def CF_QuanVal(X, Y, estimator, conformalSignificance):
print("Starting quantitative conformal prediction validation")
icp = AggregatedCp(IcpRegressor(RegressorNc(RegressorAdapter(estimator))),
BootstrapSampler())
# icp = AggregatedCp(IcpRegressor(RegressorNc(RegressorAdapter(estimator),
# AbsErrorErrFunc(), RegressorNormalizer(estimator,
# RegressorAdapter(copy.copy(estimator)), AbsErrorErrFunc()))))
# icp_cv = RegIcpCvHelper(icp)
# scores = conformal_cross_val_score(icp_cv,
# X,
# Y,
# iterations=5,
# folds=5,
# scoring_funcs=[reg_mean_errors, reg_median_size, reg_mean_size],
# significance_levels=[0.05, 0.1, 0.2, conformalSignificance])
icp.fit(X[:30], Y[:30])
prediction = icp.predict(X[30:])
prediction_sign = icp.predict(X[30:], significance=0.25)
interval = prediction_sign[:, 0] - prediction_sign[:, 1]
print(np.mean(interval))
print(interval)
print("\n")
print(prediction)
print(prediction_sign)
return (icp)
def build(self):
'''Build a new qualitative GNB model with the X and Y numpy matrices'''
# Make a copy of data matrices
X = self.X.copy()
Y = self.Y.copy()
results = []
results.append(('nobj', 'number of objects', self.nobj))
results.append(('nvarx', 'number of predictor variables', self.nvarx))
# Build estimator
LOG.info('Building GaussianNB model')
self.estimator = GaussianNB(**self.estimator_parameters)
results.append(('model', 'model type', 'GNB qualitative'))
self.estimator.fit(X, Y)
if not self.param.getVal('conformal'):
return True, results
# If conformal, then create aggregated conformal classifier
self.estimator_temp = copy(self.estimator)
self.estimator = AggregatedCp(
IcpClassifier(
ClassifierNc(ClassifierAdapter(self.estimator_temp),
MarginErrFunc())), BootstrapSampler())
# Fit estimator to the data
self.estimator.fit(X, Y)
results.append(('model', 'model type', 'conformal GNB qualitative'))
return True, results
def CF_QualVal(X, Y, estimator, conformalSignificance):
""" Qualitative conformal predictor validation"""
print("Starting qualitative conformal prediction validation")
icp = AggregatedCp(
IcpClassifier(
ClassifierNc(ClassifierAdapter(estimator), MarginErrFunc())),
BootstrapSampler())
Y = np.asarray(Y).reshape(-1, 1)
loo = LeaveOneOut()
predictions = []
for train, test in loo.split(X):
Xn = [X[i] for i in train]
Yn = [Y[i] for i in train]
Xn, mux = center(Xn)
Xn, wgx = scale(Xn, True)
Yn = np.asarray(Yn)
Xout = X[test]
Yout = Y[test[0]]
icp.fit(Xn, Yn)
predictions.append(icp.predict(Xout, significance=0.15))
predictions = [(x[0]).tolist() for x in predictions]
predictions = np.asarray(predictions)
table = np.hstack((predictions, Y))
print('Error rate: {}'.format(class_mean_errors(predictions, Y, 0.15)))
print('Class one: ', class_one_c(predictions, Y, 0.15))
return icp
def CF_quantitative_validation(self):
''' Performs internal validation for conformal quantitative models '''
# Make a copy of original matrices.
X = self.X.copy()
Y = self.Y.copy()
# Number of external validations for the aggregated conformal estimator.
seeds = [5, 7, 35]
# Interval means for each aggregated conformal estimator (out of 3)
interval_means = []
# Accuracies for each aggregated conformal estimator (out of 3)
accuracies = []
results = []
try:
for i in range(len(seeds)):
# Generate training a test sets
X_train, X_test, Y_train, Y_test = train_test_split(
X, Y, test_size=0.25, random_state=i, shuffle=False)
# Create the aggregated conformal regressor.
conformal_pred = AggregatedCp(
IcpRegressor(RegressorNc(RegressorAdapter(
self.estimator))), BootstrapSampler())
# Fit conformal regressor to the data
conformal_pred.fit(X_train, Y_train)
# Perform prediction on test set
prediction = conformal_pred.predict(X_test,
self.conformalSignificance)
# Add the n validation interval means
interval_means.append(
np.mean(
np.abs(prediction[:, 0]) - np.abs(prediction[:, 1])))
Y_test = Y_test.reshape(-1, 1)
# Get boolean mask of instances within the applicability domain.
inside_interval = ((prediction[:, 0].reshape(-1, 1) < Y_test) &
(prediction[:, 1].reshape(-1, 1) > Y_test))
# Compute the accuracy (number of instances within the AD).
accuracy = np.sum(inside_interval) / len(Y_test)
# Add validation result to the list of accuracies.
accuracies.append(accuracy)
except Exception as e:
LOG.error(f'Quantitative conformal validation'
f' failed with exception: {e}')
raise e
# Compute mean interval_means and accuracy.
interval_means = np.mean(interval_means)
accuracies = np.mean(accuracies)
# Cut into two decimals.
self.conformal_accuracy = float("{0:.2f}".format(accuracies))
self.conformal_mean_interval = float("{0:.2f}".format(interval_means))
#Add quality metrics to results.
