Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ENH(OPT,TST): make test_transformations run 7 sec instead of 150 or so #413

Merged
merged 3 commits into from
Mar 21, 2019
Merged

ENH(OPT,TST): make test_transformations run 7 sec instead of 150 or so #413

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2e4d736
ENH: do not hardcode sampling rate(s) and expected values - use/compute
yarikoptic Mar 5, 2019
101956c
OPT(TST): select only 2 subjects for testing, hardcode even less numbers
yarikoptic Mar 5, 2019
9a1c357
OPT(TST): cache ds005 collection and return a clone upon invocation
yarikoptic Mar 5, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
64 changes: 46 additions & 18 deletions bids/analysis/tests/test_transformations.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
from bids.variables.entities import RunInfo
from bids.variables.kollekshuns import BIDSRunVariableCollection
from bids.layout import BIDSLayout
import math
import pytest
from os.path import join, sep
from bids.tests import get_test_data_path
Expand All @@ -16,14 +17,30 @@
import mock


# Sub-select collection for faster testing, without sacrificing anything
# in the tests
SUBJECTS = ['01', '02']
NRUNS = 3
SCAN_LENGTH = 480

cached_collections = {}


@pytest.fixture
def collection():
layout_path = join(get_test_data_path(), 'ds005')
layout = BIDSLayout(layout_path)
collection = layout.get_collections('run', types=['events'],
scan_length=480, merge=True,
sampling_rate=10)
return collection
if 'ds005' not in cached_collections:
layout_path = join(get_test_data_path(), 'ds005')
layout = BIDSLayout(layout_path)
cached_collections['ds005'] = layout.get_collections(
'run',
types=['events'],
scan_length=SCAN_LENGTH,
merge=True,
sampling_rate=10,
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

btw, IIRC interesting "effects" did appear when I set it to 0.31, you get wonderful

_____________________________________________ test_resample_dense ______________________________________________

collection = <bids.variables.kollekshuns.BIDSRunVariableCollection object at 0x7fae82ce3810>

    def test_resample_dense(collection):
        new_sampling_rate = 50
        old_sampling_rate = collection.sampling_rate
        upsampling = float(new_sampling_rate) / old_sampling_rate
    
        collection['RT'] = collection['RT'].to_dense(old_sampling_rate)
        old_rt = collection['RT'].clone()
>       collection.resample(new_sampling_rate, in_place=True)

bids/analysis/tests/test_transformations.py:192: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
bids/variables/kollekshuns.py:279: in resample
    kind=kind)
bids/variables/variables.py:460: in resample
    f = interp1d(x, self.values.values.ravel(), kind=kind)
/usr/lib/python2.7/dist-packages/scipy/interpolate/interpolate.py:433: in __init__
    _Interpolator1D.__init__(self, x, y, axis=axis)
/usr/lib/python2.7/dist-packages/scipy/interpolate/polyint.py:60: in __init__
    self._set_yi(yi, xi=xi, axis=axis)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = <scipy.interpolate.interpolate.interp1d object at 0x7fae81d4f050>
yi = array([0.000e+00, 1.793e+00, 1.637e+00, 0.000e+00, 0.000e+00, 0.000e+00,
     ...e+00, 0.000e+00,
       1.440e+00, 0.000e+00, 2.071e+00, 0.000e+00, 0.000e+00])
xi = array([  0,   1,   2,   3,   4,   5,   6,   7,   8,   9,  10,  11,  12,
      ..., 880, 881, 882, 883,
       884, 885, 886, 887, 888, 889, 890, 891, 892, 893])
axis = -1

    def _set_yi(self, yi, xi=None, axis=None):
        if axis is None:
            axis = self._y_axis
        if axis is None:
            raise ValueError("no interpolation axis specified")
    
        yi = np.asarray(yi)
    
        shape = yi.shape
        if shape == ():
            shape = (1,)
        if xi is not None and shape[axis] != len(xi):
>           raise ValueError("x and y arrays must be equal in length along "
                             "interpolation axis.")
E           ValueError: x and y arrays must be equal in length along interpolation axis.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ah, good catch. Maybe open a separate issue for that.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

isn't it #361?

