def test_terminal_taxa_duplicate(self):
""" Test the terminal taxa function with two duplicate terminal taxa"""
taxa = [
"k__k1;p__p1", "k__k1;p__p1;c__c1", "k__k2;p__p2",
"k__k3;p__p3;c__c2;o__o3", "k__k3;p__p3;c__c2;o__o3"
]
data = [[1], [2], [3], [4], [5]]
# it is expected that order of the taxa will stay the same as the original input
expected_taxa = [
"k__k1;p__p1;c__c1", "k__k2;p__p2", "k__k3;p__p3;c__c2;o__o3"
]
expected_data = [[2], [3], [9]]
actual_taxa, actual_data = utilities.terminal_taxa(taxa, data)
self.assertEqual(actual_taxa, expected_taxa)
self.assertEqual(actual_data, expected_data)
def test_terminal_taxa_unclassified_species(self):
""" Test the terminal taxa function with a taxon with unclassified at species level"""
taxa = [
"k__k3;p__p3;c__c2;o__o3;f__f1;g__g1;s__",
"k__k3;p__p3;c__c2;o__o3;f__f1;g__g1;s__s1"
]
data = [[1], [2]]
# it is expected that order of the taxa will stay the same as the original input
expected_taxa = [
"k__k3;p__p3;c__c2;o__o3;f__f1;g__g1;s__",
"k__k3;p__p3;c__c2;o__o3;f__f1;g__g1;s__s1"
]
expected_data = [[1], [2]]
actual_taxa, actual_data = utilities.terminal_taxa(taxa, data)
self.assertEqual(actual_taxa, expected_taxa)
self.assertEqual(actual_data, expected_data)
def test_terminal_taxa_unclassified_family(self):
""" Test the terminal taxa function with a taxon with unclassified at family level"""
taxa = [
"k__k1;p__p1", "k__k1;p__p1;c__c1", "k__k2;p__p2",
"k__k3;p__p3;c__c2;o__o3;f__;g__;s__",
"k__k3;p__p3;c__c2;o__o3;f__f1"
]
data = [[1], [2], [3], [4], [5]]
# it is expected that order of the taxa will stay the same as the original input
expected_taxa = [
"k__k1;p__p1;c__c1", "k__k2;p__p2",
"k__k3;p__p3;c__c2;o__o3;f__;g__;s__",
"k__k3;p__p3;c__c2;o__o3;f__f1"
]
expected_data = [[2], [3], [4], [5]]
actual_taxa, actual_data = utilities.terminal_taxa(taxa, data)
self.assertEqual(actual_taxa, expected_taxa)
self.assertEqual(actual_data, expected_data)
vars,
sorted_samples,
sorted_top_data_plus_other,
top_taxa_short_names_plus_other,
max_taxa,
feature="genera")
#' <% if pdf_format: print("\clearpage") %>
#' ## Terminal Taxa
#+ echo=False
# plot the relative abundance of the top terminal taxa
# get the terminal taxa
terminal_taxa_relab, terminal_data_relab = utilities.terminal_taxa(
taxonomy, relab_data)
# get the top rows of terminal taxa
top_terminal_taxa, top_terminal_data = utilities.top_rows(terminal_taxa_relab,
terminal_data_relab,
max_taxa,
function="average")
# reduce the taxa names to just the most specific identifier
shorted_names = utilities.taxonomy_trim(top_terminal_taxa)
# sort the data with the samples with the top terminal taxa first
sorted_samples_terminal, sorted_data_terminal = utilities.sort_data(
top_terminal_data[0], samples)
transpose_top_terminal_data = numpy.transpose(top_terminal_data)
sorted_top_terminal_data = numpy.transpose([
transpose_top_terminal_data[samples.index(sample)]