def modify_tags(tags_list, direct_map=None, regex_map=None, regex_aug=None,
delete_unmapped=False, return_unmapped=False,
return_map=False):
import utool as ut
tag_vocab = ut.unique(ut.flatten(tags_list))
alias_map = ut.odict()
if regex_map is not None:
alias_map.update(**ut.build_alias_map(regex_map, tag_vocab))
if direct_map is not None:
alias_map.update(ut.odict(direct_map))
new_tags_list = tags_list
new_tags_list = ut.alias_tags(new_tags_list, alias_map)
if regex_aug is not None:
alias_aug = ut.build_alias_map(regex_aug, tag_vocab)
aug_tags_list = ut.alias_tags(new_tags_list, alias_aug)
new_tags_list = [ut.unique(t1 + t2) for t1, t2 in zip(new_tags_list, aug_tags_list)]
unmapped = list(set(tag_vocab) - set(alias_map.keys()))
if delete_unmapped:
new_tags_list = [ut.setdiff(tags, unmapped) for tags in new_tags_list]
toreturn = None
if return_map:
toreturn = (alias_map,)
if return_unmapped:
toreturn = toreturn + (unmapped,)
if toreturn is None:
toreturn = new_tags_list
else:
toreturn = (new_tags_list,) + toreturn
return toreturn
def __init__(self, img, **kwargs):
super(PaintInteraction, self).__init__(**kwargs)
init_mask = kwargs.get('init_mask', None)
if init_mask is None:
mask = np.full(img.shape, 255, dtype=np.uint8)
else:
mask = init_mask
self.mask = mask
self.img = img
self.brush_size = 75
import wbia.plottool as pt
self.valid_colors1 = ut.odict([
# ('background', (255 * pt.BLACK).tolist()),
('scenery', (255 * pt.BLACK).tolist()),
('photobomb', (255 * pt.RED).tolist()),
])
self.valid_colors2 = ut.odict([('foreground',
(255 * pt.WHITE).tolist())])
self.color1_idx = 0
self.color1 = self.valid_colors1['scenery']
self.color2 = self.valid_colors2['foreground']
self.background = None
self.last_stroke = None
self.finished_callback = None
self._imshow_running = True
def __init__(self, img, **kwargs):
super(PaintInteraction, self).__init__(**kwargs)
init_mask = kwargs.get('init_mask', None)
if init_mask is None:
mask = np.full(img.shape, 255, dtype=np.uint8)
else:
mask = init_mask
self.mask = mask
self.img = img
self.brush_size = 75
import plottool as pt
self.valid_colors1 = ut.odict([
#('background', (255 * pt.BLACK).tolist()),
('scenery', (255 * pt.BLACK).tolist()),
('photobomb', (255 * pt.RED).tolist()),
])
self.valid_colors2 = ut.odict([
('foreground', (255 * pt.WHITE).tolist()),
])
self.color1_idx = 0
self.color1 = self.valid_colors1['scenery']
self.color2 = self.valid_colors2['foreground']
self.background = None
self.last_stroke = None
self.finished_callback = None
self._imshow_running = True
def __init__(db, sqldb_dpath='.', sqldb_fname='database.sqlite3',
text_factory=unicode):
""" Creates db and opens connection """
with utool.Timer('New SQLDatabaseController'):
#printDBG('[sql.__init__]')
# Table info
db.table_columns = utool.odict()
db.table_constraints = utool.odict()
db.table_docstr = utool.odict()
# TODO:
db.stack = []
db.cache = {} # key \in [tblname][colnames][rowid]
# Get SQL file path
db.dir_ = sqldb_dpath
db.fname = sqldb_fname
assert exists(db.dir_), '[sql] db.dir_=%r does not exist!' % db.dir_
fpath = join(db.dir_, db.fname)
if not exists(fpath):
print('[sql] Initializing new database')
# Open the SQL database connection with support for custom types
#lite.enable_callback_tracebacks(True)
#fpath = ':memory:'
db.connection = lite.connect2(fpath)
db.connection.text_factory = text_factory
#db.connection.isolation_level = None # turns sqlite3 autocommit off
COPY_TO_MEMORY = utool.get_flag('--copy-db-to-memory')
if COPY_TO_MEMORY:
db._copy_to_memory()
db.connection.text_factory = text_factory
# Get a cursor which will preform sql commands / queries / executions
db.cur = db.connection.cursor()
class META_DECISION(object): # NOQA
"""
Enumerated types of review codes and texts
Notes:
unreviewed: we dont have a meta decision
same: we know this is the same animal through non-visual means
diff: we know this is the different animal through non-visual means
Example:
>>> # ENABLE_DOCTEST
>>> from wbia.constants import * # NOQA
>>> assert hasattr(META_DECISION, 'CODE')
>>> assert hasattr(META_DECISION, 'NICE')
>>> code1 = META_DECISION.INT_TO_CODE[META_DECISION.NULL]
>>> code2 = META_DECISION.CODE.NULL
>>> assert code1 == code2
>>> nice1 = META_DECISION.INT_TO_NICE[META_DECISION.NULL]
>>> nice2 = META_DECISION.NICE.NULL
>>> assert nice1 == nice2
"""
NULL = None
DIFF = 0
SAME = 1
INT_TO_CODE = ut.odict([(NULL, 'null'), (DIFF, 'diff'), (SAME, 'same')])
INT_TO_NICE = ut.odict([(NULL, 'NULL'), (DIFF, 'Different'),
(SAME, 'Same')])
CODE_TO_NICE = ut.map_keys(INT_TO_CODE, INT_TO_NICE)
CODE_TO_INT = ut.invert_dict(INT_TO_CODE)
NICE_TO_CODE = ut.invert_dict(CODE_TO_NICE)
NICE_TO_INT = ut.invert_dict(INT_TO_NICE)
class CONFIDENCE(object):
UNKNOWN = None
GUESSING = 1
NOT_SURE = 2
PRETTY_SURE = 3
ABSOLUTELY_SURE = 4
INT_TO_CODE = ut.odict([
(ABSOLUTELY_SURE, 'absolutely_sure'),
(PRETTY_SURE, 'pretty_sure'),
(NOT_SURE, 'not_sure'),
(GUESSING, 'guessing'),
(UNKNOWN, 'unspecified'),
])
INT_TO_NICE = ut.odict([
(ABSOLUTELY_SURE, 'Doubtless'),
(PRETTY_SURE, 'Sure'),
(NOT_SURE, 'Unsure'),
(GUESSING, 'Guessing'),
(UNKNOWN, 'Unspecified'),
])
CODE_TO_NICE = ut.map_keys(INT_TO_CODE, INT_TO_NICE)
CODE_TO_INT = ut.invert_dict(INT_TO_CODE)
NICE_TO_CODE = ut.invert_dict(CODE_TO_NICE)
NICE_TO_INT = ut.invert_dict(INT_TO_NICE)
class QUAL(object):
EXCELLENT = 5
GOOD = 4
OK = 3
POOR = 2
JUNK = 1
UNKNOWN = None
INT_TO_CODE = ut.odict([
(EXCELLENT, 'excellent'),
(GOOD, 'good'),
(OK, 'ok'),
(POOR, 'poor'),
(JUNK, 'junk'),
(UNKNOWN, 'unspecified'),
])
INT_TO_NICE = ut.odict([
(EXCELLENT, 'Excellent'),
(GOOD, 'Good'),
(OK, 'OK'),
(POOR, 'Poor'),
(JUNK, 'Junk'),
(UNKNOWN, 'Unspecified'),
])
CODE_TO_NICE = ut.map_keys(INT_TO_CODE, INT_TO_NICE)
CODE_TO_INT = ut.invert_dict(INT_TO_CODE)
NICE_TO_CODE = ut.invert_dict(CODE_TO_NICE)
NICE_TO_INT = ut.invert_dict(INT_TO_NICE)
def parse_abbrev():
ref_text = 'Acoustics Acoust.\nAdministration Admin.\nAdministrative Administ.\nAmerican Amer.\nAnalysis Anal.\nAnnals Ann.\nAnnual Annu.\nApparatus App.\nApplications Appl.\nApplied Appl.\nAssociation Assoc.\nAutomatic Automat.\nBritish Brit.\nBroadcasting Broadcast.\nBusiness Bus.\nCanadian Can.\nChinese Chin.\nCommunications Commun.\nComputer(s) Comput.\nConference Conf.\nCongress Congr.\nConvention Conv.\nCorrespondence Corresp.\nCybernetics Cybern.\nDepartment Dept.\nDesign Des.\nDevelopment Develop.\nDigest Dig.\nEconomic(s) Econ.\nEducation Edu.\nElectric Elect.\nElectrical Elect.\nElectronic Electron.\nElectronics Electron.\nEngineering Eng.\nErgonomics Ergonom.\nEuropean Eur.\nEvolutionary Evol.\nExpress Express\nFoundation Found.\nGeoscience Geosci.\nGraphics Graph.\nIndustrial Ind.\nInformation Inform.\nInstitute Inst.\nIntelligence Intell.\nInternational Int.\nJapan Jpn.\nJournal J.\nLetter(s) Lett.\nMachine Mach.\nMagazine Mag.\nMagnetics Magn.\nManagement Manage.\nManaging Manag.\nMathematical Math.\nMechanical Mech.\nMeeting Meeting\nNational Nat.\nNewsletter Newslett.\nNuclear Nucl.\nOccupation Occupat.\nOperational Oper.\nOptical Opt.\nOptics Opt.\nOrganization Org.\nPhilosophical Philosoph.\nProceedings Proc.\nProcessing Process.\nProduction Prod.\nProductivity Productiv.\nQuarterly Quart.\nRecord Rec.\nReliability Rel.\nReport Rep.\nResearch Res.\nReview Rev.\nRoyal Roy.\nScience Sci.\nSelected Select.\nSociety Soc.\nSociological Sociol.\nStatistics Statist.\nStudies Stud.\nSupplement Suppl.\nSymposium Symp.\nSystems Syst.\nTechnical Tech.\nTechniques Techn.\nTechnology Technol.\nTelecommunications Telecommun.\nTransactions Trans.\nVehicular Veh.\nWorking Work.'
