def test_default():
params = Params({
'workspace_id': 'ws_id',
'amp_mat_upa': '1/2/3',
'output_name': 'out_name',
'rdp_clsf': {
'conf': 0.8,
'gene': 'silva_138_ssu',
},
})
assert params['amp_mat_upa'] == '1/2/3'
assert params['output_name'] == 'out_name'
assert params.getd('conf') == 0.8
assert params.getd('gene') == 'silva_138_ssu'
assert(
params.get_prose_args() == {
'conf': '0.8',
'gene': 'silva_138_ssu',
}
), json.dumps(params.get_prose_args(), indent=4)
assert(
params.cli_args == [
'--train_propfile',
Var.propfile['silva_138_ssu'],
]
), params.cli_args
str(params) # should not throw
def test_non_default():
params = Params({
'workspace_id': 'ws_id',
'amp_mat_upa': '5/5/5',
'output_name': 'out_name',
'rdp_clsf': {
'conf': 0.99999,
'gene': 'fungallsu',
},
})
assert params['amp_mat_upa'] == '5/5/5'
assert params['output_name'] == 'out_name'
assert params.getd('conf') == 0.99999
assert params.getd('gene') == 'fungallsu'
assert(
params.get_prose_args() == {
'conf': '0.99999',
'gene': 'fungallsu',
}
), json.dumps(params.get_prose_args(), indent=4)
assert(
params.cli_args == [
'--conf', '0.99999', '--gene', 'fungallsu',
]
), params.cli_args
str(params) # should not throw
def test_no_user_supplied_values():
params = Params({
'workspace_id': 'ws_id',
'amp_mat_upa': '6/6/6',
'output_name': 'out_name',
})
assert params['amp_mat_upa'] == '6/6/6'
assert params['output_name'] == 'out_name'
assert params.getd('conf') == 0.8
assert params.getd('gene') == 'silva_138_ssu'
assert(
params.get_prose_args() == {
'conf': '0.8',
'gene': 'silva_138_ssu',
}
), json.dumps(params.get_prose_args(), indent=4)
assert(
params.cli_args == [
'--train_propfile',
Var.propfile['silva_138_ssu'],
]
), params.cli_args
str(params) # should not throw
def test_get_fix_filtered_id2tax():
'''
Test: demangling, skipped ranks, filtered ranks
'''
Var.out_allRank_flpth = os.path.join(TEST_DATA_DIR, 'example_allRank.tsv') # old one without 'Genera Incertae Sedis'
Var.params = Params({
**req,
'conf': 0.8
})
id2tax = app_file.get_fix_filtered_id2tax()
id2tax_first = {
'000b0b88ceb19d19678f6c3a39f2db73': 'Bacteria;Proteobacteria;Alphaproteobacteria;Rhizobiales;Xanthobacteraceae;uncultured;',
'0013aacacdba8495d504237c6334ddfb': 'Bacteria;',
'00209e5d2aadb8c762613b92f7f4b21c': 'Bacteria;Verrucomicrobiota;Omnitrophia;Omnitrophales;Omnitrophaceae;Candidatus Omnitrophus;',
'0022fa9d411c3edb1b584d7fb5193749': 'Bacteria;Verrucomicrobiota;Verrucomicrobiae;Pedosphaerales;Pedosphaeraceae;',
'00250d6b968f2ad29019c64d89ece283': 'Bacteria;Proteobacteria;Gammaproteobacteria;Burkholderiales;Nitrosomonadaceae;MND1;',
'002597380ec40da68af2362f47542f89': '',
'0030f073f1f67fa8c7f01795583706e6': 'Bacteria;Proteobacteria;Gammaproteobacteria;Burkholderiales;Comamonadaceae;Rhodoferax;',
'0032ab5da12fadd744023dc9bbba5169': 'Bacteria;Proteobacteria;Gammaproteobacteria;Burkholderiales;',
'00360e9b675235e3ba5f1e6cf402cd73': 'Bacteria;Proteobacteria;Gammaproteobacteria;Burkholderiales;',
'0037cbd3eb6eaf9cba6a4c2b7d866d1f': 'Bacteria;Proteobacteria;Gammaproteobacteria;Diplorickettsiales;Diplorickettsiaceae;Aquicella;',
}
id2tax_skipRanks = {
'0134a9074c4afc9ac763f0482578f9e5': 'Bacteria;Firmicutes;Limnochordia;;;Hydrogenispora;',
