metavar = "filename", help = "[REQUIRED] outfile name", required = True) options = parser.parse_args() ############################# # Import json formatted OTU # ############################# import json jsondata = open(options.biominputfile) biom = json.load(jsondata) jsondata.close() from biom import Table table = Table.from_json(biom) print("") print("Original OTU Table (without taxonomy)") print("-------------------------------------") print("") print(table) print("") min_samplesize = int(min(table.sum(axis='sample'))) print("Subsampling to the smallest sample size: " + str(min_samplesize)) # Subsample table_ss = table.subsample(min_samplesize) # Output
def setUpClass(cls): _table1 = [ 'a\ta\t1\t0.0\t0.5\t0.1', 'a\ta\t1\t1.0\t1.0\t0.2', 'a\ta\t1\t2.0\t1.5\t0.2', 'a\tb\t1\t3.0\t2.0\t8.', 'a\tb\t1\t4.0\t2.5\t9.', 'a\tb\t1\t5.0\t3.0\t10.', 'b\ta\t1\t0.0\t2.0\t0.1', 'b\ta\t1\t1.0\t3.0\t0.3', 'b\ta\t1\t2.0\t4.0\t0.1', 'b\tb\t1\t3.0\t5.0\t9.', 'b\tb\t1\t4.0\t6.0\t11.', 'b\tb\t1\t5.0\t7.0\t10.' ] cls.table1 = pd.DataFrame( [(n.split('\t')) for n in _table1], columns=['group', 'dataset', 'level', 'x', 'y', 'c'], dtype=float) cls.table2 = """{"id": "None", "format": "Biological Observation Matrix 1.0.0", "format_url": "http:\/\/biom-format.org", "type": "OTU table", "generated_by": "greg", "date": "2013-08-22T13:10:23.907145", "matrix_type": "sparse", "matrix_element_type": "float", "shape": [ 3, 4 ], "data": [ [ 0, 0, 1 ], [ 0, 1, 2 ], [ 0, 2, 3 ], [ 0, 3, 4 ], [ 1, 0, 2 ], [ 1, 1, 0 ], [ 1, 2, 7 ], [ 1, 3, 8 ], [ 2, 0, 9 ], [ 2, 1, 10 ], [ 2, 2, 11 ], [ 2, 3, 12 ] ], "rows": [ { "id": "o1", "metadata": { "domain": "Archaea" } }, { "id": "o2", "metadata": { "domain": "Bacteria" } }, { "id": "o3", "metadata": { "domain": "Bacteria" } } ], "columns": [ { "id": "s1", "metadata": { "method": "A", "Sample": "A", "parameters": "A" } }, { "id": "s2", "metadata": { "method": "A", "Sample": "A", "parameters": "B" } }, { "id": "s3", "metadata": { "method": "A", "Sample": "A", "parameters": "C" } }, { "id": "s4", "metadata": { "method": "B", "Sample": "A", "parameters": "D" } } ] }""" # table 2 # OTU ID s1 s2 s3 s4 # o1 1.0 2.0 3.0 4.0 # o2 2.0 0.0 7.0 8.0 # o3 9.0 10.0 11.0 12.0 cls.tmpdir = mkdtemp() cls.table2 = Table.from_json(json.loads(cls.table2)) write_biom_table(cls.table2, 'hdf5', join(cls.tmpdir, 'table2.biom')) cls.dm, cls.s_md = make_distance_matrix(join(cls.tmpdir, 'table2.biom'), method="braycurtis") cls.dist = per_method_distance(cls.dm, cls.s_md, group_by='method', standard='B', metric='distance', sample='Sample')
metavar="filename", help="[REQUIRED] outfile name", required=True) options = parser.parse_args() ############################# # Import json formatted OTU # ############################# import json jsondata = open(options.biominputfile) biom = json.load(jsondata) jsondata.close() from biom import Table table = Table.from_json(biom) print("") print("Original OTU Table (without taxonomy)") print("-------------------------------------") print("") print(table) print("") min_samplesize = int(min(table.sum(axis='sample'))) print("Subsampling to the smallest sample size: " + str(min_samplesize)) # Subsample table_ss = table.subsample(min_samplesize) # Output
def setUp(self): self.table1 = Table.from_json(json.load(StringIO(table1))) self.table2 = Table.from_json(json.load(StringIO(table2))) self.table3 = Table.from_json(json.load(StringIO(table3))) self.mock_result_table1 = pd.DataFrame.from_csv(StringIO(mock_result_table1))
def setUp(self): _table1 = """{"id": "None", "format": "Biological Observation Matrix 1.0.0", "format_url": "http://biom-format.org", "type": "OTU table", "generated_by": "greg", "date": "2013-08-22T13:10:23.907145", "matrix_type": "sparse", "matrix_element_type": "float", "shape": [ 3, 4 ], "data": [ [ 0, 0, 1 ], [ 0, 1, 2 ], [ 0, 2, 3 ], [ 0, 3, 4 ], [ 1, 0, 2 ], [ 1, 1, 0 ], [ 1, 2, 7 ], [ 1, 3, 8 ], [ 2, 0, 9 ], [ 2, 1, 10 ], [ 2, 2, 11 ], [ 2, 3, 12 ] ], "rows": [ { "id": "k__Bacteria", "metadata": { "domain": "Bacteria" } }, { "id": "k__Archaea", "metadata": { "domain": "Archaea" } }, { "id": "k__[Fungi]", "metadata": { "domain": "[Fungi]" } } ], "columns": [ { "id": "s1", "metadata": { "country": "Peru", "pH": 4.2 } }, { "id": "s2", "metadata": { "country": "Peru", "pH": 5.2 } }, { "id": "s3", "metadata": { "country": "Peru", "pH": 5 } }, { "id": "s4", "metadata": { "country": "Peru", "pH": 4.9 } } ] }""" # table 1 # OTU ID s1 s2 s3 s4 # k__Archaea 1.0 2.0 3.0 4.0 # k__Bacteria 2.0 0.0 7.0 8.0 # k__[Fungi] 9.0 10.0 11.0 12.0 self.table1 = Table.from_json(json.loads(_table1))
def setUp(self): self.table1 = Table.from_json(json.load(StringIO(table1))) self.table2 = Table.from_json(json.load(StringIO(table2)))