abbrev_map = {}
for line in ref_text.split('\n'):
full, accro = line.split(' ')
if full.endswith('(s)'):
full_single = full[:-3]
abbrev_map[full_single] = accro
abbrev_map[full_single + 's'] = accro
else:
abbrev_map[full] = accro
ut.odict(abbrev_map)
def make_layer_json_dict(layer, layer_info, layer_to_id, extra=True):
"""
>>> from ibeis_cnn.net_strs import * # NOQA
"""
#layer_type = layer_info['classname']
#attr_key_list = layer_info['layer_attrs']
json_dict = ut.odict([])
if extra:
json_dict['name'] = layer_info['name']
json_dict['type'] = layer_info['classname']
json_dict['id'] = layer_to_id[layer]
if hasattr(layer, 'input_layer'):
#json_dict['input_layer'] = layer.input_layer.name
# HACK FOR WHEN DROPOUT LAYERS DONT EXIST
def get_mrp_id(in_layer):
if in_layer in layer_to_id:
return layer_to_id[in_layer]
else:
return get_mrp_id(in_layer.input_layer)
json_dict['input_layer'] = get_mrp_id(layer.input_layer)
if hasattr(layer, 'input_layers'):
#json_dict['input_layers'] = [l.name for l in layer.input_layers]
json_dict['input_layers'] = [layer_to_id[l] for l in layer.input_layers]
json_dict.update(**layer_info['layer_attrs'])
nonlin = layer_info.get('nonlinearity', None)
if nonlin is not None:
json_dict['nonlinearity'] = nonlin
json_params = []
for param_info in layer_info['param_infos']:
p = ut.odict()
p['name'] = param_info['basename']
if extra:
init = param_info.get('init', None)
if init is not None:
p['init'] = init
tags = param_info.get('tags', None)
if tags is not None:
if extra:
p['tags'] = list(tags)
else:
if len(tags) > 0:
p['tags'] = list(tags)
json_params.append(p)
if len(json_params) > 0:
json_dict['params'] = json_params
return json_dict
def inference_stats(infr_list_):
relabel_stats = []
for infr in infr_list_:
num_ccs, num_inconsistent = infr.relabel_using_reviews()
state_hist = ut.dict_hist(nx.get_edge_attributes(infr.graph, 'decision').values())
if POSTV not in state_hist:
state_hist[POSTV] = 0
hist = ut.dict_hist(nx.get_edge_attributes(infr.graph, '_speed_split').values())
subgraphs = infr.positive_connected_compoments()
subgraph_sizes = [len(g) for g in subgraphs]
info = ut.odict([
('num_nonmatch_edges', state_hist[NEGTV]),
('num_match_edges', state_hist[POSTV]),
('frac_nonmatch_edges', state_hist[NEGTV] / (state_hist[POSTV] + state_hist[NEGTV])),
('num_inconsistent', num_inconsistent),
('num_ccs', num_ccs),
('edges_flipped', hist.get('flip', 0)),
('edges_unchanged', hist.get('orig', 0)),
('bad_unreviewed_edges', hist.get('new', 0)),
('orig_size', len(infr.graph)),
('new_sizes', subgraph_sizes),
])
relabel_stats.append(info)
return relabel_stats
def precompute_data():
"""
Ensure features and such are computed
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-precompute_data
Example:
>>> from ibeis.scripts.gen_cand_expts import *
>>> make_standard_test_scripts(precompute_data())
"""
#basecmd = 'python -m ibeis.expt.experiment_printres
#--exec-print_latexsum --rank-lt-list=1,5,10,100 '
varydict = ut.odict([
('preload_flags', [
#'--preload-chip',
#'--preload-feat',
#'--preload-feeatweight',
'--preload',
'--preindex',
]),
('dbname', get_dbnames()),
('acfg_name', ['default:qaids=allgt,species=primary,view=primary,is_known=True']),
('cfg_name', ['default', 'candidacy_baseline', 'candidacy_invariance']),
])
return (varydict, 'preload', 'preload')
def precompute_data():
"""
Ensure features and such are computed
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-precompute_data
Example:
>>> from ibeis.scripts.gen_cand_expts import *
>>> make_standard_test_scripts(precompute_data())
"""
#basecmd = 'python -m ibeis.expt.experiment_printres
#--exec-print_latexsum --rank-lt-list=1,5,10,100 '
varydict = ut.odict([
('preload_flags', [
#'--preload-chip',
#'--preload-feat',
#'--preload-feeatweight',
'--preload',
'--preindex',
]),
('dbname', get_dbnames()),
('acfg_name', ['default:qaids=allgt,species=primary,view=primary,is_known=True']),
('cfg_name', ['default', 'candidacy_baseline', 'candidacy_invariance']),
])
return (varydict, 'preload', 'preload')
def _debug_repr_cpd(cpd):
import re
import utool as ut
code_fmt = ut.codeblock(
'''
{variable} = pgmpy.factors.TabularCPD(
variable={variable_repr},
variable_card={variable_card_repr},
values={get_cpd_repr},
evidence={evidence_repr},
evidence_card={evidence_card_repr},
)
''')
keys = ['variable', 'variable_card', 'values', 'evidence', 'evidence_card']
dict_ = ut.odict(zip(keys, [getattr(cpd, key) for key in keys]))
# HACK
dict_['values'] = cpd.get_cpd()
r = ut.repr2(dict_, explicit=True, nobraces=True, nl=True)
print(r)
# Parse props that are needed for this fmtstr
fmt_keys = [match.groups()[0] for match in re.finditer('{(.*?)}', code_fmt)]
need_reprs = [key[:-5] for key in fmt_keys if key.endswith('_repr')]
need_keys = [key for key in fmt_keys if not key.endswith('_repr')]
# Get corresponding props
# Call methods if needbe
tmp = [(prop, getattr(cpd, prop)) for prop in need_reprs]
tmp = [(x, y()) if ut.is_funclike(y) else (x, y) for (x, y) in tmp]
fmtdict = dict(tmp)
fmtdict = ut.map_dict_vals(ut.repr2, fmtdict)
fmtdict = ut.map_dict_keys(lambda x: x + '_repr', fmtdict)
tmp2 = [(prop, getattr(cpd, prop)) for prop in need_keys]
fmtdict.update(dict(tmp2))
code = code_fmt.format(**fmtdict)
return code
def isect_info(self, other):
set1 = set(self.rel_fpath_list)
set2 = set(other.rel_fpath_list)
set_comparisons = ut.odict([
('s1', set1),
('s2', set2),
('union', set1.union(set2)),
('isect', set1.intersection(set2)),
('s1 - s2', set1.difference(set2)),
('s2 - s1', set1.difference(set1)),
])
stat_stats = ut.map_vals(len, set_comparisons)
print(ut.repr4(stat_stats))
return set_comparisons
if False:
idx_lookup1 = ut.make_index_lookup(self.rel_fpath_list)
idx_lookup2 = ut.make_index_lookup(other.rel_fpath_list)
uuids1 = ut.take(self.uuids,
ut.take(idx_lookup1, set_comparisons['union']))
uuids2 = ut.take(other.uuids,
ut.take(idx_lookup2, set_comparisons['union']))
uuids1 == uuids2
def get_cfgstr(nnindexer, noquery=False):
r""" returns string which uniquely identified configuration and support data
Args:
noquery (bool): if True cfgstr is only relevant to building the
index. No search params are returned (default = False)
Returns:
str: flann_cfgstr
CommandLine:
python -m wbia.algo.hots.neighbor_index --test-get_cfgstr
Example:
>>> # DISABLE_DOCTEST
>>> from wbia.algo.hots.neighbor_index import * # NOQA
>>> import wbia
>>> cfgdict = dict(fg_on=False)
>>> qreq_ = wbia.testdata_qreq_(defaultdb='testdb1', p='default:fg_on=False')
>>> qreq_.load_indexer()
>>> nnindexer = qreq_.indexer
>>> noquery = True
>>> flann_cfgstr = nnindexer.get_cfgstr(noquery)
>>> result = ('flann_cfgstr = %s' % (str(flann_cfgstr),))
>>> print(result)
flann_cfgstr = _FLANN((algo=kdtree,seed=42,t=8,))_VECS((11260,128)gj5nea@ni0%f3aja)