'18a980ed927822f60eebf93600ee8ff4': 'Bacteria;Acidobacteriota;Acidobacteriae;;;Paludibaculum;',
'1a9c864d1f706bf185928fbf666f6880': 'Bacteria;Firmicutes;Clostridia;;Hungateiclostridiaceae;',
'1d1f284b1a3fc4545be7430ae7365c91': 'Bacteria;Firmicutes;Desulfotomaculia;Desulfotomaculales;;Pelotomaculum;',
'1ec12548cafe627d1212ffa9f9ef24c3': 'Bacteria;Acidobacteriota;Acidobacteriae;;;Paludibaculum;',
'209d2a7b32e4fd9500896c1910760c01': 'Bacteria;Acidobacteriota;Acidobacteriae;;;Paludibaculum;',
'22b3c70cdfb1714224e1bf8a6314bee9': 'Bacteria;Firmicutes;Clostridia;Peptostreptococcales-Tissierellales;;Finegoldia;',
'24a0b0f872dcff5625c7e671b86607bc': 'Bacteria;Firmicutes;Clostridia;;Hungateiclostridiaceae;HN-HF0106;',
'faec42549c32f5c311164c00ff260f72': 'Bacteria;Acidobacteriota;Acidobacteriae;;;Paludibaculum;',
'ff48ea2b9d30c737b53aeb9841179d57': 'Bacteria;Firmicutes;Clostridia;Peptostreptococcales-Tissierellales;;Parvimonas;',
}
id2tax_demangle = {
'000b0b88ceb19d19678f6c3a39f2db73': 'Bacteria;Proteobacteria;Alphaproteobacteria;Rhizobiales;Xanthobacteraceae;uncultured;',
'006344897e91aa92c15114a635558e4c': 'Bacteria;Firmicutes;Dethiobacteria;Dethiobacterales;Dethiobacteraceae;uncultured;',
'0063886685aeb8abd4643ca43d63c6fd': 'Bacteria;Gemmatimonadota;Gemmatimonadetes;Gemmatimonadales;Gemmatimonadaceae;uncultured;',
'00d4306620fb956f4cb8ea6616da13a3': 'Bacteria;Proteobacteria;Alphaproteobacteria;Rhizobiales;Rhizobiales Incertae Sedis;uncultured;',
'010a64540ce2e484b2177289a377246b': 'Bacteria;Proteobacteria;Alphaproteobacteria;Rhizobiales;Xanthobacteraceae;uncultured;',
'017740e814c004489ef488d9ba7e6bba': 'Bacteria;Chloroflexi;Anaerolineae;Anaerolineales;Anaerolineaceae;uncultured;',
'018e02f503aa9297bdf4fa8a3a5caf0d': 'Bacteria;Spirochaetota;Spirochaetia;Spirochaetales;Spirochaetaceae;uncultured;',
'019a8e93cde9dfce660c99097f2bc8ef': 'Bacteria;Proteobacteria;Alphaproteobacteria;Reyranellales;Reyranellaceae;uncultured;',
'ffdb83232218318beacfa5b9d2802d23': 'Bacteria;Gemmatimonadota;Gemmatimonadetes;Gemmatimonadales;Gemmatimonadaceae;uncultured;',
'ffe9568c3bbd5838f866595074ba1148': 'Bacteria;Desulfobacterota;Desulfuromonadia;Geobacterales;Geobacteraceae;uncultured;',
}
id2tax_expected = _add_dicts(
id2tax_first,
id2tax_skipRanks,
id2tax_demangle,
)
dprint('len(id2tax_expected) # should be about 30')
for id in id2tax_expected.keys():
assert id2tax[id] == id2tax_expected[id], '%s:\n%s\n%s' % (id, id2tax[id], id2tax_expected[id])
def test_small():
out_dir = os.path.join(TEST_DATA_DIR,
'return/enigma50by30/return/RDP_Classifier_output')
Var.out_allRank_flpth = os.path.join(out_dir, 'out_allRank.tsv')
Var.report_dir = os.path.join(run_dir, 'report_enigma50by30')
os.mkdir(Var.report_dir)
Var.params = Params(dict(**req, conf=0.8))
report.HTMLReportWriter(cmd_l=['test,', 'test,', 'small']).write()
def test_validation():
p = dict(
workspace_id=None,
amp_mat_upa=None,
rdp_clsf=dict(
gene=None,
conf=None,
),
output_name=None,
)
Params(p)
p = dict(
workspace_id=None,
amp_mat_upa=None,
rdp_clsf=dict(
gene=None,
conf=None,
),
outptu_name=None,
)
with raises(Exception): Params(p)
def test_dummy(i, conf):
out_dir = os.path.join(TEST_DATA_DIR,
'return/dummy10by8/return/RDP_Classifier_output')
Var.out_allRank_flpth = os.path.join(out_dir, 'out_allRank.tsv')
