def get_dbinfo(ibs,
verbose=True,
with_imgsize=False,
with_bytes=False,
with_contrib=False,
with_agesex=False,
with_header=True,
short=False,
tag='dbinfo',
aid_list=None,
aids=None):
"""
Returns dictionary of digestable database information
Infostr is a string summary of all the stats. Prints infostr in addition to
returning locals
Args:
ibs (IBEISController):
verbose (bool):
with_imgsize (bool):
with_bytes (bool):
Returns:
dict:
SeeAlso:
python -m ibeis.other.ibsfuncs --exec-get_annot_stats_dict --db PZ_PB_RF_TRAIN --use-hist=True --old=False --per_name_vpedge=False
python -m ibeis.other.ibsfuncs --exec-get_annot_stats_dict --db PZ_PB_RF_TRAIN --all
CommandLine:
python -m ibeis.other.dbinfo --exec-get_dbinfo:0
python -m ibeis.other.dbinfo --test-get_dbinfo:1
python -m ibeis.other.dbinfo --test-get_dbinfo:0 --db NNP_Master3
python -m ibeis.other.dbinfo --test-get_dbinfo:0 --db PZ_Master1
python -m ibeis.other.dbinfo --test-get_dbinfo:0 --db GZ_ALL
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 --db PZ_ViewPoints
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 --db GZ_Master1
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 --db LF_Bajo_bonito -a default
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 --db DETECT_SEATURTLES -a default --readonly
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 -a ctrl
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 -a default:minqual=ok,require_timestamp=True --dbdir ~/lev/media/danger/LEWA
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 -a default:minqual=ok,require_timestamp=True --dbdir ~/lev/media/danger/LEWA --loadbackup=0
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 -a default: --dbdir ~/lev/media/danger/LEWA
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 -a default: --dbdir ~/lev/media/danger/LEWA --loadbackup=0
Example1:
>>> # SCRIPT
>>> from ibeis.other.dbinfo import * # NOQA
>>> import ibeis
>>> defaultdb = 'testdb1'
>>> ibs, aid_list = ibeis.testdata_aids(defaultdb, a='default:minqual=ok,view=primary,view_ext1=1')
>>> kwargs = ut.get_kwdefaults(get_dbinfo)
>>> kwargs['verbose'] = False
>>> kwargs['aid_list'] = aid_list
>>> kwargs = ut.parse_dict_from_argv(kwargs)
>>> output = get_dbinfo(ibs, **kwargs)
>>> result = (output['info_str'])
>>> print(result)
>>> #ibs = ibeis.opendb(defaultdb='testdb1')
>>> # <HACK FOR FILTERING>
>>> #from ibeis.expt import cfghelpers
>>> #from ibeis.expt import annotation_configs
>>> #from ibeis.init import filter_annots
>>> #named_defaults_dict = ut.dict_take(annotation_configs.__dict__,
>>> # annotation_configs.TEST_NAMES)
>>> #named_qcfg_defaults = dict(zip(annotation_configs.TEST_NAMES,
>>> # ut.get_list_column(named_defaults_dict, 'qcfg')))
>>> #acfg = cfghelpers.parse_argv_cfg(('--annot-filter', '-a'), named_defaults_dict=named_qcfg_defaults, default=None)[0]
>>> #aid_list = ibs.get_valid_aids()
>>> # </HACK FOR FILTERING>
Example1:
>>> # ENABLE_DOCTEST
>>> from ibeis.other.dbinfo import * # NOQA
>>> import ibeis
>>> verbose = True
>>> short = True
>>> #ibs = ibeis.opendb(db='GZ_ALL')
>>> #ibs = ibeis.opendb(db='PZ_Master0')
>>> ibs = ibeis.opendb('testdb1')
>>> assert ibs.get_dbname() == 'testdb1', 'DO NOT DELETE CONTRIBUTORS OF OTHER DBS'
>>> ibs.delete_contributors(ibs.get_valid_contributor_rowids())
>>> ibs.delete_empty_nids()
>>> #ibs = ibeis.opendb(db='PZ_MTEST')
>>> output = get_dbinfo(ibs, with_contrib=False, verbose=False, short=True)
>>> result = (output['info_str'])
>>> print(result)
+============================
DB Info: testdb1
DB Notes: None
DB NumContrib: 0
----------
# Names = 7
# Names (unassociated) = 0
# Names (singleton) = 5
# Names (multiton) = 2
----------
# Annots = 13
# Annots (unknown) = 4
# Annots (singleton) = 5
# Annots (multiton) = 4
----------
# Img = 13
L============================
"""
# TODO Database size in bytes
# TODO: occurrence, contributors, etc...
if aids is not None:
aid_list = aids
# Basic variables
request_annot_subset = False
_input_aid_list = aid_list # NOQA
if aid_list is None:
valid_aids = ibs.get_valid_aids()
valid_nids = ibs.get_valid_nids()
valid_gids = ibs.get_valid_gids()
else:
if isinstance(aid_list, str):
# Hack to get experiment stats on aids
acfg_name_list = [aid_list]
print('Specified custom aids via acfgname %s' % (acfg_name_list, ))
from ibeis.expt import experiment_helpers
acfg_list, expanded_aids_list = experiment_helpers.get_annotcfg_list(
ibs, acfg_name_list)
aid_list = sorted(
list(set(ut.flatten(ut.flatten(expanded_aids_list)))))
#aid_list =
if verbose:
print('Specified %d custom aids' % (len(aid_list, )))
request_annot_subset = True
valid_aids = aid_list
valid_nids = list(
set(ibs.get_annot_nids(aid_list, distinguish_unknowns=False)) -
{const.UNKNOWN_NAME_ROWID})
valid_gids = list(set(ibs.get_annot_gids(aid_list)))
#associated_nids = ibs.get_valid_nids(filter_empty=True) # nids with at least one annotation
valid_images = ibs.images(valid_gids)
valid_annots = ibs.annots(valid_aids)
# Image info
if verbose:
print('Checking Image Info')
gx2_aids = valid_images.aids
if request_annot_subset:
# remove annots not in this subset
valid_aids_set = set(valid_aids)
gx2_aids = [
list(set(aids_).intersection(valid_aids_set)) for aids_ in gx2_aids
]
gx2_nAnnots = np.array(list(map(len, gx2_aids)))
image_without_annots = len(np.where(gx2_nAnnots == 0)[0])
gx2_nAnnots_stats = ut.repr4(ut.get_stats(gx2_nAnnots, use_median=True),
nl=0,
precision=2,
si=True)
image_reviewed_list = ibs.get_image_reviewed(valid_gids)
# Name stats
if verbose:
print('Checking Name Info')
nx2_aids = ibs.get_name_aids(valid_nids)
if request_annot_subset:
# remove annots not in this subset
valid_aids_set = set(valid_aids)
nx2_aids = [
list(set(aids_).intersection(valid_aids_set)) for aids_ in nx2_aids
]
associated_nids = ut.compress(valid_nids, list(map(len, nx2_aids)))
ibs.check_name_mapping_consistency(nx2_aids)
if False:
# Occurrence Info
def compute_annot_occurrence_ids(ibs, aid_list):
from ibeis.algo.preproc import preproc_occurrence
gid_list = ibs.get_annot_gids(aid_list)
gid2_aids = ut.group_items(aid_list, gid_list)
config = {'seconds_thresh': 4 * 60 * 60}
flat_imgsetids, flat_gids = preproc_occurrence.ibeis_compute_occurrences(
ibs, gid_list, config=config, verbose=False)
occurid2_gids = ut.group_items(flat_gids, flat_imgsetids)
occurid2_aids = {
oid: ut.flatten(ut.take(gid2_aids, gids))
for oid, gids in occurid2_gids.items()
}
return occurid2_aids
import utool
with utool.embed_on_exception_context:
occurid2_aids = compute_annot_occurrence_ids(ibs, valid_aids)
occur_nids = ibs.unflat_map(ibs.get_annot_nids,
occurid2_aids.values())
occur_unique_nids = [ut.unique(nids) for nids in occur_nids]
nid2_occurxs = ut.ddict(list)
for occurx, nids in enumerate(occur_unique_nids):
for nid in nids:
nid2_occurxs[nid].append(occurx)
nid2_occurx_single = {
nid: occurxs
for nid, occurxs in nid2_occurxs.items() if len(occurxs) <= 1
}
nid2_occurx_resight = {
nid: occurxs
for nid, occurxs in nid2_occurxs.items() if len(occurxs) > 1
}
singlesight_encounters = ibs.get_name_aids(nid2_occurx_single.keys())
singlesight_annot_stats = ut.get_stats(list(
map(len, singlesight_encounters)),
use_median=True,
use_sum=True)
