diff --git a/summit/multiview_platform/monoview_classifiers/random_scm.py b/summit/multiview_platform/monoview_classifiers/random_scm.py
index c648c01f40c968cbff0d4bc2a570990cc15b63cd..287cfcabf1ae29a1ea88bbd49b3f2b22be2e4ee1 100644
--- a/summit/multiview_platform/monoview_classifiers/random_scm.py
+++ b/summit/multiview_platform/monoview_classifiers/random_scm.py
@@ -82,7 +82,7 @@ class ScmBagging(RandomScmClassifier, BaseMonoviewClassifier):
max_samples=max_samples,
max_features=max_features,
max_rules=max_rules,
- p_options=p_options,
+ p=p_options,
model_type=model_type,
random_state=random_state)
self.param_names = ["n_estimators", "max_rules", "max_samples", "max_features", "model_type", "p_options", "random_state"]
@@ -94,7 +94,7 @@ class ScmBagging(RandomScmClassifier, BaseMonoviewClassifier):
def set_params(self, p_options=[0.316], **kwargs):
if not isinstance(p_options, list):
p_options = [p_options]
- kwargs["p_options"] = p_options
+ kwargs["p"] = p_options
for parameter, value in iteritems(kwargs):
setattr(self, parameter, value)
return self
diff --git a/summit/multiview_platform/multiview_classifiers/mucombo.py b/summit/multiview_platform/multiview_classifiers/mucombo.py
index 9fbb698c54621f8456e5ae4a74d348134c854a70..2776055ebd88b74cf3ae6a976cc3d7928597233c 100644
--- a/summit/multiview_platform/multiview_classifiers/mucombo.py
+++ b/summit/multiview_platform/multiview_classifiers/mucombo.py
@@ -7,20 +7,20 @@ from ..utils.hyper_parameter_search import CustomRandint
from ..utils.dataset import get_samples_views_indices
from ..utils.base import base_boosting_estimators
-classifier_class_name = "MuCumbo"
+classifier_class_name = "MuCombo"
class MuCombo(BaseMultiviewClassifier, MuComboClassifier):
- def __init__(self, estimator=None,
+ def __init__(self, base_estimator=None,
n_estimators=50,
random_state=None,**kwargs):
BaseMultiviewClassifier.__init__(self, random_state)
- estimator = self.set_base_estim_from_dict(estimator, **kwargs)
- MuComboClassifier.__init__(self, estimator=estimator,
+ base_estimator = self.set_base_estim_from_dict(base_estimator, **kwargs)
+ MuComboClassifier.__init__(self, base_estimator=base_estimator,
n_estimators=n_estimators,
random_state=random_state,)
- self.param_names = ["estimator", "n_estimators", "random_state",]
+ self.param_names = ["base_estimator", "n_estimators", "random_state",]
self.distribs = [base_boosting_estimators,
CustomRandint(5,200), [random_state],]
@@ -43,6 +43,12 @@ class MuCombo(BaseMultiviewClassifier, MuComboClassifier):
view_indices=view_indices)
return MuComboClassifier.predict(self, numpy_X)
- def get_interpretation(self, directory, base_file_name, labels,
- multiclass=False):
+ def get_interpretation(self, directory, base_file_name, y_test, feature_ids,
+ multi_class=False):
return ""
+
+ def set_base_estim_from_dict(self, dict):
+ key, args = list(dict.items())[0]
+
+ if key == "decision_tree":
+ return DecisionTreeClassifier(**args)
\ No newline at end of file
diff --git a/summit/multiview_platform/multiview_classifiers/mumbo.py b/summit/multiview_platform/multiview_classifiers/mumbo.py
index fcaf64ab5ccdbb29867b19740c986ce4118ae8f6..b3933cbaafccec4f62b70208779d46897549ade9 100644
--- a/summit/multiview_platform/multiview_classifiers/mumbo.py
+++ b/summit/multiview_platform/multiview_classifiers/mumbo.py
@@ -13,21 +13,22 @@ from .. import monoview_classifiers
classifier_class_name = "Mumbo"
+
class Mumbo(BaseMultiviewClassifier, MumboClassifier):
- def __init__(self, estimator=None,
+ def __init__(self, base_estimator=None,
n_estimators=50,
random_state=None,
best_view_mode="edge", **kwargs):
BaseMultiviewClassifier.__init__(self, random_state)
- base_estimator = self.set_base_estim_from_dict(estimator, **kwargs)
- MumboClassifier.__init__(self, base_estimator=estimator,
- n_estimators=n_estimators,
- random_state=random_state,
- best_view_mode=best_view_mode)
- self.param_names = ["estimator", "n_estimators", "random_state", "best_view_mode"]
+ base_estimator = self.set_base_estim_from_dict(base_estimator)
+ MumboClassifier.__init__(self, base_estimator=base_estimator,
+ n_estimators=n_estimators,
+ random_state=random_state,
+ best_view_mode=best_view_mode)
+ self.param_names = ["base_estimator", "n_estimators", "random_state", "best_view_mode"]
self.distribs = [base_boosting_estimators,
- CustomRandint(5,200), [random_state], ["edge", "error"]]
+ CustomRandint(5, 200), [random_state], ["edge", "error"]]
def set_params(self, estimator=None, **params):
"""
@@ -42,23 +43,22 @@ class Mumbo(BaseMultiviewClassifier, MumboClassifier):
self.base_estimator = self.set_base_estim_from_dict(estimator)
MumboClassifier.set_params(self, **params)
else:
- MumboClassifier.set_params(self, estimator=estimator, **params)
-
+ MumboClassifier.set_params(self, base_estimator=estimator, **params)
def fit(self, X, y, train_indices=None, view_indices=None):
train_indices, view_indices = get_samples_views_indices(X,
- train_indices,
- view_indices)
+ train_indices,
+ view_indices)
self.used_views = view_indices
self.view_names = [X.get_view_name(view_index)
for view_index in view_indices]
numpy_X, view_limits = X.to_numpy_array(sample_indices=train_indices,
