def adult(dataType):
title = '{0} Ada Boost'.format(dataType)
package = data.createData(dataType)
xTrain = package.xTrain
xTest = package.xTest
yTrain = package.yTrain
yTest = package.yTest
param_range = list(range(1, 160, 10))
param = 'n_estimators'
# params = {'algorithm': 'SAMME.R'}
clf = AdaBoostClassifier()
# clf.set_params(**params)
plotter.plotValidationCurve(clf,
xTrain,
yTrain,
param,
param_range,
graphTitle=title)
clf.n_estimators = 40
plotter.plotLearningCurve(clf, title=title, xTrain=xTrain, yTrain=yTrain)
title = 'Adult'
clf.fit(xTrain, yTrain)
plotter.plotConfusion(clf, title, ['>50K', '<=50K'], xTest, yTest)
"""Run evaluation of a classifier, for one category.
If data isn't set explicitly, the test set is
used by default.
"""
log_file = os.path.join(datamanager.PATHS["LOGS"], "evaluation",
class_name(clf), category)
log_file = os.path.join(log_file, str(datetime.now()) + ".log")
vcd = VisualConceptDetection(None, datamanager, log_file=log_file)
clf = vcd.load_object("Classifier", category, clf)
vcd.classifier = clf
if (data[0] is None) or (data[1] is None):
return vcd.evaluate_test_set(category)
else:
return vcd.evaluate(X_test=data[0], y_test=data[1])
if __name__ == '__main__':
# classifier = RandomForestClassifier()
classifier = AdaBoostClassifier()
classifier.n_estimators = 2000
classifier.base_estimator.max_depth = 4
# classifier = LinearSVC(C=100)
category = "airplanes"
datamanager = CaltechManager()
evaluate(category, classifier, datamanager)
def evaluate(category, clf, datamanager, data=(None, None)):
"""Run evaluation of a classifier, for one category.
If data isn't set explicitly, the test set is
used by default.
"""
log_file = os.path.join(datamanager.PATHS["LOGS"], "evaluation", class_name(clf), category)
log_file = os.path.join(log_file, str(datetime.now()) + ".log")
vcd = VisualConceptDetection(None, datamanager, log_file=log_file)
clf = vcd.load_object("Classifier", category, clf)
vcd.classifier = clf
if (data[0] is None) or (data[1] is None):
return vcd.evaluate_test_set(category)
else:
return vcd.evaluate(X_test=data[0], y_test=data[1])
if __name__ == "__main__":
# classifier = RandomForestClassifier()
classifier = AdaBoostClassifier()
classifier.n_estimators = 2000
classifier.base_estimator.max_depth = 4
# classifier = LinearSVC(C=100)
category = "airplanes"
datamanager = CaltechManager()
evaluate(category, classifier, datamanager)
