def test_small_moddata_feature_selection_classif(small_moddata):
""" This test creates classifier MODData and test the feature selection method """
x1 = np.array([0] * 500 + [1] * 500 + [2] * 500, dtype='float')
x2 = np.random.choice(2, 1500)
x3 = x1 * x2
x4 = x1 + (x2 * 0.5)
targets = np.array(x1, dtype='int').reshape(-1, 1)
features = np.array([x1, x2, x3, x4]).T
names = ['my_classes']
c_nmi = pd.DataFrame([[1, 0, 0.5, 0.5], [0, 1, 0.5, 0.5],
[0.5, 0.5, 1, 0.5], [0.5, 0.5, 0.5, 1]],
columns=['f1', 'f2', 'f3', 'f4'],
index=['f1', 'f2', 'f3', 'f4'])
classif_md = MODData(['dummy'] * 1500,
targets,
target_names=names,
num_classes={"my_classes": 3})
classif_md.df_featurized = pd.DataFrame(features,
columns=['f1', 'f2', 'f3', 'f4'])
classif_md.feature_selection(n=3, cross_nmi=c_nmi)
assert len(classif_md.get_optimal_descriptors()) == 3
assert classif_md.get_optimal_descriptors() == ['f1', 'f4', 'f3']
def test_precomputed_cross_nmi(small_moddata):
new = MODData(
materials=small_moddata.structures,
targets=small_moddata.targets,
target_names=small_moddata.names,
df_featurized=small_moddata.df_featurized,
)
new.feature_selection(5, use_precomputed_cross_nmi=True)
"structure"] if "structure" in train_df.columns else train_df[
"composition"].map(Composition)
except KeyError:
raise RuntimeError(
f"Could not find any materials data dataset for task {task!r}!"
)
fast_oxid_featurizer = DeBreuck2020Featurizer(fast_oxid=True)
train_data = MODData(
materials=materials.tolist(),
targets=train_df[targets].values,
target_names=targets,
featurizer=fast_oxid_featurizer,
)
train_data.featurize(n_jobs=32)
train_data.feature_selection(n=-1, use_precomputed_cross_nmi=True)
# create model
targets_hierarchy = [[[field for field in targets]]]
weights = {field: 1 for field in targets}
model = EnsembleMODNetModel(targets_hierarchy, weights)
# fit model
if USE_GA:
# you can either use a GA for hyper-parameter optimization or...
from modnet.hyper_opt import FitGenetic
ga = FitGenetic(train_data)
model = ga.run(
size_pop=20,
num_generations=10,