def tmva_process(classifier, info, data, labels, sample_weight):
"""
Create TMVA classification factory, train, test and evaluate all methods
:param classifier: classifier to train
:type classifier: rep.estimators.tmva.TMVAClassifier or rep.estimators.tmva.TMVARegressor
:param rep.estimators.tmva._AdditionalInformation info: additional information
:param pandas.DataFrame data: train data
:param labels: array-like - targets
:param sample_weight: array-like - weights
"""
ROOT.TMVA.Tools.Instance()
file_out = ROOT.TFile(os.path.join(info.directory, info.tmva_root), "RECREATE")
print(classifier.factory_options)
factory = ROOT.TMVA.Factory(info.tmva_job, file_out, classifier.factory_options)
for var in data.columns:
factory.AddVariable(var)
# Set data
if info.model_type == "classification":
if classifier.method == "kCuts":
# signal must the first added tree, because rectangular cut optimization in another way doesn't work
inds = numpy.argsort(labels)[::-1]
data = data.ix[inds, :]
labels = labels[inds]
sample_weight = sample_weight[inds]
add_classification_events(factory, numpy.array(data), labels, weights=sample_weight)
add_classification_events(factory, numpy.array(data), labels, weights=sample_weight, test=True)
elif info.model_type == "regression":
factory.AddTarget("target")
add_regression_events(factory, numpy.array(data), labels, weights=sample_weight)
add_regression_events(factory, numpy.array(data), labels, weights=sample_weight, test=True)
else:
raise NotImplementedError("Doesn't support type {}".format(info.model_type))
factory.PrepareTrainingAndTestTree(ROOT.TCut("1"), "")
# Set method
parameters = ":".join(
["{key}={value}".format(key=key, value=value) for key, value in classifier.method_parameters.items()]
)
factory.BookMethod(
ROOT.TMVA.Types.__getattribute__(ROOT.TMVA.Types, classifier.method), classifier._method_name, parameters
)
factory.TrainAllMethods()
file_out.Close()
def tmva_process(classifier, info, data, labels, sample_weight):
"""
Create TMVA classification factory, train, test and evaluate all methods
:param classifier: classifier to train
:type classifier: rep.estimators.tmva.TMVAClassifier or rep.estimators.tmva.TMVARegressor
:param rep.estimators.tmva._AdditionalInformation info: additional information
:param pandas.DataFrame data: train data
:param labels: array-like - targets
:param sample_weight: array-like - weights
"""
ROOT.TMVA.Tools.Instance()
file_out = ROOT.TFile(os.path.join(info.directory, info.tmva_root), "RECREATE")
print(classifier.factory_options)
factory = ROOT.TMVA.Factory(info.tmva_job, file_out, classifier.factory_options)
for var in data.columns:
factory.AddVariable(var)
# Set data
if info.model_type == 'classification':
if classifier.method == 'kCuts':
# signal must the first added tree, because rectangular cut optimization in another way doesn't work
inds = numpy.argsort(labels)[::-1]
data = data.ix[inds, :]
labels = labels[inds]
sample_weight = sample_weight[inds]
add_classification_events(factory, numpy.array(data), labels, weights=sample_weight)
add_classification_events(factory, numpy.array(data), labels, weights=sample_weight, test=True)
elif info.model_type == 'regression':
factory.AddTarget('target')
add_regression_events(factory, numpy.array(data), labels, weights=sample_weight)
add_regression_events(factory, numpy.array(data), labels, weights=sample_weight, test=True)
else:
raise NotImplementedError("Doesn't support type {}".format(info.model_type))
factory.PrepareTrainingAndTestTree(ROOT.TCut('1'), "")
# Set method
parameters = ":".join(
["{key}={value}".format(key=key, value=value) for key, value in classifier.method_parameters.items()])
factory.BookMethod(ROOT.TMVA.Types.__getattribute__(ROOT.TMVA.Types, classifier.method), classifier._method_name,
parameters)
factory.TrainAllMethods()
file_out.Close()
def tmva_process(estimator, info, data, target, sample_weight):
"""
Create a TMVA classification/regression factory; training, testing and evaluating.