resight_name_stats = ut.get_stats(list(
map(len, nid2_occurx_resight.values())),
use_median=True,
use_sum=True)
# Encounter Info
def break_annots_into_encounters(aids):
from ibeis.algo.preproc import occurrence_blackbox
import datetime
thresh_sec = datetime.timedelta(minutes=30).seconds
posixtimes = np.array(ibs.get_annot_image_unixtimes_asfloat(aids))
#latlons = ibs.get_annot_image_gps(aids)
labels = occurrence_blackbox.cluster_timespace2(posixtimes,
None,
thresh_sec=thresh_sec)
return labels
#ave_enc_time = [np.mean(times) for lbl, times in ut.group_items(posixtimes, labels).items()]
#ut.square_pdist(ave_enc_time)
try:
am_rowids = ibs.get_annotmatch_rowids_between_groups([valid_aids],
[valid_aids])[0]
aid_pairs = ibs.filter_aidpairs_by_tags(min_num=0, am_rowids=am_rowids)
undirected_tags = ibs.get_aidpair_tags(aid_pairs.T[0],
aid_pairs.T[1],
directed=False)
tagged_pairs = list(zip(aid_pairs.tolist(), undirected_tags))
tag_dict = ut.groupby_tags(tagged_pairs, undirected_tags)
pair_tag_info = ut.map_dict_vals(len, tag_dict)
except Exception:
pair_tag_info = {}
#print(ut.repr2(pair_tag_info))
# Annot Stats
# TODO: number of images where chips cover entire image
# TODO: total image coverage of annotation
# TODO: total annotation overlap
"""
ax2_unknown = ibs.is_aid_unknown(valid_aids)
ax2_nid = ibs.get_annot_name_rowids(valid_aids)
assert all([nid < 0 if unknown else nid > 0 for nid, unknown in
zip(ax2_nid, ax2_unknown)]), 'bad annot nid'
"""
#
if verbose:
print('Checking Annot Species')
unknown_annots = valid_annots.compress(ibs.is_aid_unknown(valid_annots))
species_list = valid_annots.species_texts
species2_annots = valid_annots.group_items(valid_annots.species_texts)
species2_nAids = {key: len(val) for key, val in species2_annots.items()}
if verbose:
print('Checking Multiton/Singleton Species')
nx2_nAnnots = np.array(list(map(len, nx2_aids)))
# Seperate singleton / multitons
multiton_nxs = np.where(nx2_nAnnots > 1)[0]
singleton_nxs = np.where(nx2_nAnnots == 1)[0]
unassociated_nxs = np.where(nx2_nAnnots == 0)[0]
assert len(np.intersect1d(singleton_nxs,
multiton_nxs)) == 0, 'intersecting names'
valid_nxs = np.hstack([multiton_nxs, singleton_nxs])
num_names_with_gt = len(multiton_nxs)
# Annot Info
if verbose:
print('Checking Annot Info')
multiton_aids_list = ut.take(nx2_aids, multiton_nxs)
assert len(set(multiton_nxs)) == len(multiton_nxs)
if len(multiton_aids_list) == 0:
multiton_aids = np.array([], dtype=np.int)
else:
multiton_aids = np.hstack(multiton_aids_list)
assert len(set(multiton_aids)) == len(multiton_aids), 'duplicate annot'
singleton_aids = ut.take(nx2_aids, singleton_nxs)
multiton_nid2_nannots = list(map(len, multiton_aids_list))
# Image size stats
if with_imgsize:
if verbose:
print('Checking ImageSize Info')
gpath_list = ibs.get_image_paths(valid_gids)
def wh_print_stats(wh_list):
if len(wh_list) == 0:
return '{empty}'
wh_list = np.asarray(wh_list)
stat_dict = collections.OrderedDict([('max', wh_list.max(0)),
('min', wh_list.min(0)),
('mean', wh_list.mean(0)),
('std', wh_list.std(0))])
def arr2str(var):
return ('[' +
(', '.join(list(map(lambda x: '%.1f' % x, var)))) +
']')
ret = (',\n '.join([
'%s:%s' % (key, arr2str(val))
for key, val in stat_dict.items()
]))
return '{\n ' + ret + '\n}'
print('reading image sizes')
# Image size stats
img_size_list = ibs.get_image_sizes(valid_gids)
img_size_stats = wh_print_stats(img_size_list)
# Chip size stats
annotation_bbox_list = ibs.get_annot_bboxes(valid_aids)
annotation_bbox_arr = np.array(annotation_bbox_list)
if len(annotation_bbox_arr) == 0:
annotation_size_list = []
else:
annotation_size_list = annotation_bbox_arr[:, 2:4]
chip_size_stats = wh_print_stats(annotation_size_list)
imgsize_stat_lines = [
(' # Img in dir = %d' % len(gpath_list)),
(' Image Size Stats = %s' % (img_size_stats, )),
(' * Chip Size Stats = %s' % (chip_size_stats, )),
]
else:
imgsize_stat_lines = []
if verbose:
print('Building Stats String')
multiton_stats = ut.repr3(ut.get_stats(multiton_nid2_nannots,
use_median=True),
nl=0,
precision=2,
si=True)
# Time stats
unixtime_list = valid_images.unixtime2
#valid_unixtime_list = [time for time in unixtime_list if time != -1]
#unixtime_statstr = ibs.get_image_time_statstr(valid_gids)
if ut.get_argflag('--hackshow-unixtime'):
show_time_distributions(ibs, unixtime_list)
ut.show_if_requested()
unixtime_statstr = ut.repr3(ut.get_timestats_dict(unixtime_list,
full=True),
si=True)
# GPS stats
gps_list_ = ibs.get_image_gps(valid_gids)
gpsvalid_list = [gps != (-1, -1) for gps in gps_list_]
gps_list = ut.compress(gps_list_, gpsvalid_list)
def get_annot_age_stats(aid_list):
annot_age_months_est_min = ibs.get_annot_age_months_est_min(aid_list)
annot_age_months_est_max = ibs.get_annot_age_months_est_max(aid_list)
age_dict = ut.ddict((lambda: 0))
for min_age, max_age in zip(annot_age_months_est_min,
annot_age_months_est_max):
if max_age is None:
max_age = min_age
if min_age is None:
min_age = max_age
if max_age is None and min_age is None:
print('Found UNKNOWN Age: %r, %r' % (
min_age,
max_age,
))
age_dict['UNKNOWN'] += 1
elif (min_age is None or min_age < 12) and max_age < 12:
age_dict['Infant'] += 1
elif 12 <= min_age and min_age < 36 and 12 <= max_age and max_age < 36:
age_dict['Juvenile'] += 1
elif 36 <= min_age and (max_age is None or 36 <= max_age):
age_dict['Adult'] += 1
return age_dict
def get_annot_sex_stats(aid_list):
annot_sextext_list = ibs.get_annot_sex_texts(aid_list)
sextext2_aids = ut.group_items(aid_list, annot_sextext_list)
sex_keys = list(ibs.const.SEX_TEXT_TO_INT.keys())
assert set(sex_keys) >= set(annot_sextext_list), 'bad keys: ' + str(
set(annot_sextext_list) - set(sex_keys))
sextext2_nAnnots = ut.odict([(key, len(sextext2_aids.get(key, [])))
for key in sex_keys])
# Filter 0's
sextext2_nAnnots = {
key: val
for key, val in six.iteritems(sextext2_nAnnots) if val != 0
}
return sextext2_nAnnots
def get_annot_qual_stats(ibs, aid_list):
annots = ibs.annots(aid_list)
qualtext2_nAnnots = ut.order_dict_by(
ut.map_vals(len, annots.group_items(annots.quality_texts)),
list(ibs.const.QUALITY_TEXT_TO_INT.keys()))
return qualtext2_nAnnots
def get_annot_viewpoint_stats(ibs, aid_list):
annots = ibs.annots(aid_list)
viewcode2_nAnnots = ut.order_dict_by(
ut.map_vals(len, annots.group_items(annots.viewpoint_code)),
list(ibs.const.VIEW.CODE_TO_INT.keys()) + [None])
return viewcode2_nAnnots
if verbose:
print('Checking Other Annot Stats')
qualtext2_nAnnots = get_annot_qual_stats(ibs, valid_aids)
viewcode2_nAnnots = get_annot_viewpoint_stats(ibs, valid_aids)
agetext2_nAnnots = get_annot_age_stats(valid_aids)
sextext2_nAnnots = get_annot_sex_stats(valid_aids)
if verbose:
print('Checking Contrib Stats')
# Contributor Statistics
# hack remove colon for image alignment
def fix_tag_list(tag_list):
return [
None if tag is None else tag.replace(':', ';') for tag in tag_list
]
image_contributor_tags = fix_tag_list(
ibs.get_image_contributor_tag(valid_gids))
annot_contributor_tags = fix_tag_list(
ibs.get_annot_image_contributor_tag(valid_aids))
contributor_tag_to_gids = ut.group_items(valid_gids,
image_contributor_tags)
contributor_tag_to_aids = ut.group_items(valid_aids,
annot_contributor_tags)
