def test_dataframe():
"tests dataframe production"
data = next(
create(utfilepath('big_selected'), EventDetectionTask(),
PeakSelectorTask(),
DataFrameTask(merge=True, measures=dict(dfevents=True))).run())
assert isinstance(data, pd.DataFrame)
assert 'track' in data.index.names
assert 'bead' in data.index.names
assert 'peakposition' in data
assert 'events' in data
assert isinstance(data.events[0], pd.DataFrame)
data = next(
create(utfilepath('big_selected'), EventDetectionTask(),
PeakSelectorTask(), DataFrameTask(merge=True)).run())
assert isinstance(data, pd.DataFrame)
assert 'track' in data.index.names
assert 'bead' in data.index.names
assert 'cycle' not in data.index.names
assert 'peakposition' in data
data = next(
create(utfilepath('big_selected'), EventDetectionTask(),
PeakSelectorTask(),
DataFrameTask(merge=True, measures=dict(events=True))).run())
assert isinstance(data, pd.DataFrame)
assert 'track' in data.index.names
assert 'bead' in data.index.names
assert 'cycle' in data.index.names
assert 'peakposition' in data
def test_reporting():
"tests processor"
for path in Path(gettempdir()).glob("*_peakfindingtest*.xlsx"):
path.unlink()
out = mktemp() + "_peakfindingtest3.xlsx"
fname = Path(cast(str, utfilepath("big_legacy"))).parent / "*.trk"
tasks = computereporters(
dict(track=(fname, cast(str, utfilepath("CTGT_selection"))),
reporting=out))
_ = next(tasks)
assert Path(out).exists()
def test_reporting():
"tests processor"
for path in Path(gettempdir()).glob("*_hybridstattest*.*"):
path.unlink()
out = mktemp() + "_hybridstattest5.xlsx"
tasks = computereporters(
dict(track=(Path(utfilepath("big_legacy")).parent / "*.trk",
utfilepath("CTGT_selection")),
reporting=out,
sequence=utfilepath("hairpins.fasta")))
_ = next(tasks)
assert Path(out).exists()
def test_processor():
"tests processor"
for path in Path(gettempdir()).glob("*_hybridstattest*.xlsx"):
path.unlink()
out = mktemp() + "_hybridstattest3.xlsx"
task = HybridstatBatchTask()
task.addpaths(track=(Path(utfilepath("big_legacy")).parent / "*.trk",
utfilepath("CTGT_selection")),
reporting=out,
sequence=utfilepath("hairpins.fasta"))
pair = create((task, ))
assert not Path(out).exists()
pair.run()
assert Path(out).exists()
def test_control():
"tests task controller"
peaks = [1., 5., 10., 20.]
pair = create((EventSimulatorTask(peaks=peaks,
brownian=.01,
stretch=None,
bias=None,
rates=None,
baselineargs=None,
nbeads=2,
ncycles=20), PeakSelectorTask()))
beads = tuple(tuple(i) for i in pair.run())[0]
assert tuple(i[0] for i in beads) == (0, 1)
vals = tuple(beads[0][1])
assert_allclose([i for i, _ in vals], [0.] + peaks, atol=.01, rtol=1e-2)
for peak, evts in vals:
assert evts.dtype == 'O'
assert all(i.dtype == EVENTS_DTYPE for i in evts)
tmp = [i[0]['data'].min() for i in evts]
assert_allclose(tmp, (peak, ) * 20, atol=0.1)
tmp = [i[0]['data'].max() for i in evts]
assert_allclose(tmp, (peak, ) * 20, atol=0.1)
# test that things don't crash
pair = create(utfilepath('big_selected'), EventDetectionTask(),
PeakSelectorTask())
beads = tuple(next(pair.run())[0])
def test_hybridstat_xlsxio():
"tests xlxs production"
from tornado.ioloop import IOLoop # noqa: E402
from tornado.platform.asyncio import AsyncIOMainLoop # noqa: E402
from tests.testingcore import path as utfilepath # noqa: E402
from hybridstat.reporting.batch import createmodels as _hmodels # noqa: E402