results.append(('Conformal_mean_interval', 'Conformal mean interval',
self.conformal_mean_interval))
results.append(('Conformal_accuracy', 'Conformal accuracy',
self.conformal_accuracy))
return True, (results, )
def build(self):
if not self.quantitative:
print("PLSR only applies to quantitative data")
return False, "PLSR only applies to quantitative data"
if self.failed:
return False, "Error initiating model"
X = self.X.copy()
Y = self.Y.copy()
results = []
results.append(('nobj', 'number of objects', self.nobj))
results.append(('nvarx', 'number of predictor variables', self.nvarx))
if self.cv:
self.cv = getCrossVal(self.cv, 46, self.n, self.p)
if self.tune:
if self.optimiz == 'auto':
super(PLSR, self).optimize(X, Y, PLS_r(
**self.estimator_parameters), self.tune_parameters)
elif self.optimiz == 'manual':
self.optimize(X, Y, PLS_r(
**self.estimator_parameters), self.tune_parameters)
results.append(
('model', 'model type', 'PLSR quantitative (optimized)'))
else:
print("Building Quantitative PLSR")
self.estimator = PLS_r(**self.estimator_parameters)
results.append(('model', 'model type', 'PLSR quantitative'))
if self.conformal:
underlying_model = RegressorAdapter(self.estimator)
normalizing_model = RegressorAdapter(
KNeighborsRegressor(n_neighbors=1))
normalizing_model = RegressorAdapter(self.estimator)
normalizer = RegressorNormalizer(
underlying_model, normalizing_model, AbsErrorErrFunc())
nc = RegressorNc(underlying_model, AbsErrorErrFunc(), normalizer)
self.conformal_pred = AggregatedCp(IcpRegressor(nc),
BootstrapSampler())
# self.conformal_pred = AggregatedCp(IcpRegressor(RegressorNc(RegressorAdapter(self.estimator))),
# BootstrapSampler())
self.conformal_pred.fit(X, Y)
# overrides non-conformal
results.append(
('model', 'model type', 'conformal PLSR quantitative'))
self.estimator.fit(X, Y)
return True, results
def test_acp_regression_tree(self):
# -----------------------------------------------------------------------------
# Experiment setup
# -----------------------------------------------------------------------------
data = load_diabetes()
idx = np.random.permutation(data.target.size)
train = idx[:int(2 * idx.size / 3)]
test = idx[int(2 * idx.size / 3):]
truth = data.target[test]
columns = ["min", "max", "truth"]
significance = 0.1
# -----------------------------------------------------------------------------
# Define models
# -----------------------------------------------------------------------------
models = {
"ACP-RandomSubSampler":
AggregatedCp(
IcpRegressor(
RegressorNc(RegressorAdapter(DecisionTreeRegressor()))),
RandomSubSampler(),
),
"ACP-CrossSampler":
AggregatedCp(
IcpRegressor(
RegressorNc(RegressorAdapter(DecisionTreeRegressor()))),
CrossSampler(),
),
"ACP-BootstrapSampler":
AggregatedCp(
IcpRegressor(
RegressorNc(RegressorAdapter(DecisionTreeRegressor()))),
BootstrapSampler(),
),
}
# -----------------------------------------------------------------------------
# Train, predict and evaluate
# -----------------------------------------------------------------------------
for name, model in models.items():
model.fit(data.data[train, :], data.target[train])
prediction = model.predict(data.data[test, :])
prediction_sign = model.predict(data.data[test, :],
significance=significance)
table = np.vstack((prediction_sign.T, truth)).T
df = pd.DataFrame(table, columns=columns)
print("\n{}".format(name))
print("Error rate: {}".format(
reg_mean_errors(prediction, truth, significance)))
print(df)
def CF_QualCal(X, Y, estimator):
"""Qualitative conformal predictor calibration"""
acp = AggregatedCp(
IcpClassifier(
ClassifierNc(ClassifierAdapter(estimator), MarginErrFunc())),
BootstrapSampler())
acp.fit(X, Y)
# X_train, X_test, y_train, y_test = train_test_split( X, Y, test_size=0.30, random_state=42)
# icp = IcpClassifier(ClassifierNc(ClassifierAdapter(estimator),
# MarginErrFunc()))
# icp.fit(X_train, y_train)
# icp.calibrate(X_test, y_test)
return acp
def SelectLabeled(self, labeled_data_x, labeled_data_y, unlabeled_data_x):
# just append train data to labeled data
labeled_x = np.concatenate(
(self.init_labeled_data_x, labeled_data_x
)) if len(labeled_data_x) > 0 else self.init_labeled_data_x
labeled_y = np.concatenate(
(self.init_labeled_data_y, labeled_data_y
)) if len(labeled_data_x) > 0 else self.init_labeled_data_y
#
# create model to predict with confidence and credibility
model = ClassifierAdapter(
DecisionTreeClassifier(random_state=config.random_state,
min_samples_leaf=config.min_samples_leaf))
model_acp = AggregatedCp(
IcpClassifier(ClassifierNc(model), smoothing=True),
BootstrapSampler())
model_acp.fit(labeled_x, labeled_y)
s = model_acp.predict(unlabeled_data_x)
# print(s)
#
# selection method
labeled_ind = [
i for i, a in enumerate(s)
if a.max() > config.confidence and 1 - a.min() > config.credibility
]
unlabeled_ind = [
i for i, a in enumerate(s)
if a.max() < config.confidence or 1 - a.min() < config.credibility
]
labeled_unlabeled_x, labeled_unlabeled_y, unlabeled_data_x = \
np.take(unlabeled_data_x, labeled_ind, axis=0), np.take(s.argmax(axis=1), labeled_ind), np.take(
unlabeled_data_x, unlabeled_ind, axis=0)
#
return labeled_unlabeled_x, labeled_unlabeled_y, unlabeled_data_x
def build(self):
'''Build a new qualitative GNB model with the X and Y numpy matrices'''
if self.failed:
return False, "Error initiating model"
X = self.X.copy()
Y = self.Y.copy()
results = []
results.append(('nobj', 'number of objects', self.nobj))
results.append(('nvarx', 'number of predictor variables', self.nvarx))
if self.cv:
self.cv = getCrossVal(self.cv, 46, self.n, self.p)
if self.quantitative:
print("GNB only applies to qualitative data")
return False, "GNB only applies to qualitative data"
else:
print("Building GaussianNB model")
print(self.estimator_parameters)
self.estimator = GaussianNB(**self.estimator_parameters)
results.append(('model', 'model type', 'GNB qualitative'))
if self.conformal:
self.conformal_pred = AggregatedCp(
IcpClassifier(
ClassifierNc(ClassifierAdapter(self.estimator),
MarginErrFunc())), BootstrapSampler())
self.conformal_pred.fit(X, Y)
# overrides non-conformal
results.append(
('model', 'model type', 'conformal GNB qualitative'))
self.estimator.fit(X, Y)
return True, results
def build(self):
'''Build a new SVM model with the X and Y numpy matrices'''
# Make a copy of data matrices
X = self.X.copy()
Y = self.Y.copy()
results = []
results.append(('nobj', 'number of objects', self.nobj))
results.append(('nvarx', 'number of predictor variables', self.nvarx))
# If tune then call gridsearch to optimize the estimator
if self.param.getVal('tune'):
try:
# Check type of model
if self.param.getVal('quantitative'):
self.optimize(X, Y, svm.SVR(**self.estimator_parameters),
self.tune_parameters)
results.append(('model', 'model type',
'SVM quantitative (optimized)'))
else:
self.optimize(X, Y, svm.SVC(**self.estimator_parameters),
self.tune_parameters)
results.append(
('model', 'model type', 'SVM qualitative (optimized)'))
LOG.debug('SVM estimator optimized')
except Exception as e:
LOG.error(f'Exception optimizing SVM'
f'estimator with exception {e}')
else:
try:
LOG.info("Building SVM model")
if self.param.getVal('quantitative'):
LOG.info("Building Quantitative SVM-R model")
self.estimator = svm.SVR(**self.estimator_parameters)
results.append(('model', 'model type', 'SVM quantitative'))
else:
self.estimator = svm.SVC(**self.estimator_parameters)
results.append(('model', 'model type', 'SVM qualitative'))
except Exception as e:
LOG.error(f'Exception building SVM'
f'estimator with exception {e}')
self.estimator.fit(X, Y)
self.estimator_temp = copy(self.estimator)
if self.param.getVal('conformal'):
try:
LOG.info("Building aggregated conformal SVM model")
if self.param.getVal('quantitative'):
underlying_model = RegressorAdapter(self.estimator_temp)
# normalizing_model = RegressorAdapter(
# KNeighborsRegressor(n_neighbors=5))
normalizing_model = RegressorAdapter(self.estimator_temp)
normalizer = RegressorNormalizer(underlying_model,
normalizing_model,
AbsErrorErrFunc())
nc = RegressorNc(underlying_model, AbsErrorErrFunc(),
normalizer)
# self.conformal_pred = AggregatedCp(IcpRegressor(
# RegressorNc(RegressorAdapter(self.estimator))),
# BootstrapSampler())
self.estimator = AggregatedCp(IcpRegressor(nc),
BootstrapSampler())
self.estimator.fit(X, Y)
# overrides non-conformal
results.append(
('model', 'model type', 'conformal SVM quantitative'))
else:
self.estimator = AggregatedCp(
IcpClassifier(
ClassifierNc(
ClassifierAdapter(self.estimator_temp),
MarginErrFunc())), BootstrapSampler())
self.estimator.fit(X, Y)
# overrides non-conformal
results.append(
('model', 'model type', 'conformal SVM qualitative'))
except Exception as e:
LOG.error(f'Exception building aggregated conformal SVM '
f'estimator with exception {e}')
# Fit estimator to the data
return True, results
# Define models
# -----------------------------------------------------------------------------
models = {
'ACP-RandomSubSampler':
AggregatedCp(
IcpRegressor(RegressorNc(RegressorAdapter(DecisionTreeRegressor()))),
RandomSubSampler()),
'ACP-CrossSampler':
AggregatedCp(
IcpRegressor(RegressorNc(RegressorAdapter(DecisionTreeRegressor()))),
CrossSampler()),
'ACP-BootstrapSampler':
AggregatedCp(
IcpRegressor(RegressorNc(RegressorAdapter(DecisionTreeRegressor()))),
BootstrapSampler())
}
# -----------------------------------------------------------------------------
# Train, predict and evaluate
# -----------------------------------------------------------------------------
for name, model in models.iteritems():
model.fit(data.data[train, :], data.target[train])
prediction = model.predict(data.data[test, :])
prediction_sign = model.predict(data.data[test, :],
significance=significance)
table = np.vstack((prediction_sign.T, truth)).T
df = pd.DataFrame(table, columns=columns)
print('\n{}'.format(name))
print('Error rate: {}'.format(
reg_mean_errors(prediction, truth, significance)))
def CF_qualitative_validation(self):
''' performs validation for conformal qualitative models '''
# Make a copy of original matrices.
X = self.X.copy()
Y = self.Y.copy()
# Total number of class 0 correct predictions.
c0_correct_all = 0
# Total number of class 0 incorrect predictions.
c0_incorrect_all = 0
# Total number of class 1 correct predictions.
c1_correct_all = 0
# Total number of class 1 incorrect predictions
c1_incorrect_all = 0
# Total number of instances out of the applicability domain.
not_predicted_all = 0
info = []
kf = KFold(n_splits=5, shuffle=True, random_state=46)
# Copy Y vector to use it as template to assign predictions
Y_pred = copy.copy(Y).tolist()
try:
for train_index, test_index in kf.split(X):
# Generate training and test sets
X_train, X_test = X[train_index], X[test_index]
Y_train, Y_test = Y[train_index], Y[test_index]
# Create the aggregated conformal classifier.
conformal_pred = AggregatedCp(
IcpClassifier(
ClassifierNc(ClassifierAdapter(self.estimator_temp),
MarginErrFunc())), BootstrapSampler())
# Fit the conformal classifier to the data
conformal_pred.fit(X_train, Y_train)
# Perform prediction on test set
prediction = conformal_pred.predict(
X_test, self.param.getVal('conformalSignificance'))
# Assign the prediction the correct index.
for index, el in enumerate(test_index):
Y_pred[el] = prediction[index]
# Iterate over the prediction and check the result
for i in range(len(Y_pred)):
real = float(Y[i])
predicted = Y_pred[i]
if predicted[0] != predicted[1]:
if real == 0 and predicted[0] == True:
c0_correct_all += 1
if real == 0 and predicted[1] == True:
c0_incorrect_all += 1
if real == 1 and predicted[1] == True:
c1_correct_all += 1
if real == 1 and predicted[0] == True:
c1_incorrect_all += 1
else:
not_predicted_all += 1
except Exception as e:
LOG.error(f'Qualitative conformal validation'
f' failed with exception: {e}')
