def done_part(cand, num_neighbs):
# Find the first `num_neighbs` complete columns in each row
rowxs, colxs = np.where(cand.validflags)
unique_rows, groupxs = vt.group_indices(rowxs, assume_sorted=True)
first_k_groupxs = [groupx[0:num_neighbs] for groupx in groupxs]
if DEBUG_REQUERY:
assert all(ut.issorted(groupx) for groupx in groupxs)
assert all([len(group) == num_neighbs for group in first_k_groupxs])
chosen_xs = np.array(ut.flatten(first_k_groupxs), dtype=np.int)
# chosen_xs = np.hstack(first_k_groupxs)
# then convert these to multi-indices
done_rows = rowxs.take(chosen_xs)
done_cols = colxs.take(chosen_xs)
multi_index = (done_rows, done_cols)
# done_shape = (cand.validflags.shape[0], num_neighbs)
# flat_xs = np.ravel_multi_index(multi_index, done_shape)
flat_xs = np.ravel_multi_index(multi_index, cand.idxs.shape)
_shape = (-1, num_neighbs)
idxs = cand.idxs.take(flat_xs).reshape(_shape)
dists = cand.dists.take(flat_xs).reshape(_shape)
trueks = colxs.take(chosen_xs).reshape(_shape)
if DEBUG_REQUERY:
# dists2 = dists.copy()
for count, (row, cols) in enumerate(zip(unique_rows, groupxs)):
pass
assert np.all(np.diff(dists, axis=1) >= 0)
valid = cand.validflags.take(flat_xs).reshape(_shape)
assert np.all(valid)
return idxs, dists, trueks
def trytest_multiple_add_removes():
r"""
CommandLine:
python -m wbia.algo.hots._neighbor_experiment --exec-test_multiple_add_removes
Example:
>>> # DISABLE_DOCTEST
>>> from wbia.algo.hots._neighbor_experiment import * # NOQA
>>> result = test_multiple_add_removes()
>>> print(result)
"""
from wbia.algo.hots.neighbor_index_cache import test_nnindexer
K = 4
nnindexer, qreq_, ibs = test_nnindexer('PZ_MTEST', use_memcache=False)
assert len(nnindexer.get_removed_idxs()) == 0
logger.info('\n\n --- got nnindex testdata --- ')
logger.info('')
@ut.tracefunc_xml
def print_nnindexer(nnindexer):
logger.info('nnindexer.get_indexed_aids() = %r' %
(nnindexer.get_indexed_aids(), ))
logger.info('nnindexer.num_indexed_vecs() = %r' %
(nnindexer.num_indexed_vecs(), ))
logger.info('nnindexer.get_removed_idxs().shape = %r' %
(nnindexer.get_removed_idxs().shape, ))
logger.info('INITIALIZE TEST')
print_nnindexer(nnindexer)
config2_ = qreq_.get_internal_query_config2()
qaid = 1
qfx2_vec = ibs.get_annot_vecs(qaid, config2_=config2_)
(qfx2_idx1, qfx2_dist1) = nnindexer.knn(qfx2_vec, K)
aids1 = set(nnindexer.get_nn_aids(qfx2_idx1).ravel())
logger.info('aids1 = %r' % (aids1, ))
logger.info('')
logger.info('TESTING ADD')
add_first_daids = [17, 22]
nnindexer.add_wbia_support(qreq_, add_first_daids)
print_nnindexer(nnindexer)
(qfx2_idx0, qfx2_dist0) = nnindexer.knn(qfx2_vec, K)
assert np.any(qfx2_idx0 != qfx2_idx1), 'some should change'
aids0 = set(nnindexer.get_nn_aids(qfx2_idx0).ravel())
logger.info('aids0 = %r' % (aids0, ))
# execute test function
logger.info('')
logger.info('TESTING REMOVE')
remove_daid_list = [8, 10, 11]
nnindexer.remove_wbia_support(qreq_, remove_daid_list)
print_nnindexer(nnindexer)
# test after modification
(qfx2_idx2, qfx2_dist2) = nnindexer.knn(qfx2_vec, K)
aids2 = set(nnindexer.get_nn_aids(qfx2_idx2).ravel())
logger.info('aids2 = %r' % (aids2, ))
assert len(aids2.intersection(remove_daid_list)) == 0
__removed_ids = nnindexer.flann._FLANN__removed_ids
invalid_idxs = nnindexer.get_removed_idxs()
assert len(np.intersect1d(invalid_idxs,
__removed_ids)) == len(__removed_ids)
logger.info('')
logger.info('TESTING DUPLICATE REMOVE')
nnindexer.remove_wbia_support(qreq_, remove_daid_list)
print_nnindexer(nnindexer)
# test after modification
(qfx2_idx2_, qfx2_dist2_) = nnindexer.knn(qfx2_vec, K)
assert np.all(qfx2_idx2_ == qfx2_idx2)
assert np.all(qfx2_dist2_ == qfx2_dist2)
logger.info('')
logger.info('TESTING ADD AFTER REMOVE')