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It is!

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@yarikoptic great minds fail alike

subject=SUBJECTS
)
# Always return a clone!
return cached_collections['ds005'].clone()


@pytest.fixture
Expand Down Expand Up @@ -77,8 +94,8 @@ def test_convolve(collection):


def test_rename(collection):
dense_rt = collection.variables['RT'].to_dense(10)
assert len(dense_rt.values) == 230400
dense_rt = collection.variables['RT'].to_dense(collection.sampling_rate)
assert len(dense_rt.values) == math.ceil(len(SUBJECTS) * NRUNS * SCAN_LENGTH * collection.sampling_rate)
transform.Rename(collection, 'RT', output='reaction_time')
assert 'reaction_time' in collection.variables
assert 'RT' not in collection.variables
Expand Down Expand Up @@ -132,9 +149,10 @@ def test_demean(collection):
def test_orthogonalize_dense(collection):
transform.Factor(collection, 'trial_type', sep=sep)

sampling_rate = collection.sampling_rate
# Store pre-orth variables needed for tests
pg_pre = collection['trial_type/parametric gain'].to_dense(10)
rt = collection['RT'].to_dense(10)
pg_pre = collection['trial_type/parametric gain'].to_dense(sampling_rate)
rt = collection['RT'].to_dense(sampling_rate)

# Orthogonalize and store result
transform.Orthogonalize(collection, variables='trial_type/parametric gain',
Expand Down Expand Up @@ -174,7 +192,8 @@ def test_split(collection):

orig = collection['RT'].clone(name='RT_2')
collection['RT_2'] = orig.clone()
collection['RT_3'] = collection['RT'].clone(name='RT_3').to_dense(10)
collection['RT_3'] = collection['RT']\
.clone(name='RT_3').to_dense(collection.sampling_rate)

rt_pre_onsets = collection['RT'].onset

Expand Down Expand Up @@ -208,14 +227,22 @@ def test_split(collection):


def test_resample_dense(collection):
collection['RT'] = collection['RT'].to_dense(10)
new_sampling_rate = 50
old_sampling_rate = collection.sampling_rate
upsampling = float(new_sampling_rate) / old_sampling_rate

collection['RT'] = collection['RT'].to_dense(old_sampling_rate)
old_rt = collection['RT'].clone()
collection.resample(50, in_place=True)
assert len(old_rt.values) * 5 == len(collection['RT'].values)
collection.resample(new_sampling_rate, in_place=True)
assert math.floor(len(old_rt.values) * upsampling) == len(collection['RT'].values)
# Should work after explicitly converting categoricals
transform.Factor(collection, 'trial_type')
collection.resample(5, force_dense=True, in_place=True)
assert len(old_rt.values) == len(collection['parametric gain'].values) * 2

new_sampling_rate2 = 5
upsampling2 = float(new_sampling_rate2) / old_sampling_rate

collection.resample(new_sampling_rate2, force_dense=True, in_place=True)
assert len(old_rt.values) == math.ceil(float(len(collection['parametric gain'].values) / upsampling2))


def test_threshold(collection):
Expand Down Expand Up @@ -346,12 +373,13 @@ def test_filter(collection):
transform.Filter(collection, 'RT', query=q, by='parametric gain')
assert len(orig.values) != len(collection['RT'].values)
# There is some bizarro thing going on where, on travis, the result is
# randomly either 1536 or 3909 when running on Python 3 (on linux or mac).
# randomly either 1536 (when all subjects are used) or 3909 when running
# on Python 3 (on linux or mac).
# Never happens locally, and I've had no luck tracking down the problem.
# Best guess is it reflects either some non-deterministic ordering of
# variables somewhere, or some weird precision issues when resampling to
# dense. Needs to be tracked down and fixed.
assert len(collection['RT'].values) in [1536, 3909]
assert len(collection['RT'].values) in [96 * len(SUBJECTS), 3909]


def test_replace(collection):
Expand Down