def build(kernel, metric, keys_limit, svm_C, logs):
trainX = genfromtxt('input/arcene_train.data', delimiter=' ')
trainY = genfromtxt('input/arcene_train.labels', delimiter=' ')
validX = genfromtxt('input/arcene_valid.data', delimiter=' ')
validY = genfromtxt('input/arcene_valid.labels', delimiter=' ')
keys = metric.build(trainX.transpose(),
trainY,
logs=logs,
limit=keys_limit)
tX = []
for x in trainX:
tX.append(np.take(x, keys))
tX = np.array(tX)
clf = SVM(kernel=kernel.kernel, C=svm_C)
clf.fit(tX, trainY)
vX = []
for x in validX:
vX.append(np.take(x, keys))
vX = np.array(vX)
predict_arr = [clf.predict(x) for x in vX]
confusion_matrix = Statistic.get_metrics(predict_arr, validY)
f_measure = Statistic.get_f_measure(confusion_matrix)
return keys, confusion_matrix, f_measure
