def testOnData(models,
testData,
store_classifiers=False,
store_examples=False):
""" Makes used of Bulk-Predict"""
evaluator = VarCtrlVal()
test_results = orngTest.ExperimentResults(
1,
classifierNames=[getobjectname(l) for l in models],
domain=testData.domain) #,
# test_type = test_type,
# weights=weight)
test_results.classifiers = []
if store_examples:
test_results.examples = testData
if store_classifiers:
test_results.classifiers = models
results = evaluator._test_on_data(models, testData, example_ids=None)
test_results.results.extend(
test_results.create_tested_example(0, example)
for i, example in enumerate(testData))
for nEx, nModel, res in results:
test_results.results[nEx].set_result(nModel, *res)
return test_results
def encode_PP(self, pps):
for pp in pps:
objname = getobjectname(pp[1])
if len(objname):
pps += "_" + objname
else:
return "*"
return pps
def learn_and_test_on_learn_data(self,
learners,
examples,
preprocessors=(),
callback=None,
store_classifiers=False,
store_examples=False):
"""
Perform a test where learners are trained and tested on the same data.
:param learners: list of learners to be tested
:param examples: data table on which the learners will be tested
:param preprocessors: a list of preprocessors to be used on data.
:param callback: a function that will be called after each fold is computed.
:param store_classifiers: if True, classifiers will be accessible in test_results.
:param store_examples: if True, examples will be accessible in test_results.
:return: :obj:`ExperimentResults`
"""
examples, weight = demangle_examples(examples)
test_type = self.check_test_type(examples, learners)
# If preprocessors are not used, we use the same dataset for learning and testing. Otherwise we need to
# clone it.
if not filter(lambda x: x[0] != "B", preprocessors):
learn_set, test_set = self._preprocess_data(
examples, Orange.data.Table(examples.domain), preprocessors)
test_set = learn_set
else:
learn_set, test_set = self._preprocess_data(
examples, Orange.data.Table(examples), preprocessors)
classifiers = self._train_with_callback(learners, learn_set, weight,
callback)
test_results = ExperimentResults(
1,
classifier_names=[getobjectname(l) for l in learners],
test_type=test_type,
domain=examples.domain,
weights=weight)
test_results.results = [
test_results.create_tested_example(0, example)
for i, example in enumerate(examples)
]
if store_classifiers:
test_results.classifiers = classifiers
if store_examples:
test_results.examples = test_set
results = self._test_on_data(classifiers, test_set)
for example, classifier, result in results:
test_results.results[example].set_result(classifier, *result)
return test_results
def proportion_test(self, learners, data, learning_proportion, times=10,
stratification=Orange.core.MakeRandomIndices.StratifiedIfPossible, preprocessors=(), random_generator=0,
callback=None, store_classifiers=False, store_examples=False, testAttrFilter=None, testFilterVal=None):
"""
Perform a test, where learners are trained and tested on different data sets. Training and test sets are
generated by proportionally splitting data.
:param learners: list of learners to be tested
:param data: a dataset used for evaluation
:param learning_proportion: proportion of examples to be used for training
:param times: number of test repetitions
:param stratification: use stratification when constructing train and test sets.
:param preprocessors: a list of preprocessors to be used on data.
:param callback: a function that is be called after each classifier is computed.
:param store_classifiers: if True, classifiers will be accessible in test_results.
:param store_examples: if True, examples will be accessible in test_results.
:return: :obj:`ExperimentResults`
"""
examples = self.getExamplesAndSetTrainBias(data, testAttrFilter, testFilterVal)
pick = Orange.core.MakeRandomIndices2(stratified = stratification, p0 = learning_proportion, randomGenerator = random_generator)
examples, weight = demangle_examples(examples)
test_type = self.check_test_type(examples, learners)
test_results = orngTest.ExperimentResults(times,
classifierNames = [getobjectname(l) for l in learners],
domain=examples.domain,
test_type = test_type,
weights=weight)
test_results.classifiers = []
offset=0
for time in xrange(times):
indices = pick(examples)
learn_set = examples.selectref(indices, 0)
test_set = examples.selectref(indices, 1)
#Add train bias to the lear_set
if self.trainBias:
learn_set = dataUtilities.concatenate([learn_set, self.trainBias], True)[0]
classifiers, results = self._learn_and_test_on_test_data(learners, learn_set, weight, test_set, preprocessors)
if store_classifiers:
test_results.classifiers.append(classifiers)
test_results.results.extend(test_results.create_tested_example(time, example)
for i, example in enumerate(test_set))
for example, classifier, result in results:
test_results.results[offset+example].set_result(classifier, *result)
offset += len(test_set)
if callback:
callback()
return test_results
def learn_and_test_on_test_data(self,
learners,
learn_set,
test_set,
preprocessors=(),
callback=None,
store_classifiers=False,
store_examples=False):
"""
Perform a test, where learners are trained on one dataset and tested
on another.
