diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py
index 3f32dbaae718bc407956e958b8473ca1e6119679..d63dd748e940dd1bb5e788aeb127f405a2c3227c 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py
@@ -191,7 +191,7 @@ class ClassifiersGenerator(BaseEstimator, TransformerMixin):
class TreeClassifiersGenerator(ClassifiersGenerator):
- def __init__(self, random_state, max_depth=2, self_complemented=True, criterion="gini", splitter="best", n_trees=100, distribution_type="uniform", low=0, high=10):
+ def __init__(self, random_state, max_depth=2, self_complemented=True, criterion="gini", splitter="best", n_trees=100, distribution_type="uniform", low=0, high=10, attributes_ratio=0.6, examples_ratio=0.95):
super(TreeClassifiersGenerator, self).__init__(self_complemented)
self.max_depth=max_depth
self.criterion=criterion
@@ -201,17 +201,32 @@ class TreeClassifiersGenerator(ClassifiersGenerator):
self.distribution_type = distribution_type
self.low = low
self.high = high
+ self.attributes_ratio = attributes_ratio
+ self.examples_ratio = examples_ratio
def fit(self, X, y=None):
estimators_ = []
- self.distributions = np.zeros((self.n_trees, X.shape[0]))
- distrib_method = getattr(self.random_state, self.distribution_type)
+ self.attribute_indices = [self.sub_sample_attributes(X) for _ in range(self.n_trees)]
+ self.example_indices = [self.sub_sample_examples(X) for _ in range(self.n_trees)]
for i in range(self.n_trees):
- self.distributions[i,:] = distrib_method(self.low, self.high, size=X.shape[0])
- estimators_.append(DecisionTreeClassifier(criterion=self.criterion, splitter=self.splitter, max_depth=self.max_depth).fit(X, y, sample_weight=self.distributions[i,:]))
+ estimators_.append(DecisionTreeClassifier(criterion=self.criterion, splitter=self.splitter, max_depth=self.max_depth).fit(X[:, self.attribute_indices[i]][self.example_indices[i], :], y[self.example_indices[i]]))
self.estimators_ = np.asarray(estimators_)
return self
+ def sub_sample_attributes(self, X):
+ n_attributes = X.shape[1]
+ attributes_indices = np.arange(n_attributes)
+ kept_indices = self.random_state.choice(attributes_indices, size=int(self.attributes_ratio*n_attributes), replace=True)
+ return kept_indices
+
+ def sub_sample_examples(self, X):
+ n_examples = X.shape[0]
+ examples_indices = np.arange(n_examples)
+ kept_indices = self.random_state.choice(examples_indices, size=int(self.examples_ratio*n_examples), replace=True)
+ return kept_indices
+
+
+
class StumpsClassifiersGenerator(ClassifiersGenerator):
"""Decision Stump Voters transformer.
@@ -753,8 +768,11 @@ def get_accuracy_graph(plotted_data, classifier_name, file_name, name="Accuracie
class BaseBoost(object):
- def _collect_probas(self, X):
- return np.asarray([clf.predict_proba(X) for clf in self.estimators_generator.estimators_])
+ def _collect_probas(self, X, sub_sampled=False):
+ if self.estimators_generator.__class__.__name__ == "TreeClassifiersGenerator":
+ return np.asarray([clf.predict_proba(X[:,attribute_indices]) for clf, attribute_indices in zip(self.estimators_generator.estimators_, self.estimators_generator.attribute_indices)])
+ else:
+ return np.asarray([clf.predict_proba(X) for clf in self.estimators_generator.estimators_])
def _binary_classification_matrix(self, X):
probas = self._collect_probas(X)
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
index 9156bf763014a37f89778a1e693b6db564a09bcc..c0d43c74edb4e61c6214ea96a687c85c75680338 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
@@ -82,7 +82,6 @@ def ExecMonoview(directory, X, Y, name, labelsNames, classificationIndices, KFol
logging.debug("Start:\t Predicting")
y_train_pred = classifier.predict(X_train)
y_test_pred = classifier.predict(X_test)
- print(np.unique(y_test_pred))
full_labels_pred = np.zeros(Y.shape, dtype=int)-100
for trainIndex, index in enumerate(classificationIndices[0]):
full_labels_pred[index] = y_train_pred[trainIndex]
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/MonoviewUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/MonoviewUtils.py