# Is the error here happening because added points seem to
# get the ids of the removed points?
new_daid_list = [8, 10]
nnindexer.add_wbia_support(qreq_, new_daid_list)
print_nnindexer(nnindexer)
# test after modification
(qfx2_idx3, qfx2_dist3) = nnindexer.knn(qfx2_vec, K)
qfx2_aid3 = nnindexer.get_nn_aids(qfx2_idx3)
found_removed_idxs = np.intersect1d(qfx2_idx3,
nnindexer.get_removed_idxs())
if len(found_removed_idxs) != 0:
logger.info('found_removed_idxs.max() = %r' %
(found_removed_idxs.max(), ))
logger.info('found_removed_idxs.min() = %r' %
(found_removed_idxs.min(), ))
raise AssertionError('found_removed_idxs.shape = %r' %
(found_removed_idxs.shape, ))
aids3 = set(qfx2_aid3.ravel())
assert aids3.intersection(remove_daid_list) == set(
new_daid_list).intersection(remove_daid_list)
logger.info('TESTING DUPLICATE ADD')
new_daid_list = [8, 10]
nnindexer.add_wbia_support(qreq_, new_daid_list)
# test after modification
print_nnindexer(nnindexer)
(qfx2_idx3_, qfx2_dist3_) = nnindexer.knn(qfx2_vec, K)
qfx2_aid3_ = nnindexer.get_nn_aids(qfx2_idx3_)
assert np.all(qfx2_aid3 == qfx2_aid3_)
logger.info('TESTING ADD QUERY TO DATABASE')
add_daid_list1 = [qaid]
nnindexer.add_wbia_support(qreq_, add_daid_list1)
print_nnindexer(nnindexer)
(qfx2_idx4_, qfx2_dist4_) = nnindexer.knn(qfx2_vec, K)
qfx2_aid4_ = nnindexer.get_nn_aids(qfx2_idx4_)
qfx2_fx4_ = nnindexer.get_nn_featxs(qfx2_idx4_)
assert np.all(qfx2_aid4_.T[0] == qaid), 'should find self'
assert ut.issorted(qfx2_fx4_.T[0]), 'should be in order'
logger.info('TESTING REMOVE QUERY POINTS')
add_daid_list1 = [qaid]
nnindexer.remove_wbia_support(qreq_, add_daid_list1)
print_nnindexer(nnindexer)
(qfx2_idx5_, qfx2_dist5_) = nnindexer.knn(qfx2_vec, K)
issame = qfx2_idx5_ == qfx2_idx3_
percentsame = issame.sum() / issame.size
logger.info('percentsame = %r' % (percentsame, ))
assert (percentsame > 0.85
), 'a large majority of the feature idxs should remain the same'
print_nnindexer(nnindexer)
# Do this multiple times
for _ in range(10):
add_daid_list1 = [qaid]
nnindexer.add_wbia_support(qreq_, add_daid_list1, verbose=False)
nnindexer.remove_wbia_support(qreq_, add_daid_list1, verbose=False)
(qfx2_idxX_, qfx2_distX_) = nnindexer.knn(qfx2_vec, K)
issame = qfx2_idxX_ == qfx2_idx3_
percentsame = issame.sum() / issame.size
logger.info('percentsame = %r' % (percentsame, ))
assert (
percentsame > 0.85
), 'a large majority of the feature idxs should remain the same'
# Test again with more data
logger.info('testing remove query points with more data')
nnindexer.add_wbia_support(qreq_, ibs.get_valid_aids())
(qfx2_idx6_, qfx2_dist6_) = nnindexer.knn(qfx2_vec, K)
qfx2_aid6_ = nnindexer.get_nn_aids(qfx2_idx6_)
