def stack_graphs(graph_list, vert=False, pad=None):
graph_list_ = [g.copy() for g in graph_list]
for g in graph_list_:
translate_graph_to_origin(g)
bbox_list = [ut.get_graph_bounding_box(g) for g in graph_list_]
if vert:
dim1 = 3
dim2 = 2
else:
dim1 = 2
dim2 = 3
dim1_list = np.array([bbox[dim1] for bbox in bbox_list])
dim2_list = np.array([bbox[dim2] for bbox in bbox_list])
if pad is None:
pad = np.mean(dim1_list) / 2
offset1_list = ut.cumsum([0] + [d + pad for d in dim1_list[:-1]])
max_dim2 = max(dim2_list)
offset2_list = [(max_dim2 - d2) / 2 for d2 in dim2_list]
if vert:
t_xy_list = [(d2, d1) for d1, d2 in zip(offset1_list, offset2_list)]
else:
t_xy_list = [(d1, d2) for d1, d2 in zip(offset1_list, offset2_list)]
for g, t_xy in zip(graph_list_, t_xy_list):
ut.translate_graph(g, t_xy)
nx.set_node_attributes(g, name='pin', values='true')
new_graph = nx.compose_all(graph_list_)
#pt.show_nx(new_graph, layout='custom', node_labels=False, as_directed=False) # NOQA
return new_graph
def accumulate_input_ids(edge_list):
"""
python -m dtool.example_depcache2 testdata_depc4 --show
"""
edge_data = ut.take_column(edge_list, 3)
# We are accumulating local input ids
toaccum_list_ = ut.dict_take_column(edge_data, 'local_input_id')
if BIG_HACK and True:
v_list = ut.take_column(edge_list, 1)
# show the local_input_ids at the entire level
pred_ids = ([[
x['local_input_id']
for x in list(graph.pred[node].values())[0].values()
] if len(graph.pred[node]) else [] for node in v_list])
toaccum_list = [
x + ':' + ';'.join(y) for x, y in zip(toaccum_list_, pred_ids)
]
else:
toaccum_list = toaccum_list_
# Default dumb accumulation
accum_ids_ = ut.cumsum(zip(toaccum_list), tuple())
accum_ids = ut.lmap(condense_accum_ids, accum_ids_)
if BIG_HACK:
accum_ids = ut.lmap(condense_accum_ids_stars, accum_ids)
accum_ids = [('t', ) + x for x in accum_ids]
ut.dict_set_column(edge_data, 'accum_id', accum_ids)
return accum_ids
def update(self, iterable):
_lists = self._lists
values = list(iterable)
_load = self._load
_lists.extend(values[pos:(pos + _load)]
for pos in range(0, len(values), _load))
self._cumlen = ut.cumsum(map(len, _lists))
self._len = len(values)
def run_asmk_script():
with ut.embed_on_exception_context: # NOQA
"""
>>> from wbia.algo.smk.script_smk import *
"""
# NOQA
# ==============================================
# PREPROCESSING CONFIGURATION
# ==============================================
config = {
# 'data_year': 2013,
'data_year': None,
'dtype': 'float32',
# 'root_sift': True,
'root_sift': False,
# 'centering': True,
'centering': False,
'num_words': 2**16,
# 'num_words': 1E6
# 'num_words': 8000,
'kmeans_impl': 'sklearn.mini',
'extern_words': False,
'extern_assign': False,
'assign_algo': 'kdtree',
'checks': 1024,
'int_rvec': True,
'only_xy': False,
}
# Define which params are relevant for which operations
relevance = {}
relevance['feats'] = ['dtype', 'root_sift', 'centering', 'data_year']
relevance['words'] = relevance['feats'] + [
'num_words',
'extern_words',
'kmeans_impl',
]
relevance['assign'] = relevance['words'] + [
'checks',
'extern_assign',
'assign_algo',
]
# relevance['ydata'] = relevance['assign'] + ['int_rvec']
# relevance['xdata'] = relevance['assign'] + ['only_xy', 'int_rvec']
nAssign = 1
class SMKCacher(ut.Cacher):
def __init__(self, fname, ext='.cPkl'):
relevant_params = relevance[fname]
relevant_cfg = ut.dict_subset(config, relevant_params)
cfgstr = ut.get_cfg_lbl(relevant_cfg)
dbdir = ut.truepath('/raid/work/Oxford/')
super(SMKCacher, self).__init__(fname,
cfgstr,
cache_dir=dbdir,
ext=ext)
# ==============================================
# LOAD DATASET, EXTRACT AND POSTPROCESS FEATURES
# ==============================================
if config['data_year'] == 2007:
data = load_oxford_2007()
elif config['data_year'] == 2013:
data = load_oxford_2013()
elif config['data_year'] is None:
data = load_oxford_wbia()
offset_list = data['offset_list']
all_kpts = data['all_kpts']
raw_vecs = data['all_vecs']
query_uri_order = data['query_uri_order']
data_uri_order = data['data_uri_order']
# del data
# ================
# PRE-PROCESS
# ================
import vtool as vt
# Alias names to avoid errors in interactive sessions
proc_vecs = raw_vecs
del raw_vecs
