diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py
index 877e262d82110305e876b0d674b66312cc55c237..3ac3c046ed335487c7e43339241cd1381d0501f0 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py
@@ -782,7 +782,6 @@ class BaseBoost(object):
def _collect_probas(self, X, sub_sampled=False):
if self.estimators_generator.__class__.__name__ == "TreeClassifiersGenerator":
- print("frogom")
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_])
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/CGDescUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/CGDescUtils.py
index 9b1f8f9aac0e2b750ffa1ade0d8c8565705fd7d2..a3e53c6b873eec0f9fd3e7a9933d16b644a99140 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/CGDescUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/CGDescUtils.py
@@ -154,7 +154,6 @@ class ColumnGenerationClassifierQar(BaseEstimator, ClassifierMixin, BaseBoost):
end = time.time()
self.predict_time = end - start
self.step_predict(classification_matrix)
- print(np.unique(signs_array))
return signs_array
def step_predict(self, classification_matrix):
@@ -490,7 +489,6 @@ class ColumnGenerationClassifierQar(BaseEstimator, ClassifierMixin, BaseBoost):
return 1.0 / n_examples * np.ones((n_examples,))
def get_step_decision_test_graph(self, directory, y_test):
- print(np.unique(y_test))
np.savetxt(directory + "y_test_step.csv", self.step_decisions, delimiter=',')
step_metrics = []
for step_index in range(self.step_decisions.shape[1]-1):
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/CQBoostUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/CQBoostUtils.py
index 401bcdcabef83269739d6d8f85e165b3dd1052c8..6560eb1a4eee3c279dad43cbbf4b1f0a07376d93 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/CQBoostUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/CQBoostUtils.py
@@ -36,7 +36,6 @@ class ColumnGenerationClassifier(BaseEstimator, ClassifierMixin, BaseBoost):
elif self.estimators_generator is "Trees":
self.estimators_generator = TreeClassifiersGenerator(max_depth=self.max_depth, n_trees=self.n_stumps, self_complemented=True)
- print(self.max_depth, self.n_stumps)
self.estimators_generator.fit(X, y)
self.classification_matrix = self._binary_classification_matrix(X)
self.c_bounds = []
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/MinCQUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/MinCQUtils.py
index afa55be54a04bf63d9e6a0e3f8ad018e37a4eacb..0e8479a394c1e0d51820eae2e43322e8ebdf26d7 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/MinCQUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/MinCQUtils.py
@@ -272,7 +272,6 @@ class RegularizedBinaryMinCqClassifier(MinCqClassifier):
# Keep learning information for further use.
self.learner_info_ = {}
- print(np.unique(weights))
# We count the number of non-zero weights, including the implicit voters.
# TODO: Verify how we define non-zero weights here, could be if the weight is near 1/2n.
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/PregenUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/PregenUtils.py
index 92a603e8d98c8759f77209925f12cf49deb8fe34..6011f7c6560d246634ad13df8632eb0168a18231 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/PregenUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/PregenUtils.py
@@ -1,7 +1,7 @@
from ..MonoviewUtils import change_label_to_minus
from .BoostUtils import StumpsClassifiersGenerator, BaseBoost, TreeClassifiersGenerator
-import numpy as np
+
class PregenClassifier(BaseBoost):
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
index c0d43c74edb4e61c6214ea96a687c85c75680338..156c187a8e13c5071085a833a81db9637b031099 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/ExecClassifMonoView.py
@@ -52,6 +52,7 @@ def ExecMonoview(directory, X, Y, name, labelsNames, classificationIndices, KFol
learningRate, \
labelsString, \
outputFileName = initConstants(args, X, classificationIndices, labelsNames, name, directory)
+
logging.debug("Done:\t Loading data")
logging.debug("Info:\t Classification - Database:" + str(name) + " Feature:" + str(feat) + " train ratio:"
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CGDesc.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CGDesc.py
index 76ba5daee5cbb3ace48f8cfd16f4bb1d0a96c804..ed2d9536c81e51aa4f7063ae08279dfedd0b1a85 100644
--- a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CGDesc.py
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CGDesc.py
@@ -18,7 +18,7 @@ class CGDesc(ColumnGenerationClassifierQar, BaseMonoviewClassifier):
estimators_generator="Stumps"
)
self.param_names = ["n_max_iterations", "n_stumps", "random_state"]
- self.distribs = [CustomRandint(low=2, high=1000), [n_stumps],
+ self.distribs = [CustomRandint(low=2, high=500), [n_stumps],
[random_state]]
self.classed_params = []
self.weird_strings = {}
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CQBoost.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CQBoost.py
index dfed2a182b5e9c91bc090a1948c2f526467ccafe..14d654531b5183944f1e4913941ccb65229089e9 100644
--- a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CQBoost.py
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CQBoost.py
@@ -7,13 +7,13 @@ import os
class CQBoost(ColumnGenerationClassifier, BaseMonoviewClassifier):
- def __init__(self, random_state=None, mu=0.01, epsilon=1e-06, n_stumps=1, n_max_iterations=100, **kwargs):
+ def __init__(self, random_state=None, mu=0.01, epsilon=1e-06, n_stumps=1, n_max_iterations=None, **kwargs):
