diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/MonoviewUtils.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/MonoviewUtils.py
index e5d2049776658a4adef48bd2395bcd0855cf0b20..e07ce04b0e3aa93de1afaa89d741d3f860d4e6a3 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/MonoviewUtils.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/MonoviewUtils.py
@@ -1,7 +1,9 @@
from sklearn.model_selection import RandomizedSearchCV
from scipy.stats import uniform, randint
-from sklearn.pipeline import Pipeline
import numpy as np
+import matplotlib.pyplot as plt
+from matplotlib.ticker import FuncFormatter
+import pickle
from .. import Metrics
from ..utils import HyperParameterSearch
@@ -113,11 +115,39 @@ class BaseMonoviewClassifier(object):
else:
return str(self.get_params()[param_name])
+ def getFeatureImportance(self, directory, nb_considered_feats=50):
+ """Used to generate a graph and a pickle dictionary representing feature importances"""
+ featureImportances = self.feature_importances_
+ sortedArgs = np.argsort(-featureImportances)
+ featureImportancesSorted = featureImportances[sortedArgs][:nb_considered_feats]
+ featureIndicesSorted = sortedArgs[:nb_considered_feats]
+ fig, ax = plt.subplots()
+ x = np.arange(len(featureIndicesSorted))
+ formatter = FuncFormatter(percent)
+ ax.yaxis.set_major_formatter(formatter)
+ plt.bar(x, featureImportancesSorted)
+ plt.title("Importance depending on feature")
+ fig.savefig(directory + "feature_importances.png")
+ plt.close()
+ featuresImportancesDict = dict((featureIndex, featureImportance)
+ for featureIndex, featureImportance in enumerate(featureImportances)
+ if featureImportance != 0)
+ with open(directory + 'feature_importances.pickle', 'wb') as handle:
+ pickle.dump(featuresImportancesDict, handle)
+ interpretString = "Feature importances : \n"
+ for featureIndex, featureImportance in zip(featureIndicesSorted, featureImportancesSorted):
+ if featureImportance > 0:
+ interpretString += "- Feature index : " + str(featureIndex) + \
+ ", feature importance : " + str(featureImportance) + "\n"
+ return interpretString
+
def get_names(classed_list):
return np.array([object_.__class__.__name__ for object_ in classed_list])
-
+def percent(x, pos):
+ """Used to print percentage of importance on the y axis"""
+ return '%1.1f %%' % (x * 100)
# def isUseful(labelSupports, index, CLASS_LABELS, labelDict):
diff --git a/multiview_platform/MonoMultiViewClassifiers/Monoview/analyzeResult.py b/multiview_platform/MonoMultiViewClassifiers/Monoview/analyzeResult.py
index d367589549d7b1571ebc46be4668d444c172a262..b81e84af5593ec70708596ddf4e712098d9274ec 100644
--- a/multiview_platform/MonoMultiViewClassifiers/Monoview/analyzeResult.py
+++ b/multiview_platform/MonoMultiViewClassifiers/Monoview/analyzeResult.py
@@ -18,12 +18,12 @@ def getDBConfigString(name, feat, classificationIndices, shape, classLabelsNames
def getClassifierConfigString(gridSearch, nbCores, nIter, clKWARGS, classifier, directory):
classifierConfigString = "Classifier configuration : \n"
- classifierConfigString += "\t- " + classifier.getConfig(clKWARGS)[5:] + "\n"
+ classifierConfigString += "\t- " + classifier.getConfig()[5:] + "\n"
classifierConfigString += "\t- Executed on " + str(nbCores) + " core(s) \n"
if gridSearch:
classifierConfigString += "\t- Got configuration using randomized search with " + str(nIter) + " iterations \n"
classifierConfigString += "\n\n"
- classifierInterpretString = classifier.getInterpret(classifier, directory)
+ classifierInterpretString = classifier.getInterpret(directory)
return classifierConfigString, classifierInterpretString
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/Adaboost.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/Adaboost.py
index 1808176c466095342ced5d92ec054c2e6fd4c265..9980f721d6226110f532525e6fe78a258f4ac107 100644
--- a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/Adaboost.py
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/Adaboost.py
@@ -1,7 +1,6 @@
from sklearn.ensemble import AdaBoostClassifier
from sklearn.tree import DecisionTreeClassifier
-from ..utils.Interpret import getFeatureImportance
from ..Monoview.MonoviewUtils import CustomRandint, BaseMonoviewClassifier
# Author-Info
@@ -35,28 +34,9 @@ class Adaboost(AdaBoostClassifier, BaseMonoviewClassifier):
"base_estimator": DecisionTreeClassifier()})
return paramsSet
- # def genPipeline(self):
- # return Pipeline([('classifier', AdaBoostClassifier())])
-
- # def genDistribs(self,):
- # return {"classifier__n_estimators": CustomRandint(low=1, high=500),
- # "classifier__base_estimator": [DecisionTreeClassifier()]}
-
- # def genParamsFromDetector(self, detector):
