy is not None
assert c.disp is not None
assert c.separator is not None
def test_full():
from aict_tools.configuration import AICTConfig
c = AICTConfig.from_yaml('examples/full_config.yaml')
assert c.energy is not None
assert c.disp is not None
assert c.separator is not None
def test_energy():
from aict_tools.configuration import AICTConfig
c = AICTConfig.from_yaml('examples/config_energy.yaml')
assert c.energy is not None
assert c.disp is None
assert c.separator is None
assert 'size' in c.energy.columns_to_read_apply
assert 'corsika_event_header_total_energy' not in c.energy.columns_to_read_apply
assert 'corsika_event_header_total_energy' in c.energy.columns_to_read_train
def test_energy():
from aict_tools.configuration import AICTConfig
c = AICTConfig.from_yaml("examples/config_energy.yaml")
assert c.energy is not None
assert c.disp is None
assert c.separator is None
assert "size" in c.energy.columns_to_read_apply
assert "corsika_event_header_total_energy" not in c.energy.columns_to_read_apply
assert "corsika_event_header_total_energy" in c.energy.columns_to_read_train
def test_energy_regression_results():
from aict_tools.scripts.train_energy_regressor import main as train
from aict_tools.io import read_telescope_data
from aict_tools.apply import predict_energy
import joblib
from aict_tools.configuration import AICTConfig
configuration_path = "examples/full_config.yaml"
with tempfile.TemporaryDirectory(prefix="aict_tools_test_") as d:
data_path = os.path.join(d, "gamma.hdf5")
model_path = os.path.join(d, "test.pkl")
shutil.copy("examples/gamma.hdf5", data_path)
runner = CliRunner()
result = runner.invoke(
train,
[
configuration_path,
data_path,
os.path.join(d, "test.hdf5"),
model_path,
],
)
assert result.exit_code == 0
config = AICTConfig.from_yaml(configuration_path)
model_config = config.energy
model = joblib.load(model_path)
df = read_telescope_data(
data_path,
config,
model_config.columns_to_read_apply,
feature_generation_config=model_config.feature_generation,
)
energy_prediction = predict_energy(
df[model_config.features],
model,
log_target=model_config.log_target,
)
expectation = pd.read_csv("tests/expected_results.csv")
np.testing.assert_array_almost_equal(energy_prediction,
expectation["energy_prediction"])
def hdf5_file(tmpdir_factory, request):
fn = tmpdir_factory.mktemp("aict_test_data").join("test_file.hdf5")
shutil.copy("examples/gamma.hdf5", fn)
return fn, "events", AICTConfig.from_yaml("examples/config_energy.yaml")
def test_source():
from aict_tools.configuration import AICTConfig
with raises(ValueError):
AICTConfig.from_yaml("tests/config_source.yaml")
def test_source():
from aict_tools.configuration import AICTConfig
with raises(ValueError):
AICTConfig.from_yaml('tests/config_source.yaml')
from aict_tools.cta_helpers import camera_to_horizontal_cta_simtel, horizontal_to_camera_cta_simtel
from aict_tools.apply import predict_disp
from aict_tools.configuration import AICTConfig
from aict_tools.preprocessing import convert_to_float32, check_valid_rows, calc_true_disp
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='PATH AND STUFF')
parser.add_argument('data_path', type=str)
parser.add_argument('disp_model_path', type=str)
parser.add_argument('sign_model_path', type=str)
parser.add_argument('configuration_path', type=str)
parser.add_argument('output', type=str)
args = parser.parse_args()
config = AICTConfig.from_yaml(args.configuration_path)
model_config = config.disp
disp_model = load_model(args.disp_model_path)
sign_model = load_model(args.sign_model_path)
chunked_frames = []
chunksize = 2000
df_generator = read_telescope_data_chunked(
args.data_path,
config,
chunksize,
model_config.columns_to_read_apply + ['mc_energy'],
feature_generation_config=model_config.feature_generation)
for df_data, start, stop in tqdm(df_generator):
df_data[model_config.delta_column] = np.deg2rad(
from sklearn.externals import joblib
from aict_tools.plotting import (
plot_roc,
plot_probabilities,
plot_precision_recall,
plot_feature_importances,
)
import argparse
import matplotlib.pyplot as plt
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='PATH AND STUFF')
parser.add_argument('model_path', type=str)
parser.add_argument('model_name', type=str)
parser.add_argument('config_path', type=str)
parser.add_argument('output_path', type=str)
args = parser.parse_args()
config = AICTConfig.from_yaml(args.config_path)
if args.model_name == 'disp':
model_config = config.disp
elif args.model_name == 'separator':
model_config = config.separator
features = model_config.features
#features = [f.replace('_', r'\_') for f in features]
model = joblib.load(args.model_path)
#from IPython import embed; embed()
fig, ax = plt.subplots(1, 1)
plot_feature_importances(model, features, ax=ax)
plt.savefig(args.output_path)
def fact_config():
from aict_tools.configuration import AICTConfig
return AICTConfig.from_yaml('examples/config_energy.yaml')
def hdf5_file(tmpdir_factory, request):
fn = tmpdir_factory.mktemp('aict_test_data').join('test_file.hdf5')
shutil.copy('examples/gamma.hdf5', fn)
return fn, 'events', AICTConfig.from_yaml('examples/config_energy.yaml')
def cta_config():
from aict_tools.configuration import AICTConfig
return AICTConfig.from_yaml('examples/cta_config.yaml')