diff --git a/config_files/config_cuisine.yml b/config_files/config_cuisine.yml
index 656d2d87e2f506e1687a057dd68a25bc3a198f9c..0bab158fc3457b297cabb806f5d6bf6dad2b2b99 100644
--- a/config_files/config_cuisine.yml
+++ b/config_files/config_cuisine.yml
@@ -22,7 +22,7 @@ nb_folds: 5
nb_class: 2
classes:
type: ["monoview"]
-algos_monoview: ["scm_bagging",]
+algos_monoview: ["scm_bagging", "scm", "cb_boost", "adaboost"]
algos_multiview: ["group_scm"]
stats_iter: 2
metrics:
@@ -30,5 +30,8 @@ metrics:
f1_score:
average: 'binary'
metric_princ: "f1_score"
-hps_type: "Random"
-hps_args: {}
\ No newline at end of file
+hps_type: "None"
+hps_args: {}
+
+cb_boost:
+ n_stumps: 10
\ No newline at end of file
diff --git a/summit/multiview_platform/monoview_classifiers/additions/CBBoostUtils.py b/summit/multiview_platform/monoview_classifiers/additions/CBBoostUtils.py
index 88ec05acf5e868817e9919b7e5b39d8574a92ec6..704a58951fb617738b42160019c2b311410ce268 100644
--- a/summit/multiview_platform/monoview_classifiers/additions/CBBoostUtils.py
+++ b/summit/multiview_platform/monoview_classifiers/additions/CBBoostUtils.py
@@ -57,6 +57,7 @@ class CBBoostClassifier(BaseEstimator, ClassifierMixin, BaseBoost):
self.step_prod = None
self.n_max_iterations = n_max_iterations
self.estimators_generator = estimators_generator
+ self.estimators_generator_name = estimators_generator
self.self_complemented = self_complemented
self.twice_the_same = twice_the_same
self.random_start = random_start
@@ -72,6 +73,7 @@ class CBBoostClassifier(BaseEstimator, ClassifierMixin, BaseBoost):
self.mincq_tracking = mincq_tracking
def fit(self, X, y):
+ self.n_features = X.shape[1]
formatted_X, formatted_y = self.format_X_y(X, y)
self.init_info_containers()
@@ -131,6 +133,11 @@ class CBBoostClassifier(BaseEstimator, ClassifierMixin, BaseBoost):
end = time.time()
self.train_time = end - start
+ self.feature_importances_ = np.zeros(X.shape[1])
+ for iter_index, iteration_feature_imporances in enumerate(self.chosen_features):
+ for feature_index, importance in iteration_feature_imporances:
+ self.feature_importances_[feature_index] += importance*self.weights_[iter_index]
+ self.feature_importances_ /= np.sum(self.feature_importances_)
return self
def predict(self, X):
@@ -239,6 +246,13 @@ class CBBoostClassifier(BaseEstimator, ClassifierMixin, BaseBoost):
def append_new_voter(self, new_voter_index):
"""Used to append the voter to the majority vote"""
self.chosen_columns_.append(new_voter_index)
+ if self.estimators_generator_name=="Stumps":
+ self.chosen_features.append([(int(new_voter_index%(self.n_stumps*self.n_features)/self.n_stumps), 1)])
+ elif self.estimators_generator_name == "Trees":
+ self.chosen_features.append([(self.estimators_generator.attribute_indices[new_voter_index][fake_ind], importance)
+ for fake_ind, importance
+ in enumerate(self.estimators_generator.estimators_[new_voter_index].feature_importances_)
+ if importance>0])
self.new_voter = self.classification_matrix[:, new_voter_index].reshape(
(self.n_total_examples, 1))
@@ -309,6 +323,7 @@ class CBBoostClassifier(BaseEstimator, ClassifierMixin, BaseBoost):
def init_info_containers(self):
"""Initialize the containers that will be collected at each iteration for the analysis"""
self.weights_ = []
+ self.chosen_features = []
self.chosen_columns_ = []
self.fobidden_columns = []
self.c_bounds = []
@@ -468,7 +483,7 @@ class CBBoostClassifier(BaseEstimator, ClassifierMixin, BaseBoost):
os.path.join(directory, 'step_test_c_bounds.png'),
"C_bound", set="test")
- def getInterpretCBBoost(self, directory, y_test=None):
+ def getInterpretCBBoost(self, directory, base_file_name="", y_test=None):
self.directory = directory
"""Used to interpret the functionning of the algorithm"""
if self.step_decisions is not None:
@@ -539,7 +554,7 @@ class CBBoostClassifier(BaseEstimator, ClassifierMixin, BaseBoost):
interpretString += "\n \n With arguments : \n" + u'\u2022 ' + (
"\n" + u'\u2022 ').join(['%s: \t%s' % (key, value)
for (key, value) in
- args_dict.items()])
+ args_dict.items()])+"\n\n"
if not self.respected_bound:
interpretString += "\n\n The bound was not respected"
diff --git a/summit/multiview_platform/monoview_classifiers/cb_boost.py b/summit/multiview_platform/monoview_classifiers/cb_boost.py
