def gen_feature_nodearray()

in liblinear/liblinear.py [0:0]

• 42 lines of code
• 11 McCabe index (conditional complexity)

def gen_feature_nodearray(xi, feature_max=None):
	if feature_max:
		assert(isinstance(feature_max, int))

	xi_shift = 0 # ensure correct indices of xi
	if scipy and isinstance(xi, tuple) and len(xi) == 2\
			and isinstance(xi[0], scipy.ndarray) and isinstance(xi[1], scipy.ndarray): # for a sparse vector
		index_range = xi[0] + 1 # index starts from 1
		if feature_max:
			index_range = index_range[scipy.where(index_range <= feature_max)]
	elif scipy and isinstance(xi, scipy.ndarray):
		xi_shift = 1
		index_range = xi.nonzero()[0] + 1 # index starts from 1
		if feature_max:
			index_range = index_range[scipy.where(index_range <= feature_max)]
	elif isinstance(xi, (dict, list, tuple)):
		if isinstance(xi, dict):
			index_range = xi.keys()
		elif isinstance(xi, (list, tuple)):
			xi_shift = 1
			index_range = range(1, len(xi) + 1)
		index_range = filter(lambda j: xi[j-xi_shift] != 0, index_range)

		if feature_max:
			index_range = filter(lambda j: j <= feature_max, index_range)
		index_range = sorted(index_range)
	else:
		raise TypeError('xi should be a dictionary, list, tuple, 1-d numpy array, or tuple of (index, data)')

	ret = (feature_node*(len(index_range)+2))()
	ret[-1].index = -1 # for bias term
	ret[-2].index = -1

	if scipy and isinstance(xi, tuple) and len(xi) == 2\
			and isinstance(xi[0], scipy.ndarray) and isinstance(xi[1], scipy.ndarray): # for a sparse vector
		for idx, j in enumerate(index_range):
			ret[idx].index = j
			ret[idx].value = (xi[1])[idx]
	else:
		for idx, j in enumerate(index_range):
			ret[idx].index = j
			ret[idx].value = xi[j - xi_shift]

	max_idx = 0
	if len(index_range) > 0:
		max_idx = index_range[-1]
	return ret, max_idx