raise e
# Get the mean confusion matrix.
self.TN = c0_correct_all
self.FP = c0_incorrect_all
self.TP = c1_correct_all
self.FN = c1_incorrect_all
not_predicted_all = not_predicted_all
info.append(('TP', 'True positives in cross-validation', self.TP))
info.append(('TN', 'True negatives in cross-validation', self.TN))
info.append(('FP', 'False positives in cross-validation', self.FP))
info.append(('FN', 'False negatives in cross-validation', self.FN))
# Compute sensitivity, specificity and MCC
try:
self.sensitivity = (self.TP / (self.TP + self.FN))
except Exception as e:
LOG.error(f'Failed to compute sensibility with' f'exception {e}')
self.sensitivity = '-'
try:
self.specificity = (self.TN / (self.TN + self.FP))
except Exception as e:
LOG.error(f'Failed to compute specificity with' f'exception {e}')
self.specificity = '-'
try:
# Compute Matthews Correlation Coefficient
self.mcc = (((self.TP * self.TN) - (self.FP * self.FN)) / np.sqrt(
(self.TP + self.FP) * (self.TP + self.FN) *
(self.TN + self.FP) * (self.TN + self.FN)))
except Exception as e:
LOG.error(f'Failed to compute Mathews Correlation Coefficient'
f'exception {e}')
self.mcc = '-'
info.append(('Sensitivity', 'Sensitivity in cross-validation',
self.sensitivity))
info.append(('Specificity', 'Specificity in cross-validation',
self.specificity))
info.append(
('MCC', 'Matthews Correlation Coefficient in cross-validation',
self.mcc))
try:
# Compute coverage (% of compounds inside the applicability domain)
self.conformal_coverage = (
self.TN + self.FP + self.TP + self.FN) / (
(self.TN + self.FP + self.TP + self.FN) +
not_predicted_all)
except Exception as e:
LOG.error(f'Failed to compute conformal coverage with'
f'exception {e}')
self.conformal_coverage = '-'
try:
# Compute accuracy (% of correct predictions)
self.conformal_accuracy = (
float(self.TN + self.TP) /
float(self.FP + self.FN + self.TN + self.TP))
except Exception as e:
LOG.error(f'Failed to compute conformal accuracy with'
f'exception {e}')
self.conformal_accuracy = '-'
info.append(('Conformal_coverage', 'Conformal coverage',
self.conformal_coverage))
info.append(('Conformal_accuracy', 'Conformal accuracy',
self.conformal_accuracy))
results = {}
results['quality'] = info
#results ['classes'] = prediction
return True, results
def CF_quantitative_validation(self):
''' Performs internal validation for conformal quantitative models '''
# Make a copy of original matrices.
X = self.X.copy()
Y = self.Y.copy()
info = []
kf = KFold(n_splits=self.param.getVal('ModelValidationN'),
shuffle=True,
random_state=46)
# Copy Y vector to use it as template to assign predictions
Y_pred = copy.copy(Y).tolist()
try:
for train_index, test_index in kf.split(X):
# Generate training and test sets
X_train, X_test = X[train_index], X[test_index]
Y_train, Y_test = Y[train_index], Y[test_index]
# Generate training a test sets
# Create the aggregated conformal regressor.
conformal_pred = AggregatedCp(
IcpRegressor(
RegressorNc(RegressorAdapter(self.estimator_temp))),
BootstrapSampler())
# Fit conformal regressor to the data
conformal_pred.fit(X_train, Y_train)
# Perform prediction on test set
prediction = conformal_pred.predict(
X_test, self.param.getVal('conformalSignificance'))
# Assign the prediction its original index
for index, el in enumerate(test_index):
Y_pred[el] = prediction[index]
except Exception as e:
LOG.error(f'Quantitative conformal validation'
f' failed with exception: {e}')
raise e
Y_pred = np.asarray(Y_pred)
# Add the n validation interval means
interval_mean = np.mean(np.abs((Y_pred[:, 0]) - (Y_pred[:, 1])))
# Get boolean mask of instances
# within the applicability domain.
inside_interval = ((Y_pred[:, 0].reshape(-1, 1) < Y) &
(Y_pred[:, 1].reshape(-1, 1) > Y))
# Compute the accuracy (number of instances within the AD).
accuracy = np.sum(inside_interval) / len(Y)
# Cut into two decimals.
self.conformal_interval_medians = (np.mean(Y_pred, axis=1))
self.conformal_accuracy = float("{0:.2f}".format(accuracy))
self.conformal_mean_interval = float("{0:.2f}".format(interval_mean))
#Add quality metrics to results.
info.append(('Conformal_mean_interval', 'Conformal mean interval',
self.conformal_mean_interval))
info.append(('Conformal_accuracy', 'Conformal accuracy',
self.conformal_accuracy))
info.append(
('Conformal_interval_medians', 'Conformal interval medians',
self.conformal_interval_medians))
info.append(('Conformal_prediction_ranges',
'Conformal prediction ranges', Y_pred))
results = {}
results['quality'] = info
return True, results
def build(self):
# Make a copy of data matrices
X = self.X.copy()
Y = self.Y.copy()
results = []
results.append(('nobj', 'number of objects', self.nobj))
results.append(('nvarx', 'number of predictor variables', self.nvarx))
if self.param.getVal('tune'):
# Optimize estimator using sklearn-gridsearch
if self.estimator_parameters['optimize'] == 'auto':
try:
LOG.info('Optimizing PLSR using SK-LearnGridSearch')
# Remove optimize key from parameter dictionary
# to avoid sklearn estimator error (unexpected keyword)
self.estimator_parameters.pop("optimize")
super(PLSR, self).optimize(X, Y, PLS_r(
**self.estimator_parameters),
self.param.getDict('PLSR_optimize'))
except Exception as e:
LOG.error(f'Error performing SK-LearnGridSearch'
f' on PLSR estimator with exception {e}')
return False, f'Error performing SK-LearnGridSearch on PLSR estimator with exception {e}'
# Optimize using flame implementation (recommended)
elif self.estimator_parameters['optimize'] == 'manual':
LOG.info('Optimizing PLSR using manual method')
# Remove optimize key from parameter dictionary
# to avoid sklearn estimator error (unexpected keyword)
self.estimator_parameters.pop("optimize")
success, message = self.optimize(X, Y, PLS_r(