"""
flann_cfgstr_list = []
use_params_hash = True
use_data_hash = True
if use_params_hash:
flann_defaults = vt.get_flann_params(
nnindexer.flann_params['algorithm'])
# flann_params_clean = flann_defaults.copy()
flann_params_clean = ut.sort_dict(flann_defaults)
ut.update_existing(flann_params_clean, nnindexer.flann_params)
if noquery:
ut.delete_dict_keys(flann_params_clean, ['checks'])
shortnames = dict(algorithm='algo',
checks='chks',
random_seed='seed',
trees='t')
short_params = ut.odict([
(shortnames.get(key, key), str(val)[0:7])
for key, val in six.iteritems(flann_params_clean)
])
flann_valsig_ = ut.repr2(short_params,
nl=False,
explicit=True,
strvals=True)
flann_valsig_ = flann_valsig_.lstrip('dict').replace(' ', '')
# flann_valsig_ = str(list(flann_params.values()))
# flann_valsig = ut.remove_chars(flann_valsig_, ', \'[]')
flann_cfgstr_list.append('_FLANN(' + flann_valsig_ + ')')
if use_data_hash:
vecs_hashstr = ut.hashstr_arr(nnindexer.idx2_vec, '_VECS')
flann_cfgstr_list.append(vecs_hashstr)
flann_cfgstr = ''.join(flann_cfgstr_list)
return flann_cfgstr
def as_dict(self):
return ut.odict([
('type', self.type),
('accro', self._accro),
('full', self._full),
('abbrev', self.abbrev()),
('publisher', self._publisher),
])
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 measure_error_edges(infr):
for edge, data in infr.edges(data=True):
true_state = data['truth']
pred_state = data.get('evidence_decision', UNREV)
if pred_state != UNREV:
if true_state != pred_state:
error = ut.odict([('real', true_state),
('pred', pred_state)])
yield edge, error
def parse_theano_flags():
import os
theano_flags_str = os.environ.get('THEANO_FLAGS', '')
theano_flags_itemstrs = theano_flags_str.split(',')
theano_flags = ut.odict([
itemstr.split('=') for itemstr in theano_flags_itemstrs
if len(itemstr) > 0
])
return theano_flags
class EVIDENCE_DECISION(object): # NOQA
"""
TODO: change to EVIDENCE_DECISION / VISUAL_DECISION
Enumerated types of review codes and texts
Notes:
Unreviewed: Not comparared yet.
nomatch: Visually comparable and the different
match: Visually comparable and the same
notcomp: Not comparable means it is actually impossible to determine.
unknown: means that it was reviewed, but we just can't figure it out.
"""
UNREVIEWED = None
NEGATIVE = 0
POSITIVE = 1
INCOMPARABLE = 2
UNKNOWN = 3
INT_TO_CODE = ut.odict([
(POSITIVE, 'match'),
(NEGATIVE, 'nomatch'),
(INCOMPARABLE, 'notcomp'),
(UNKNOWN, 'unknown'),
(UNREVIEWED, 'unreviewed'),
])
INT_TO_NICE = ut.odict([
(POSITIVE, 'Positive'),
(NEGATIVE, 'Negative'),
(INCOMPARABLE, 'Incomparable'),
(UNKNOWN, 'Unknown'),
(UNREVIEWED, 'Unreviewed'),
])
CODE_TO_NICE = ut.map_keys(INT_TO_CODE, INT_TO_NICE)
CODE_TO_INT = ut.invert_dict(INT_TO_CODE)
NICE_TO_CODE = ut.invert_dict(CODE_TO_NICE)
NICE_TO_INT = ut.invert_dict(INT_TO_NICE)
MATCH_CODE = CODE_TO_INT
def parse_theano_flags():
"""
export THEANO_FLAGS="device=cpu,print_active_device=True,enable_initial_driver_test=True"
export THEANO_FLAGS="device=gpu2,print_active_device=True,enable_initial_driver_test=False"
set THEANO_FLAGS="device=cpu,print_active_device=True,enable_initial_driver_test=True"
"""
theano_flags_str = os.environ.get('THEANO_FLAGS', '')
theano_flags_itemstrs = theano_flags_str.split(',')
theano_flags = ut.odict([
itemstr.split('=') for itemstr in theano_flags_itemstrs
if len(itemstr) > 0
])
return theano_flags
def simulate_user_feedback(infr):
qreq_ = infr.qreq_
aid_pairs = np.array(ut.take_column(infr.needs_review_list, [0, 1]))
nid_pairs = qreq_.ibs.get_annot_nids(aid_pairs)
truth = nid_pairs.T[0] == nid_pairs.T[1]
user_feedback = ut.odict([
('aid1', aid_pairs.T[0]),
('aid2', aid_pairs.T[1]),
('p_match', truth.astype(np.float)),
('p_nomatch', 1.0 - truth),
('p_notcomp', np.array([0.0] * len(aid_pairs))),
])
return user_feedback
def simulate_user_feedback(infr):
qreq_ = infr.qreq_
aid_pairs = np.array(ut.take_column(infr.needs_review_list, [0, 1]))
nid_pairs = qreq_.ibs.get_annot_nids(aid_pairs)
truth = nid_pairs.T[0] == nid_pairs.T[1]
user_feedback = ut.odict([
('aid1', aid_pairs.T[0]),
('aid2', aid_pairs.T[1]),
('p_match', truth.astype(np.float)),
('p_nomatch', 1.0 - truth),
('p_notcomp', np.array([0.0] * len(aid_pairs))),
])
return user_feedback
def get_cfgstr(nnindexer, noquery=False):
r""" returns string which uniquely identified configuration and support data
Args:
noquery (bool): if True cfgstr is only relevant to building the
index. No search params are returned (default = False)
Returns:
str: flann_cfgstr
CommandLine:
python -m ibeis.algo.hots.neighbor_index --test-get_cfgstr
Example:
>>> # DISABLE_DOCTEST
>>> from ibeis.algo.hots.neighbor_index import * # NOQA
>>> import ibeis
>>> cfgdict = dict(fg_on=False)
>>> qreq_ = ibeis.testdata_qreq_(defaultdb='testdb1', p='default:fg_on=False')
>>> qreq_.load_indexer()
>>> nnindexer = qreq_.indexer
>>> noquery = True
>>> flann_cfgstr = nnindexer.get_cfgstr(noquery)
>>> result = ('flann_cfgstr = %s' % (str(flann_cfgstr),))
>>> print(result)
flann_cfgstr = _FLANN((algo=kdtree,seed=42,t=8,))_VECS((11260,128)gj5nea@ni0%f3aja)
"""
flann_cfgstr_list = []
use_params_hash = True
use_data_hash = True
if use_params_hash:
flann_defaults = vt.get_flann_params(nnindexer.flann_params['algorithm'])
#flann_params_clean = flann_defaults.copy()
flann_params_clean = ut.sort_dict(flann_defaults)
ut.updateif_haskey(flann_params_clean, nnindexer.flann_params)
if noquery:
ut.delete_dict_keys(flann_params_clean, ['checks'])
shortnames = dict(algorithm='algo', checks='chks', random_seed='seed', trees='t')
short_params = ut.odict([(shortnames.get(key, key), str(val)[0:7])
for key, val in six.iteritems(flann_params_clean)])
flann_valsig_ = ut.dict_str(
short_params, nl=False, explicit=True, strvals=True)
flann_valsig_ = flann_valsig_.lstrip('dict').replace(' ', '')
#flann_valsig_ = str(list(flann_params.values()))
#flann_valsig = ut.remove_chars(flann_valsig_, ', \'[]')
flann_cfgstr_list.append('_FLANN(' + flann_valsig_ + ')')
if use_data_hash:
vecs_hashstr = ut.hashstr_arr(nnindexer.idx2_vec, '_VECS')
flann_cfgstr_list.append(vecs_hashstr)
flann_cfgstr = ''.join(flann_cfgstr_list)
return flann_cfgstr
def get_addtable_kw(table):
primary_coldef = [(table.rowid_colname, 'INTEGER PRIMARY KEY')]
parent_coldef = [(key, 'INTEGER NOT NULL') for key in table.parent_rowid_colnames]
config_coldef = [(CONFIG_ROWID, 'INTEGER DEFAULT 0')]
internal_data_coldef = list(zip(table._internal_data_colnames,
table._internal_data_coltypes))
coldef_list = primary_coldef + parent_coldef + config_coldef + internal_data_coldef
add_table_kw = ut.odict([
('tablename', table.tablename,),
('coldef_list', coldef_list,),
('docstr', table.docstr,),
('superkeys', [table.superkey_colnames],),
('dependson', table.parents),