index 7a9fa525c6ab7c01d977cb31e7f60c557772c7a7..5e80bbc76f20a29ae8e44f1847ec0fde2f919092 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/MonoviewUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/MonoviewUtils.py
@@ -146,7 +146,6 @@ class BaseMonoviewClassifier(object):
else:
return self.weird_strings[param_name](self.get_params()[param_name])
else:
- print(self.get_params())
return str(self.get_params()[param_name])
def getFeatureImportance(self, directory, nb_considered_feats=50):
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/AdaboostPregenTree.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/AdaboostPregenTree.py
index 16378a77d9b32d5ea02f61d071fbc81576f6862e..6f5aaf497956fa831fc044d3ea825882e955e4b4 100644
--- a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/AdaboostPregenTree.py
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/AdaboostPregenTree.py
@@ -18,7 +18,7 @@ __status__ = "Prototype" # Production, Development, Prototype
class AdaboostPregenTree(AdaBoostClassifier, BaseMonoviewClassifier, PregenClassifier):
def __init__(self, random_state=None, n_estimators=50,
- base_estimator=None, n_stumps=1, self_complemeted=True, max_depth=2 , **kwargs):
+ base_estimator=None, n_stumps=1, self_complemeted=True, max_depth=2, **kwargs):
super(AdaboostPregenTree, self).__init__(
random_state=random_state,
n_estimators=n_estimators,
@@ -40,7 +40,7 @@ class AdaboostPregenTree(AdaBoostClassifier, BaseMonoviewClassifier, PregenClass
def fit(self, X, y, sample_weight=None):
begin = time.time()
- pregen_X, pregen_y = self.pregen_voters(X, y)
+ pregen_X, pregen_y = self.pregen_voters(X, y, generator=self.estimators_generator)
super(AdaboostPregenTree, self).fit(pregen_X, pregen_y, sample_weight=sample_weight)
end = time.time()
self.train_time = end-begin
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMPregen.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMPregen.py
index b92cd0445867a269dacc2e094ab8f93d1f60bdf1..dd6224cff74b0f63b5147d550d21e7b756290eec 100644
--- a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMPregen.py
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMPregen.py
@@ -34,7 +34,7 @@ class SCMPregen(scm, BaseMonoviewClassifier, PregenClassifier):
def fit(self, X, y, tiebreaker=None, iteration_callback=None, **fit_params):
pregen_X, _ = self.pregen_voters(X, y)
list_files = os.listdir(".")
- a = int(np.random.randint(0, 10000))
+ a = int(self.random_state.randint(0, 10000))
if "pregen_x"+str(a)+".csv" in list_files:
a = int(np.random.randint(0, 10000))
file_name = "pregen_x" + str(a) + ".csv"
@@ -51,13 +51,14 @@ class SCMPregen(scm, BaseMonoviewClassifier, PregenClassifier):
def predict(self, X):
pregen_X, _ = self.pregen_voters(X)
list_files = os.listdir(".")
- if "pregen_x.csv" in list_files:
- i = 0
- file_name = "pregen_x" + str(i) + ".csv"
+ a = int(self.random_state.randint(0, 10000))
+ if "pregen_x"+str(a)+".csv" in list_files:
+ a = int(np.random.randint(0, 10000))
+ file_name = "pregen_x" + str(a) + ".csv"
while file_name in list_files:
- i += 1
+ a = int(np.random.randint(0, 10000))
else:
- file_name = "pregen_x.csv"
+ file_name = "pregen_x"+str(a)+".csv"
np.savetxt(file_name, pregen_X, delimiter=',')
place_holder = np.genfromtxt(file_name, delimiter=',')
os.remove(file_name)
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMPregenTree.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMPregenTree.py
index 9ce31788d118bc99c3c2c0d46deaa5b929268d2d..fd48a5ff5510edf5cad948704198f3e4fecfdd9a 100644
--- a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMPregenTree.py
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMPregenTree.py
@@ -36,7 +36,7 @@ class SCMPregenTree(scm, BaseMonoviewClassifier, PregenClassifier):
def fit(self, X, y, tiebreaker=None, iteration_callback=None, **fit_params):
pregen_X, _ = self.pregen_voters(X, y, generator="Trees")
list_files = os.listdir(".")