**self.estimator_parameters),
self.param.getDict('PLSR_optimize'))
if not success:
return False, message
else:
LOG.error('Type of tune not recognized, check the input')
return False, 'Type of tune not recognized, check the input'
results.append(('model', 'model type', 'PLSR quantitative (optimized)'))
else:
LOG.info('Building Quantitative PLSR with no optimization')
try:
# Remove optimize key from parameters to avoid error
self.estimator_parameters.pop("optimize")
# as the sklearn estimator does not have this key
self.estimator = PLS_r(**self.estimator_parameters)
except Exception as e:
LOG.error(f'Error at PLS_r instantiation with '
f'exception {e}')
return False, f'Error at PLS_da instantiation with exception {e}'
results.append(('model', 'model type', 'PLSR quantitative'))
# Fit estimator to the data
self.estimator.fit(X, Y)
if not self.param.getVal('conformal'):
return True, results
self.estimator_temp = copy(self.estimator)
try:
LOG.info('Building PLSR aggregated conformal predictor')
underlying_model = RegressorAdapter(self.estimator_temp)
# normalizing_model = RegressorAdapter(
# KNeighborsRegressor(n_neighbors=1))
normalizing_model = RegressorAdapter(self.estimator_temp)
normalizer = RegressorNormalizer(underlying_model, normalizing_model, AbsErrorErrFunc())
nc = RegressorNc(underlying_model, AbsErrorErrFunc(), normalizer)
self.estimator = AggregatedCp(IcpRegressor(nc), BootstrapSampler())
except Exception as e:
LOG.error(f'Error building aggregated PLSR conformal'
f' regressor with exception: {e}')
return False, f'Error building aggregated PLSR conformal regressor with exception: {e}'
# self.conformal_pred = AggregatedCp(IcpRegressor(
# RegressorNc(RegressorAdapter(self.estimator))),
# BootstrapSampler())
# Fit conformal estimator to the data
self.estimator.fit(X, Y)
# overrides non-conformal
results.append(('model', 'model type', 'conformal PLSR quantitative'))
return True, results
def build(self):
'''Build a new XGBOOST model with the X and Y numpy matrices '''
try:
from xgboost.sklearn import XGBClassifier
from xgboost.sklearn import XGBRegressor
except Exception as e:
return False, 'XGboost not found, please revise your environment'
# Make a copy of data matrices
X = self.X.copy()
Y = self.Y.copy()
results = []
results.append(('nobj', 'number of objects', self.nobj))
results.append(('nvarx', 'number of predictor variables', self.nvarx))
# If tune then call gridsearch to optimize the estimator
if self.param.getVal('tune'):
LOG.info("Optimizing XGBOOST estimator")
try:
# Check type of model
if self.param.getVal('quantitative'):
self.estimator = XGBRegressor(
**self.estimator_parameters)
self.optimize(X, Y, self.estimator, self.tune_parameters)
results.append(('model','model type','XGBOOST quantitative (optimized)'))
else:
self.estimator = XGBClassifier(
**self.estimator_parameters)
params = self.estimator.get_params()
params['num_class'] = 2
self.optimize(X, Y, self.estimator,
self.tune_parameters)
results.append(('model','model type','XGBOOST qualitative (optimized)'))
except Exception as e:
return False, f'Exception optimizing XGBOOST estimator with exception {e}'
else:
try:
if self.param.getVal('quantitative'):
LOG.info("Building Quantitative XGBOOST model")
# params = {
# 'objective': 'reg:squarederror',
# 'missing': -99.99999,
# # 'max_depth': 20,
# # 'learning_rate': 1.0,
# # 'silent': 1,
# # 'n_estimators': 25
# }
# self.estimator = XGBRegressor(**params)
self.estimator = XGBRegressor(**self.estimator_parameters)
results.append(('model', 'model type', 'XGBOOST quantitative'))
else:
LOG.info("Building Qualitative XGBOOST model")
# params = {
# 'objective': 'binary:logistic',
# 'max_depth': 3,
# #'learning_rate': 0.7,
# #'silent': 1,
# 'n_estimators': 100
# }
self.estimator = XGBClassifier(**self.estimator_parameters)
results.append(('model', 'model type', 'XGBOOST qualitative'))
self.estimator.fit(X, Y)
print(self.estimator)
except Exception as e:
raise e
return False, f'Exception building XGBOOST estimator with exception {e}'
self.estimator_temp = copy(self.estimator)
if not self.param.getVal('conformal'):
return True, results
# Create the conformal estimator
try:
# Conformal regressor
if self.param.getVal('quantitative'):
LOG.info("Building conformal Quantitative XGBOOST model")
underlying_model = RegressorAdapter(self.estimator_temp)
#normalizing_model = RegressorAdapter(
#KNeighborsRegressor(n_neighbors=5))
normalizing_model = RegressorAdapter(self.estimator_temp)
normalizer = RegressorNormalizer(
underlying_model,
normalizing_model,
AbsErrorErrFunc())
nc = RegressorNc(underlying_model,
AbsErrorErrFunc(),
normalizer)
# self.conformal_pred = AggregatedCp(IcpRegressor
# (RegressorNc(RegressorAdapter(self.estimator))),
# BootstrapSampler())
self.estimator = AggregatedCp(IcpRegressor(nc),
BootstrapSampler())
self.estimator.fit(X, Y)
results.append(('model', 'model type', 'conformal XGBOOST quantitative'))
# Conformal classifier
else:
LOG.info("Building conformal Qualitative XGBOOST model")
self.estimator = AggregatedCp(
IcpClassifier(
ClassifierNc(
ClassifierAdapter(self.estimator_temp),
MarginErrFunc()
)
),
BootstrapSampler())
# Fit estimator to the data
self.estimator.fit(X, Y)
results.append(('model', 'model type', 'conformal XGBOOST qualitative'))
except Exception as e:
raise e
return False, f'Exception building conformal XGBOOST estimator with exception {e}'
return True, results