contributor_tag_to_qualstats = {
key: get_annot_qual_stats(ibs, aids)
for key, aids in six.iteritems(contributor_tag_to_aids)
}
contributor_tag_to_viewstats = {
key: get_annot_viewpoint_stats(ibs, aids)
for key, aids in six.iteritems(contributor_tag_to_aids)
}
contributor_tag_to_nImages = {
key: len(val)
for key, val in six.iteritems(contributor_tag_to_gids)
}
contributor_tag_to_nAnnots = {
key: len(val)
for key, val in six.iteritems(contributor_tag_to_aids)
}
if verbose:
print('Summarizing')
# Summarize stats
num_names = len(valid_nids)
num_names_unassociated = len(valid_nids) - len(associated_nids)
num_names_singleton = len(singleton_nxs)
num_names_multiton = len(multiton_nxs)
num_singleton_annots = len(singleton_aids)
num_multiton_annots = len(multiton_aids)
num_unknown_annots = len(unknown_annots)
num_annots = len(valid_aids)
if with_bytes:
if verbose:
print('Checking Disk Space')
ibsdir_space = ut.byte_str2(ut.get_disk_space(ibs.get_ibsdir()))
dbdir_space = ut.byte_str2(ut.get_disk_space(ibs.get_dbdir()))
imgdir_space = ut.byte_str2(ut.get_disk_space(ibs.get_imgdir()))
cachedir_space = ut.byte_str2(ut.get_disk_space(ibs.get_cachedir()))
if True:
if verbose:
print('Check asserts')
try:
bad_aids = np.intersect1d(multiton_aids, unknown_annots)
_num_names_total_check = num_names_singleton + num_names_unassociated + num_names_multiton
_num_annots_total_check = num_unknown_annots + num_singleton_annots + num_multiton_annots
assert len(
bad_aids) == 0, 'intersecting multiton aids and unknown aids'
assert _num_names_total_check == num_names, 'inconsistent num names'
#if not request_annot_subset:
# dont check this if you have an annot subset
assert _num_annots_total_check == num_annots, 'inconsistent num annots'
except Exception as ex:
ut.printex(ex,
keys=[
'_num_names_total_check',
'num_names',
'_num_annots_total_check',
'num_annots',
'num_names_singleton',
'num_names_multiton',
'num_unknown_annots',
'num_multiton_annots',
'num_singleton_annots',
])
raise
# Get contributor statistics
contributor_rowids = ibs.get_valid_contributor_rowids()
num_contributors = len(contributor_rowids)
# print
num_tabs = 5
def align2(str_):
return ut.align(str_, ':', ' :')
def align_dict2(dict_):
str_ = ut.repr2(dict_, si=True)
return align2(str_)
header_block_lines = ([
('+============================'),
] + ([
('+ singleton := single sighting'),
('+ multiton := multiple sightings'),
('--' * num_tabs),
] if not short and with_header else []))
source_block_lines = [
('DB Info: ' + ibs.get_dbname()),
('DB Notes: ' + ibs.get_dbnotes()),
('DB NumContrib: %d' % num_contributors),
]
bytes_block_lines = [
('--' * num_tabs),
('DB Bytes: '),
(' +- dbdir nBytes: ' + dbdir_space),
(' | +- _ibsdb nBytes: ' + ibsdir_space),
(' | | +-imgdir nBytes: ' + imgdir_space),
(' | | +-cachedir nBytes: ' + cachedir_space),
] if with_bytes else []
name_block_lines = [
('--' * num_tabs),
('# Names = %d' % num_names),
('# Names (unassociated) = %d' % num_names_unassociated),
('# Names (singleton) = %d' % num_names_singleton),
('# Names (multiton) = %d' % num_names_multiton),
]
subset_str = ' ' if not request_annot_subset else '(SUBSET)'
annot_block_lines = [
('--' * num_tabs),
('# Annots %s = %d' % (
subset_str,
num_annots,
)),
('# Annots (unknown) = %d' % num_unknown_annots),
('# Annots (singleton) = %d' % num_singleton_annots),
('# Annots (multiton) = %d' % num_multiton_annots),
]
annot_per_basic_block_lines = [
('--' * num_tabs),
('# Annots per Name (multiton) = %s' % (align2(multiton_stats), )),
('# Annots per Image = %s' % (align2(gx2_nAnnots_stats), )),
('# Annots per Species = %s' %
(align_dict2(species2_nAids), )),
] if not short else []
occurrence_block_lines = [
('--' * num_tabs),
#('# Occurrence Per Name (Resights) = %s' % (align_dict2(resight_name_stats),)),
#('# Annots per Encounter (Singlesights) = %s' % (align_dict2(singlesight_annot_stats),)),
('# Pair Tag Info (annots) = %s' % (align_dict2(pair_tag_info), )),
] if not short else []
annot_per_qualview_block_lines = [
None if short else '# Annots per Viewpoint = %s' %
align_dict2(viewcode2_nAnnots),
None if short else '# Annots per Quality = %s' %
align_dict2(qualtext2_nAnnots),
]
annot_per_agesex_block_lines = [
'# Annots per Age = %s' % align_dict2(agetext2_nAnnots),
'# Annots per Sex = %s' % align_dict2(sextext2_nAnnots),
] if not short and with_agesex else []
contributor_block_lines = [
'# Images per contributor = ' +
align_dict2(contributor_tag_to_nImages),
'# Annots per contributor = ' +
align_dict2(contributor_tag_to_nAnnots),
'# Quality per contributor = ' +
ut.repr2(contributor_tag_to_qualstats, sorted_=True),
'# Viewpoint per contributor = ' +
ut.repr2(contributor_tag_to_viewstats, sorted_=True),
] if with_contrib else []
img_block_lines = [
('--' * num_tabs),
('# Img = %d' % len(valid_gids)),
None if short else
('# Img reviewed = %d' % sum(image_reviewed_list)),
None if short else
('# Img with gps = %d' % len(gps_list)),
#('# Img with timestamp = %d' % len(valid_unixtime_list)),
None if short else
('Img Time Stats = %s' % (align2(unixtime_statstr), )),
]
info_str_lines = (header_block_lines + bytes_block_lines +
source_block_lines + name_block_lines +
annot_block_lines + annot_per_basic_block_lines +
occurrence_block_lines + annot_per_qualview_block_lines +
annot_per_agesex_block_lines + img_block_lines +
contributor_block_lines + imgsize_stat_lines + [
('L============================'),
])
info_str = '\n'.join(ut.filter_Nones(info_str_lines))
info_str2 = ut.indent(info_str, '[{tag}]'.format(tag=tag))
if verbose:
print(info_str2)
locals_ = locals()
return locals_
def testdata_expanded_aids(defaultdb=None, a=None, ibs=None,
default_qaids=None, default_daids=None,
qaid_override=None, daid_override=None,
return_annot_info=False, verbose=False,
use_cache=None):
r"""
Args:
default_qaids (list): (default = [1])
default_daids (str): (default = 'all')
defaultdb (str): (default = 'testdb1')
ibs (IBEISController): ibeis controller object(default = None)
verbose (bool): verbosity flag(default = False)
return_annot_info (bool): (default = False)
Returns:
ibs, qaid_list, daid_list, annot_info:
CommandLine:
python -m ibeis.init.main_helpers --exec-testdata_expanded_aids
python -m ibeis.init.main_helpers --exec-testdata_expanded_aids --db PZ_MTEST --acfg default:index=0:25 --verbose-testdata
python -m ibeis.init.main_helpers --exec-testdata_expanded_aids --db PZ_MTEST --qaid 3
python -m ibeis.init.main_helpers --exec-testdata_expanded_aids --db GZ_ALL --acfg ctrl --verbose-testdata
Example:
>>> # ENABLE_DOCTEST
>>> from ibeis.init.main_helpers import * # NOQA
>>> import ibeis
>>> from ibeis.expt import annotation_configs
>>> ibs, qaid_list, daid_list, aidcfg = testdata_expanded_aids(return_annot_info=True)
>>> print('Printing annot config')
>>> annotation_configs.print_acfg(aidcfg)
>>> print('Printing annotconfig stats')
>>> #print('qaid_list = %r' % (np.array(qaid_list),))
>>> ibs.print_annotconfig_stats(qaid_list, daid_list)
>>> print('Combined annotconfig stats')
>>> ibs.print_annot_stats(qaid_list + daid_list, yawtext_isect=True)
>>> print('qaid_list = %r' % (qaid_list,))
"""
print('[main_helpers] testdata_expanded_aids')