view_indices=view_indices)
- self.view_shapes = [view_limits[ind+1]-view_limits[ind]
- for ind in range(len(self.used_views)) ]
+ self.view_shapes = [view_limits[ind + 1] - view_limits[ind]
+ for ind in range(len(self.used_views))]
return MumboClassifier.fit(self, numpy_X, y[train_indices],
- view_limits)
+ view_limits)
def predict(self, X, sample_indices=None, view_indices=None):
sample_indices, view_indices = get_samples_views_indices(X,
@@ -69,10 +69,11 @@ class Mumbo(BaseMultiviewClassifier, MumboClassifier):
view_indices=view_indices)
return MumboClassifier.predict(self, numpy_X)
- def get_interpretation(self, directory, base_file_name, labels, multiclass=False):
+ def get_interpretation(self, directory, base_file_name, y_test, feature_ids,
+ multi_class=False):
self.view_importances = np.zeros(len(self.used_views))
self.feature_importances_ = [np.zeros(view_shape)
- for view_shape in self.view_shapes]
+ for view_shape in self.view_shapes]
for best_view, estimator_weight, estimator in zip(self.best_views_, self.estimator_weights_, self.estimators_):
self.view_importances[best_view] += estimator_weight
if hasattr(estimator, "feature_importances_"):
@@ -80,26 +81,32 @@ class Mumbo(BaseMultiviewClassifier, MumboClassifier):
importances_sum = sum([np.sum(feature_importances)
for feature_importances
in self.feature_importances_])
- self.feature_importances_ = [feature_importances/importances_sum
+ self.feature_importances_ = [feature_importances / importances_sum
for feature_importances
in self.feature_importances_]
for feature_importances, view_name in zip(self.feature_importances_, self.view_names):
secure_file_path(os.path.join(directory, "feature_importances",
- base_file_name+view_name+"-feature_importances.csv"))
+ base_file_name + view_name + "-feature_importances.csv"))
np.savetxt(os.path.join(directory, "feature_importances",
- base_file_name+view_name+"-feature_importances.csv"),
+ base_file_name + view_name + "-feature_importances.csv"),
feature_importances, delimiter=',')
self.view_importances /= np.sum(self.view_importances)
- np.savetxt(os.path.join(directory, base_file_name+"view_importances.csv"), self.view_importances,
+ np.savetxt(os.path.join(directory, base_file_name + "view_importances.csv"), self.view_importances,
delimiter=',')
sorted_view_indices = np.argsort(-self.view_importances)
interpret_string = "Mumbo used {} iterations to converge.".format(self.best_views_.shape[0])
- interpret_string+= "\n\nViews importance : \n"
+ interpret_string += "\n\nViews importance : \n"
for view_index in sorted_view_indices:
- interpret_string+="- View {} ({}), importance {}\n".format(view_index,
- self.view_names[view_index],
- self.view_importances[view_index])
- interpret_string +="\n The boosting process selected views : \n" + ", ".join(map(str, self.best_views_))
- interpret_string+="\n\n With estimator weights : \n"+ "\n".join(map(str,self.estimator_weights_/np.sum(self.estimator_weights_)))
+ interpret_string += "- View {} ({}), importance {}\n".format(view_index,
+ self.view_names[view_index],
+ self.view_importances[view_index])
+ interpret_string += "\n The boosting process selected views : \n" + ", ".join(map(str, self.best_views_))
+ interpret_string += "\n\n With estimator weights : \n" + "\n".join(
+ map(str, self.estimator_weights_ / np.sum(self.estimator_weights_)))
return interpret_string
+
+ def set_base_estim_from_dict(self, dict):
+ key, args = list(dict.items())[0]
+ if key == "decision_tree":
+ return DecisionTreeClassifier(**args)
diff --git a/summit/multiview_platform/result_analysis/feature_importances.py b/summit/multiview_platform/result_analysis/feature_importances.py
index 36c0eb3514b0fa3db388af10803b60f2f245f011..735455abab7676bd95c9e8d821c7042b028ef6a0 100644
--- a/summit/multiview_platform/result_analysis/feature_importances.py
+++ b/summit/multiview_platform/result_analysis/feature_importances.py
@@ -44,7 +44,7 @@ def get_feature_importances(result, feature_ids=None, view_names=None,):
v_feature_id]
feature_importances["mv"] = pd.DataFrame(index=feat_ids)
if hasattr(classifier_result.clf, 'feature_importances_'):
- feature_importances["mv"][classifier_result.classifier_name] = classifier_result.clf.feature_importances_
+ feature_importances["mv"][classifier_result.classifier_name] = np.concatenate(classifier_result.clf.feature_importances_)
return feature_importances
diff --git a/summit/multiview_platform/utils/dataset.py b/summit/multiview_platform/utils/dataset.py
index 98dc7a39ea552e70b5f555fb0728b650aa26fa5b..beaf5829d86231854630d0f935968b7e450e343a 100644
--- a/summit/multiview_platform/utils/dataset.py
+++ b/summit/multiview_platform/utils/dataset.py
@@ -106,9 +106,9 @@ class Dataset():
return concat_views, view_limits
def select_labels(self, selected_label_names):
- selected_labels = [self.get_label_names(decode=True).index(label_name.decode())
+ selected_labels = [self.get_label_names().index(label_name.decode())
if isinstance(label_name, bytes)
- else self.get_label_names(decode=True).index(label_name)
+ else self.get_label_names().index(label_name)
for label_name in selected_label_names]
selected_indices = np.array([index
for index, label in