])
return add_table_kw
def initializer_info(initclass):
initclassname = initclass.__class__.__name__
if initclassname == 'Constant':
spec = initclass.val
else:
spec = ut.odict()
spec['type'] = initclassname
for key, val in initclass.__dict__.items():
if isinstance(val, lasagne.init.Initializer):
spec[key] = initializer_info(val)
elif isinstance(val, type) and issubclass(val, lasagne.init.Initializer):
spec[key] = val.__name__
#initializer_info(val())
else:
spec[key] = val
return spec
def infodict2(player):
infodict = ut.odict(
[
# ('id_', player.id_),
("turn", player.turn),
("life", player.life),
("library_hash", ut.hashstr27(str(player.deck.library))),
("library_size", len(player.deck)),
("hand_size", len(player.hand)),
("bfield_size", len(player.bfield)),
("graveyard_size", len(player.graveyard)),
("exiled_size", len(player.exiled)),
("hand", mtgobjs.CardGroup(player.hand).infohist),
("bfield", mtgobjs.CardGroup(player.bfield).infohist),
("graveyard", mtgobjs.CardGroup(player.graveyard).infohist),
]
)
return infodict
def experiments_k():
"""
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-experiments_k
python -m ibeis.scripts.gen_cand_expts --exec-experiments_k --full
./experiment_k.sh
Example:
>>> from ibeis.scripts.gen_cand_expts import *
>>> make_standard_test_scripts(experiments_k())
"""
varydict = ut.odict([
('acfg_name', ACFG_OPTION_VARYSIZE),
('cfg_name', ['candidacy_k']),
('dbname', get_dbnames(exclude_list=['PZ_FlankHack', 'PZ_MTEST'])),
])
#return (varydict, 'k', ['surface3d', 'surface2d'])
return (varydict, 'k', ['surface2d'])
def experiments_k():
"""
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-experiments_k
python -m ibeis.scripts.gen_cand_expts --exec-experiments_k --full
./experiment_k.sh
Example:
>>> from ibeis.scripts.gen_cand_expts import *
>>> make_standard_test_scripts(experiments_k())
"""
varydict = ut.odict([
('acfg_name', ACFG_OPTION_VARYSIZE),
('cfg_name', ['candidacy_k']),
('dbname', get_dbnames(exclude_list=['PZ_FlankHack', 'PZ_MTEST'])),
])
#return (varydict, 'k', ['surface3d', 'surface2d'])
return (varydict, 'k', ['surface2d'])
def infer_monitor_specs(res_w, res_h, inches_diag):
"""
monitors = [
dict(name='work1', inches_diag=23, res_w=1920, res_h=1080),
dict(name='work2', inches_diag=24, res_w=1920, res_h=1200),
dict(name='hp-129', inches_diag=25, res_w=1920, res_h=1080),
dict(name='?-26', inches_diag=26, res_w=1920, res_h=1080),
dict(name='?-27', inches_diag=27, res_w=1920, res_h=1080),
]
for info in monitors:
name = info['name']
inches_diag = info['inches_diag']
res_h = info['res_h']
res_w = info['res_w']
print('---')
print(name)
inches_w = inches_diag * res_w / np.sqrt(res_h**2 + res_w**2)
inches_h = inches_diag * res_h / np.sqrt(res_h**2 + res_w**2)
print('inches diag = %.2f' % (inches_diag))
print('inches WxH = %.2f x %.2f' % (inches_w, inches_h))
#inches_w = inches_diag * res_w/sqrt(res_h**2 + res_w**2)
"""
import sympy
# Build a system of equations and solve it
inches_w, inches_h = sympy.symbols(
'inches_w inches_h'.split(), real=True, positive=True
)
res_w, res_h = sympy.symbols('res_w res_h'.split(), real=True, positive=True)
(inches_diag,) = sympy.symbols('inches_diag'.split(), real=True, positive=True)
equations = [
sympy.Eq(inches_diag, (inches_w ** 2 + inches_h ** 2) ** 0.5),
sympy.Eq(res_w / res_h, inches_w / inches_h),
]
print('Possible solutions:')
query_vars = [inches_w, inches_h]
for solution in sympy.solve(equations, query_vars):
print('Solution:')
reprstr = ut.repr3(
ut.odict(zip(query_vars, solution)), explicit=True, nobr=1, with_comma=False
)
print(ut.indent(ut.autopep8_format(reprstr)))
def module_stdinfo_dict(module, versionattr='__version__', version=None,
libdep=None, name=None, **kwargs):
infodict = ut.odict()
if module is None:
infodict['__version__'] = version
infodict['__name__'] = name
infodict['__file__'] = 'None'
else:
if version is not None:
infodict['__version__'] = version
else:
infodict['__version__'] = getattr(module, versionattr, None)
infodict['__name__'] = name
infodict['__name__'] = getattr(module, '__name__', None)
infodict['__file__'] = getattr(module, '__file__', None)
if libdep is not None:
infodict['libdep'] = libdep
infodict.update(kwargs)
return infodict
def initialize(depc):
print('[depc] INITIALIZE DEPCACHE')
if depc._use_globals:
print(' * regsitering %d global preproc funcs' % (len(__PREPROC_REGISTER__),))
for args_, kwargs_ in __PREPROC_REGISTER__:
depc._register_prop(*args_, **kwargs_)
ut.ensuredir(depc.cache_dpath)
#print('depc.cache_dpath = %r' % (depc.cache_dpath,))
config_addtable_kw = ut.odict(
[
('tablename', CONFIG_TABLE,),
('coldef_list', [
(CONFIG_ROWID, 'INTEGER PRIMARY KEY'),
(CONFIG_HASHID, 'TEXT'),
],),
('docstr', 'table for algo configurations'),
('superkeys', [(CONFIG_HASHID,)]),
('dependson', [])
]
)
#print(ut.repr3(config_addtable_kw))
#print('depc.fname_to_db.keys = %r' % (depc.fname_to_db,))
for fname in depc.fname_to_db.keys():
#print('fname = %r' % (fname,))
if fname == ':memory:':
fpath = fname
else:
fname_ = ut.ensure_ext(fname, '.sqlite')
fpath = ut.unixjoin(depc.cache_dpath, fname_)
#print('fpath = %r' % (fpath,))
db = SQLDatabaseController(fpath=fpath, simple=True)
if not db.has_table(CONFIG_TABLE):
db.add_table(**config_addtable_kw)
depc.fname_to_db[fname] = db
print('[depc] Finished initialization')
for table in depc.cachetable_dict.values():
table.initialize()
def inspect_annotation_configs():
r"""
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-inspect_annotation_configs
python -m ibeis.scripts.gen_cand_expts --exec-inspect_annotation_configs --full
Example:
>>> # SCRIPT
>>> from ibeis.scripts.gen_cand_expts import * # NOQA
>>> make_standard_test_scripts(inspect_annotation_configs())
"""
testdef_list = [func() for func in TEST_GEN_FUNCS]
acfg_name_list = ut.flatten([tup[0]['acfg_name'] for tup in testdef_list])
acfg_name_list = list(set(acfg_name_list))
varydict = ut.odict([
#('acfg_name', ['controlled']),
#('acfg_name', ['controlled', 'controlled2']),
('acfg_name', [' '.join(acfg_name_list)]),
('dbname', get_dbnames()),
])
return varydict, 'inspect_acfg', 'inspect_acfg'
def experiments_baseline():
"""
Generates the experiments we are doing on invariance
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-experiments_baseline
./experiment_baseline.sh
Example:
>>> from ibeis.scripts.gen_cand_expts import *
>>> make_standard_test_scripts(experiments_baseline())
"""
# Invariance Experiments
varydict = ut.odict([
#('acfg_name', ['controlled']),
#('acfg_name', ['controlled', 'controlled2']),
('acfg_name', ACFG_OPTION_CONTROLLED),
('cfg_name', ['candidacy_baseline']),
('dbname', get_dbnames()),
])
return (varydict, 'baseline', 'cumhist')
def experiments_viewpoint():
"""
Generates the experiments we are doing on invariance