if default_qaids is None:
# Hack to aggree with experiment-helpers
default_qaids = ut.get_argval(('--qaid', '--qaid-override'), type_=list, default=[1])
if defaultdb is None:
defaultdb = 'testdb1'
import ibeis
if ibs is None:
ibs = ibeis.opendb(defaultdb=defaultdb)
# TODO: rectify command line with function arguments
from ibeis.expt import experiment_helpers
_specified2 = True
if a is None:
_specified2 = False
a = ['default']
if isinstance(a, six.string_types):
a = [a]
aidcfg_name_list, _specified = ut.get_argval(('--aidcfg', '--acfg', '-a'),
type_=list,
default=a,
return_specified=True)
acfg_list, expanded_aids_list = experiment_helpers.get_annotcfg_list(
ibs, aidcfg_name_list, qaid_override=qaid_override,
use_cache=use_cache,
daid_override=daid_override, verbose=verbose)
#aidcfg = old_main_helpers.get_commandline_aidcfg()
assert len(acfg_list) == 1, (
('multiple acfgs specified, but this function'
'is built to return only 1. len(acfg_list)=%r') %
(len(acfg_list),))
aidcfg = acfg_list[0]
qaid_list, daid_list = expanded_aids_list[0]
if not (_specified or _specified2):
# hack
if default_qaids is not None and qaid_override is None:
qaid_list = default_qaids
if default_daids is not None and daid_override is None:
daid_list = default_daids
if ut.VERYVERBOSE:
ibs.print_annotconfig_stats(qaid_list, daid_list)
#ibeis.other.dbinfo.print_qd_info(ibs, qaid_list, daid_list, verbose=True)
if return_annot_info:
return ibs, qaid_list, daid_list, aidcfg
else:
return ibs, qaid_list, daid_list
def run_expt(ibs,
acfg_name_list,
test_cfg_name_list,
use_cache=None,
qaid_override=None,
daid_override=None,
initial_aids=None):
r"""
Loops over annot configs.
Try and use this function as a starting point to clean up this module.
The code is getting too untenable.
CommandLine:
python -m ibeis.expt.harness run_expt --acfginfo
python -m ibeis.expt.harness run_expt --pcfginfo
python -m ibeis.expt.harness run_expt
Ignore:
test_cfg_name_list = [p]
Example:
>>> # SLOW_DOCTEST
>>> from ibeis.expt.harness import * # NOQA
>>> import ibeis
>>> ibs = ibeis.opendb(defaultdb='PZ_MTEST')
>>> default_acfgstrs = ['ctrl:qsize=20,dpername=1,dsize=10',
>>> 'ctrl:qsize=20,dpername=10,dsize=20']
>>> acfg_name_list = default_acfgstrs
>>> test_cfg_name_list = ['default:proot=smk', 'default']
>>> #test_cfg_name_list = ['custom', 'custom:fg_on=False']
>>> use_cache = False
>>> testres_list = run_expt(ibs, acfg_name_list, test_cfg_name_list, use_cache)
"""
print('[harn] run_expt')
# Generate list of database annotation configurations
if len(acfg_name_list) == 0:
raise ValueError('must give acfg name list')
acfg_list, expanded_aids_list = experiment_helpers.get_annotcfg_list(
ibs,
acfg_name_list,
qaid_override=qaid_override,
daid_override=daid_override,
initial_aids=initial_aids,
use_cache=use_cache)
# Generate list of query pipeline param configs
cfgdict_list, pipecfg_list = experiment_helpers.get_pipecfg_list(
test_cfg_name_list, ibs=ibs)
cfgx2_lbl = experiment_helpers.get_varied_pipecfg_lbls(cfgdict_list)
# NOTE: Can specify --pcfginfo or --acfginfo
if ut.NOT_QUIET:
ut.colorprint(
textwrap.dedent("""
[harn]================
[harn] harness.test_configurations2()""").strip(), 'white')
msg = '[harn] Running %s using %s and %s' % (
ut.quantstr('test',
len(acfg_list) * len(cfgdict_list)),
ut.quantstr('pipeline config', len(cfgdict_list)),
ut.quantstr('annot config', len(acfg_list)),
)
ut.colorprint(msg, 'white')
testres_list = []
nAcfg = len(acfg_list)
testnameid = (ibs.get_dbname() + ' ' + str(test_cfg_name_list) +
str(acfg_name_list))
lbl = '[harn] TEST_CFG ' + str(test_cfg_name_list) + str(acfg_name_list)
expanded_aids_iter = ut.ProgIter(expanded_aids_list,
lbl='annot config',
freq=1,
autoadjust=False,
enabled=ut.NOT_QUIET)
for acfgx, (qaids, daids) in enumerate(expanded_aids_iter):
assert len(qaids) != 0, ('[harness] No query annots specified')
assert len(daids) != 0, ('[harness] No database annotas specified')
acfg = acfg_list[acfgx]
if ut.NOT_QUIET:
ut.colorprint('\n---Annot config testnameid=%r' % (testnameid, ),
'turquoise')
subindexer_partial = ut.ProgPartial(parent_index=acfgx,
parent_length=nAcfg,
enabled=ut.NOT_QUIET)
testres_ = make_single_testres(ibs,
qaids,
daids,
pipecfg_list,
cfgx2_lbl,
cfgdict_list,
lbl,
testnameid,
use_cache=use_cache,
subindexer_partial=subindexer_partial)
if DRY_RUN:
continue
testres_.acfg = acfg
testres_.test_cfg_name_list = test_cfg_name_list
testres_list.append(testres_)
if DRY_RUN:
print('DRYRUN: Cannot continue past run_expt')
sys.exit(0)
testres = test_result.combine_testres_list(ibs, testres_list)
# testres.print_results()
print('Returning Test Result')
return testres
def testdata_expanded_aids(defaultdb=None,
a=None,
ibs=None,
default_qaids=None,
default_daids=None,
qaid_override=None,
daid_override=None,
return_annot_info=False,
verbose=None,
use_cache=None):
r"""
Args:
default_qaids (list): (default = [1])
default_daids (str): (default = 'all')
defaultdb (str): (default = 'testdb1')
ibs (IBEISController): ibeis controller object(default = None)
verbose (bool): verbosity flag(default = False)
return_annot_info (bool): (default = False)
Returns:
ibs, qaid_list, daid_list, annot_info:
CommandLine:
python -m ibeis.init.main_helpers testdata_expanded_aids
python -m ibeis.init.main_helpers testdata_expanded_aids --db PZ_MTEST --acfg default:index=0:25 --verbose-testdata
python -m ibeis.init.main_helpers testdata_expanded_aids --db PZ_MTEST --qaid 3
python -m ibeis.init.main_helpers testdata_expanded_aids --db GZ_ALL --acfg ctrl --verbose-testdata
Example:
>>> # ENABLE_DOCTEST
>>> from ibeis.init.main_helpers import * # NOQA
>>> import ibeis
>>> from ibeis.expt import annotation_configs
>>> ibs, qaid_list, daid_list, aidcfg = testdata_expanded_aids(return_annot_info=True)
>>> print('Printing annot config')
>>> annotation_configs.print_acfg(aidcfg)
>>> print('Printing annotconfig stats')
>>> ibs.print_annotconfig_stats(qaid_list, daid_list)
>>> print('Combined annotconfig stats')
>>> ibs.print_annot_stats(qaid_list + daid_list, viewcode_isect=True)
>>> print('qaid_list = %r' % (qaid_list,))
"""
if verbose is None:
verbose = 1
if verbose:
print('[main_helpers] testdata_expanded_aids')
default_qaids = ut.get_argval(('--qaid', '--qaid-override'),
type_=list,
default=default_qaids)
if default_qaids is None:
default_qaids = [1]
if defaultdb is None:
defaultdb = 'testdb1'
import ibeis
if ibs is None:
ibs = ibeis.opendb(defaultdb=defaultdb)
# TODO: rectify command line with function arguments
from ibeis.expt import experiment_helpers
_specified2 = True
if a is None:
_specified2 = False
a = ['default']
if isinstance(a, six.string_types):
a = [a]
aidcfg_name_list, _specified = ut.get_argval(('--aidcfg', '--acfg', '-a'),
type_=list,
default=a,
return_specified=True)
if not _specified:
# Allow a to be specified an explicit default
if len(a) == 2:
qaids, daids = a
if ut.is_int(qaids[0]) and ut.is_int(daids[0]):
if return_annot_info:
return ibs, qaids, daids, None
else:
return ibs, qaids, daids
acfg_list, expanded_aids_list = experiment_helpers.get_annotcfg_list(
ibs,
aidcfg_name_list,
qaid_override=qaid_override,
use_cache=use_cache,
daid_override=daid_override,
verbose=max(0, verbose - 1))