:param estimator: classifier/regressor which should be trained
:type estimator: rep.estimators.tmva.TMVAClassifier or rep.estimators.tmva.TMVARegressor
:param rep.estimators.tmva._AdditionalInformation info: additional information
:param pandas.DataFrame data: training data
:param target: array-like targets
:param sample_weight: array-like samples weights
"""
ROOT.TMVA.Tools.Instance()
file_out = ROOT.TFile(os.path.join(info.directory, info.tmva_root), "RECREATE")
factory = ROOT.TMVA.Factory(info.tmva_job, file_out, estimator.factory_options)
for var in data.columns:
factory.AddVariable(var)
# Set data
if info.model_type == 'classification':
if estimator.method == 'kCuts':
# signal must be the first added to the tree, because method *rectangular cut optimization* doesn't work in another way
inds = numpy.argsort(target)[::-1]
data = data.ix[inds, :]
target = target[inds]
sample_weight = sample_weight[inds]
add_classification_events(factory, numpy.array(data), target, weights=sample_weight)
add_classification_events(factory, numpy.array(data), target, weights=sample_weight, test=True)
elif info.model_type == 'regression':
factory.AddTarget('target')
add_regression_events(factory, numpy.array(data), target, weights=sample_weight)
add_regression_events(factory, numpy.array(data), target, weights=sample_weight, test=True)
else:
raise NotImplementedError("Doesn't support type {}".format(info.model_type))
factory.PrepareTrainingAndTestTree(ROOT.TCut('1'), "")
# Set method
parameters = ":".join(
["{key}={value}".format(key=key, value=value) for key, value in estimator.method_parameters.items()])
factory.BookMethod(ROOT.TMVA.Types.__getattribute__(ROOT.TMVA.Types, estimator.method), estimator._method_name,
parameters)
factory.TrainAllMethods()
file_out.Close()
np.sin(6 * X).ravel() + \
RNG.normal(0, 0.1, X.shape[0])
# Fit a regression model
output = TFile('tmva_output.root', 'recreate')
factory = TMVA.Factory('regressor', output, 'AnalysisType=Regression:'
'!V:Silent:!DrawProgressBar')
if ROOT_VERSION >= '6.07/04':
data = TMVA.DataLoader('.')
else:
data = factory
data.AddVariable('x', 'F')
data.AddTarget('y', 'F')
add_regression_events(data, X, y)
add_regression_events(data, X, y, test=True)
# The following line is necessary if events have been added individually:
data.PrepareTrainingAndTestTree(TCut('1'), '')
if ROOT_VERSION >= '6.07/04':
BookMethod = factory.BookMethod
else:
BookMethod = TMVA.Factory.BookMethod
BookMethod(
data, 'BDT', 'BDT1', 'nCuts=20:NTrees=1:MaxDepth=4:BoostType=AdaBoostR2:'
'SeparationType=RegressionVariance')
BookMethod(
data, 'BDT', 'BDT2', 'nCuts=20:NTrees=300:MaxDepth=4:BoostType=AdaBoostR2:'
'SeparationType=RegressionVariance')
factory.TrainAllMethods()
RNG = np.random.RandomState(1)
# Create an example regression dataset
X = np.linspace(0, 6, 100)[:, np.newaxis]
y = np.sin(X).ravel() + \
np.sin(6 * X).ravel() + \
RNG.normal(0, 0.1, X.shape[0])
# Fit a regression model
output = TFile('tmva_output.root', 'recreate')
factory = TMVA.Factory('regressor', output, 'AnalysisType=Regression:'
'!V:Silent:!DrawProgressBar')
factory.AddVariable('x', 'F')
factory.AddTarget('y', 'F')
add_regression_events(factory, X, y)
add_regression_events(factory, X, y, test=True)
factory.PrepareTrainingAndTestTree(TCut('1'), 'NormMode=EqualNumEvents')
factory.BookMethod(
'BDT', 'BDT1', 'nCuts=20:NTrees=1:MaxDepth=4:BoostType=AdaBoostR2:'
'SeparationType=RegressionVariance')
factory.BookMethod(
'BDT', 'BDT2', 'nCuts=20:NTrees=300:MaxDepth=4:BoostType=AdaBoostR2:'
'SeparationType=RegressionVariance')
factory.TrainAllMethods()
# Predict the regression target
reader = TMVA.Reader()
reader.AddVariable('x', array('f', [0.]))
reader.BookMVA('BDT1', 'weights/regressor_BDT1.weights.xml')
reader.BookMVA('BDT2', 'weights/regressor_BDT2.weights.xml')
RNG.normal(0, 0.1, X.shape[0])
# Fit a regression model
output = TFile('tmva_output.root', 'recreate')
factory = TMVA.Factory('regressor', output,
'AnalysisType=Regression:'
'!V:Silent:!DrawProgressBar')
if ROOT_VERSION >= '6.07/04':
data = TMVA.DataLoader('.')