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-experiments_viewpoint --full
./experiment_view.sh
Example:
>>> from ibeis.scripts.gen_cand_expts import *
>>> make_standard_test_scripts(experiments_viewpoint())
"""
#basecmd = 'python -m ibeis.expt.experiment_printres
#--exec-print_latexsum --rank-lt-list=1,5,10,100 '
varydict = ut.odict([
('acfg_name', ['viewpoint_compare']),
('cfg_name', ['default']),
#('dbname', ['NNP_Master3', 'PZ_Master0']),
('dbname', ['PZ_Master1']),
])
return (varydict, 'view', 'cumhist')
def inspect_annotation_configs():
r"""
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-inspect_annotation_configs
python -m ibeis.scripts.gen_cand_expts --exec-inspect_annotation_configs --full
Example:
>>> # SCRIPT
>>> from ibeis.scripts.gen_cand_expts import * # NOQA
>>> make_standard_test_scripts(inspect_annotation_configs())
"""
testdef_list = [func() for func in TEST_GEN_FUNCS]
acfg_name_list = ut.flatten([tup[0]['acfg_name'] for tup in testdef_list])
acfg_name_list = list(set(acfg_name_list))
varydict = ut.odict([
#('acfg_name', ['controlled']),
#('acfg_name', ['controlled', 'controlled2']),
('acfg_name', [' '.join(acfg_name_list)]),
('dbname', get_dbnames()),
])
return varydict, 'inspect_acfg', 'inspect_acfg'
def experiments_baseline():
"""
Generates the experiments we are doing on invariance
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-experiments_baseline
./experiment_baseline.sh
Example:
>>> from ibeis.scripts.gen_cand_expts import *
>>> make_standard_test_scripts(experiments_baseline())
"""
# Invariance Experiments
varydict = ut.odict([
#('acfg_name', ['controlled']),
#('acfg_name', ['controlled', 'controlled2']),
('acfg_name', ACFG_OPTION_CONTROLLED),
('cfg_name', ['candidacy_baseline']),
('dbname', get_dbnames()),
])
return (varydict, 'baseline', 'cumhist')
def experiments_viewpoint():
"""
Generates the experiments we are doing on invariance
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-experiments_viewpoint --full
./experiment_view.sh
Example:
>>> from ibeis.scripts.gen_cand_expts import *
>>> make_standard_test_scripts(experiments_viewpoint())
"""
#basecmd = 'python -m ibeis.expt.experiment_printres
#--exec-print_latexsum --rank-lt-list=1,5,10,100 '
varydict = ut.odict([
('acfg_name', ['viewpoint_compare']),
('cfg_name', ['default']),
#('dbname', ['NNP_Master3', 'PZ_Master0']),
('dbname', ['PZ_Master1']),
])
return (varydict, 'view', 'cumhist')
def experiments_namescore():
"""
Generates the experiments we are doing on invariance
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-experiments_namescore --full
./experiment_namescore.sh
python -m ibeis.scripts.gen_cand_expts --exec-experiments_namescore --full
python -m ibeis.expt.experiment_helpers --exec-get_annotcfg_list:0 -a candidacy_namescore --db PZ_Master1 # NOQA
Example:
>>> from ibeis.scripts.gen_cand_expts import *
>>> make_standard_test_scripts(experiments_namescore())
"""
varydict = ut.odict([
#('acfg_name', ['controlled', 'controlled2']),
('acfg_name', ACFG_OPTION_CONTROLLED + ACFG_OPTION_VARYPERNAME),
('cfg_name', ['candidacy_namescore', 'candidacy_namescore:K=1']),
('dbname', get_dbnames()),
])
return (varydict, 'namescore', 'cumhist')
def experiments_invariance():
"""
Generates the experiments we are doing on invariance
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-experiments_invariance
python -m ibeis.scripts.gen_cand_expts --exec-experiments_invariance --full
Example:
>>> from ibeis.scripts.gen_cand_expts import *
>>> make_standard_test_scripts(experiments_invariance())
"""
# Invariance Experiments
#static_flags += ' --dpi=512 --figsize=11,4 --clipwhite'
varydict = ut.odict([
#('acfg_name', ['controlled']),
#('acfg_name', ['controlled', 'controlled2']),
('acfg_name', ACFG_OPTION_CONTROLLED),
('cfg_name', ['candidacy_invariance']),
('dbname', get_dbnames()),
])
return (varydict, 'invar', 'cumhist')
def experiments_namescore():
"""
Generates the experiments we are doing on invariance
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-experiments_namescore --full
./experiment_namescore.sh
python -m ibeis.scripts.gen_cand_expts --exec-experiments_namescore --full
python -m ibeis.expt.experiment_helpers --exec-get_annotcfg_list:0 -a candidacy_namescore --db PZ_Master1 # NOQA
Example:
>>> from ibeis.scripts.gen_cand_expts import *
>>> make_standard_test_scripts(experiments_namescore())
"""
varydict = ut.odict([
#('acfg_name', ['controlled', 'controlled2']),
('acfg_name', ACFG_OPTION_CONTROLLED + ACFG_OPTION_VARYPERNAME),
('cfg_name', ['candidacy_namescore', 'candidacy_namescore:K=1']),
('dbname', get_dbnames()),
])
return (varydict, 'namescore', 'cumhist')
def experiments_invariance():
"""
Generates the experiments we are doing on invariance
CommandLine:
python -m ibeis.scripts.gen_cand_expts --exec-experiments_invariance
python -m ibeis.scripts.gen_cand_expts --exec-experiments_invariance --full
Example:
>>> from ibeis.scripts.gen_cand_expts import *
>>> make_standard_test_scripts(experiments_invariance())
"""
# Invariance Experiments
#static_flags += ' --dpi=512 --figsize=11,4 --clipwhite'
varydict = ut.odict([
#('acfg_name', ['controlled']),
#('acfg_name', ['controlled', 'controlled2']),
('acfg_name', ACFG_OPTION_CONTROLLED),
('cfg_name', ['candidacy_invariance']),
('dbname', get_dbnames()),
])
return (varydict, 'invar', 'cumhist')
def _debug_repr_cpd(cpd):
import re
import utool as ut
code_fmt = ut.codeblock("""
{variable} = pgmpy.factors.TabularCPD(
variable={variable_repr},
variable_card={variable_card_repr},
values={get_cpd_repr},
evidence={evidence_repr},
evidence_card={evidence_card_repr},
)
""")
keys = ['variable', 'variable_card', 'values', 'evidence', 'evidence_card']
dict_ = ut.odict(zip(keys, [getattr(cpd, key) for key in keys]))
# HACK
dict_['values'] = cpd.get_cpd()
r = ut.repr2(dict_, explicit=True, nobraces=True, nl=True)
logger.info(r)
# Parse props that are needed for this fmtstr
fmt_keys = [
match.groups()[0] for match in re.finditer('{(.*?)}', code_fmt)
]
need_reprs = [key[:-5] for key in fmt_keys if key.endswith('_repr')]
need_keys = [key for key in fmt_keys if not key.endswith('_repr')]
# Get corresponding props
# Call methods if needbe
tmp = [(prop, getattr(cpd, prop)) for prop in need_reprs]
tmp = [(x, y()) if ut.is_funclike(y) else (x, y) for (x, y) in tmp]
fmtdict = dict(tmp)
fmtdict = ut.map_dict_vals(ut.repr2, fmtdict)
fmtdict = ut.map_dict_keys(lambda x: x + '_repr', fmtdict)
tmp2 = [(prop, getattr(cpd, prop)) for prop in need_keys]
fmtdict.update(dict(tmp2))
code = code_fmt.format(**fmtdict)
return code
def build_alias_map(regex_map, tag_vocab):
"""
Constructs explicit mapping. Order of items in regex map matters.
Items at top are given preference.
