From ac9f952c56e9c6d4518ed9e52dea88be38bf3b07 Mon Sep 17 00:00:00 2001
From: Baptiste Bauvin <baptiste.bauvin@lis-lab.fr>
Date: Mon, 25 Feb 2019 15:16:53 -0500
Subject: [PATCH] Added grad desc modified saved vars
---
.../Monoview/Additions/BoostUtils.py | 27 +++++------
.../Monoview/Additions/QarBoostUtils.py | 39 ++++++++++-----
.../MonoviewClassifiers/CGDesc.py | 48 +++++++++++++++++++
.../MonoviewClassifiers/CGreed.py | 2 +-
.../utils/execution.py | 12 ++++-
5 files changed, 99 insertions(+), 29 deletions(-)
create mode 100644 multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CGDesc.py
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py
index e7242ee6..d3432116 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/BoostUtils.py
@@ -669,15 +669,18 @@ class ConvexProgram(object):
return signs
-def get_accuracy_graph(train_accuracies, classifier_name, file_name, name="Accuracies", bounds=None, bound_name=None, boosting_bound=None, set="train"):
+def get_accuracy_graph(plotted_data, classifier_name, file_name, name="Accuracies", bounds=None, bound_name=None, boosting_bound=None, set="train", zero_to_one=True):
if type(name) is not str:
name = " ".join(name.getConfig().strip().split(" ")[:2])
- if bounds:
- f, ax = plt.subplots(nrows=1, ncols=1)
+ f, ax = plt.subplots(nrows=1, ncols=1)
+ if zero_to_one:
ax.set_ylim(bottom=0.0,top=1.0)
- ax.set_title(name+" during "+set+" for "+classifier_name)
- x = np.arange(len(train_accuracies))
- scat = ax.scatter(x, np.array(train_accuracies), marker=".")
+ ax.set_title(name+" during "+set+" for "+classifier_name)
+ x = np.arange(len(plotted_data))
+ if name == "zero_one_loss":
+ print(plotted_data)
+ scat = ax.scatter(x, np.array(plotted_data), marker=".")
+ if bounds:
if boosting_bound:
scat2 = ax.scatter(x, boosting_bound, marker=".")
scat3 = ax.scatter(x, np.array(bounds), marker=".", )
@@ -687,18 +690,10 @@ def get_accuracy_graph(train_accuracies, classifier_name, file_name, name="Accur
ax.legend((scat, scat2),
(name, bound_name))
# plt.tight_layout()
- f.savefig(file_name)
- plt.close()
else:
- f, ax = plt.subplots(nrows=1, ncols=1)
- ax.set_ylim(bottom=0.0, top=1.0)
- ax.set_title(name + " during "+set+" for " + classifier_name)
- x = np.arange(len(train_accuracies))
- scat = ax.scatter(x, np.array(train_accuracies), marker=".", )
ax.legend((scat,), (name,))
- plt.tight_layout()
- f.savefig(file_name)
- plt.close()
+ f.savefig(file_name)
+ plt.close()
class BaseBoost(object):
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/QarBoostUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/QarBoostUtils.py
index 50eb7948..74ab90e3 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/QarBoostUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/Additions/QarBoostUtils.py
@@ -182,11 +182,13 @@ class ColumnGenerationClassifierQar(BaseEstimator, ClassifierMixin, BaseBoost):
def update_info_containers(self, y, voter_perf, k):
"""Is used at each iteration to compute and store all the needed quantities for later analysis"""
self.example_weights_.append(self.example_weights)
+ self.tau.append(np.sum(np.multiply(self.previous_vote, self.new_voter))/float(self.n_total_examples))
self.previous_vote += self.q * self.new_voter
+ self.norm.append(np.linalg.norm(self.previous_vote)**2)
self.previous_votes.append(self.previous_vote)
self.previous_margins.append(
- np.multiply(y, self.previous_vote))
- self.selected_margins.append(np.sum(np.multiply(y, self.new_voter)))
+ np.sum(np.multiply(y, self.previous_vote))/float(self.n_total_examples))
+ self.selected_margins.append(np.sum(np.multiply(y, self.new_voter))/float(self.n_total_examples))
train_metric = self.plotted_metric.score(y, np.sign(self.previous_vote))
if self.use_r:
bound = self.bounds[-1] * math.sqrt(1 - voter_perf ** 2)