#aidcfg = old_main_helpers.get_commandline_aidcfg()
assert len(acfg_list) == 1, (
('multiple acfgs specified, but this function'
'is built to return only 1. len(acfg_list)=%r') % (len(acfg_list), ))
aidcfg = acfg_list[0]
qaid_list, daid_list = expanded_aids_list[0]
if not (_specified or _specified2):
# hack
if default_qaids is not None and qaid_override is None:
qaid_list = default_qaids
if default_daids is not None and daid_override is None:
daid_list = default_daids
if ut.VERYVERBOSE:
ibs.print_annotconfig_stats(qaid_list, daid_list)
#ibeis.other.dbinfo.print_qd_info(ibs, qaid_list, daid_list, verbose=True)
if return_annot_info:
return ibs, qaid_list, daid_list, aidcfg
else:
return ibs, qaid_list, daid_list
def run_test_configurations2(ibs, acfg_name_list, test_cfg_name_list,
use_cache=None, qaid_override=None,
daid_override=None, initial_aids=None):
"""
Loops over annot configs.
Try and use this function as a starting point to clean up this module.
The code is getting too untenable.
CommandLine:
python -m ibeis.expt.harness --exec-run_test_configurations2
Example:
>>> # SLOW_DOCTEST
>>> from ibeis.expt.harness import * # NOQA
>>> import ibeis
>>> ibs = ibeis.opendb(defaultdb='PZ_MTEST')
>>> default_acfgstrs = ['controlled:qsize=20,dpername=1,dsize=10', 'controlled:qsize=20,dpername=10,dsize=100']
>>> acfg_name_list = ut.get_argval(('--aidcfg', '--acfg', '-a'), type_=list, default=default_acfgstrs)
>>> test_cfg_name_list = ut.get_argval(('-t', '-p')), type_=list, default=['custom', 'custom:fg_on=False'])
>>> use_cache = False
>>> testres_list = run_test_configurations2(ibs, acfg_name_list, test_cfg_name_list, use_cache)
"""
print('[harn] run_test_configurations2')
# Generate list of database annotation configurations
if len(acfg_name_list) == 0:
raise ValueError('must give acfg name list')
acfg_list, expanded_aids_list = experiment_helpers.get_annotcfg_list(
ibs, acfg_name_list, qaid_override=qaid_override,
daid_override=daid_override, initial_aids=initial_aids,
use_cache=use_cache)
# Generate list of query pipeline param configs
cfgdict_list, pipecfg_list = experiment_helpers.get_pipecfg_list(
test_cfg_name_list, ibs=ibs)
cfgx2_lbl = experiment_helpers.get_varied_pipecfg_lbls(cfgdict_list)
# NOTE: Can specify --pcfginfo or --acfginfo
if ut.NOT_QUIET:
ut.colorprint(textwrap.dedent("""
[harn]================
[harn] harness.test_configurations2()""").strip(), 'white')
msg = '[harn] Running %s using %s and %s' % (
ut.quantstr('test', len(acfg_list) * len(pipecfg_list)),
ut.quantstr('pipeline config', len(pipecfg_list)),
ut.quantstr('annot config', len(acfg_list)),
)
ut.colorprint(msg, 'white')
testres_list = []
nAcfg = len(acfg_list)
testnameid = ibs.get_dbname() + ' ' + str(test_cfg_name_list) + str(acfg_name_list)
lbl = '[harn] TEST_CFG ' + str(test_cfg_name_list) + str(acfg_name_list)
expanded_aids_iter = ut.ProgressIter(expanded_aids_list,
lbl='annot config',
freq=1, autoadjust=False,
enabled=ut.NOT_QUIET)
for acfgx, (qaids, daids) in enumerate(expanded_aids_iter):
assert len(qaids) != 0, (
'[harness] No query annotations specified')
assert len(daids) != 0, (
'[harness] No database annotations specified')
acfg = acfg_list[acfgx]
if ut.NOT_QUIET:
ut.colorprint('\n---Annot config testnameid=%r' % (
testnameid,), 'turquoise')
subindexer_partial = partial(ut.ProgressIter, parent_index=acfgx,
parent_nTotal=nAcfg, enabled=ut.NOT_QUIET)
testres = make_single_testres(ibs, qaids, daids, pipecfg_list,
cfgx2_lbl, cfgdict_list, lbl, testnameid,
use_cache=use_cache,
subindexer_partial=subindexer_partial)
if DRY_RUN:
continue
testres.acfg = acfg
testres.test_cfg_name_list = test_cfg_name_list
testres_list.append(testres)
if DRY_RUN:
print('DRYRUN: Cannot continue past run_test_configurations2')
sys.exit(0)
return testres_list
def get_dbinfo(ibs, verbose=True,
with_imgsize=False,
with_bytes=False,
with_contrib=False,
with_agesex=False,
with_header=True,
short=False,
tag='dbinfo',
aid_list=None):
"""
Returns dictionary of digestable database information
Infostr is a string summary of all the stats. Prints infostr in addition to
returning locals
Args:
ibs (IBEISController):
verbose (bool):
with_imgsize (bool):
with_bytes (bool):
Returns:
dict:
CommandLine:
python -m ibeis.other.dbinfo --exec-get_dbinfo:0
python -m ibeis.other.dbinfo --test-get_dbinfo:1
python -m ibeis.other.dbinfo --test-get_dbinfo:0 --db NNP_Master3
python -m ibeis.other.dbinfo --test-get_dbinfo:0 --db PZ_Master1
python -m ibeis.other.dbinfo --test-get_dbinfo:0 --db GZ_ALL
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 --db PZ_ViewPoints
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 --db GZ_Master1
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 -a ctrl
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 -a default:minqual=ok,require_timestamp=True --dbdir ~/lev/media/danger/LEWA
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 -a default:minqual=ok,require_timestamp=True --dbdir ~/lev/media/danger/LEWA --loadbackup=0
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 -a default: --dbdir ~/lev/media/danger/LEWA
python -m ibeis.other.dbinfo --exec-get_dbinfo:0 -a default: --dbdir ~/lev/media/danger/LEWA --loadbackup=0
Example1:
>>> # SCRIPT
>>> from ibeis.other.dbinfo import * # NOQA
>>> import ibeis
>>> defaultdb = 'testdb1'
>>> ibs, aid_list = ibeis.testdata_aids(defaultdb, a='default:minqual=ok,view=primary,view_ext1=1')
>>> kwargs = ut.get_kwdefaults(get_dbinfo)
>>> kwargs['verbose'] = False
>>> kwargs['aid_list'] = aid_list
>>> kwargs = ut.parse_dict_from_argv(kwargs)
>>> output = get_dbinfo(ibs, **kwargs)
>>> result = (output['info_str'])
>>> print(result)
>>> #ibs = ibeis.opendb(defaultdb='testdb1')
>>> # <HACK FOR FILTERING>
>>> #from ibeis.expt import cfghelpers
>>> #from ibeis.expt import annotation_configs
>>> #from ibeis.init import filter_annots
>>> #named_defaults_dict = ut.dict_take(annotation_configs.__dict__,
>>> # annotation_configs.TEST_NAMES)
>>> #named_qcfg_defaults = dict(zip(annotation_configs.TEST_NAMES,
>>> # ut.get_list_column(named_defaults_dict, 'qcfg')))
>>> #acfg = cfghelpers.parse_argv_cfg(('--annot-filter', '-a'), named_defaults_dict=named_qcfg_defaults, default=None)[0]
>>> #aid_list = ibs.get_valid_aids()
>>> # </HACK FOR FILTERING>
Example1:
>>> # ENABLE_DOCTEST
>>> from ibeis.other.dbinfo import * # NOQA
>>> import ibeis
>>> verbose = True
>>> short = True
>>> #ibs = ibeis.opendb(db='GZ_ALL')
>>> #ibs = ibeis.opendb(db='PZ_Master0')
>>> ibs = ibeis.opendb('testdb1')
>>> assert ibs.get_dbname() == 'testdb1', 'DO NOT DELETE CONTRIBUTORS OF OTHER DBS'
>>> ibs.delete_contributors(ibs.get_valid_contrib_rowids())
>>> ibs.delete_empty_nids()
>>> #ibs = ibeis.opendb(db='PZ_MTEST')
>>> output = get_dbinfo(ibs, with_contrib=False, verbose=False, short=True)
>>> result = (output['info_str'])
>>> print(result)
+============================
DB Info: testdb1
DB Notes: None
DB NumContrib: 0
----------
# Names = 7
# Names (unassociated) = 0
# Names (singleton) = 5
# Names (multiton) = 2
----------
# Annots = 13
# Annots (unknown) = 4
# Annots (singleton) = 5
# Annots (multiton) = 4
----------
# Img = 13
L============================
"""