feats_cacher = SMKCacher('feats', ext='.npy')
all_vecs = feats_cacher.tryload()
if all_vecs is None:
if config['dtype'] == 'float32':
logger.info('Converting vecs to float32')
proc_vecs = proc_vecs.astype(np.float32)
else:
proc_vecs = proc_vecs
raise NotImplementedError('other dtype')
if config['root_sift']:
with ut.Timer('Apply root sift'):
np.sqrt(proc_vecs, out=proc_vecs)
vt.normalize(proc_vecs, ord=2, axis=1, out=proc_vecs)
if config['centering']:
with ut.Timer('Apply centering'):
mean_vec = np.mean(proc_vecs, axis=0)
# Center and then re-normalize
np.subtract(proc_vecs, mean_vec[None, :], out=proc_vecs)
vt.normalize(proc_vecs, ord=2, axis=1, out=proc_vecs)
if config['dtype'] == 'int8':
smk_funcs
all_vecs = proc_vecs
feats_cacher.save(all_vecs)
del proc_vecs
# =====================================
# BUILD VISUAL VOCABULARY
# =====================================
if config['extern_words']:
words = data['words']
assert config['num_words'] is None or len(
words) == config['num_words']
else:
word_cacher = SMKCacher('words')
words = word_cacher.tryload()
if words is None:
with ut.embed_on_exception_context:
if config['kmeans_impl'] == 'sklearn.mini':
import sklearn.cluster
rng = np.random.RandomState(13421421)
# init_size = int(config['num_words'] * 8)
init_size = int(config['num_words'] * 4)
# converged after 26043 iterations
clusterer = sklearn.cluster.MiniBatchKMeans(
config['num_words'],
init_size=init_size,
batch_size=1000,
compute_labels=False,
max_iter=20,
random_state=rng,
n_init=1,
verbose=1,
)
clusterer.fit(all_vecs)
words = clusterer.cluster_centers_
elif config['kmeans_impl'] == 'yael':
from yael import ynumpy
centroids, qerr, dis, assign, nassign = ynumpy.kmeans(
all_vecs,
config['num_words'],
init='kmeans++',
verbose=True,
output='all',
)
words = centroids
word_cacher.save(words)
# =====================================
# ASSIGN EACH VECTOR TO ITS NEAREST WORD
# =====================================
if config['extern_assign']:
assert config[
'extern_words'], 'need extern cluster to extern assign'
idx_to_wxs = vt.atleast_nd(data['idx_to_wx'], 2)
idx_to_maws = np.ones(idx_to_wxs.shape, dtype=np.float32)
idx_to_wxs = np.ma.array(idx_to_wxs)
idx_to_maws = np.ma.array(idx_to_maws)
else:
from wbia.algo.smk import vocab_indexer
vocab = vocab_indexer.VisualVocab(words)
dassign_cacher = SMKCacher('assign')
assign_tup = dassign_cacher.tryload()
if assign_tup is None:
vocab.flann_params['algorithm'] = config['assign_algo']
vocab.build()
# Takes 12 minutes to assign jegous vecs to 2**16 vocab
with ut.Timer('assign vocab neighbors'):
_idx_to_wx, _idx_to_wdist = vocab.nn_index(
all_vecs, nAssign, checks=config['checks'])
if nAssign > 1:
idx_to_wxs, idx_to_maws = smk_funcs.weight_multi_assigns(
_idx_to_wx,
_idx_to_wdist,
massign_alpha=1.2,
massign_sigma=80.0,
massign_equal_weights=True,
)
else:
idx_to_wxs = np.ma.masked_array(_idx_to_wx,
fill_value=-1)
idx_to_maws = np.ma.ones(idx_to_wxs.shape,
fill_value=-1,
dtype=np.float32)
idx_to_maws.mask = idx_to_wxs.mask
assign_tup = (idx_to_wxs, idx_to_maws)
dassign_cacher.save(assign_tup)
idx_to_wxs, idx_to_maws = assign_tup
# Breakup vectors, keypoints, and word assignments by annotation
wx_lists = [
idx_to_wxs[left:right] for left, right in ut.itertwo(offset_list)
]
maw_lists = [
idx_to_maws[left:right] for left, right in ut.itertwo(offset_list)
]
vecs_list = [
all_vecs[left:right] for left, right in ut.itertwo(offset_list)
]
kpts_list = [
all_kpts[left:right] for left, right in ut.itertwo(offset_list)
]
# =======================
# FIND QUERY SUBREGIONS
# =======================
ibs, query_annots, data_annots, qx_to_dx = load_ordered_annots(
data_uri_order, query_uri_order)
daids = data_annots.aids
qaids = query_annots.aids
query_super_kpts = ut.take(kpts_list, qx_to_dx)
query_super_vecs = ut.take(vecs_list, qx_to_dx)
query_super_wxs = ut.take(wx_lists, qx_to_dx)
query_super_maws = ut.take(maw_lists, qx_to_dx)
# Mark which keypoints are within the bbox of the query
query_flags_list = []
only_xy = config['only_xy']
for kpts_, bbox in zip(query_super_kpts, query_annots.bboxes):
flags = kpts_inside_bbox(kpts_, bbox, only_xy=only_xy)
query_flags_list.append(flags)
logger.info('Queries are crops of existing database images.')