index 853a380f0d8bb8b73ad369f1c72140049cedb3e2..2374d68ea605a8b6f8bad0f7409dfef244685bc7 100644
--- a/summit/multiview_platform/monoview_classifiers/cb_boost.py
+++ b/summit/multiview_platform/monoview_classifiers/cb_boost.py
@@ -76,7 +76,9 @@ class CBBoost(CBBoostClassifier, BaseMonoviewClassifier):
-------
"""
- return self.getInterpretCBBoost(directory, y_test)
+ interpret_string = self.getInterpretCBBoost(directory, base_file_name, y_test)
+ interpret_string += self.get_feature_importance(directory, base_file_name)
+ return interpret_string
def get_name_for_fusion(self):
"""
diff --git a/summit/multiview_platform/monoview_classifiers/scm.py b/summit/multiview_platform/monoview_classifiers/scm.py
index c4b2dd705e020e6a6247365c8b2746dc0bf1681a..56fc0dd031929881a8a9d6bfe9ec9bf45e9aba88 100644
--- a/summit/multiview_platform/monoview_classifiers/scm.py
+++ b/summit/multiview_platform/monoview_classifiers/scm.py
@@ -1,5 +1,7 @@
from pyscm.scm import SetCoveringMachineClassifier as scm
+import numpy as np
+
from ..monoview.monoview_utils import BaseMonoviewClassifier
from ..utils.hyper_parameter_search import CustomRandint, CustomUniform
@@ -61,6 +63,18 @@ class SCM(scm, BaseMonoviewClassifier):
self.classed_params = []
self.weird_strings = {}
+ def fit(self, X, y, tiebreaker=None, iteration_callback=None, **fit_params):
+ self.n_features = X.shape[1]
+ scm.fit(self, X, y, tiebreaker=None, iteration_callback=None, **fit_params)
+ self.feature_importances_ = np.zeros(self.n_features)
+ # sum the rules importances :
+ # rules_importances = estim.get_rules_importances() #activate it when pyscm will implement importance
+ rules_importances = np.ones(len(
+ self.model_.rules)) # delete it when pyscm will implement importance
+ for rule, importance in zip(self.model_.rules, rules_importances):
+ self.feature_importances_[rule.feature_idx] += importance
+ self.feature_importances_ /= np.sum(self.feature_importances_)
+
# def canProbas(self):
# """
# Used to know if the classifier can return label probabilities
@@ -71,17 +85,11 @@ class SCM(scm, BaseMonoviewClassifier):
# """
# return False
- def get_interpretation(self, directory, y_test, multi_class=False):
- interpretString = "Model used : " + str(self.model_)
- return interpretString
-
+ def get_interpretation(self, directory, base_file_name, y_test, multi_class=False):
+ interpret_string = self.get_feature_importance(directory, base_file_name)
+ interpret_string += "Model used : " + str(self.model_)
+ return interpret_string
-# def formatCmdArgs(args):
-# """Used to format kwargs for the parsed args"""
-# kwargsDict = {"model_type": args.SCM_model_type,
-# "p": args.SCM_p,
-# "max_rules": args.SCM_max_rules}
-# return kwargsDict
def paramsToSet(nIter, random_state):
diff --git a/summit/multiview_platform/monoview_classifiers/scm_bagging.py b/summit/multiview_platform/monoview_classifiers/scm_bagging.py
index d91598cf63956de55e85a6f68deb9e2f07d6059c..90ee6772f4e5d271802a184fb8e219729f15b1f8 100644
--- a/summit/multiview_platform/monoview_classifiers/scm_bagging.py
+++ b/summit/multiview_platform/monoview_classifiers/scm_bagging.py
@@ -170,6 +170,7 @@ class ScmBaggingClassifier(BaseEnsemble, ClassifierMixin, BaseMonoviewClassifier
self.binary_to_labels = {bin_label: str_label for str_label, bin_label
in self.labels_to_binary.items()}
y = np.array([self.labels_to_binary[l] for l in y])
+ self.n_features = X.shape[1]
estimators = []
self.estim_features = []
@@ -296,6 +297,10 @@ class ScmBaggingClassifier(BaseEnsemble, ClassifierMixin, BaseMonoviewClassifier
print(feature_id_occurences)
importances = {k: round(v / feature_id_occurences[k], 3) for k, v in
importances.items()}
+ self.feature_importances_ = np.array([importances[k]
+ if k in importances else 0
+ for k in range(self.n_features)])
+ self.feature_importances_ /= np.sum(self.feature_importances_)
return importances
def get_estimators_indices(self):
@@ -313,3 +318,9 @@ class ScmBaggingClassifier(BaseEnsemble, ClassifierMixin, BaseMonoviewClassifier
def score(self, X, y):
return accuracy_score(y, self.predict(X))
+
+ def get_interpretation(self, directory, base_file_name, y_test,
+ multi_class=False):
+ self.features_importance()
+ interpret_string = self.get_feature_importance(directory, base_file_name)
+ return interpret_string