def test_reduce_to_vertices(self):
"""Tests reduce_to_vertices."""
test1 = [('1', '2', 0.1), ('2', '3', 0.2), ('1', '3', 0.3)]
expected1 = {
'1': numpy.array([0.1, 0.3]),
'2': numpy.array([0.1, 0.2]),
'3': numpy.array([0.2, 0.3]),
}
actual1 = edge_analysis.reduce_to_vertices(test1)
self._test_dict_to_numpy_array_equal(actual1, expected1)
test2 = []
expected2 = {}
actual2 = edge_analysis.reduce_to_vertices(test2)
self._test_dict_to_numpy_array_equal(actual2, expected2)
test3 = [('1', '1', 0.1), ('1', '1', 0.2), ('1', '1', 0.3)]
expected3 = {'1': numpy.array([0.1, 0.2, 0.3])}
actual3 = edge_analysis.reduce_to_vertices(test3)
self._test_dict_to_numpy_array_equal(actual3, expected3)
def test_reduce_to_vertices(self):
"""Tests reduce_to_vertices."""
test1 = [('1', '2', 0.1), ('2', '3', 0.2), ('1', '3', 0.3)]
expected1 = {
'1': numpy.array([0.1, 0.3]),
'2': numpy.array([0.1, 0.2]),
'3': numpy.array([0.2, 0.3]),
}
actual1 = edge_analysis.reduce_to_vertices(test1)
self._test_dict_to_numpy_array_equal(actual1, expected1)
test2 = []
expected2 = {}
actual2 = edge_analysis.reduce_to_vertices(test2)
self._test_dict_to_numpy_array_equal(actual2, expected2)
test3 = [('1', '1', 0.1), ('1', '1', 0.2), ('1', '1', 0.3)]
expected3 = {
'1': numpy.array([0.1, 0.2, 0.3])
}
actual3 = edge_analysis.reduce_to_vertices(test3)
self._test_dict_to_numpy_array_equal(actual3, expected3)
import edge_analysis
import simpson_diversity
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description='Calculate simpson diversity index for every vertex in '
'a network.')
parser.add_argument(
'file', nargs='?', type=argparse.FileType('r'),
default=sys.stdin, help='File to segment (default standard input).')
args = parser.parse_args()
edge_lines = edge_analysis.get_vertices_values(args.file)
edge_values = edge_analysis.reduce_to_vertices(edge_lines)
for vertex, values in edge_values.items():
# make every value in values an array because calculation functions
# expect multiple arrays grouped by segment
values_sum = numpy.sum(values)
single_value_arrays = (numpy.array(value) for value in values)
# We use weighted regardless of the input file because we the value to
# be taken into account. There is only one value, so looking at the
# number of values is useless.
diversity_index = (
simpson_diversity.calculate_weighted_simpson_diversity_index(
single_value_arrays, values_sum))
print('{}\t{}'.format(vertex, diversity_index))