Var.report_dir = os.path.join(run_dir, 'report_dummy10by8_conf%g' % conf)
os.mkdir(Var.report_dir)
Var.params = Params(dict(
**req,
conf=conf,
))
report.HTMLReportWriter(
cmd_l=['test,', 'test,', 'dummy10by8',
'conf=%g' % conf]).write()
def test_small_linspace():
out_dir = os.path.join(TEST_DATA_DIR,
'return/enigma50by30/return/RDP_Classifier_output')
Var.out_allRank_flpth = os.path.join(out_dir, 'out_allRank.tsv')
for i, conf in enumerate(np.linspace(0, 1, 11)):
Var.report_dir = os.path.join(run_dir,
'report_enigma50by30_conf%g' % conf)
os.mkdir(Var.report_dir)
Var.params = Params(dict(**req, conf=conf))
report.HTMLReportWriter(
cmd_l=['test,', 'test,', 'small',
'conf=%g' % conf]).write()
def test_tiny(i):
out_dir = os.path.join(TEST_DATA_DIR,
'return/dummyTiny/return/RDP_Classifier_output')
Var.out_allRank_flpth = os.path.join(out_dir, 'out_allRank%d.tsv' % i)
Var.report_dir = os.path.join(run_dir, 'report_dummyTiny_%d' % i)
os.mkdir(Var.report_dir)
Var.params = Params(dict(
**req,
conf=0.55555,
))
with open(Var.out_allRank_flpth) as fh:
allRank_lines = fh.readlines()
report.HTMLReportWriter(cmd_l=['test,', 'test,', 'dummyTiny',
'i=%d' % i] + allRank_lines).write()
def test_large():
'''
Globals used:
report_dir, report_template_flpth
out_allRank_flpth
params
'''
out_dir = os.path.join(
TEST_DATA_DIR, 'return/enigma17770by511/return/RDP_Classifier_output/')
Var.out_allRank_flpth = os.path.join(out_dir, 'out_allRank.tsv')
Var.report_dir = os.path.join(RUN_DIR, 'report_enigma17770by511')
os.mkdir(Var.report_dir)
Var.params = Params(dict(**req, conf=0.7777))
report.HTMLReportWriter(cmd_l=['test,', 'test,', 'large'] * 10).write()
def test_noRowAttrMap():
'''
Test row AttributeMapping behavior when AmpliconMatrix has no row AttributeMapping
'''
Var.run_dir = os.path.join(
scratch, 'test_AmpliconMatix_noRowAttributeMapping_AttributeMapping_' +
str(uuid.uuid4()))
Var.params = Params(
dict(
workspace_id='ws_id',
workspace_name='ws_name',
amp_mat_upa='amp/mat/upa',
output_name='out_name',
))
amp_mat = AmpliconMatrix(dummy10by8_AmpMat_noRowAttrMap)
attr_map = AttributeMapping(amp_mat.obj.get('row_attributemapping_ref'),
amp_mat)
##
## write new attribute/source
ind_0, attr_name_0 = attr_map.add_attribute_slot('biome', 'testing')
assert ind_0 == 0
assert attr_name_0 == 'biome', json.dumps(attr_map.obj, indent=3)
attr_map.update_attribute(
ind_0, {
"amplicon_id_0": "dummy0",
"amplicon_id_1": "dummy0",
"amplicon_id_2": "dummy0",
"amplicon_id_3": "dummy0",
"amplicon_id_4": "dummy0",
"amplicon_id_5": "dummy0",
"amplicon_id_6": "dummy0",
"amplicon_id_7": "dummy0",
"amplicon_id_8": "dummy0",
"amplicon_id_9": "dummy0"
})
assert attr_map.obj['instances']['amplicon_id_4'][ind_0] == 'dummy0'
##
## all same length
num_attr = len(attr_map.obj['attributes'])
for attr_l in attr_map.obj['instances'].values():
assert len(attr_l) == num_attr
def test_flatten():
d = {
'key0': 'hat',
'key1': 'bat',
'nest0': {
'key2': 'cat',
'key3': 'sat',
},
'key4': 'chat',
'nest1': {
'key5': 'gnat',
},
'key6': 'mat',
}
flatd = Params.flatten(d)
assert len(flatd) == 7
assert all(['key%d' % i in flatd for i in range(7)])
assert all(['nest%d' % i not in flatd for i in range(2)])
assert flatd['key5'] == 'gnat'