from hybridstat.view._io import ConfigXlsxIO # noqa: E402
asyncio.set_event_loop(asyncio.new_event_loop())
AsyncIOMainLoop().make_current()
path = cast(Path, utfilepath("big_legacy"))
track = Path(path).parent/"*.trk", utfilepath("CTGT_selection")
itr = _hmodels(dict(track = track, # type: ignore
sequence = utfilepath("hairpins.fasta")))
mdl = next(itr)
for path in Path(gettempdir()).glob("*_hybridstattest*.*"):
path.unlink()
out = mktemp()+"_hybridstattest4.xlsx"
assert not Path(out).exists()
# pylint: disable=protected-access
ConfigXlsxIO._run(dict(path = out,
oligos = 'CTGT',
sequences = utfilepath('hairpins.fasta')),
mdl)
cnt = 0
async def _run():
nonlocal cnt
for i in range(50):
if ConfigXlsxIO.RUNNING is False:
break
cnt = i
await asyncio.sleep(.5)
try:
IOLoop.current().run_sync(_run)
assert Path(out).exists()
assert cnt > 0
finally:
ConfigXlsxIO.RUNNING = False
def test_dataframe():
"tests dataframe production"
data = next(
create(utfilepath('big_selected'), EventDetectionTask(),
DataFrameTask(merge=True)).run())
assert isinstance(data, pd.DataFrame)
assert 'track' in data.index.names
assert 'bead' in data.index.names
assert 'cycle' in data.index.names
assert 'event' in data.index.names
assert 'avg' in data
assert 'modification' in data.columns
assert hasattr(data, 'tasklist')
def test_population_merge():
"tests population merge"
data = np.arange(100, dtype='f4')
intervals = np.array([(0, 10), (5, 17), (8, 20), (30, 40), (37, 41)],
dtype='i4')
merged = PopulationMerger(percentile=75.)(data, intervals)
assert tuple(tuple(i) for i in merged) == ((0, 10), (5, 20), (30, 41))
data = pickle.load(open(cast(str, utfilepath("eventsdata.pk")), 'rb'))
intervals = np.array([[1, 11], [12, 15], [16, 25], [26, 52], [55, 121],
[125, 136], [138, 453]],
dtype='i4')
merged = PopulationMerger()(data, intervals)
assert tuple(tuple(i) for i in merged) == ((1, 52), (55, 121), (125, 136),
(138, 453))
def test_ids():
"tests identifications"
for path in Path(gettempdir()).glob("*_hybridstattest*.xlsx"):
path.unlink()
out = mktemp() + "_hybridstattest10.xlsx"
assert not Path(out).exists()
writeparams(out, [('hp1', (1, 3, 5)), ('hp2', (10, )), ('hp3', tuple())])
assert Path(out).exists()
res = readparams(out)
assert set(i[:2] for i in res) == {(1, 'hp1'), (3, 'hp1'), (5, 'hp1'),
(10, 'hp2')}
res = readparams(utfilepath('hybridstat_report.xlsx'))
assert len(res) == 2
val = next(i for i in res if i[0] == 0)
assert val[:2] == (0, 'GF4')
assert_allclose(val[2:], [1173.87, 1.87], atol=2e-2)
def test_task():
"test task"
data = next(create(utfilepath('big_selected'), PeakProjectorTask()).run())
bead = data[0]
assert isinstance(bead, PeakListArray)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Tests for detection of peaks
will be expanded to include different methods
"""
import pickle
import numpy as np
from numpy.testing import assert_allclose
from peakfinding.groupby import MaxCov
from tests.testingcore import path as utfilepath
EMFITTER = MaxCov()
DATA = pickle.load(open(utfilepath('smallemdata'), "rb"))
def test_ztscore():
'tests the score method'
data = np.array([[0, 0], [10, 0], [0, 1]])
params = np.array([[0, 1, 0, 1], [10., 0.1**2, 0, 2], [5, 100, 0, 1],
[0, 100, 0.5, 1]])
score = EMFITTER.score(data, params)
assert_allclose(score,
np.array([[0.3989, 0, 0.1468], [0, 1.995, 0],
[0.0352, 0.0352, 0.0129], [0, 0, 0.0242]]),
rtol=1e-2,
atol=1e-2)