Example:
>>> tags_list = [['t1', 't2'], [], ['t3'], ['t4', 't5']]
>>> tag_vocab = ut.flat_unique(*tags_list)
>>> regex_map = [('t[3-4]', 'A9'), ('t0', 'a0')]
>>> unmapped = list(set(tag_vocab) - set(alias_map.keys()))
"""
import utool as ut
import re
alias_map = ut.odict([])
for pats, new_tag in reversed(regex_map):
pats = ut.ensure_iterable(pats)
for pat in pats:
flags = [re.match(pat, t) for t in tag_vocab]
for old_tag in ut.compress(tag_vocab, flags):
alias_map[old_tag] = new_tag
identity_map = ut.take_column(regex_map, 1)
for tag in ut.filter_Nones(identity_map):
alias_map[tag] = tag
return alias_map
def graph_info(graph, verbose=False):
import utool as ut
node_attrs = list(graph.node.values())
edge_attrs = list(ut.take_column(graph.edges(data=True), 2))
node_attr_hist = ut.dict_hist(ut.flatten([attr.keys() for attr in node_attrs]))
edge_attr_hist = ut.dict_hist(ut.flatten([attr.keys() for attr in edge_attrs]))
node_type_hist = ut.dict_hist(list(map(type, graph.nodes())))
info_dict = ut.odict([
('directed', graph.is_directed()),
('multi', graph.is_multigraph()),
('num_nodes', len(graph)),
('num_edges', len(list(graph.edges()))),
('edge_attr_hist', ut.sort_dict(edge_attr_hist)),
('node_attr_hist', ut.sort_dict(node_attr_hist)),
('node_type_hist', ut.sort_dict(node_type_hist)),
('graph_attrs', graph.graph),
('graph_name', graph.name),
])
#unique_attrs = ut.map_dict_vals(ut.unique, ut.dict_accum(*node_attrs))
#ut.dict_isect_combine(*node_attrs))
#[list(attrs.keys())]
if verbose:
print(ut.repr3(info_dict))
return info_dict
def isect_info(self, other):
set1 = set(self.rel_fpath_list)
set2 = set(other.rel_fpath_list)
set_comparisons = ut.odict([
('s1', set1),
('s2', set2),
('union', set1.union(set2)),
('isect', set1.intersection(set2)),
('s1 - s2', set1.difference(set2)),
('s2 - s1', set1.difference(set1)),
])
stat_stats = ut.map_vals(len, set_comparisons)
print(ut.repr4(stat_stats))
return set_comparisons
if False:
idx_lookup1 = ut.make_index_lookup(self.rel_fpath_list)
idx_lookup2 = ut.make_index_lookup(other.rel_fpath_list)
uuids1 = ut.take(self.uuids, ut.take(idx_lookup1, set_comparisons['union']))
uuids2 = ut.take(other.uuids, ut.take(idx_lookup2, set_comparisons['union']))
uuids1 == uuids2
def classification_report2(y_true, y_pred, target_names=None,
sample_weight=None, verbose=True):
"""
References:
https://csem.flinders.edu.au/research/techreps/SIE07001.pdf
https://www.mathworks.com/matlabcentral/fileexchange/5648-bm-cm-?requestedDomain=www.mathworks.com
Jurman, Riccadonna, Furlanello, (2012). A Comparison of MCC and CEN
Error Measures in MultiClass Prediction
Example:
>>> from ibeis.algo.verif.sklearn_utils import * # NOQA
>>> y_true = [1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3]
>>> y_pred = [1, 2, 1, 3, 1, 2, 2, 3, 2, 2, 3, 3, 2, 3, 3, 3, 1, 3]
>>> target_names = None
>>> sample_weight = None
>>> verbose = True
>>> report = classification_report2(y_true, y_pred, verbose=verbose)
Ignore:
>>> size = 100
>>> rng = np.random.RandomState(0)
>>> p_classes = np.array([.90, .05, .05][0:2])
>>> p_classes = p_classes / p_classes.sum()
>>> p_wrong = np.array([.03, .01, .02][0:2])
>>> y_true = testdata_ytrue(p_classes, p_wrong, size, rng)
>>> rs = []
>>> for x in range(17):
>>> p_wrong += .05
>>> y_pred = testdata_ypred(y_true, p_wrong, rng)
>>> report = classification_report2(y_true, y_pred, verbose='hack')
>>> rs.append(report)
>>> import plottool as pt
>>> pt.qtensure()
>>> df = pd.DataFrame(rs).drop(['raw'], axis=1)
>>> delta = df.subtract(df['target'], axis=0)
>>> sqrd_error = np.sqrt((delta ** 2).sum(axis=0))
>>> print('Error')
>>> print(sqrd_error.sort_values())
>>> ys = df.to_dict(orient='list')
>>> pt.multi_plot(ydata_list=ys)
"""
import sklearn.metrics
from sklearn.preprocessing import LabelEncoder
if target_names is None:
unique_labels = np.unique(np.hstack([y_true, y_pred]))
if len(unique_labels) == 1 and (unique_labels[0] == 0 or unique_labels[0] == 1):
target_names = np.array([False, True])
y_true_ = y_true
y_pred_ = y_pred
else:
lb = LabelEncoder()
lb.fit(unique_labels)
y_true_ = lb.transform(y_true)
y_pred_ = lb.transform(y_pred)
target_names = lb.classes_
else:
y_true_ = y_true
y_pred_ = y_pred
# Real data is on the rows,
# Pred data is on the cols.
cm = sklearn.metrics.confusion_matrix(
y_true_, y_pred_, sample_weight=sample_weight)
confusion = cm # NOQA
k = len(cm) # number of classes
N = cm.sum() # number of examples
real_total = cm.sum(axis=1)
pred_total = cm.sum(axis=0)
# the number of "positive" cases **per class**
n_pos = real_total # NOQA
# the number of times a class was predicted.
n_neg = N - n_pos # NOQA
# number of true positives per class
n_tps = np.diag(cm)
# number of true negatives per class
n_fps = (cm - np.diagflat(np.diag(cm))).sum(axis=0)
tprs = n_tps / real_total # true pos rate (recall)
tpas = n_tps / pred_total # true pos accuracy (precision)
unused = (real_total + pred_total) == 0
fprs = n_fps / n_neg # false pose rate
fprs[unused] = np.nan
# tnrs = 1 - fprs
rprob = real_total / N
pprob = pred_total / N
if len(cm) == 2:
[[A, B],
[C, D]] = cm
(A * D - B * C) / np.sqrt((A + C) * (B + D) * (A + B) * (C + D))
# c2 = vt.ConfusionMetrics().fit(scores, y)
# bookmaker is analogous to recall, but unbiased by class frequency
rprob_mat = np.tile(rprob, [k, 1]).T - (1 - np.eye(k))
bmcm = cm.T / rprob_mat
bms = np.sum(bmcm.T, axis=0) / N
# markedness is analogous to precision, but unbiased by class frequency
pprob_mat = np.tile(pprob, [k, 1]).T - (1 - np.eye(k))
mkcm = cm / pprob_mat
mks = np.sum(mkcm.T, axis=0) / N
mccs = np.sign(bms) * np.sqrt(np.abs(bms * mks))
perclass_data = ut.odict([
('precision', tpas),
('recall', tprs),
('fpr', fprs),
('markedness', mks),
('bookmaker', bms),
('mcc', mccs),
('support', real_total),
])
tpa = np.nansum(tpas * rprob)
tpr = np.nansum(tprs * rprob)
fpr = np.nansum(fprs * rprob)
mk = np.nansum(mks * rprob)
bm = np.nansum(bms * pprob)
# The simple mean seems to do the best
mccs_ = mccs[~np.isnan(mccs)]
if len(mccs_) == 0:
mcc_combo = np.nan
else:
mcc_combo = np.nanmean(mccs_)
combined_data = ut.odict([
('precision', tpa),
('recall', tpr),
('fpr', fpr),
('markedness', mk),
('bookmaker', bm),
# ('mcc', np.sign(bm) * np.sqrt(np.abs(bm * mk))),
('mcc', mcc_combo),
# np.sign(bm) * np.sqrt(np.abs(bm * mk))),
('support', real_total.sum())
])