assert np.all(qfx2_aid6_.T[0] == qaid), 'should be same'
nnindexer.remove_wbia_support(qreq_, add_daid_list1)
print_nnindexer(nnindexer)
(qfx2_idx7_, qfx2_dist6_) = nnindexer.knn(qfx2_vec, K)
qfx2_aid7_ = nnindexer.get_nn_aids(qfx2_idx7_)
assert np.all(qfx2_aid7_.T[0] != qaid), 'should not be same'
# Do this multiple times
for _ in range(10):
add_daid_list1 = [qaid]
nnindexer.add_wbia_support(qreq_, add_daid_list1, verbose=True)
nnindexer.remove_wbia_support(qreq_, add_daid_list1, verbose=True)
# weird that all seem to work here
(qfx2_idxX_, qfx2_distX_) = nnindexer.knn(qfx2_vec, K)
issame = qfx2_idxX_ == qfx2_idx7_
percentsame = issame.sum() / issame.size
logger.info('percentsame = %r' % (percentsame, ))
print_nnindexer(nnindexer)
assert (
percentsame > 0.85
), 'a large majority of the feature idxs should remain the same'
nnindexer, qreq_, ibs = test_nnindexer('PZ_MTEST', use_memcache=False)
big_set = ibs.get_valid_aids()[5:]
remove_later = big_set[10:14]
nnindexer.add_wbia_support(qreq_, big_set)
# Try again where remove is not the last operation
logger.info('testing remove query points with more op')
extra_data = np.setdiff1d(ibs.get_valid_aids()[0:5], add_daid_list1)
nnindexer.remove_wbia_support(qreq_, extra_data)
nnindexer.add_wbia_support(qreq_, add_daid_list1)
nnindexer.add_wbia_support(qreq_, extra_data)
(qfx2_idx8_, qfx2_dist8_) = nnindexer.knn(qfx2_vec, K)
qfx2_aid8_ = nnindexer.get_nn_aids(qfx2_idx8_)
assert np.all(qfx2_aid8_.T[0] == qaid), 'should be same'
nnindexer.remove_wbia_support(qreq_, extra_data)
(qfx2_idx9_, qfx2_dist9_) = nnindexer.knn(qfx2_vec, K)
qfx2_aid9_ = nnindexer.get_nn_aids(qfx2_idx9_)
assert np.all(qfx2_aid9_.T[0] == qaid), 'should be same'
nnindexer.remove_wbia_support(qreq_, add_daid_list1)
nnindexer.add_wbia_support(qreq_, add_daid_list1)
nnindexer.add_wbia_support(qreq_, extra_data)
nnindexer.remove_wbia_support(qreq_, remove_later)
logger.info(nnindexer.ax2_aid)
aid_list = nnindexer.get_indexed_aids() # NOQA
nnindexer.flann.save_index('test.flann')
idx2_vec_masked = nnindexer.idx2_vec
idx2_vec_compressed = nnindexer.get_indexed_vecs()
from vtool._pyflann_backend import pyflann as pyflann
flann1 = pyflann.FLANN()
flann1.load_index('test.flann', idx2_vec_masked)
from vtool._pyflann_backend import pyflann as pyflann
flann2 = pyflann.FLANN()
flann2.load_index('test.flann', idx2_vec_compressed)
# NOW WE NEED TO TEST THAT WE CAN SAVE AND LOAD THIS DATA
#
# ax2_nvecs = ut.dict_take(ut.dict_hist(nnindexer.idx2_ax), range(len(nnindexer.ax2_aid)))
pass
def interpolate_replbounds(xdata, ydata, pt):
"""
xdata = np.array([.1, .2, .3, .4, .5])
ydata = np.array([.1, .2, .3, .4, .5])
pt = .35
FIXME:
if duplicate xdata is given bad things happen.