## Overriding of parent methods
# def CF_quantitative_validation(self):
# ''' performs validation for conformal quantitative models '''
# def CF_qualitative_validation(self):
# ''' performs validation for conformal qualitative models '''
# def quantitativeValidation(self):
# ''' performs validation for quantitative models '''
# def qualitativeValidation(self):
# ''' performs validation for qualitative models '''
# def validate(self):
# ''' Validates the model and computes suitable model quality scoring values'''
# def optimize(self, X, Y, estimator, tune_parameters):
# ''' optimizes a model using a grid search over a range of values for diverse parameters'''
# def regularProject(self, Xb, results):
# ''' projects a collection of query objects in a regular model, for obtaining predictions '''
# def conformalProject(self, Xb, results):
# ''' projects a collection of query objects in a conformal model, for obtaining predictions '''
# def project(self, Xb, results):
# ''' Uses the X matrix provided as argument to predict Y'''
# Define models
# -----------------------------------------------------------------------------
models = {
'ACP-RandomSubSampler':
AggregatedCp(
IcpClassifier(ClassifierNc(ClassifierAdapter(
DecisionTreeClassifier()))), RandomSubSampler()),
'ACP-CrossSampler':
AggregatedCp(
IcpClassifier(ClassifierNc(ClassifierAdapter(
DecisionTreeClassifier()))), CrossSampler()),
'ACP-BootstrapSampler':
AggregatedCp(
IcpClassifier(ClassifierNc(ClassifierAdapter(
DecisionTreeClassifier()))), BootstrapSampler()),
'CCP':
CrossConformalClassifier(
IcpClassifier(ClassifierNc(ClassifierAdapter(
DecisionTreeClassifier())))),
'BCP':
BootstrapConformalClassifier(
IcpClassifier(ClassifierNc(ClassifierAdapter(
DecisionTreeClassifier()))))
}
# -----------------------------------------------------------------------------
# Train, predict and evaluate
# -----------------------------------------------------------------------------
for name, model in models.iteritems():
model.fit(data.data[train, :], data.target[train])
def build(self):
'''Build a new DL model with the X and Y numpy matrices '''
try:
from keras.wrappers.scikit_learn import KerasClassifier
from keras.wrappers.scikit_learn import KerasRegressor
except Exception as e:
return False, 'Keras not found, please revise your environment'
# Make a copy of data matrices
X = self.X.copy()
Y = self.Y.copy()
results = []
results.append(('nobj', 'number of objects', self.nobj))
results.append(('nvarx', 'number of predictor variables', self.nvarx))
# If tune then call gridsearch to optimize the estimator
if self.param.getVal('tune'):
LOG.info("Optimizing Keras estimator")
try:
# Check type of model
if self.param.getVal('quantitative'):
self.estimator = KerasRegressor(
**self.estimator_parameters)
self.optimize(X, Y, self.estimator, self.tune_parameters)
results.append(('model', 'model type',
'KERAS quantitative (optimized)'))
else:
self.estimator = KerasClassifier(
**self.estimator_parameters)
#params = self.estimator.get_params()
#params['num_class'] = 2
self.optimize(X, Y, self.estimator, self.tune_parameters)
results.append(('model', 'model type',
'KERAS qualitative (optimized)'))
except Exception as e:
return False, f'Exception optimizing KERAS estimator with exception {e}'
else:
try:
if self.param.getVal('quantitative'):
LOG.info("Building Quantitative KERAS mode")
self.estimator = KerasRegressor(
build_fn=self.create_model,
**self.estimator_parameters,
verbose=0)
results.append(
('model', 'model type', 'Keras quantitative'))
else:
LOG.info("Building Qualitative Keras model")
self.estimator = KerasClassifier(
build_fn=self.create_model,
dim=self.X.shape[1],
**self.estimator_parameters,
verbose=0)
results.append(
('model', 'model type', 'Keras qualitative'))
self.estimator.fit(X, Y)
print(self.estimator)
except Exception as e:
raise e
return False, f'Exception building Keras estimator with exception {e}'
self.estimator_temp = clone(self.estimator)
if not self.param.getVal('conformal'):
return True, results
# Create the conformal estimator
try:
# Conformal regressor
if self.param.getVal('quantitative'):
LOG.info("Building conformal Quantitative Keras model")
underlying_model = RegressorAdapter(self.estimator_temp)
normalizing_model = RegressorAdapter(
KNeighborsRegressor(n_neighbors=15))
# normalizing_model = RegressorAdapter(self.estimator_temp)
normalizer = RegressorNormalizer(underlying_model,
normalizing_model,
AbsErrorErrFunc())
nc = RegressorNc(underlying_model, AbsErrorErrFunc(),
normalizer)
# self.conformal_pred = AggregatedCp(IcpRegressor
# (RegressorNc(RegressorAdapter(self.estimator))),
# BootstrapSampler())
self.estimator = AggregatedCp(IcpRegressor(nc),
BootstrapSampler())
self.estimator.fit(X, Y)
results.append(
('model', 'model type', 'conformal Keras quantitative'))
# Conformal classifier
else:
LOG.info("Building conformal Qualitative Keras model")
self.estimator = AggregatedCp(
IcpClassifier(
ClassifierNc(ClassifierAdapter(self.estimator_temp),
MarginErrFunc())), BootstrapSampler())
# Fit estimator to the data
print('build finished')
self.estimator.fit(X, Y)
results.append(
('model', 'model type', 'conformal Keras qualitative'))
except Exception as e:
raise e
return False, f'Exception building conformal Keras estimator with exception {e}'
return True, []
def CF_qualitative_validation(self):
''' performs validation for conformal qualitative models '''
# Make a copy of original matrices.
X = self.X.copy()
Y = self.Y.copy()
# Number of external validations for the
# aggregated conformal estimator.
seeds = [5, 7, 35]
# Total number of class 0 correct predictions.
c0_correct_all = []
# Total number of class 0 incorrect predictions.
c0_incorrect_all = []
# Total number of class 1 correct predictions.
c1_correct_all = []
# Total number of class 1 incorrect predictions
c1_incorrect_all = []
# Total number of instances out of the applicability domain.
not_predicted_all = []
results = []
# Iterate over the seeds.
try:
for i in range(len(seeds)):
# Generate training and test sets
X_train, X_test,\
Y_train, Y_test = train_test_split(X, Y,
test_size=0.25,
random_state=i,
shuffle=True)