# TODO Database size in bytes
# TODO: occurrence, contributors, etc...
# Basic variables
request_annot_subset = False
_input_aid_list = aid_list # NOQA
if aid_list is None:
valid_aids = ibs.get_valid_aids()
valid_nids = ibs.get_valid_nids()
valid_gids = ibs.get_valid_gids()
else:
if isinstance(aid_list, str):
# Hack to get experiment stats on aids
acfg_name_list = [aid_list]
print('Specified custom aids via acfgname %s' % (acfg_name_list,))
from ibeis.expt import experiment_helpers
acfg_list, expanded_aids_list = experiment_helpers.get_annotcfg_list(
ibs, acfg_name_list)
aid_list = sorted(list(set(ut.flatten(ut.flatten(expanded_aids_list)))))
#aid_list =
if verbose:
print('Specified %d custom aids' % (len(aid_list,)))
request_annot_subset = True
valid_aids = aid_list
valid_nids = list(
set(ibs.get_annot_nids(aid_list, distinguish_unknowns=False)) -
{const.UNKNOWN_NAME_ROWID}
)
valid_gids = list(set(ibs.get_annot_gids(aid_list)))
#associated_nids = ibs.get_valid_nids(filter_empty=True) # nids with at least one annotation
FILTER_HACK = True
if FILTER_HACK:
# HUGE HACK - get only images and names with filtered aids
valid_aids_ = ibs.filter_aids_custom(valid_aids)
valid_nids_ = ibs.filter_nids_custom(valid_nids)
valid_gids_ = ibs.filter_gids_custom(valid_gids)
if verbose:
print('Filtered %d names' % (len(valid_nids) - len(valid_nids_)))
print('Filtered %d images' % (len(valid_gids) - len(valid_gids_)))
print('Filtered %d annots' % (len(valid_aids) - len(valid_aids_)))
valid_gids = valid_gids_
valid_nids = valid_nids_
valid_aids = valid_aids_
#associated_nids = ut.compress(associated_nids, map(any,
#ibs.unflat_map(ibs.get_annot_custom_filterflags,
# ibs.get_name_aids(associated_nids))))
# Image info
if verbose:
print('Checking Image Info')
gx2_aids = ibs.get_image_aids(valid_gids)
if FILTER_HACK:
gx2_aids = [ibs.filter_aids_custom(aids) for aids in gx2_aids] # HACK FOR FILTER
if request_annot_subset:
# remove annots not in this subset
valid_aids_set = set(valid_aids)
gx2_aids = [list(set(aids).intersection(valid_aids_set)) for aids in gx2_aids]
gx2_nAnnots = np.array(list(map(len, gx2_aids)))
image_without_annots = len(np.where(gx2_nAnnots == 0)[0])
gx2_nAnnots_stats = ut.get_stats_str(gx2_nAnnots, newlines=True, use_median=True)
image_reviewed_list = ibs.get_image_reviewed(valid_gids)
# Name stats
if verbose:
print('Checking Name Info')
nx2_aids = ibs.get_name_aids(valid_nids)
if FILTER_HACK:
nx2_aids = [ibs.filter_aids_custom(aids) for aids in nx2_aids] # HACK FOR FILTER
if request_annot_subset:
# remove annots not in this subset
valid_aids_set = set(valid_aids)
nx2_aids = [list(set(aids).intersection(valid_aids_set)) for aids in nx2_aids]
associated_nids = ut.compress(valid_nids, list(map(len, nx2_aids)))
ibs.check_name_mapping_consistency(nx2_aids)
# Occurrence Info
def compute_annot_occurrence_ids(ibs, aid_list):
from ibeis.algo.preproc import preproc_occurrence
gid_list = ibs.get_annot_gids(aid_list)
gid2_aids = ut.group_items(aid_list, gid_list)
flat_imgsetids, flat_gids = preproc_occurrence.ibeis_compute_occurrences(ibs, gid_list, seconds_thresh=4 * 60 * 60, verbose=False)
occurid2_gids = ut.group_items(flat_gids, flat_imgsetids)
occurid2_aids = {oid: ut.flatten(ut.take(gid2_aids, gids)) for oid, gids in occurid2_gids.items()}
return occurid2_aids
import utool
with utool.embed_on_exception_context:
occurid2_aids = compute_annot_occurrence_ids(ibs, valid_aids)
occur_nids = ibs.unflat_map(ibs.get_annot_nids, occurid2_aids.values())
occur_unique_nids = [ut.unique(nids) for nids in occur_nids]
nid2_occurxs = ut.ddict(list)
for occurx, nids in enumerate(occur_unique_nids):
for nid in nids:
nid2_occurxs[nid].append(occurx)
nid2_occurx_single = {nid: occurxs for nid, occurxs in nid2_occurxs.items() if len(occurxs) <= 1}
nid2_occurx_resight = {nid: occurxs for nid, occurxs in nid2_occurxs.items() if len(occurxs) > 1}
singlesight_encounters = ibs.get_name_aids(nid2_occurx_single.keys())
singlesight_annot_stats = ut.get_stats(list(map(len, singlesight_encounters)), use_median=True, use_sum=True)
resight_name_stats = ut.get_stats(list(map(len, nid2_occurx_resight.values())), use_median=True, use_sum=True)
try:
aid_pairs = ibs.filter_aidpairs_by_tags(min_num=0)
undirected_tags = ibs.get_aidpair_tags(aid_pairs.T[0], aid_pairs.T[1], directed=False)
tagged_pairs = list(zip(aid_pairs.tolist(), undirected_tags))
tag_dict = ut.groupby_tags(tagged_pairs, undirected_tags)
pair_tag_info = ut.map_dict_vals(len, tag_dict)
num_reviewed_pairs = sum(ibs.get_annot_pair_is_reviewed(aid_pairs.T[0], aid_pairs.T[1]))
pair_tag_info['num_reviewed'] = num_reviewed_pairs
except Exception:
pair_tag_info = {}
#print(ut.dict_str(pair_tag_info))
# Annot Stats
# TODO: number of images where chips cover entire image
# TODO: total image coverage of annotation
# TODO: total annotation overlap
"""
ax2_unknown = ibs.is_aid_unknown(valid_aids)
ax2_nid = ibs.get_annot_name_rowids(valid_aids)
assert all([nid < 0 if unknown else nid > 0 for nid, unknown in
zip(ax2_nid, ax2_unknown)]), 'bad annot nid'
"""
#
if verbose:
print('Checking Annot Species')
unknown_aids = ut.compress(valid_aids, ibs.is_aid_unknown(valid_aids))
species_list = ibs.get_annot_species_texts(valid_aids)
species2_aids = ut.group_items(valid_aids, species_list)
species2_nAids = {key: len(val) for key, val in species2_aids.items()}
if verbose:
print('Checking Multiton/Singleton Species')
nx2_nAnnots = np.array(list(map(len, nx2_aids)))
# Seperate singleton / multitons
multiton_nxs = np.where(nx2_nAnnots > 1)[0]
singleton_nxs = np.where(nx2_nAnnots == 1)[0]
unassociated_nxs = np.where(nx2_nAnnots == 0)[0]
assert len(np.intersect1d(singleton_nxs, multiton_nxs)) == 0, 'intersecting names'
valid_nxs = np.hstack([multiton_nxs, singleton_nxs])
num_names_with_gt = len(multiton_nxs)
# Annot Info
if verbose:
print('Checking Annot Info')
multiton_aids_list = ut.take(nx2_aids, multiton_nxs)
assert len(set(multiton_nxs)) == len(multiton_nxs)
if len(multiton_aids_list) == 0:
multiton_aids = np.array([], dtype=np.int)
else:
multiton_aids = np.hstack(multiton_aids_list)
assert len(set(multiton_aids)) == len(multiton_aids), 'duplicate annot'
singleton_aids = ut.take(nx2_aids, singleton_nxs)