BUG:
in scipy.interpolate.interp1d
If there is a duplicate xdata, then assume_sorted=False will
sort ydata by xdata, but xdata should retain its initial ordering
in places of ambuguity. Currently it does not.
Args:
xdata (ndarray):
ydata (ndarray):
pt (ndarray):
Returns:
float: interp_vals
CommandLine:
python -m vtool.confusion --exec-interpolate_replbounds
Example:
>>> # DISABLE_DOCTEST
>>> from vtool.confusion import * # NOQA
>>> xdata = np.array([0.7, 0.8, 0.8, 0.9, 0.9, 0.9])
>>> ydata = np.array([34, 26, 23, 22, 19, 17])
>>> pt = np.array([.85, 1.0, -1.0])
>>> interp_vals = interpolate_replbounds(xdata, ydata, pt)
>>> result = ('interp_vals = %s' % (str(interp_vals),))
>>> print(result)
interp_vals = [ 22.5 17. 34. ]
"""
if not ut.issorted(xdata):
raise AssertionError("need to sort xdata and ydata in function")
sortx = np.lexsort(np.vstack([np.arange(len(xdata)), xdata]))
xdata = xdata.take(sortx, axis=0)
ydata = ydata.take(sortx, axis=0)
is_scalar = not ut.isiterable(pt)
# print('----')
# print('xdata = %r' % (xdata,))
# print('ydata = %r' % (ydata,))
if is_scalar:
pt = np.array([pt])
# ut.ensure_iterable(pt)
minval = xdata.min()
maxval = xdata.max()
argx_min_list = np.argwhere(xdata == minval)
argx_max_list = np.argwhere(xdata == maxval)
argx_min = argx_min_list.min()
argx_max = argx_max_list.max()
lower_mask = pt < xdata[argx_min]
upper_mask = pt > xdata[argx_max]
interp_mask = ~np.logical_or(lower_mask, upper_mask)
# if isinstance(pt, np.ndarray):
dtype = np.result_type(np.float32, ydata.dtype)
interp_vals = np.empty(pt.shape, dtype=dtype)
interp_vals[lower_mask] = ydata[argx_min]
interp_vals[upper_mask] = ydata[argx_max]
if np.any(interp_mask):
# FIXME: allow assume_sorted = False
func = scipy.interpolate.interp1d(xdata, ydata, kind="linear", assume_sorted=True)
interp_vals[interp_mask] = func(pt[interp_mask])
if is_scalar:
interp_vals = interp_vals[0]
# interpolate to target recall
# right_index = indicies[0]
# right_recall = self.recall[right_index]
# left_index = right_index - 1
# left_recall = self.recall[left_index]
# stepsize = right_recall - left_recall
# alpha = (target_recall - left_recall) / stepsize
# left_fpr = self.fpr[left_index]
# right_fpr = self.fpr[right_index]
# interp_fpp = (left_fpr * (1 - alpha)) + (right_fpr * (alpha))
return interp_vals
def test_multiple_add_removes():
r"""
CommandLine:
python -m ibeis.algo.hots._neighbor_experiment --exec-test_multiple_add_removes
Example:
>>> # DISABLE_DOCTEST
>>> from ibeis.algo.hots._neighbor_experiment import * # NOQA
>>> result = test_multiple_add_removes()
>>> print(result)
"""
from ibeis.algo.hots.neighbor_index_cache import test_nnindexer
K = 4
nnindexer, qreq_, ibs = test_nnindexer('PZ_MTEST', use_memcache=False)
assert len(nnindexer.get_removed_idxs()) == 0
print('\n\n --- got nnindex testdata --- ')
print('')
@ut.tracefunc_xml
def print_nnindexer(nnindexer):
print('nnindexer.get_indexed_aids() = %r' % (nnindexer.get_indexed_aids(),))
print('nnindexer.num_indexed_vecs() = %r' % (nnindexer.num_indexed_vecs(),))
print('nnindexer.get_removed_idxs().shape = %r' % (nnindexer.get_removed_idxs().shape,))
print('INITIALIZE TEST')
print_nnindexer(nnindexer)
config2_ = qreq_.get_internal_query_config2()
qaid = 1
qfx2_vec = ibs.get_annot_vecs(qaid, config2_=config2_)