# Create the aggregated conformal classifier.
conformal_pred = AggregatedCp(
IcpClassifier(
ClassifierNc(ClassifierAdapter(self.estimator),
MarginErrFunc())), BootstrapSampler())
# Fit the conformal classifier to the data
conformal_pred.fit(X_train, Y_train)
# Perform prediction on test set
prediction = conformal_pred.predict(X_test,
self.conformalSignificance)
c0_correct = 0
c1_correct = 0
not_predicted = 0
c0_incorrect = 0
c1_incorrect = 0
# Iterate over the prediction and check the result
for i in range(len(Y_test)):
real = float(Y_test[i])
predicted = prediction[i]
if predicted[0] != predicted[1]:
if real == 0 and predicted[0] == True:
c0_correct += 1
if real == 0 and predicted[1] == True:
c0_incorrect += 1
if real == 1 and predicted[1] == True:
c1_correct += 1
if real == 1 and predicted[0] == True:
c1_incorrect += 1
else:
not_predicted += 1
# Add the results to the lists.
c0_correct_all.append(c0_correct)
c0_incorrect_all.append(c0_incorrect)
c1_correct_all.append(c1_correct)
c1_incorrect_all.append(c1_incorrect)
not_predicted_all.append(not_predicted)
except Exception as e:
LOG.error(f'Qualitative conformal validation'
f' failed with exception: {e}')
raise e
# Get the mean confusion matrix.
self.TN = np.int(np.mean(c0_correct_all))
self.FP = np.int(np.mean(c0_incorrect_all))
self.TP = np.int(np.mean(c1_correct_all))
self.FN = np.int(np.mean(c1_incorrect_all))
not_predicted_all = np.int(np.mean(not_predicted_all))
results.append(('TP', 'True positives in cross-validation', self.TP))
results.append(('TN', 'True negatives in cross-validation', self.TN))
results.append(('FP', 'False positives in cross-validation', self.FP))
results.append(('FN', 'False negatives in cross-validation', self.FN))
# Compute sensitivity and specificity
self.sensitivity = (self.TP / (self.TP + self.FN))
self.specificity = (self.TN / (self.TN + self.FP))
# Compute Matthews Correlation Coefficient
self.mcc = (((self.TP * self.TN) - (self.FP * self.FN)) / np.sqrt(
(self.TP + self.FP) * (self.TP + self.FN) * (self.TN + self.FP) *
(self.TN + self.FN)))
results.append(('Sensitivity', 'Sensitivity in cross-validation',
self.sensitivity))
results.append(('Specificity', 'Specificity in cross-validation',
self.specificity))
results.append(
('MCC', 'Matthews Correlation Coefficient in cross-validation',
self.mcc))
# Compute coverage (% of compouds inside the applicability domain)
self.conformal_coverage = (self.TN + self.FP + self.TP + self.FN) / (
(self.TN + self.FP + self.TP + self.FN) + not_predicted_all)
# Compute accuracy (% of correct predictions)
self.conformal_accuracy = float(self.TN +
self.TP) / float(self.FP + self.FN +
self.TN + self.TP)
results.append(('Conformal_coverage', 'Conformal coverage',
self.conformal_coverage))
results.append(('Conformal_accuracy', 'Conformal accuracy',
self.conformal_accuracy))
return True, (results, )
def build(self):
'''Build a new RF model with the X and Y numpy matrices '''
if self.failed:
return False
X = self.X.copy()
Y = self.Y.copy()
results = []
results.append(('nobj', 'number of objects', self.nobj))
results.append(('nvarx', 'number of predictor variables', self.nvarx))
if self.cv:
self.cv = getCrossVal(self.cv,
self.estimator_parameters["random_state"],
self.n, self.p)
if self.tune:
if self.quantitative:
self.optimize(X, Y, RandomForestRegressor(),
self.tune_parameters)
results.append(
('model', 'model type', 'RF quantitative (optimized)'))
else:
self.optimize(X, Y, RandomForestClassifier(),
self.tune_parameters)
results.append(
('model', 'model type', 'RF qualitative (optimized)'))
else:
if self.quantitative:
log.info("Building Quantitative RF model")
self.estimator_parameters.pop('class_weight', None)
self.estimator = RandomForestRegressor(
**self.estimator_parameters)
results.append(('model', 'model type', 'RF quantitative'))
else:
log.info("Building Qualitative RF model")
self.estimator = RandomForestClassifier(
**self.estimator_parameters)
results.append(('model', 'model type', 'RF qualitative'))
if self.conformal:
if self.quantitative:
underlying_model = RegressorAdapter(self.estimator)
normalizing_model = RegressorAdapter(
KNeighborsRegressor(n_neighbors=5))
normalizing_model = RegressorAdapter(self.estimator)
normalizer = RegressorNormalizer(underlying_model,
normalizing_model,
AbsErrorErrFunc())
nc = RegressorNc(underlying_model, AbsErrorErrFunc(),
normalizer)
# self.conformal_pred = AggregatedCp(IcpRegressor(RegressorNc(RegressorAdapter(self.estimator))),
# BootstrapSampler())
self.conformal_pred = AggregatedCp(IcpRegressor(nc),
BootstrapSampler())
self.conformal_pred.fit(X, Y)
# overrides non-conformal
results.append(
('model', 'model type', 'conformal RF quantitative'))
else:
self.conformal_pred = AggregatedCp(
IcpClassifier(
ClassifierNc(ClassifierAdapter(self.estimator),
MarginErrFunc())), BootstrapSampler())
self.conformal_pred.fit(X, Y)
# overrides non-conformal
results.append(
('model', 'model type', 'conformal RF qualitative'))
self.estimator.fit(X, Y)
return True, results
#### Overriding of parent methods
# def CF_quantitative_validation(self):
# ''' performs validation for conformal quantitative models '''
# def CF_qualitative_validation(self):
# ''' performs validation for conformal qualitative models '''
# def quantitativeValidation(self):
# ''' performs validation for quantitative models '''
# def qualitativeValidation(self):
# ''' performs validation for qualitative models '''
# def validate(self):
# ''' Validates the model and computes suitable model quality scoring values'''
# def optimize(self, X, Y, estimator, tune_parameters):
# ''' optimizes a model using a grid search over a range of values for diverse parameters'''
# def regularProject(self, Xb, results):
# ''' projects a collection of query objects in a regular model, for obtaining predictions '''
# def conformalProject(self, Xb, results):
# ''' projects a collection of query objects in a conformal model, for obtaining predictions '''
# def project(self, Xb, results):
# ''' Uses the X matrix provided as argument to predict Y'''
def test_acp_classification_tree(self):