# Not sure how to compute this. Should it agree with the sklearn impl?
if verbose == 'hack':
verbose = False
mcc_known = sklearn.metrics.matthews_corrcoef(
y_true, y_pred, sample_weight=sample_weight)
mcc_raw = np.sign(bm) * np.sqrt(np.abs(bm * mk))
import scipy as sp
def gmean(x, w=None):
if w is None:
return sp.stats.gmean(x)
return np.exp(np.nansum(w * np.log(x)) / np.nansum(w))
def hmean(x, w=None):
if w is None:
return sp.stats.hmean(x)
return 1 / (np.nansum(w * (1 / x)) / np.nansum(w))
def amean(x, w=None):
if w is None:
return np.mean(x)
return np.nansum(w * x) / np.nansum(w)
report = {
'target': mcc_known,
'raw': mcc_raw,
}
# print('%r <<<' % (mcc_known,))
means = {
'a': amean,
# 'h': hmean,
'g': gmean,
}
weights = {
'p': pprob,
'r': rprob,
'': None,
}
for mean_key, mean in means.items():
for w_key, w in weights.items():
# Hack of very wrong items
if mean_key == 'g':
if w_key in ['r', 'p', '']:
continue
if mean_key == 'g':
if w_key in ['r']:
continue
m = mean(mccs, w)
r_key = '{} {}'.format(mean_key, w_key)
report[r_key] = m
# print(r_key)
# print(np.abs(m - mcc_known))
# print(ut.repr4(report, precision=8))
return report
# print('mcc_known = %r' % (mcc_known,))
# print('mcc_combo1 = %r' % (mcc_combo1,))
# print('mcc_combo2 = %r' % (mcc_combo2,))
# print('mcc_combo3 = %r' % (mcc_combo3,))
# if target_names is None:
# target_names = list(range(k))
index = pd.Index(target_names, name='class')
perclass_df = pd.DataFrame(perclass_data, index=index)
# combined_df = pd.DataFrame(combined_data, index=['ave/sum'])
combined_df = pd.DataFrame(combined_data, index=['combined'])
metric_df = pd.concat([perclass_df, combined_df])
metric_df.index.name = 'class'
metric_df.columns.name = 'metric'
pred_id = ['%s' % m for m in target_names]
real_id = ['%s' % m for m in target_names]
confusion_df = pd.DataFrame(confusion, columns=pred_id, index=real_id)
confusion_df = confusion_df.append(pd.DataFrame(
[confusion.sum(axis=0)], columns=pred_id, index=['Σp']))
confusion_df['Σr'] = np.hstack([confusion.sum(axis=1), [0]])
confusion_df.index.name = 'real'
confusion_df.columns.name = 'pred'
if np.all(confusion_df - np.floor(confusion_df) < .000001):
confusion_df = confusion_df.astype(np.int)
confusion_df.iloc[(-1, -1)] = N
if np.all(confusion_df - np.floor(confusion_df) < .000001):
confusion_df = confusion_df.astype(np.int)
# np.nan
if verbose:
cfsm_str = confusion_df.to_string(float_format=lambda x: '%.1f' % (x,))
print('Confusion Matrix (real × pred) :')
print(ut.hz_str(' ', cfsm_str))
# ut.cprint('\nExtended Report', 'turquoise')
print('\nEvaluation Metric Report:')
float_precision = 2
float_format = '%.' + str(float_precision) + 'f'
ext_report = metric_df.to_string(float_format=float_format)
print(ut.hz_str(' ', ext_report))
report = {
'metrics': metric_df,
'confusion': confusion_df,
}
# FIXME: What is the difference between sklearn multiclass-MCC
# and BM * MK MCC?
def matthews_corrcoef(y_true, y_pred, sample_weight=None):
from sklearn.metrics.classification import (
_check_targets, LabelEncoder, confusion_matrix)
y_type, y_true, y_pred = _check_targets(y_true, y_pred)
if y_type not in {"binary", "multiclass"}:
raise ValueError("%s is not supported" % y_type)
lb = LabelEncoder()
lb.fit(np.hstack([y_true, y_pred]))
y_true = lb.transform(y_true)
y_pred = lb.transform(y_pred)
C = confusion_matrix(y_true, y_pred, sample_weight=sample_weight)
t_sum = C.sum(axis=1)
p_sum = C.sum(axis=0)
n_correct = np.trace(C)
n_samples = p_sum.sum()
cov_ytyp = n_correct * n_samples - np.dot(t_sum, p_sum)
cov_ypyp = n_samples ** 2 - np.dot(p_sum, p_sum)
cov_ytyt = n_samples ** 2 - np.dot(t_sum, t_sum)
mcc = cov_ytyp / np.sqrt(cov_ytyt * cov_ypyp)
if np.isnan(mcc):
return 0.
else:
return mcc
try:
# mcc = sklearn.metrics.matthews_corrcoef(
# y_true, y_pred, sample_weight=sample_weight)
mcc = matthews_corrcoef(y_true, y_pred, sample_weight=sample_weight)
# These scales are chosen somewhat arbitrarily in the context of a
# computer vision application with relatively reasonable quality data
# https://stats.stackexchange.com/questions/118219/how-to-interpret
mcc_significance_scales = ut.odict([
(1.0, 'perfect'),
(0.9, 'very strong'),
(0.7, 'strong'),
(0.5, 'significant'),
(0.3, 'moderate'),
(0.2, 'weak'),
(0.0, 'negligible'),
])
for k, v in mcc_significance_scales.items():
if np.abs(mcc) >= k:
if verbose:
print('classifier correlation is %s' % (v,))
break
if verbose:
float_precision = 2
print(('MCC\' = %.' + str(float_precision) + 'f') % (mcc,))
report['mcc'] = mcc
except ValueError:
pass
return report
'view_pername': '#primary>0&#primary1>1',
'sample_per_ref_name': 1,
'sample_per_name': 1,
# TODO: need to make this consistent accross both experiment modes
'sample_size': None,
}),
}
viewdiff = vp = viewpoint_compare = {
'qcfg': ut.augdict(
ctrl['qcfg'], ut.odict([
('sample_size', None),
# To be a query you must have at least two primary1 views and at
# least one primary view
('view_pername', '#primary>0&#primary1>0'),
('force_const_size', True),
('view', 'primary1'),
('sample_per_name', 1),
])),
'dcfg': ut.augdict(
ctrl['dcfg'], {
'view': ['primary'],
'force_const_size': True,
'sample_per_ref_name': 1,
'sample_per_name': 1, # None this seems to produce odd results
# where the per_ref is still more then 1
'sample_size': None,
'view_pername': '#primary>0&#primary1>0',
}),
def group_items(self, labels):
""" group as dict """
unique_labels, groups = self.group(labels)
label_to_group = ut.odict(zip(unique_labels, groups))
return label_to_group
#db.modify_table(const.FEATURE_WEIGHT_TABLE, dependson=[const.FEATURE_TABLE, const.PROBCHIP_TABLE])
#db.modify_table(const.RESIDUAL_TABLE, dependson=[const.FEATURE_TABLE, const.VOCAB_TABLE])
#db.modify_table(const.PROBCHIP_TABLE, dependson=[const.CHIP_TABLE])
# ========================
# Valid Versions & Mapping
# ========================
base = const.BASE_DATABASE_VERSION
VALID_VERSIONS = ut.odict([
#version: (Pre-Update Function, Update Function, Post-Update Function)
(base , (None, None, None,)),
('1.0.0', (None, update_1_0_0, None,)),
('1.0.1', (None, update_1_0_1, None,)),
('1.0.2', (None, update_1_0_2, None,)),
('1.0.3', (None, update_1_0_3, None,)),
('1.0.4', (None, update_1_0_4, None,)),
])
LEGACY_UPDATE_FUNCTIONS = [
('1.0.4', _sql_helpers.fix_metadata_consistency),
]
def autogen_dbcache_schema():
"""
autogen_dbcache_schema
Example:
def make_annot_inference_dict(infr, internal=False):
#import uuid
def convert_to_name_uuid(nid):
#try:
text = ibs.get_name_texts(nid, apply_fix=False)
if text is None:
text = 'NEWNAME_%s' % (str(nid),)
#uuid_ = uuid.UUID(text)
#except ValueError:
# text = 'NEWNAME_%s' % (str(nid),)
# #uuid_ = nid
return text
ibs = infr.qreq_.ibs
if internal:
get_annot_uuids = ut.identity
else:
get_annot_uuids = ibs.get_annot_uuids
#return uuid_
# Compile the cluster_dict
col_list = ['aid_list', 'orig_nid_list', 'new_nid_list',
'exemplar_flag_list', 'error_flag_list']
cluster_dict = dict(zip(col_list, ut.listT(infr.cluster_tuples)))
cluster_dict['annot_uuid_list'] = get_annot_uuids(cluster_dict['aid_list'])
# We store the name's UUID as the name's text
#cluster_dict['orig_name_uuid_list'] = [convert_to_name_uuid(nid)
# for nid in cluster_dict['orig_nid_list']]
#cluster_dict['new_name_uuid_list'] = [convert_to_name_uuid(nid)
# for nid in cluster_dict['new_nid_list']]
cluster_dict['orig_name_list'] = [convert_to_name_uuid(nid)
for nid in cluster_dict['orig_nid_list']]
cluster_dict['new_name_list'] = [convert_to_name_uuid(nid)
for nid in cluster_dict['new_nid_list']]
# Filter out only the keys we want to send back in the dictionary
#key_list = ['annot_uuid_list', 'orig_name_uuid_list',
# 'new_name_uuid_list', 'exemplar_flag_list',
# 'error_flag_list']
key_list = ['annot_uuid_list', 'orig_name_list', 'new_name_list',
'exemplar_flag_list', 'error_flag_list']
cluster_dict = ut.dict_subset(cluster_dict, key_list)
# Compile the annot_pair_dict
col_list = ['aid_1_list', 'aid_2_list', 'p_same_list',
'confidence_list', 'raw_score_list']
annot_pair_dict = dict(zip(col_list, ut.listT(infr.needs_review_list)))