:param learners: list of learners to be tested
:param learn_set: a dataset used for training
:param test_set: a dataset used for testing
:param preprocessors: a list of preprocessors to be used on data.
:param callback: a function that is be called after each classifier is computed.
:param store_classifiers: if True, classifiers will be accessible in test_results.
:param store_examples: if True, examples will be accessible in test_results.
:return: :obj:`ExperimentResults`
"""
learn_set, learn_weight = demangle_examples(learn_set)
test_set, test_weight = demangle_examples(test_set)
test_type = self.check_test_type(learn_set, learners)
self.check_test_type(test_set, learners)
test_results = ExperimentResults(
1,
classifier_names=[getobjectname(l) for l in learners],
domain=test_set.domain,
test_type=test_type,
weights=test_weight)
test_results.results = [
test_results.create_tested_example(0, example)
for i, example in enumerate(test_set)
]
classifiers, results = self._learn_and_test_on_test_data(
learners, learn_set, learn_weight, test_set, preprocessors,
callback)
if store_classifiers:
test_results.classifiers = classifiers
if store_examples:
test_results.examples = test_set
for example, classifier, result in results:
test_results.results[example].set_result(classifier, *result)
return test_results
def testOnData(models,testData, store_classifiers=False, store_examples=False):
""" Makes used of Bulk-Predict"""
evaluator = VarCtrlVal()
test_results = orngTest.ExperimentResults(1,
classifierNames = [getobjectname(l) for l in models],
domain=testData.domain)#,
# test_type = test_type,
# weights=weight)
test_results.classifiers = []
if store_examples:
test_results.examples = testData
if store_classifiers:
test_results.classifiers = models
results = evaluator._test_on_data(models, testData, example_ids=None)
test_results.results.extend(test_results.create_tested_example(0, example)
for i, example in enumerate(testData))
for nEx, nModel, res in results:
test_results.results[nEx].set_result(nModel, *res)
return test_results
def test_on_data(self,
classifiers,
examples,
store_classifiers=False,
store_examples=False):
"""
Test classifiers on examples
:param classifiers: classifiers to test
:param examples: examples to test on
:param store_classifiers: if True, classifiers will be accessible in test_results.
:param store_examples: if True, examples will be accessible in test_results.
"""
examples, weight = demangle_examples(examples)
test_type = self.check_test_type(examples, classifiers)
test_results = ExperimentResults(
1,
classifier_names=[getobjectname(l) for l in classifiers],
domain=examples.domain,
test_type=test_type,
weights=weight)
test_results.results = [
test_results.create_tested_example(0, example)
for i, example in enumerate(examples)
]
if store_examples:
test_results.examples = examples
if store_classifiers:
test_results.classifiers = classifiers
results = self._test_on_data(classifiers, examples)
for example, classifier, result in results:
test_results.results[example].set_result(classifier, *result)
return test_results
def proportion_test(
self,
learners,
data,
learning_proportion,
times=10,
stratification=Orange.core.MakeRandomIndices.StratifiedIfPossible,
preprocessors=(),
random_generator=0,
callback=None,
store_classifiers=False,
store_examples=False,
testAttrFilter=None,
testFilterVal=None):
"""
Perform a test, where learners are trained and tested on different data sets. Training and test sets are
generated by proportionally splitting data.
:param learners: list of learners to be tested
:param data: a dataset used for evaluation
:param learning_proportion: proportion of examples to be used for training
:param times: number of test repetitions
:param stratification: use stratification when constructing train and test sets.
:param preprocessors: a list of preprocessors to be used on data.
:param callback: a function that is be called after each classifier is computed.
:param store_classifiers: if True, classifiers will be accessible in test_results.
:param store_examples: if True, examples will be accessible in test_results.