@@ -258,6 +260,7 @@ class ColumnGenerationClassifierQar(BaseEstimator, ClassifierMixin, BaseBoost):
first_voter_index].reshape((m, 1)), copy=True)
self.previous_vote = self.new_voter
+ self.norm.append(np.linalg.norm(self.previous_vote) ** 2)
if self.use_r:
r = self._compute_r(y)
@@ -280,8 +283,11 @@ class ColumnGenerationClassifierQar(BaseEstimator, ClassifierMixin, BaseBoost):
self.previous_margins.append(
- np.multiply(y, self.previous_vote))
+ np.sum(np.multiply(y, self.previous_vote))/float(self.n_total_examples))
self.selected_margins.append(np.sum(np.multiply(y, self.previous_vote)))
+ self.tau.append(
+ np.sum(np.multiply(self.previous_vote, self.new_voter)) / float(
+ self.n_total_examples))
train_metric = self.plotted_metric.score(y, np.sign(self.previous_vote))
if self.use_r:
@@ -339,6 +345,8 @@ class ColumnGenerationClassifierQar(BaseEstimator, ClassifierMixin, BaseBoost):
self.previous_margins = []
self.respected_bound = True
self.selected_margins = []
+ self.tau = []
+ self.norm=[]
def _compute_epsilon(self, y):
"""Updating the error variable, the old fashioned way uses the whole majority vote to update the error"""
@@ -480,21 +488,24 @@ class ColumnGenerationClassifierQar(BaseEstimator, ClassifierMixin, BaseBoost):
"""Used to interpret the functionning of the algorithm"""
if self.step_decisions is not None:
self.get_step_decision_test_graph(directory, y_test)
- get_accuracy_graph(self.voter_perfs[:20], self.__class__.__name__,
- directory + 'voter_perfs.png', "Rs")
+ # get_accuracy_graph(self.voter_perfs[:20], self.__class__.__name__,
+ # directory + 'voter_perfs.png', "Rs")
get_accuracy_graph(self.weights_, self.__class__.__name__,
- directory+'vote_weights.png', "weights")
+ directory+'vote_weights.png', "weights", zero_to_one=False)
get_accuracy_graph(self.c_bounds, self.__class__.__name__,
directory + 'c_bounds.png', "C-Bounds")
- get_accuracy_graph(self.margins, self.__class__.__name__,
- directory + 'margins.png', "Squared Margins")
+ get_accuracy_graph(self.previous_margins, self.__class__.__name__,
+ directory + 'margins.png', "Margins", zero_to_one=False)
get_accuracy_graph(self.selected_margins, self.__class__.__name__,
directory + 'selected_margins.png', "Selected Margins")
- self.disagreements[0] = 0
- get_accuracy_graph(self.disagreements, self.__class__.__name__,
- directory + 'disagreements.png', "disagreements")
+ self.tau[0] = 0
+ get_accuracy_graph(self.tau, self.__class__.__name__,
+ directory + 'disagreements.png', "disagreements", zero_to_one=False)
get_accuracy_graph(self.train_metrics[:-1], self.__class__.__name__,
directory + 'c_bounds_train_metrics.png', self.plotted_metric, self.c_bounds, "C-Bound", self.bounds[:-1])
+ get_accuracy_graph(self.norm, self.__class__.__name__,
+ directory + 'norms.png',
+ "squared 2-norm",zero_to_one=False)
interpretString = getInterpretBase(self, directory, self.__class__.__name__,
self.weights_, self.break_cause)
if self.save_train_data:
@@ -503,6 +514,12 @@ class ColumnGenerationClassifierQar(BaseEstimator, ClassifierMixin, BaseBoost):
np.savetxt(directory + "raw_weights.csv", self.raw_weights, delimiter=',')
np.savetxt(directory + "c_bounds.csv", self.c_bounds, delimiter=',')
np.savetxt(directory + "train_metrics.csv", self.train_metrics, delimiter=',')
+ np.savetxt(directory + "margins.csv", self.previous_margins,
+ delimiter=',')
+ np.savetxt(directory + "disagreements.csv", self.tau,
+ delimiter=',')
+ np.savetxt(directory + "disagreements.csv", self.norm,
+ delimiter=',')
args_dict = dict(
(arg_name, str(self.__dict__[arg_name])) for arg_name in
self.printed_args_name_list)
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CGDesc.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CGDesc.py
new file mode 100644
index 00000000..8a520a0c
--- /dev/null
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CGDesc.py
@@ -0,0 +1,48 @@
