def __init__(self, data, regularization_term=1.0, gamma=0.0):
features, weights, labels = data
self.gamma = gamma
self.c = regularization_term
self.clf = svm.SVC(C=self.c, gamma=self.gamma)
self.predictions, self.trnaccuracy, self.tstaccuracy = None, None, None
self.dataset = split_dataset(features, weights, labels)
def grid_search_best_parameter(data):
features, weights, labels = data
labels = np.array([1 if l == 'b' else 0 for l in labels])
trnfeatures, tstfeatures, trnweights, tstweights, trnlabels, tstlabels = split_dataset(features, weights, labels)
# Set the parameters by cross-validation
tuned_parameters = [{'kernel': ['rbf'], 'gamma': [1e-3, 1e-4], 'C': [1, 10, 100, 1000]}]
scores = ['precision', 'recall']
reports = {}
for score in scores:
LOGGER.info("# Tuning hyper-parameters for %s" % score)
clf = GridSearchCV(svm.SVC(C=1), tuned_parameters, cv=5, scoring=score)
clf.fit(trnfeatures, trnlabels)
LOGGER.info("Best parameters set found on development set:")
LOGGER.info(clf.best_estimator_)
LOGGER.info("Grid scores on development set:")
for params, mean_score, scores in clf.grid_scores_:
LOGGER.info("%0.3f (+/-%0.03f) for %r" % (mean_score, scores.std() / 2, params))
LOGGER.info("Detailed classification report:")
LOGGER.info("The model is trained on the full development set.")
LOGGER.info("The scores are computed on the full evaluation set.")
y_true, y_pred = tstlabels, clf.predict(tstfeatures)
reports[score] = classification_report(y_true, y_pred)
return reports
def _prepare_data(self):
self.dataset = split_dataset(self.features, self.weights, self.labels)
classes = set(self.labels)
def training_set():
ds = ClassificationDataSet(
self.dataset['training']['features'].shape[1],
1,
nb_classes=len(classes))
for i in range(self.dataset['training']['features'].shape[0]):
ds.addSample(self.dataset['training']['features'][i],
self.dataset['training']['labels'][i])
return ds
def test_set():
ds = ClassificationDataSet(self.features.shape[1],
1,
nb_classes=len(classes))
for i in range(self.dataset['test']['features'].shape[0]):
ds.addSample(self.dataset['test']['features'][i],
self.dataset['test']['labels'][i])
return ds
self.trndata = training_set()
self.tstdata = test_set()
self.tstdata._convertToOneOfMany()
self.trndata._convertToOneOfMany()
def grid_search_tradeoff_estimators_learning_rate(raw_data):
features, weights, labels = raw_data
dataset = split_dataset(features, weights, labels)
dataset['training']['labels'] = [1 if l == 's' else 0 for l in dataset['training']['labels']]
dataset['test']['labels'] = [1 if l == 's' else 0 for l in dataset['test']['labels']]
tunning_parameters = {'n_estimators': np.arange(50, 100, 5),
'learning_rate': np.arange(0.2, 2.2, .2)}
scores = ['precision', 'recall']
report = grid_search_best_parameter(dataset, AdaBoostClassifier, tunning_parameters, scores=scores)
return report
def grid_search_tradeoff_estimators_learning_rate(raw_data):
features, weights, labels = raw_data
dataset = split_dataset(features, weights, labels)
dataset['training']['labels'] = [
1 if l == 's' else 0 for l in dataset['training']['labels']
]
dataset['test']['labels'] = [
1 if l == 's' else 0 for l in dataset['test']['labels']
]
tunning_parameters = {
'n_estimators': np.arange(50, 100, 5),
'learning_rate': np.arange(0.2, 2.2, .2)
}
scores = ['precision', 'recall']
report = grid_search_best_parameter(dataset,
AdaBoostClassifier,
tunning_parameters,
scores=scores)
return report
def _prepare_data(self):
self.dataset = split_dataset(self.features, self.weights, self.labels)
classes = set(self.labels)
def training_set():
ds = ClassificationDataSet(self.dataset['training']['features'].shape[1], 1, nb_classes=len(classes))
for i in range(self.dataset['training']['features'].shape[0]):
ds.addSample(self.dataset['training']['features'][i],
self.dataset['training']['labels'][i])
return ds
def test_set():
ds = ClassificationDataSet(self.features.shape[1], 1, nb_classes=len(classes))
for i in range(self.dataset['test']['features'].shape[0]):
ds.addSample(self.dataset['test']['features'][i],
self.dataset['test']['labels'][i])
return ds
self.trndata = training_set()
self.tstdata = test_set()
self.tstdata._convertToOneOfMany()
self.trndata._convertToOneOfMany()
def estimate_components(data, iterations=10):
features, weights, labels = data
n_components = features.shape[1]
baseline_estimator = LinearSVC()
dataset = split_dataset(features, weights, labels)
train_features = dataset['training']['features']
test_features = dataset['test']['features']
start = time()
baseline_estimator.fit(train_features, dataset['training']['labels'])
elapsed = time() - start
baseline_accuracy = baseline_estimator.score(
test_features,
dataset['test']['labels'],
sample_weight=dataset['test']['weights'])
scores = []
baseline_record = [[n, 0, baseline_accuracy, elapsed]
for n in range(1, n_components)]
[scores.append(b) for b in baseline_record]
for component in range(1, n_components):
estimator = random_projection.SparseRandomProjection()
estimator.n_components = component
start = time()
for iter in range(1, iterations):
transformed_train_features = estimator.fit_transform(
train_features)
transformed_test_features = estimator.transform(test_features)
baseline_estimator.fit(transformed_train_features,
dataset['training']['labels'])
accuracy = baseline_estimator.score(
transformed_test_features,
dataset['test']['labels'],
sample_weight=dataset['test']['weights'])
scores.append([component, iter, accuracy, time() - start])
df = pd.DataFrame.from_records(
scores,
columns=['components', 'iteration', 'classification_accuracy', 'time'])
return df
def __init__(self, data, n_estimators=50, learning_rate=1.0):
features, weights, labels = data
self.clf = AdaBoostClassifier(n_estimators=n_estimators,
learning_rate=learning_rate)
self.predictions, self.trnaccuracy, self.tstaccuracy = None, None, None
self.dataset = split_dataset(features, weights, labels)
def __init__(self, data, n_neighbours=3, power_parameter=2):
features, weights, labels = data
self.clf = KNeighborsClassifier(n_neighbors=n_neighbours, p=power_parameter)
self.predictions, self.trnaccuracy, self.tstaccuracy = None, None, None
self.dataset = split_dataset(features, weights, labels)
def __init__(self, data, criterion='gini', min_samples_split=60):
features, weights, labels = data
self.clf = tree.DecisionTreeClassifier(criterion=criterion, min_samples_split=min_samples_split)
self.predictions, self.trnaccuracy, self.tstaccuracy = None, None, None
self.dataset = split_dataset(features, weights, labels)
def __init__(self, data, n_estimators=50, learning_rate=1.0):
features, weights, labels = data
self.clf = AdaBoostClassifier(n_estimators=n_estimators, learning_rate=learning_rate)
self.predictions, self.trnaccuracy, self.tstaccuracy = None, None, None
self.dataset = split_dataset(features, weights, labels)