annot_pair_dict['annot_uuid_1_list'] = get_annot_uuids(annot_pair_dict['aid_1_list'])
annot_pair_dict['annot_uuid_2_list'] = get_annot_uuids(annot_pair_dict['aid_2_list'])
zipped = zip(annot_pair_dict['annot_uuid_1_list'],
annot_pair_dict['annot_uuid_2_list'],
annot_pair_dict['p_same_list'])
annot_pair_dict['review_pair_list'] = [
{
'annot_uuid_key' : annot_uuid_1,
'annot_uuid_1' : annot_uuid_1,
'annot_uuid_2' : annot_uuid_2,
'prior_matching_state' : {
'p_match' : p_same,
'p_nomatch' : 1.0 - p_same,
'p_notcomp' : 0.0,
}
}
for (annot_uuid_1, annot_uuid_2, p_same) in zipped
]
# Filter out only the keys we want to send back in the dictionary
key_list = ['review_pair_list', 'confidence_list']
annot_pair_dict = ut.dict_subset(annot_pair_dict, key_list)
# Compile the inference dict
inference_dict = ut.odict([
('cluster_dict', cluster_dict),
('annot_pair_dict', annot_pair_dict),
('_internal_state', None),
])
return inference_dict
def get_orgres_desc_match_dists(allres, orgtype_list=['false', 'true'],
distkey_list=['L2'],
verbose=True):
r"""
computes distances between matching descriptors of orgtypes in allres
Args:
allres (AllResults): AllResults object
orgtype_list (list): of strings denoting the type of results to compare
distkey_list (list): list of requested distance types
Returns:
dict: orgres2_descmatch_dists mapping from orgtype to dicts of distances (ndarrays)
Notes:
Just SIFT distance seems to have a very interesting property
CommandLine:
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists --show
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists --db PZ_Master0 --show
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists --db PZ_Master0 --distkeys=fs,lnbnn,bar_L2_sift --show
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists --db PZ_MTEST --distkeys=fs,lnbnn,bar_L2_sift,cos_sift --show
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists --db PZ_Master0 --distkeys=fs,lnbnn,bar_L2_sift,cos_sift --show
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists --db PZ_MTEST --distkeys=cos_sift --show
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists --db PZ_Master0 --distkeys=fs,lnbnn,bar_L2_sift,cos_sift --show --nosupport
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists --db PZ_MTEST --distkeys=lnbnn --show --feat_type=hesaff+siam128
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists --db PZ_MTEST --distkeys=lnbnn --show --feat_type=hesaff+sift
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists --db PZ_MTEST --distkeys=lnbnn --show --feat_type=hesaff+sift --num-top-fs=2
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists --db PZ_MTEST --distkeys=lnbnn --show --feat_type=hesaff+sift --num-top-fs=10
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists --db PZ_MTEST --distkeys=lnbnn --show --feat_type=hesaff+sift --num-top-fs=1000
python -m ibeis.expt.results_analyzer --test-get_orgres_desc_match_dists --db PZ_MTEST --distkeys=lnbnn --show --feat_type=hesaff+siam128 --num-top-fs=1
Example:
>>> # SLOW_DOCTEST
>>> from ibeis.expt.results_analyzer import * # NOQA
>>> from ibeis.expt import results_all
>>> import ibeis
>>> ibs = ibeis.opendb(defaultdb='PZ_MTEST')
>>> qaid_list = ibs.get_valid_aids(hasgt=True)
>>> from ibeis.model import Config
>>> cfgdict = ut.argparse_dict(dict(Config.parse_config_items(Config.QueryConfig())), only_specified=True)
>>> allres = results_all.get_allres(ibs, qaid_list, cfgdict=cfgdict)
>>> # {'feat_type': 'hesaff+siam128'})
>>> orgtype_list = ['false', 'top_true']
>>> verbose = True
>>> distkey_list = ut.get_argval('--distkeys', type_=list, default=['fs', 'lnbnn', 'bar_L2_sift'])
>>> #distkey_list = ['hist_isect']
>>> #distkey_list = ['L2_sift', 'bar_L2_sift']
>>> # execute function
>>> orgres2_descmatch_dists = get_orgres_desc_match_dists(allres, orgtype_list, distkey_list, verbose)
>>> #print('orgres2_descmatch_dists = ' + ut.dict_str(orgres2_descmatch_dists, truncate=-1, precision=3))
>>> stats_ = {key: ut.dict_val_map(val, ut.get_stats) for key, val in orgres2_descmatch_dists.items()}
>>> print('orgres2_descmatch_dists = ' + ut.dict_str(stats_, truncate=2, precision=3, nl=4))
>>> # ------ VISUALIZE ------------
>>> ut.quit_if_noshow()
>>> import vtool as vt
>>> # If viewing a large amount of data this might help on OverFlowError
>>> #ut.embed()
>>> # http://stackoverflow.com/questions/20330475/matplotlib-overflowerror-allocated-too-many-blocks
>>> # http://matplotlib.org/1.3.1/users/customizing.html
>>> limit_ = len(qaid_list) > 100
>>> if limit_ or True:
>>> import matplotlib as mpl
>>> mpl.rcParams['agg.path.chunksize'] = 100000
>>> # visualize the descriptor scores
>>> for fnum, distkey in enumerate(distkey_list, start=1):
>>> encoder = vt.ScoreNormalizer()
>>> tn_scores, tp_scores = ut.get_list_column(ut.dict_take(orgres2_descmatch_dists, orgtype_list), distkey)
>>> encoder.fit_partitioned(tp_scores, tn_scores, verbose=False)
>>> figtitle = 'Descriptor Distance: %r. db=%r\norgtype_list=%r' % (distkey, ibs.get_dbname(), orgtype_list)
>>> use_support = not ut.get_argflag('--nosupport')
>>> encoder.visualize(figtitle=figtitle, use_stems=not limit_, fnum=fnum, with_normscore=use_support, with_scores=use_support)
>>> ut.show_if_requested()
"""
import vtool as vt
orgres2_descmatch_dists = {}
desc_dist_xs, other_xs = vt.index_partition(distkey_list, vt.VALID_DISTS)
distkey_list1 = ut.list_take(distkey_list, desc_dist_xs)
distkey_list2 = ut.list_take(distkey_list, other_xs)
for orgtype in orgtype_list:
if verbose:
print('[rr2] getting orgtype=%r distances between vecs' % orgtype)
orgres = allres.get_orgtype(orgtype)
qaids = orgres.qaids
aids = orgres.aids
# DO distance that need real computation
if len(desc_dist_xs) > 0:
try:
stacked_qvecs, stacked_dvecs = get_matching_descriptors(allres, qaids, aids)
except Exception as ex:
orgres.printme3()
ut.printex(ex)
raise
if verbose:
print('[rr2] * stacked_qvecs.shape = %r' % (stacked_qvecs.shape,))
print('[rr2] * stacked_dvecs.shape = %r' % (stacked_dvecs.shape,))
#distkey_list = ['L1', 'L2', 'hist_isect', 'emd']
#distkey_list = ['L1', 'L2', 'hist_isect']
#distkey_list = ['L2', 'hist_isect']
hist1 = np.asarray(stacked_qvecs, dtype=np.float32)
hist2 = np.asarray(stacked_dvecs, dtype=np.float32)
# returns an ordered dictionary
distances1 = vt.compute_distances(hist1, hist2, distkey_list1)
else:
distances1 = {}
# DO precomputed distances like fs (true weights) or lnbnn
if len(other_xs) > 0:
distances2 = ut.odict([(disttype, []) for disttype in distkey_list2])
for qaid, daid in zip(qaids, aids):
try:
qres = allres.qaid2_qres[qaid]
for disttype in distkey_list2:
if disttype == 'fs':
# hack in full fs
assert disttype == 'fs', 'unimplemented'
vals = qres.aid2_fs[daid]
else:
assert disttype in qres.filtkey_list, 'no score labeled %' % (disttype,)
index = qres.filtkey_list.index(disttype)
vals = qres.aid2_fsv[daid].T[index]
if len(vals) == 0:
continue
else:
# individual score component
pass
#num_top_vec_scores = None
num_top_vec_scores = ut.get_argval('--num-top-fs', type_=int, default=None)
if num_top_vec_scores is not None:
# Take only the best matching descriptor scores for each pair in this analysis
# This tries to see how deperable the BEST descriptor score is for each match
vals = vals[vals.argsort()[::-1][0:num_top_vec_scores]]
vals = vals[vals.argsort()[::-1][0:num_top_vec_scores]]
distances2[disttype].extend(vals)
except KeyError:
continue
# convert to numpy array
for disttype in distkey_list2:
distances2[disttype] = np.array(distances2[disttype])
else:
distances2 = {}
# Put things back in expected order
dist1_vals = ut.dict_take(distances1, distkey_list1)
dist2_vals = ut.dict_take(distances2, distkey_list2)
dist_vals = vt.rebuild_partition(dist1_vals, dist2_vals, desc_dist_xs, other_xs)
distances = ut.odict(list(zip(distkey_list, dist_vals)))
orgres2_descmatch_dists[orgtype] = distances
return orgres2_descmatch_dists
def _asdict(cm):
return ut.odict(
[(field, None if getattr(cm, field) is None else getattr(cm, field).copy())
for field in cm._oldfields])