multiton_nid2_nannots = list(map(len, multiton_aids_list))
# Image size stats
if with_imgsize:
if verbose:
print('Checking ImageSize Info')
gpath_list = ibs.get_image_paths(valid_gids)
def wh_print_stats(wh_list):
if len(wh_list) == 0:
return '{empty}'
wh_list = np.asarray(wh_list)
stat_dict = OrderedDict(
[( 'max', wh_list.max(0)),
( 'min', wh_list.min(0)),
('mean', wh_list.mean(0)),
( 'std', wh_list.std(0))])
def arr2str(var):
return ('[' + (
', '.join(list(map(lambda x: '%.1f' % x, var)))
) + ']')
ret = (',\n '.join([
'%s:%s' % (key, arr2str(val))
for key, val in stat_dict.items()
]))
return '{\n ' + ret + '\n}'
print('reading image sizes')
# Image size stats
img_size_list = ibs.get_image_sizes(valid_gids)
img_size_stats = wh_print_stats(img_size_list)
# Chip size stats
annotation_bbox_list = ibs.get_annot_bboxes(valid_aids)
annotation_bbox_arr = np.array(annotation_bbox_list)
if len(annotation_bbox_arr) == 0:
annotation_size_list = []
else:
annotation_size_list = annotation_bbox_arr[:, 2:4]
chip_size_stats = wh_print_stats(annotation_size_list)
imgsize_stat_lines = [
(' # Img in dir = %d' % len(gpath_list)),
(' Image Size Stats = %s' % (img_size_stats,)),
(' * Chip Size Stats = %s' % (chip_size_stats,)),
]
else:
imgsize_stat_lines = []
if verbose:
print('Building Stats String')
multiton_stats = ut.get_stats_str(multiton_nid2_nannots, newlines=True, use_median=True)
# Time stats
unixtime_list = ibs.get_image_unixtime(valid_gids)
unixtime_list = ut.list_replace(unixtime_list, -1, float('nan'))
#valid_unixtime_list = [time for time in unixtime_list if time != -1]
#unixtime_statstr = ibs.get_image_time_statstr(valid_gids)
if ut.get_argflag('--hackshow-unixtime'):
show_time_distributions(ibs, unixtime_list)
ut.show_if_requested()
unixtime_statstr = ut.get_timestats_str(unixtime_list, newlines=True, full=True)
# GPS stats
gps_list_ = ibs.get_image_gps(valid_gids)
gpsvalid_list = [gps != (-1, -1) for gps in gps_list_]
gps_list = ut.compress(gps_list_, gpsvalid_list)
def get_annot_age_stats(aid_list):
annot_age_months_est_min = ibs.get_annot_age_months_est_min(aid_list)
annot_age_months_est_max = ibs.get_annot_age_months_est_max(aid_list)
age_dict = ut.ddict((lambda : 0))
for min_age, max_age in zip(annot_age_months_est_min, annot_age_months_est_max):
if (min_age is None or min_age < 12) and max_age < 12:
age_dict['Infant'] += 1
elif 12 <= min_age and min_age < 36 and 12 <= max_age and max_age < 36:
age_dict['Juvenile'] += 1
elif 36 <= min_age and (36 <= max_age or max_age is None):
age_dict['Adult'] += 1
else:
print('Found UNKNOWN Age: %r, %r' % (min_age, max_age, ))
age_dict['UNKNOWN'] += 1
return age_dict
def get_annot_sex_stats(aid_list):
annot_sextext_list = ibs.get_annot_sex_texts(aid_list)
sextext2_aids = ut.group_items(aid_list, annot_sextext_list)
sex_keys = list(ibs.const.SEX_TEXT_TO_INT.keys())
assert set(sex_keys) >= set(annot_sextext_list), 'bad keys: ' + str(set(annot_sextext_list) - set(sex_keys))
sextext2_nAnnots = ut.odict([(key, len(sextext2_aids.get(key, []))) for key in sex_keys])
# Filter 0's
sextext2_nAnnots = {key: val for key, val in six.iteritems(sextext2_nAnnots) if val != 0}
return sextext2_nAnnots
if verbose:
print('Checking Other Annot Stats')
qualtext2_nAnnots = ibs.get_annot_qual_stats(valid_aids)
yawtext2_nAnnots = ibs.get_annot_yaw_stats(valid_aids)
agetext2_nAnnots = get_annot_age_stats(valid_aids)
sextext2_nAnnots = get_annot_sex_stats(valid_aids)
if verbose:
print('Checking Contrib Stats')
# Contributor Statistics
# hack remove colon for image alignment
def fix_tag_list(tag_list):
return [None if tag is None else tag.replace(':', ';') for tag in tag_list]
image_contrib_tags = fix_tag_list(ibs.get_image_contributor_tag(valid_gids))
annot_contrib_tags = fix_tag_list(ibs.get_annot_image_contributor_tag(valid_aids))
contrib_tag_to_gids = ut.group_items(valid_gids, image_contrib_tags)
contrib_tag_to_aids = ut.group_items(valid_aids, annot_contrib_tags)
contrib_tag_to_qualstats = {key: ibs.get_annot_qual_stats(aids) for key, aids in six.iteritems(contrib_tag_to_aids)}
contrib_tag_to_viewstats = {key: ibs.get_annot_yaw_stats(aids) for key, aids in six.iteritems(contrib_tag_to_aids)}
contrib_tag_to_nImages = {key: len(val) for key, val in six.iteritems(contrib_tag_to_gids)}
contrib_tag_to_nAnnots = {key: len(val) for key, val in six.iteritems(contrib_tag_to_aids)}
if verbose:
print('Summarizing')
# Summarize stats
num_names = len(valid_nids)
num_names_unassociated = len(valid_nids) - len(associated_nids)
num_names_singleton = len(singleton_nxs)
num_names_multiton = len(multiton_nxs)
num_singleton_annots = len(singleton_aids)
num_multiton_annots = len(multiton_aids)
num_unknown_annots = len(unknown_aids)
num_annots = len(valid_aids)
if with_bytes:
if verbose:
print('Checking Disk Space')
ibsdir_space = ut.byte_str2(ut.get_disk_space(ibs.get_ibsdir()))
dbdir_space = ut.byte_str2(ut.get_disk_space(ibs.get_dbdir()))
imgdir_space = ut.byte_str2(ut.get_disk_space(ibs.get_imgdir()))
cachedir_space = ut.byte_str2(ut.get_disk_space(ibs.get_cachedir()))
if True:
if verbose:
print('Check asserts')
try:
bad_aids = np.intersect1d(multiton_aids, unknown_aids)
_num_names_total_check = num_names_singleton + num_names_unassociated + num_names_multiton
_num_annots_total_check = num_unknown_annots + num_singleton_annots + num_multiton_annots
assert len(bad_aids) == 0, 'intersecting multiton aids and unknown aids'
assert _num_names_total_check == num_names, 'inconsistent num names'
#if not request_annot_subset:
# dont check this if you have an annot subset
assert _num_annots_total_check == num_annots, 'inconsistent num annots'
except Exception as ex:
ut.printex(ex, keys=[
'_num_names_total_check',
'num_names',
'_num_annots_total_check',
'num_annots',
'num_names_singleton',
'num_names_multiton',
'num_unknown_annots',
'num_multiton_annots',
'num_singleton_annots',
])
raise
# Get contributor statistics
contrib_rowids = ibs.get_valid_contrib_rowids()
num_contributors = len(contrib_rowids)
# print
num_tabs = 5
def align2(str_):
return ut.align(str_, ':', ' :')
def align_dict2(dict_):
str_ = ut.dict_str(dict_)
return align2(str_)
header_block_lines = (
[('+============================'), ] + (
[