:return: :obj:`ExperimentResults`
"""
examples = self.getExamplesAndSetTrainBias(data, testAttrFilter,
testFilterVal)
pick = Orange.core.MakeRandomIndices2(stratified=stratification,
p0=learning_proportion,
randomGenerator=random_generator)
examples, weight = demangle_examples(examples)
test_type = self.check_test_type(examples, learners)
test_results = orngTest.ExperimentResults(
times,
classifierNames=[getobjectname(l) for l in learners],
domain=examples.domain,
test_type=test_type,
weights=weight)
test_results.classifiers = []
offset = 0
for time in xrange(times):
indices = pick(examples)
learn_set = examples.selectref(indices, 0)
test_set = examples.selectref(indices, 1)
#Add train bias to the lear_set
if self.trainBias:
learn_set = dataUtilities.concatenate(
[learn_set, self.trainBias], True)[0]
classifiers, results = self._learn_and_test_on_test_data(
learners, learn_set, weight, test_set, preprocessors)
if store_classifiers:
test_results.classifiers.append(classifiers)
test_results.results.extend(
test_results.create_tested_example(time, example)
for i, example in enumerate(test_set))
for example, classifier, result in results:
test_results.results[offset + example].set_result(
classifier, *result)
offset += len(test_set)
if callback:
callback()
return test_results
def learning_curve_with_test_data(
self,
learners,
learn_set,
test_set,
times=10,
proportions=Orange.core.frange(0.1),
stratification=Orange.core.MakeRandomIndices.StratifiedIfPossible,
preprocessors=(),
random_generator=0,
store_classifiers=False,
store_examples=False):
"""
Compute a learning curve given two datasets. Models are learned on
proportion of the first dataset and then used to make predictions for
the second dataset.
:param learners: list of learners to be tested
:param learn_set: a dataset used for evaluation
:param test_set: a dataset used for evaluation
:param proportions: proportions of train data to be used
:param preprocessors: a list of preprocessors to be used on data.
:return: list of :obj:`ExperimentResults`
"""
learn_set, learn_weight = demangle_examples(learn_set)
test_set, test_weight = demangle_examples(test_set)
test_type = self.check_test_type(learn_set, learners)
self.check_test_type(test_set, learners)
indices = Orange.core.MakeRandomIndices2(
stratified=stratification, randomGenerator=random_generator)
all_results = []
for p in proportions:
test_results = ExperimentResults(
times,
classifier_names=[getobjectname(l) for l in learners],
domain=test_set.domain,
test_type=test_type,
weights=test_weight)
offset = 0
for t in xrange(times):
test_results.results.extend(
test_results.create_tested_example(t, example)
for i, example in enumerate(test_set))
learn_examples = learn_set.selectref(indices(learn_set, p), 0)
classifiers, results = self._learn_and_test_on_test_data\
(learners, learn_examples, learn_weight, test_set,
preprocessors=preprocessors)
for example, classifier, result in results:
test_results.results[offset + example].set_result(
classifier, *result)
offset += len(test_set)
if store_classifiers:
test_results.classifiers.append(classifiers)
if store_examples:
test_results.examples = learn_examples
all_results.append(test_results)
return all_results
def test_with_indices(self,
learners,
examples,
indices,
preprocessors=(),
callback=None,
store_classifiers=False,
store_examples=False,
**kwargs):
"""
Perform a cross-validation-like test. Examples for each fold are
selected based on given indices.
:param learners: list of learners to be tested
:param examples: data table on which the learners will be tested
:param indices: a list of integers that defines, which examples will be
used for testing in each fold. The number of indices should be
equal to the number of examples.
:param preprocessors: a list of preprocessors to be used on data.
:param callback: a function that will be called after each fold is
computed.
:param store_classifiers: if True, classifiers will be accessible in test_results.
:param store_examples: if True, examples will be accessible in test_results.
:return: :obj:`ExperimentResults`
"""
examples, weight = demangle_examples(examples)
if not examples:
raise ValueError("Test data set with no examples")
test_type = self.check_test_type(examples, learners)
if "cache" in kwargs:
raise ValueError("This feature is no longer supported.")
niterations = max(indices) + 1
test_result = ExperimentResults(
niterations,
classifier_names=[getobjectname(l) for l in learners],
domain=examples.domain,
weights=weight,
test_type=test_type)
test_result.results = [
test_result.create_tested_example(indices[i], example)
for i, example in enumerate(examples)
]
if store_examples:
test_result.examples = examples
for fold in xrange(niterations):
results, classifiers = self.one_fold_with_indices(
learners, examples, fold, indices, preprocessors, weight)
for example, learner, result in results:
test_result.results[example].set_result(learner, *result)
if store_classifiers:
test_result.classifiers.append(classifiers)
if callback:
callback()
return test_result