if __name__ == "__main__":
# main protoml pipeline
P = Pipeline()
# load data
digits = datasets.load_digits()
test = int(digits.data.shape[0] * .25)
# construct all nodes to be used
# data nodes
P.add_nodes(
# node for training data
("Training Data", LabeledTrainingDataNode(digits.data[:-test],
digits.target[:-test])),
# node for validation data
("Validation Data", LabeledTestDataNode(digits.data[-test:],
digits.target[-test:])),
)
# create nodes using scikit-learn's support vector classification
# over logarithmic range of C from 0.01 to 1000
for exp in range(-1, 3):
# use one vs all node for multi-classification
# note use of node naming
P.add_node("SVM %s" % 10 ** exp, SklearnOneVsRestNode(svm.SVC, C=10 ** exp))
# create node for scoring the classifers
P.add_node("Metrics", MetricNode([accuracy_score, f1_score],
verbose=True))