- a = int(np.random.randint(0, 10000))
+ a = int(self.random_state.randint(0, 10000))
if "pregen_x"+str(a)+".csv" in list_files:
a = int(np.random.randint(0, 10000))
file_name = "pregen_x" + str(a) + ".csv"
@@ -51,9 +51,10 @@ class SCMPregenTree(scm, BaseMonoviewClassifier, PregenClassifier):
return self
def predict(self, X):
- pregen_X, _ = self.pregen_voters(X, generator="Trees")
+ pregen_X, _ = self.pregen_voters(X,)
list_files = os.listdir(".")
- a = int(np.random.randint(0, 10000))
+ print(list_files)
+ a = int(self.random_state.randint(0, 10000))
if "pregen_x"+str(a)+".csv" in list_files:
a = int(np.random.randint(0, 10000))
file_name = "pregen_x" + str(a) + ".csv"
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMSparsity.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMSparsity.py
index 62b8ee8ebaa16ea046810f448231ad0c9484a874..27745be1513fbe62cbb3f90bd0a22b36e5a04456 100644
--- a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMSparsity.py
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMSparsity.py
@@ -43,7 +43,7 @@ class SCMSparsity(BaseMonoviewClassifier, PregenClassifier):
def fit(self, X, y, tiebreaker=None, iteration_callback=None, **fit_params):
pregen_X, _ = self.pregen_voters(X, y)
list_files = os.listdir(".")
- a = int(np.random.randint(0, 10000))
+ a = int(self.random_state.randint(0, 10000))
if "pregen_x"+str(a)+".csv" in list_files:
a = int(np.random.randint(0, 10000))
file_name = "pregen_x" + str(a) + ".csv"
@@ -65,13 +65,14 @@ class SCMSparsity(BaseMonoviewClassifier, PregenClassifier):
def predict(self, X):
pregen_X, _ = self.pregen_voters(X,)
list_files = os.listdir(".")
- if "pregen_x.csv" in list_files:
- i = 0
- file_name = "pregen_x" + str(i) + ".csv"
+ a = int(self.random_state.randint(0, 10000))
+ if "pregen_x"+str(a)+".csv" in list_files:
+ a = int(np.random.randint(0, 10000))
+ file_name = "pregen_x" + str(a) + ".csv"
while file_name in list_files:
- i += 1
+ a = int(np.random.randint(0, 10000))
else:
- file_name="pregen_x.csv"
+ file_name = "pregen_x"+str(a)+".csv"
np.savetxt(file_name, pregen_X, delimiter=',')
place_holder = np.genfromtxt(file_name, delimiter=',')
os.remove(file_name)
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMSparsityTree.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMSparsityTree.py
index bd883c61db2c039791f77788f6d8b8f238d7473b..e28a99f1c8faec17f7bac255812d0f0982ea6160 100644
--- a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMSparsityTree.py
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/SCMSparsityTree.py
@@ -43,7 +43,7 @@ class SCMSparsityTree(BaseMonoviewClassifier, PregenClassifier):
def fit(self, X, y, tiebreaker=None, iteration_callback=None, **fit_params):
pregen_X, _ = self.pregen_voters(X, y, generator="Trees")
list_files = os.listdir(".")
- a = int(np.random.randint(0, 10000))
+ a = int(self.random_state.randint(0, 10000))
if "pregen_x"+str(a)+".csv" in list_files:
a = int(np.random.randint(0, 10000))
file_name = "pregen_x" + str(a) + ".csv"
@@ -65,7 +65,7 @@ class SCMSparsityTree(BaseMonoviewClassifier, PregenClassifier):
def predict(self, X):
pregen_X, _ = self.pregen_voters(X, generator="Trees")
list_files = os.listdir(".")
- a = int(np.random.randint(0, 10000))
+ a = int(self.random_state.randint(0, 10000))
if "pregen_x"+str(a)+".csv" in list_files:
a = int(np.random.randint(0, 10000))
file_name = "pregen_x" + str(a) + ".csv"