(qfx2_idx1, qfx2_dist1) = nnindexer.knn(qfx2_vec, K)
aids1 = set(nnindexer.get_nn_aids(qfx2_idx1).ravel())
print('aids1 = %r' % (aids1,))
print('')
print('TESTING ADD')
add_first_daids = [17, 22]
nnindexer.add_ibeis_support(qreq_, add_first_daids)
print_nnindexer(nnindexer)
(qfx2_idx0, qfx2_dist0) = nnindexer.knn(qfx2_vec, K)
assert np.any(qfx2_idx0 != qfx2_idx1), 'some should change'
aids0 = set(nnindexer.get_nn_aids(qfx2_idx0).ravel())
print('aids0 = %r' % (aids0,))
# execute test function
print('')
print('TESTING REMOVE')
remove_daid_list = [8, 10, 11]
nnindexer.remove_ibeis_support(qreq_, remove_daid_list)
print_nnindexer(nnindexer)
# test after modification
(qfx2_idx2, qfx2_dist2) = nnindexer.knn(qfx2_vec, K)
aids2 = set(nnindexer.get_nn_aids(qfx2_idx2).ravel())
print('aids2 = %r' % (aids2,))
assert len(aids2.intersection(remove_daid_list)) == 0
__removed_ids = nnindexer.flann._FLANN__removed_ids
invalid_idxs = nnindexer.get_removed_idxs()
assert len(np.intersect1d(invalid_idxs, __removed_ids)) == len(__removed_ids)
print('')
print('TESTING DUPLICATE REMOVE')
nnindexer.remove_ibeis_support(qreq_, remove_daid_list)
print_nnindexer(nnindexer)
# test after modification
(qfx2_idx2_, qfx2_dist2_) = nnindexer.knn(qfx2_vec, K)
assert np.all(qfx2_idx2_ == qfx2_idx2)
assert np.all(qfx2_dist2_ == qfx2_dist2)
print('')
print('TESTING ADD AFTER REMOVE')
# Is the error here happening because added points seem to
# get the ids of the removed points?
new_daid_list = [8, 10]
nnindexer.add_ibeis_support(qreq_, new_daid_list)
print_nnindexer(nnindexer)
# test after modification
(qfx2_idx3, qfx2_dist3) = nnindexer.knn(qfx2_vec, K)
qfx2_aid3 = nnindexer.get_nn_aids(qfx2_idx3)
found_removed_idxs = np.intersect1d(qfx2_idx3, nnindexer.get_removed_idxs())
if len(found_removed_idxs) != 0:
print('found_removed_idxs.max() = %r' % (found_removed_idxs.max(),))
print('found_removed_idxs.min() = %r' % (found_removed_idxs.min(),))
raise AssertionError('found_removed_idxs.shape = %r' % (found_removed_idxs.shape,))
aids3 = set(qfx2_aid3.ravel())
assert aids3.intersection(remove_daid_list) == set(new_daid_list).intersection(remove_daid_list)
print('TESTING DUPLICATE ADD')
new_daid_list = [8, 10]
nnindexer.add_ibeis_support(qreq_, new_daid_list)
# test after modification
print_nnindexer(nnindexer)
(qfx2_idx3_, qfx2_dist3_) = nnindexer.knn(qfx2_vec, K)
qfx2_aid3_ = nnindexer.get_nn_aids(qfx2_idx3_)
assert np.all(qfx2_aid3 == qfx2_aid3_)
print('TESTING ADD QUERY TO DATABASE')
add_daid_list1 = [qaid]
nnindexer.add_ibeis_support(qreq_, add_daid_list1)
print_nnindexer(nnindexer)
(qfx2_idx4_, qfx2_dist4_) = nnindexer.knn(qfx2_vec, K)
qfx2_aid4_ = nnindexer.get_nn_aids(qfx2_idx4_)
qfx2_fx4_ = nnindexer.get_nn_featxs(qfx2_idx4_)
assert np.all(qfx2_aid4_.T[0] == qaid), 'should find self'
assert ut.issorted(qfx2_fx4_.T[0]), 'should be in order'
print('TESTING REMOVE QUERY POINTS')
add_daid_list1 = [qaid]
nnindexer.remove_ibeis_support(qreq_, add_daid_list1)
print_nnindexer(nnindexer)
(qfx2_idx5_, qfx2_dist5_) = nnindexer.knn(qfx2_vec, K)
issame = (qfx2_idx5_ == qfx2_idx3_)
percentsame = issame.sum() / issame.size
print('percentsame = %r' % (percentsame,))
assert percentsame > .85, 'a large majority of the feature idxs should remain the same'
print_nnindexer(nnindexer)
# Do this multiple times
for _ in range(10):