super(CQBoost, self).__init__(
random_state=random_state,
mu=mu,
epsilon=epsilon,
estimators_generator="Stumps",
- n_max_iterations=100
+ n_max_iterations=n_max_iterations
)
self.param_names = ["mu", "epsilon", "n_stumps", "random_state", "n_max_iterations"]
self.distribs = [CustomUniform(loc=0.5, state=1.0, multiplier="e-"),
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CQBoostTree.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CQBoostTree.py
index b7a8dad5c24cf964c91448cb31b8eee002411f09..25c2a5ea5412d1ffcd6752c6909375b0d5deda28 100644
--- a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CQBoostTree.py
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CQBoostTree.py
@@ -8,7 +8,6 @@ import os
class CQBoostTree(ColumnGenerationClassifier, BaseMonoviewClassifier):
def __init__(self, random_state=None, mu=0.01, epsilon=1e-06, n_stumps=1, max_depth=2, n_max_iterations=100, **kwargs):
- print(n_max_iterations)
super(CQBoostTree, self).__init__(
random_state=random_state,
mu=mu,
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/DecisionTreePregen.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/DecisionTreePregen.py
new file mode 100644
index 0000000000000000000000000000000000000000..14f554e5281b3b267188f4feed31293e16c616c6
--- /dev/null
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/DecisionTreePregen.py
@@ -0,0 +1,84 @@
+from sklearn.tree import DecisionTreeClassifier
+import time
+import numpy as np
+
+from ..Monoview.MonoviewUtils import CustomRandint, BaseMonoviewClassifier, change_label_to_minus, change_label_to_zero
+from ..Monoview.Additions.PregenUtils import PregenClassifier
+
+# Author-Info
+__author__ = "Baptiste Bauvin"
+__status__ = "Prototype" # Production, Development, Prototype
+
+
+class DecisionTreePregen(DecisionTreeClassifier, BaseMonoviewClassifier, PregenClassifier):
+
+ def __init__(self, random_state=None, max_depth=None,
+ criterion='gini', splitter='best', n_stumps=1, self_complemented=True, **kwargs):
+ super(DecisionTreePregen, self).__init__(
+ max_depth=max_depth,
+ criterion=criterion,
+ splitter=splitter,
+ random_state=random_state
+ )
+ self.estimators_generator = "Stumps"
+ self.n_stumps = n_stumps
+ self.self_complemented = self_complemented
+ self.param_names = ["max_depth", "criterion", "splitter",'random_state',
+ 'n_stumps']
+ self.classed_params = []
+ self.distribs = [CustomRandint(low=1, high=300),
+ ["gini", "entropy"],
+ ["best", "random"], [random_state], [n_stumps]]
+ self.weird_strings = {}
+
+ def fit(self, X, y, sample_weight=None, check_input=True,
+ X_idx_sorted=None):
+ begin = time.time()
+ pregen_X, pregen_y = self.pregen_voters(X, y)
+ super(DecisionTreePregen, self).fit(pregen_X, pregen_y,
+ sample_weight=sample_weight,
+ check_input=check_input,
+ X_idx_sorted=X_idx_sorted)
+ end = time.time()
+ self.train_time = end - begin
+ self.train_shape = pregen_X.shape
+ return self
+
+ def predict(self, X, check_input=True):
+ begin = time.time()
+ pregen_X, _ = self.pregen_voters(X)
+ pred = super(DecisionTreePregen, self).predict(pregen_X, check_input=check_input)
+ end = time.time()
+ self.pred_time = end - begin
+ return change_label_to_zero(pred)
+
+ def canProbas(self):
+ """Used to know if the classifier can return label probabilities"""
+ return True
+
+ def getInterpret(self, directory, y_test):
+ interpretString = ""
+ interpretString += self.getFeatureImportance(directory)
+ np.savetxt(directory + "times.csv",
+ np.array([self.train_time, self.pred_time]), delimiter=',')
+ return interpretString
+
+
+def formatCmdArgs(args):
+ """Used to format kwargs for the parsed args"""
+ kwargsDict = {"max_depth": args.DTP_depth,
+ "criterion": args.DTP_criterion,
+ "splitter": args.DTP_splitter,
+ "n_stumps":args.DTP_stumps}
+ return kwargsDict
+
+
+def paramsToSet(nIter, randomState):
+ paramsSet = []
+ for _ in range(nIter):
+ paramsSet.append({"max_depth": randomState.randint(1, 300),
+ "criterion": randomState.choice(["gini", "entropy"]),
+ "splitter": randomState.choice(["best", "random"])})
+ return paramsSet
+
+
diff --git a/multiview_platform/MonoMultiViewClassifiers/utils/execution.py b/multiview_platform/MonoMultiViewClassifiers/utils/execution.py
index 3e235fae6f1c764d54bd2bcee7c93fb36e6bfce0..189de2032fb85bfcfdee21c0f040194bf57aefd9 100644
--- a/multiview_platform/MonoMultiViewClassifiers/utils/execution.py
+++ b/multiview_platform/MonoMultiViewClassifiers/utils/execution.py
@@ -157,6 +157,20 @@ def parseTheArgs(arguments):
groupDT.add_argument('--DT_splitter', metavar='STRING', action='store',
help='Determine criterion for Decision Trees', default="random")
+ groupDTP = parser.add_argument_group('Decision Trees pregen arguments')
+ groupDTP.add_argument('--DTP_depth', metavar='INT', type=int, action='store',
+ help='Determine max depth for Decision Trees',
+ default=3)
+ groupDTP.add_argument('--DTP_criterion', metavar='STRING', action='store',
+ help='Determine max depth for Decision Trees',
+ default="entropy")
+ groupDTP.add_argument('--DTP_splitter', metavar='STRING', action='store',
+ help='Determine criterion for Decision Trees',
+ default="random")
+ groupDTP.add_argument('--DTP_stumps', metavar='INT', type=int, action='store',
+ help='Determine the number of stumps for Decision Trees pregen',
+ default=1)
+
groupSGD = parser.add_argument_group('SGD arguments')
groupSGD.add_argument('--SGD_alpha', metavar='FLOAT', type=float, action='store',
help='Determine alpha for SGDClassifier', default=0.1)