('+ singleton := single sighting'),
('+ multiton := multiple sightings'),
('--' * num_tabs),
] if not short and with_header else []
)
)
source_block_lines = [
('DB Info: ' + ibs.get_dbname()),
('DB Notes: ' + ibs.get_dbnotes()),
('DB NumContrib: %d' % num_contributors),
]
bytes_block_lines = [
('--' * num_tabs),
('DB Bytes: '),
(' +- dbdir nBytes: ' + dbdir_space),
(' | +- _ibsdb nBytes: ' + ibsdir_space),
(' | | +-imgdir nBytes: ' + imgdir_space),
(' | | +-cachedir nBytes: ' + cachedir_space),
] if with_bytes else []
name_block_lines = [
('--' * num_tabs),
('# Names = %d' % num_names),
('# Names (unassociated) = %d' % num_names_unassociated),
('# Names (singleton) = %d' % num_names_singleton),
('# Names (multiton) = %d' % num_names_multiton),
]
subset_str = ' ' if not request_annot_subset else '(SUBSET)'
annot_block_lines = [
('--' * num_tabs),
('# Annots %s = %d' % (subset_str, num_annots,)),
('# Annots (unknown) = %d' % num_unknown_annots),
('# Annots (singleton) = %d' % num_singleton_annots),
('# Annots (multiton) = %d' % num_multiton_annots),
]
annot_per_basic_block_lines = [
('--' * num_tabs),
('# Annots per Name (multiton) = %s' % (align2(multiton_stats),)),
('# Annots per Image = %s' % (align2(gx2_nAnnots_stats),)),
('# Annots per Species = %s' % (align_dict2(species2_nAids),)),
] if not short else []
occurrence_block_lines = [
('--' * num_tabs),
('# Occurrence Per Name (Resights) = %s' % (align_dict2(resight_name_stats),)),
('# Annots per Encounter (Singlesights) = %s' % (align_dict2(singlesight_annot_stats),)),
('# Pair Tag Info (annots) = %s' % (align_dict2(pair_tag_info),)),
] if not short else []
annot_per_qualview_block_lines = [
None if short else '# Annots per Viewpoint = %s' % align_dict2(yawtext2_nAnnots),
None if short else '# Annots per Quality = %s' % align_dict2(qualtext2_nAnnots),
]
annot_per_agesex_block_lines = [
'# Annots per Age = %s' % align_dict2(agetext2_nAnnots),
'# Annots per Sex = %s' % align_dict2(sextext2_nAnnots),
] if not short and with_agesex else []
contrib_block_lines = [
'# Images per contributor = ' + align_dict2(contrib_tag_to_nImages),
'# Annots per contributor = ' + align_dict2(contrib_tag_to_nAnnots),
'# Quality per contributor = ' + ut.dict_str(contrib_tag_to_qualstats, sorted_=True),
'# Viewpoint per contributor = ' + ut.dict_str(contrib_tag_to_viewstats, sorted_=True),
] if with_contrib else []
img_block_lines = [
('--' * num_tabs),
('# Img = %d' % len(valid_gids)),
None if short else ('# Img reviewed = %d' % sum(image_reviewed_list)),
None if short else ('# Img with gps = %d' % len(gps_list)),
#('# Img with timestamp = %d' % len(valid_unixtime_list)),
None if short else ('Img Time Stats = %s' % (align2(unixtime_statstr),)),
]
info_str_lines = (
header_block_lines +
bytes_block_lines +
source_block_lines +
name_block_lines +
annot_block_lines +
annot_per_basic_block_lines +
occurrence_block_lines +
annot_per_qualview_block_lines +
annot_per_agesex_block_lines +
img_block_lines +
contrib_block_lines +
imgsize_stat_lines +
[('L============================'), ]
)
info_str = '\n'.join(ut.filter_Nones(info_str_lines))
info_str2 = ut.indent(info_str, '[{tag}]'.format(tag=tag))
if verbose:
print(info_str2)
locals_ = locals()
return locals_
def precfg(ibs, acfg_name_list, test_cfg_name_list):
r"""
Helper to precompute information
Args:
ibs (IBEISController): ibeis controller object
qaids (list): query annotation ids
daids (list): database annotation ids
test_cfg_name_list (list):
CommandLine:
python -m ibeis.expt.precomputer --exec-precfg -t custom --expt-preload
python -m ibeis.expt.precomputer --exec-precfg -t candidacy -a default:qaids=allgt --preload
python -m ibeis.expt.precomputer --exec-precfg -t candidacy_invariance -a default:qaids=allgt --preload
python -m ibeis.expt.precomputer --exec-precfg --delete-nn-cache
Example:
>>> # DISABLE_DOCTEST
>>> from ibeis.expt.precomputer import * # NOQA
>>> import ibeis
>>> ibs = ibeis.opendb(defaultdb='PZ_MTEST')
>>> default_acfgstrs = ['default:qaids=allgt']
>>> acfg_name_list = ut.get_argval(('--aidcfg', '--acfg', '-a'), type_=list, default=default_acfgstrs)
>>> test_cfg_name_list = ut.get_argval('-t', type_=list, default=['custom'])
>>> result = precfg(ibs, acfg_name_list, test_cfg_name_list)
>>> print(result)
"""
# Generate list of database annotation configurations
acfg_list, expanded_aids_list = experiment_helpers.get_annotcfg_list(ibs, acfg_name_list)
# Generate list of query pipeline param configs
cfgdict_list, pipecfg_list = experiment_helpers.get_pipecfg_list(test_cfg_name_list, ibs=ibs)
#cfgx2_lbl = experiment_helpers.get_varied_cfg_lbls(cfgdict_list)
expanded_aids_iter = ut.ProgressIter(expanded_aids_list, lbl='annot config', freq=1, autoadjust=False)
nAcfg = len(acfg_list)
for acfgx, (qaids, daids) in enumerate(expanded_aids_iter):
if len(qaids) == 0:
print('[harness] WARNING No query annotations specified')
continue
if len(daids) == 0:
print('[harness] WARNING No database annotations specified')
continue
ut.colorprint('\n---Annot config', 'turquoise')
nCfg = len(pipecfg_list) # number of configurations (cols)
dbname = ibs.get_dbname()
cfgiter = ut.ProgressIter(pipecfg_list, lbl='query config', freq=1, autoadjust=False, parent_index=acfgx, parent_nTotal=nAcfg)
flag = False
if ut.get_argflag('--delete-nn-cache'):
ibs.delete_neighbor_cache()
flag = True
for cfgx, query_cfg in enumerate(cfgiter):
print('')
ut.colorprint(query_cfg.get_cfgstr(), 'turquoise')
verbose = True
with ut.Indenter('[%s cfg %d/%d]' % (dbname, (acfgx * nCfg) + cfgx * + 1, nCfg * nAcfg)):
qreq_ = ibs.new_query_request(qaids, daids, verbose=True, query_cfg=query_cfg)
if ut.get_argflag('--preload'):
qreq_.lazy_preload(verbose=verbose)
flag = True
if ut.get_argflag('--preload-chip'):
qreq_.ensure_chips(verbose=verbose, extra_tries=1)
flag = True
if ut.get_argflag('--preload-feat'):
qreq_.ensure_features(verbose=verbose)
flag = True
if ut.get_argflag('--preload-featweight'):
qreq_.ensure_featweights(verbose=verbose)
flag = True
if ut.get_argflag('--preindex'):
flag = True
if qreq_.qparams.pipeline_root in ['vsone', 'vsmany']:
qreq_.load_indexer(verbose=verbose)
assert flag is True, 'no flag specified'
assert flag is True, 'no flag specified'