+from ..Monoview.MonoviewUtils import BaseMonoviewClassifier, CustomRandint
+from ..Monoview.Additions.BoostUtils import getInterpretBase
+from ..Monoview.Additions.QarBoostUtils import ColumnGenerationClassifierQar
+
+
+class CGDesc(ColumnGenerationClassifierQar, BaseMonoviewClassifier):
+
+ def __init__(self, random_state=None, n_max_iterations=500, n_stumps_per_attribute=10, **kwargs):
+ super(CGDesc, self).__init__(n_max_iterations=n_max_iterations,
+ random_state=random_state,
+ self_complemented=True,
+ twice_the_same=True,
+ c_bound_choice=True,
+ random_start=False,
+ n_stumps_per_attribute=n_stumps_per_attribute,
+ use_r=True,
+ c_bound_sol=True
+ )
+
+ self.param_names = ["n_max_iterations"]
+ self.distribs = [CustomRandint(low=1, high=500)]
+ self.classed_params = []
+ self.weird_strings = {}
+
+ def canProbas(self):
+ """Used to know if the classifier can return label probabilities"""
+ return True
+
+ def getInterpret(self, directory, y_test):
+ return self.getInterpretQar(directory, y_test)
+
+ def get_name_for_fusion(self):
+ return "CGr"
+
+
+def formatCmdArgs(args):
+ """Used to format kwargs for the parsed args"""
+ kwargsDict = {"n_stumps_per_attribute":args.CGD_stumps,
+ "n_max_iterations":args.CGD_n_iter}
+ return kwargsDict
+
+
+def paramsToSet(nIter, randomState):
+ """Used for weighted linear early fusion to generate random search sets"""
+ paramsSet = []
+ for _ in range(nIter):
+ paramsSet.append({})
+ return paramsSet
\ No newline at end of file
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CGreed.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CGreed.py
index b2d7dcad..ed2271d3 100644
--- a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CGreed.py
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/CGreed.py
@@ -9,7 +9,7 @@ class CGreed(ColumnGenerationClassifierQar, BaseMonoviewClassifier):
super(CGreed, self).__init__(n_max_iterations=n_max_iterations,
random_state=random_state,
self_complemented=True,
- twice_the_same=True,
+ twice_the_same=False,
c_bound_choice=True,
random_start=False,
n_stumps_per_attribute=n_stumps_per_attribute,
diff --git a/multiview_platform/MonoMultiViewClassifiers/utils/execution.py b/multiview_platform/MonoMultiViewClassifiers/utils/execution.py
index bd653055..46af685c 100644
--- a/multiview_platform/MonoMultiViewClassifiers/utils/execution.py
+++ b/multiview_platform/MonoMultiViewClassifiers/utils/execution.py
@@ -186,6 +186,16 @@ def parseTheArgs(arguments):
groupCGreed.add_argument('--CGR_n_iter', metavar='INT', type=int, action='store',
help='Set the n_max_iterations parameter for CGreed', default=100)
+ groupCGDesc = parser.add_argument_group('CGDesc arguments')
+ groupCGDesc.add_argument('--CGD_stumps', metavar='INT', type=int,
+ action='store',
+ help='Set the n_stumps_per_attribute parameter for CGreed',
+ default=1)
+ groupCGDesc.add_argument('--CGD_n_iter', metavar='INT', type=int,
+ action='store',
+ help='Set the n_max_iterations parameter for CGreed',
+ default=100)
+
groupQarBoostv3 = parser.add_argument_group('QarBoostv3 arguments')
groupQarBoostv3.add_argument('--QarB3_mu', metavar='FLOAT', type=float, action='store',
help='Set the mu parameter for QarBoostv3', default=0.001)
@@ -395,7 +405,7 @@ def initLogFile(name, views, CL_type, log, debug, label):
if debug:
resultDirectory = "../Results/" + name + "/debug_started_" + time.strftime("%Y_%m_%d-%H_%M_%S") + "_" + label + "/"
else:
- resultDirectory = "../Results/" + name + "/started_" + time.strftime("%Y_%m_%d-%H_%M") +"_" + label + "/"
+ resultDirectory = "../Results/" + name + "/started_" + time.strftime("%Y_%m_%d-%H_%M") + "_" + label + "/"
logFileName = time.strftime("%Y_%m_%d-%H_%M") + "-" + ''.join(CL_type) + "-" + "_".join(
views) + "-" + name + "-LOG"
if os.path.exists(os.path.dirname(resultDirectory)):
--
GitLab