else:
data = factory
data.AddVariable('x', 'F')
data.AddTarget('y', 'F')
add_regression_events(data, X, y)
add_regression_events(data, X, y, test=True)
# The following line is necessary if events have been added individually:
data.PrepareTrainingAndTestTree(TCut('1'), '')
if ROOT_VERSION >= '6.07/04':
BookMethod = factory.BookMethod
else:
BookMethod = TMVA.Factory.BookMethod
BookMethod(data, 'BDT', 'BDT1',
'nCuts=20:NTrees=1:MaxDepth=4:BoostType=AdaBoostR2:'
'SeparationType=RegressionVariance')
BookMethod(data, 'BDT', 'BDT2',
'nCuts=20:NTrees=300:MaxDepth=4:BoostType=AdaBoostR2:'
'SeparationType=RegressionVariance')
def tmva_process(estimator, info, data, target, sample_weight):
"""
Create a TMVA classification/regression factory; training, testing and evaluating.
:param estimator: classifier/regressor which should be trained
:type estimator: rep.estimators.tmva.TMVAClassifier or rep.estimators.tmva.TMVARegressor
:param rep.estimators.tmva._AdditionalInformation info: additional information
:param pandas.DataFrame data: training data
:param target: array-like targets
:param sample_weight: array-like samples weights
"""
ROOT.TMVA.Tools.Instance()
file_out = ROOT.TFile(os.path.join(info.directory, info.tmva_root),
"RECREATE")
factory = ROOT.TMVA.Factory(info.tmva_job, file_out,
estimator.factory_options)
dataloader = ROOT.TMVA.DataLoader("DataLoader")
for var in data.columns:
dataloader.AddVariable(var)
# Set data
if info.model_type == 'classification':
if estimator.method == 'kCuts':
# signal must be the first added to the tree, because method *rectangular cut optimization* doesn't work in another way
inds = numpy.argsort(target)[::-1]
data = data.ix[inds, :]
target = target[inds]
sample_weight = sample_weight[inds]
add_classification_events(dataloader,
numpy.array(data),
target,
weights=sample_weight)
add_classification_events(dataloader,
numpy.array(data),
target,
weights=sample_weight,
test=True)
elif info.model_type == 'regression':
factory.AddTarget('target')
add_regression_events(dataloader,
numpy.array(data),
target,
weights=sample_weight)
add_regression_events(dataloader,
numpy.array(data),
target,
weights=sample_weight,
test=True)
else:
raise NotImplementedError("Doesn't support type {}".format(
info.model_type))
dataloader.PrepareTrainingAndTestTree(ROOT.TCut('1'), "")
# Set method
parameters = ":".join([
"{key}={value}".format(key=key, value=value)
for key, value in estimator.method_parameters.items()
])
factory.BookMethod(
dataloader,
ROOT.TMVA.Types.__getattribute__(ROOT.TMVA.Types, estimator.method),
estimator._method_name, parameters)
factory.TrainAllMethods()
file_out.Close()
# Create an example regression dataset
X = np.linspace(0, 6, 100)[:, np.newaxis]
y = np.sin(X).ravel() + \
np.sin(6 * X).ravel() + \
RNG.normal(0, 0.1, X.shape[0])
# Fit a regression model
output = TFile('tmva_output.root', 'recreate')
factory = TMVA.Factory('regressor', output,
'AnalysisType=Regression:'
'!V:Silent:!DrawProgressBar')
factory.AddVariable('x', 'F')
factory.AddTarget('y', 'F')
add_regression_events(factory, X, y)
add_regression_events(factory, X, y, test=True)
# The following line is necessary if events have been added individually:
factory.PrepareTrainingAndTestTree(TCut('1'), '')
factory.BookMethod('BDT', 'BDT1',
'nCuts=20:NTrees=1:MaxDepth=4:BoostType=AdaBoostR2:'
'SeparationType=RegressionVariance')
factory.BookMethod('BDT', 'BDT2',
'nCuts=20:NTrees=300:MaxDepth=4:BoostType=AdaBoostR2:'
'SeparationType=RegressionVariance')
factory.TrainAllMethods()
# Predict the regression target
reader = TMVA.Reader()
reader.AddVariable('x', array('f', [0.]))