# -----------------------------------------------------------------------------
# Experiment setup
# -----------------------------------------------------------------------------
data = load_iris()
idx = np.random.permutation(data.target.size)
train = idx[:int(2 * idx.size / 3)]
test = idx[int(2 * idx.size / 3):]
truth = data.target[test].reshape(-1, 1)
columns = ["C-{}".format(i)
for i in np.unique(data.target)] + ["truth"]
significance = 0.1
# -----------------------------------------------------------------------------
# Define models
# -----------------------------------------------------------------------------
models = {
"ACP-RandomSubSampler":
AggregatedCp(
IcpClassifier(
ClassifierNc(ClassifierAdapter(DecisionTreeClassifier()))),
RandomSubSampler(),
),
"ACP-CrossSampler":
AggregatedCp(
IcpClassifier(
ClassifierNc(ClassifierAdapter(DecisionTreeClassifier()))),
CrossSampler(),
),
"ACP-BootstrapSampler":
AggregatedCp(
IcpClassifier(
ClassifierNc(ClassifierAdapter(DecisionTreeClassifier()))),
BootstrapSampler(),
),
"CCP":
CrossConformalClassifier(
IcpClassifier(
ClassifierNc(ClassifierAdapter(
DecisionTreeClassifier())))),
"BCP":
BootstrapConformalClassifier(
IcpClassifier(
ClassifierNc(ClassifierAdapter(
DecisionTreeClassifier())))),
}
# -----------------------------------------------------------------------------
# Train, predict and evaluate
# -----------------------------------------------------------------------------
for name, model in models.items():
model.fit(data.data[train, :], data.target[train])
prediction = model.predict(data.data[test, :],
significance=significance)
table = np.hstack((prediction, truth))
df = pd.DataFrame(table, columns=columns)
print("\n{}".format(name))
print("Error rate: {}".format(
class_mean_errors(prediction, truth, significance)))
print(df)
self.assertTrue(True)
def build(self):
'''Build a new RF model with the X and Y numpy matrices '''
# Make a copy of data matrices
X = self.X.copy()
Y = self.Y.copy()
results = []
results.append(('nobj', 'number of objects', self.nobj))
results.append(('nvarx', 'number of predictor variables', self.nvarx))
results.append(('model', 'model type', 'RF'))
conformal = self.param.getVal('conformal')
# If tune then call gridsearch to optimize the estimator
if self.param.getVal('tune'):
LOG.info("Optimizing RF estimator")
try:
# Check type of model
if self.param.getVal('quantitative'):
self.estimator = RandomForestRegressor(
**self.estimator_parameters)
self.optimize(X, Y, self.estimator, self.tune_parameters)
# results.append(('model','model type','RF quantitative (optimized)'))
else:
self.estimator = RandomForestClassifier(
**self.estimator_parameters)
self.optimize(X, Y, self.estimator, self.tune_parameters)
# results.append(('model','model type','RF qualitative (optimized)'))
except Exception as e:
return False, f'Exception optimizing RF estimator with exception {e}'
else:
try:
if self.param.getVal('quantitative'):
self.estimator = RandomForestRegressor(
**self.estimator_parameters)
if not conformal:
LOG.info("Building Quantitative RF model")
# results.append(('model', 'model type', 'RF quantitative'))
else:
self.estimator = RandomForestClassifier(
**self.estimator_parameters)
if not conformal:
LOG.info("Building Qualitative RF model")
# results.append(('model', 'model type', 'RF qualitative'))
self.estimator.fit(X, Y)
except Exception as e:
return False, f'Exception building RF estimator with exception {e}'
if not conformal:
return True, results
self.estimator_temp = copy(self.estimator)
# Create the conformal estimator
try:
# Conformal regressor
if self.param.getVal('quantitative'):
conformal_settings = self.param.getDict('conformal_settings')
LOG.info("Building conformal Quantitative RF model")
underlying_model = RegressorAdapter(self.estimator_temp)
self.normalizing_model = RegressorAdapter(
KNeighborsRegressor(
n_neighbors=conformal_settings['KNN_NN']))
# normalizing_model = RegressorAdapter(self.estimator_temp)
normalizer = RegressorNormalizer(underlying_model,
copy(self.normalizing_model),
AbsErrorErrFunc())
nc = RegressorNc(underlying_model, AbsErrorErrFunc(),
normalizer)
# self.conformal_pred = AggregatedCp(IcpRegressor
# (RegressorNc(RegressorAdapter(self.estimator))),
# BootstrapSampler())
self.estimator = AggregatedCp(IcpRegressor(nc),
BootstrapSampler())
self.estimator.fit(X, Y)
# results.append(('model', 'model type', 'conformal RF quantitative'))
# Conformal classifier
else:
LOG.info("Building conformal Qualitative RF model")
self.estimator = AggregatedCp(
IcpClassifier(
ClassifierNc(ClassifierAdapter(self.estimator_temp),
MarginErrFunc())), BootstrapSampler())
# Fit estimator to the data
self.estimator.fit(X, Y)
# results.append(('model', 'model type', 'conformal RF qualitative'))
except Exception as e:
return False, f'Exception building conformal RF estimator with exception {e}'
return True, results
## Overriding of parent methods
# def CF_quantitative_validation(self):
# ''' performs validation for conformal quantitative models '''
# def CF_qualitative_validation(self):
# ''' performs validation for conformal qualitative models '''
# def quantitativeValidation(self):
# ''' performs validation for quantitative models '''
# def qualitativeValidation(self):
# ''' performs validation for qualitative models '''
# def validate(self):
# ''' Validates the model and computes suitable model quality scoring values'''
# def optimize(self, X, Y, estimator, tune_parameters):
# ''' optimizes a model using a grid search over a range of values for diverse parameters'''
# def regularProject(self, Xb, results):
# ''' projects a collection of query objects in a regular model, for obtaining predictions '''
# def conformalProject(self, Xb, results):
# ''' projects a collection of query objects in a conformal model, for obtaining predictions '''
# def project(self, Xb, results):
# ''' Uses the X matrix provided as argument to predict Y'''