- # nIter = len(detector.cv_results_['param_classifier__n_estimators'])
- # return [("baseEstimators", np.array(["DecisionTree" for _ in range(nIter)])),
- # ("nEstimators", np.array(detector.cv_results_['param_classifier__n_estimators']))]
-
- def getConfig(self, config):
- if type(config) is not dict: # Used in late fusion when config is a classifier
- return "\n\t\t- Adaboost with num_esimators : " + str(config.n_estimators) + ", base_estimators : " + str(
- config.base_estimator)
- else:
- return "\n\t\t- Adaboost with n_estimators : " + str(config["n_estimators"]) + ", base_estimator : " + str(
- config["base_estimator"])
-
- def getInterpret(self, classifier, directory):
- interpretString = getFeatureImportance(classifier, directory)
+ def getInterpret(self, directory):
+ interpretString = ""
+ interpretString += self.getFeatureImportance(directory)
return interpretString
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/DecisionTree.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/DecisionTree.py
index 165123726da54b9bd733c8fc1bde32a2c9483ef4..ac4f9bd5750b04b77dd50c6050fce8868ee92ed3 100644
--- a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/DecisionTree.py
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/DecisionTree.py
@@ -8,7 +8,6 @@ import numpy as np
from .. import Metrics
from ..utils.HyperParameterSearch import genHeatMaps
-from ..utils.Interpret import getFeatureImportance
# Author-Info
__author__ = "Baptiste Bauvin"
diff --git a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/RandomForest.py b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/RandomForest.py
index 2130acfb779fb29fda488eb0082b8d3a0e210945..a49b6113591b866e5df97f1670f383727deed2a6 100644
--- a/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/RandomForest.py
+++ b/multiview_platform/MonoMultiViewClassifiers/MonoviewClassifiers/RandomForest.py
@@ -3,11 +3,6 @@ from sklearn.pipeline import Pipeline
from sklearn.model_selection import RandomizedSearchCV
from scipy.stats import randint
import numpy as np
-# import cPickle
-
-from .. import Metrics
-from ..utils.HyperParameterSearch import genHeatMaps
-from ..utils.Interpret import getFeatureImportance
# Author-Info
__author__ = "Baptiste Bauvin"
diff --git a/multiview_platform/MonoMultiViewClassifiers/utils/Interpret.py b/multiview_platform/MonoMultiViewClassifiers/utils/Interpret.py
deleted file mode 100644
index dc816ac35d50a330fdaf5835106f3da814470a4d..0000000000000000000000000000000000000000
--- a/multiview_platform/MonoMultiViewClassifiers/utils/Interpret.py
+++ /dev/null
@@ -1,36 +0,0 @@
-import numpy as np
-import matplotlib.pyplot as plt
-from matplotlib.ticker import FuncFormatter
-import pickle
-
-
-def percent(x, pos):
- """Used to print percentage of importance on the y axis"""
- return '%1.1f %%' % (x * 100)
-
-
-def getFeatureImportance(classifier, directory, interpretString=""):
- """Used to generate a graph and a pickle dictionary representing feature importances"""
- featureImportances = classifier.feature_importances_
- sortedArgs = np.argsort(-featureImportances)
- featureImportancesSorted = featureImportances[sortedArgs][:50]
- featureIndicesSorted = sortedArgs[:50]
- fig, ax = plt.subplots()
- x = np.arange(len(featureIndicesSorted))
- formatter = FuncFormatter(percent)
- ax.yaxis.set_major_formatter(formatter)
- plt.bar(x, featureImportancesSorted)
- plt.title("Importance depending on feature")
- fig.savefig(directory + "feature_importances.png")
- plt.close()
- featuresImportancesDict = dict((featureIndex, featureImportance)
- for featureIndex, featureImportance in enumerate(featureImportances)
- if featureImportance != 0)
- with open(directory+'feature_importances.pickle', 'wb') as handle:
- pickle.dump(featuresImportancesDict, handle)
- interpretString += "Feature importances : \n"
- for featureIndex, featureImportance in zip(featureIndicesSorted, featureImportancesSorted):
- if featureImportance>0:
- interpretString+="- Feature index : "+str(featureIndex)+\
- ", feature importance : "+str(featureImportance)+"\n"
- return interpretString
\ No newline at end of file
diff --git a/multiview_platform/MonoMultiViewClassifiers/utils/__init__.py b/multiview_platform/MonoMultiViewClassifiers/utils/__init__.py
index 5baa4d9cca647d122ac24808c64040829eb58200..842d824c6b28acf620ca3b31f973f2a924bd9415 100644
--- a/multiview_platform/MonoMultiViewClassifiers/utils/__init__.py
+++ b/multiview_platform/MonoMultiViewClassifiers/utils/__init__.py
@@ -1 +1 @@
-from . import Dataset, execution, HyperParameterSearch, Transformations, Interpret
+from . import Dataset, execution, HyperParameterSearch, Transformations