add_daid_list1 = [qaid]
nnindexer.add_ibeis_support(qreq_, add_daid_list1, verbose=False)
nnindexer.remove_ibeis_support(qreq_, add_daid_list1, verbose=False)
(qfx2_idxX_, qfx2_distX_) = nnindexer.knn(qfx2_vec, K)
issame = (qfx2_idxX_ == qfx2_idx3_)
percentsame = issame.sum() / issame.size
print('percentsame = %r' % (percentsame,))
assert percentsame > .85, 'a large majority of the feature idxs should remain the same'
# Test again with more data
print('testing remove query points with more data')
nnindexer.add_ibeis_support(qreq_, ibs.get_valid_aids())
(qfx2_idx6_, qfx2_dist6_) = nnindexer.knn(qfx2_vec, K)
qfx2_aid6_ = nnindexer.get_nn_aids(qfx2_idx6_)
assert np.all(qfx2_aid6_.T[0] == qaid), 'should be same'
nnindexer.remove_ibeis_support(qreq_, add_daid_list1)
print_nnindexer(nnindexer)
(qfx2_idx7_, qfx2_dist6_) = nnindexer.knn(qfx2_vec, K)
qfx2_aid7_ = nnindexer.get_nn_aids(qfx2_idx7_)
assert np.all(qfx2_aid7_.T[0] != qaid), 'should not be same'
# Do this multiple times
for _ in range(10):
add_daid_list1 = [qaid]
nnindexer.add_ibeis_support(qreq_, add_daid_list1, verbose=True)
nnindexer.remove_ibeis_support(qreq_, add_daid_list1, verbose=True)
# weird that all seem to work here
(qfx2_idxX_, qfx2_distX_) = nnindexer.knn(qfx2_vec, K)
issame = (qfx2_idxX_ == qfx2_idx7_)
percentsame = issame.sum() / issame.size
print('percentsame = %r' % (percentsame,))
print_nnindexer(nnindexer)
assert percentsame > .85, 'a large majority of the feature idxs should remain the same'
nnindexer, qreq_, ibs = test_nnindexer('PZ_MTEST', use_memcache=False)
big_set = ibs.get_valid_aids()[5:]
remove_later = big_set[10:14]
nnindexer.add_ibeis_support(qreq_, big_set)
# Try again where remove is not the last operation
print('testing remove query points with more op')
extra_data = np.setdiff1d(ibs.get_valid_aids()[0:5], add_daid_list1)
nnindexer.remove_ibeis_support(qreq_, extra_data)
nnindexer.add_ibeis_support(qreq_, add_daid_list1)
nnindexer.add_ibeis_support(qreq_, extra_data)
(qfx2_idx8_, qfx2_dist8_) = nnindexer.knn(qfx2_vec, K)
qfx2_aid8_ = nnindexer.get_nn_aids(qfx2_idx8_)
assert np.all(qfx2_aid8_.T[0] == qaid), 'should be same'
nnindexer.remove_ibeis_support(qreq_, extra_data)
(qfx2_idx9_, qfx2_dist9_) = nnindexer.knn(qfx2_vec, K)
qfx2_aid9_ = nnindexer.get_nn_aids(qfx2_idx9_)
assert np.all(qfx2_aid9_.T[0] == qaid), 'should be same'
nnindexer.remove_ibeis_support(qreq_, add_daid_list1)
nnindexer.add_ibeis_support(qreq_, add_daid_list1)
nnindexer.add_ibeis_support(qreq_, extra_data)
nnindexer.remove_ibeis_support(qreq_, remove_later)
print(nnindexer.ax2_aid)
aid_list = nnindexer.get_indexed_aids() # NOQA
nnindexer.flann.save_index('test.flann')
idx2_vec_masked = nnindexer.idx2_vec
idx2_vec_compressed = nnindexer.get_indexed_vecs()
import pyflann
flann1 = pyflann.FLANN()
flann1.load_index('test.flann', idx2_vec_masked)
import pyflann
flann2 = pyflann.FLANN()
flann2.load_index('test.flann', idx2_vec_compressed)
# NOW WE NEED TO TEST THAT WE CAN SAVE AND LOAD THIS DATA
#
#ax2_nvecs = ut.dict_take(ut.dict_hist(nnindexer.idx2_ax), range(len(nnindexer.ax2_aid)))
pass
def interpolate_replbounds(xdata, ydata, pt):
"""
xdata = np.array([.1, .2, .3, .4, .5])
ydata = np.array([.1, .2, .3, .4, .5])
pt = .35
FIXME:
if duplicate xdata is given bad things happen.
BUG:
in scipy.interpolate.interp1d
If there is a duplicate xdata, then assume_sorted=False will
sort ydata by xdata, but xdata should retain its initial ordering
in places of ambuguity. Currently it does not.
Args:
xdata (ndarray):
ydata (ndarray):
pt (ndarray):
Returns:
float: interp_vals
CommandLine:
python -m vtool.confusion --exec-interpolate_replbounds
Example:
>>> # DISABLE_DOCTEST
>>> from vtool.confusion import * # NOQA
>>> xdata = np.array([0.7, 0.8, 0.8, 0.9, 0.9, 0.9])
>>> ydata = np.array([34, 26, 23, 22, 19, 17])
>>> pt = np.array([.85, 1.0, -1.0])
>>> interp_vals = interpolate_replbounds(xdata, ydata, pt)
>>> result = ('interp_vals = %s' % (str(interp_vals),))
>>> print(result)
interp_vals = [ 22.5 17. 34. ]
"""
if not ut.issorted(xdata):
raise AssertionError('need to sort xdata and ydata in function')
sortx = np.lexsort(np.vstack([np.arange(len(xdata)), xdata]))
xdata = xdata.take(sortx, axis=0)
ydata = ydata.take(sortx, axis=0)
is_scalar = not ut.isiterable(pt)
#print('----')
#print('xdata = %r' % (xdata,))
#print('ydata = %r' % (ydata,))
if is_scalar:
pt = np.array([pt])
#ut.ensure_iterable(pt)
minval = xdata.min()
maxval = xdata.max()
argx_min_list = np.argwhere(xdata == minval)
argx_max_list = np.argwhere(xdata == maxval)
argx_min = argx_min_list.min()
argx_max = argx_max_list.max()
lower_mask = pt < xdata[argx_min]
upper_mask = pt > xdata[argx_max]
interp_mask = ~np.logical_or(lower_mask, upper_mask)
#if isinstance(pt, np.ndarray):
dtype = np.result_type(np.float32, ydata.dtype)
interp_vals = np.empty(pt.shape, dtype=dtype)
interp_vals[lower_mask] = ydata[argx_min]
interp_vals[upper_mask] = ydata[argx_max]
if np.any(interp_mask):
# FIXME: allow assume_sorted = False
func = scipy.interpolate.interp1d(xdata,
ydata,
kind='linear',
assume_sorted=True)
interp_vals[interp_mask] = func(pt[interp_mask])
if is_scalar:
interp_vals = interp_vals[0]
# interpolate to target recall
#right_index = indicies[0]
#right_recall = self.recall[right_index]
#left_index = right_index - 1
#left_recall = self.recall[left_index]
#stepsize = right_recall - left_recall
#alpha = (target_recall - left_recall) / stepsize
#left_fpr = self.fpr[left_index]
#right_fpr = self.fpr[right_index]
#interp_fpp = (left_fpr * (1 - alpha)) + (right_fpr * (alpha))
return interp_vals