logger.info('Looking at average percents')
percent_list = [
flags_.sum() / flags_.shape[0] for flags_ in query_flags_list
]
percent_stats = ut.get_stats(percent_list)
logger.info('percent_stats = %s' % (ut.repr4(percent_stats), ))
import vtool as vt
query_kpts = vt.zipcompress(query_super_kpts, query_flags_list, axis=0)
query_vecs = vt.zipcompress(query_super_vecs, query_flags_list, axis=0)
query_wxs = vt.zipcompress(query_super_wxs, query_flags_list, axis=0)
query_maws = vt.zipcompress(query_super_maws, query_flags_list, axis=0)
# =======================
# CONSTRUCT QUERY / DATABASE REPR
# =======================
# int_rvec = not config['dtype'].startswith('float')
int_rvec = config['int_rvec']
X_list = []
_prog = ut.ProgPartial(length=len(qaids),
label='new X',
bs=True,
adjust=True)
for aid, fx_to_wxs, fx_to_maws in _prog(
zip(qaids, query_wxs, query_maws)):
X = new_external_annot(aid, fx_to_wxs, fx_to_maws, int_rvec)
X_list.append(X)
# ydata_cacher = SMKCacher('ydata')
# Y_list = ydata_cacher.tryload()
# if Y_list is None:
Y_list = []
_prog = ut.ProgPartial(length=len(daids),
label='new Y',
bs=True,
adjust=True)
for aid, fx_to_wxs, fx_to_maws in _prog(zip(daids, wx_lists,
maw_lists)):
Y = new_external_annot(aid, fx_to_wxs, fx_to_maws, int_rvec)
Y_list.append(Y)
# ydata_cacher.save(Y_list)
# ======================
# Add in some groundtruth
logger.info('Add in some groundtruth')
for Y, nid in zip(Y_list, ibs.get_annot_nids(daids)):
Y.nid = nid
for X, nid in zip(X_list, ibs.get_annot_nids(qaids)):
X.nid = nid
for Y, qual in zip(Y_list, ibs.get_annot_quality_texts(daids)):
Y.qual = qual
# ======================
# Add in other properties
for Y, vecs, kpts in zip(Y_list, vecs_list, kpts_list):
Y.vecs = vecs
Y.kpts = kpts
imgdir = ut.truepath('/raid/work/Oxford/oxbuild_images')
for Y, imgid in zip(Y_list, data_uri_order):
gpath = ut.unixjoin(imgdir, imgid + '.jpg')
Y.gpath = gpath
for X, vecs, kpts in zip(X_list, query_vecs, query_kpts):
X.kpts = kpts
X.vecs = vecs
# ======================
logger.info('Building inverted list')
daids = [Y.aid for Y in Y_list]
# wx_list = sorted(ut.list_union(*[Y.wx_list for Y in Y_list]))
wx_list = sorted(set.union(*[Y.wx_set for Y in Y_list]))
assert daids == data_annots.aids
assert len(wx_list) <= config['num_words']
wx_to_aids = smk_funcs.invert_lists(daids, [Y.wx_list for Y in Y_list],
all_wxs=wx_list)
# Compute IDF weights
logger.info('Compute IDF weights')
ndocs_total = len(daids)
# Use only the unique number of words
ndocs_per_word = np.array([len(set(wx_to_aids[wx])) for wx in wx_list])
logger.info('ndocs_perword stats: ' +
ut.repr4(ut.get_stats(ndocs_per_word)))
idf_per_word = smk_funcs.inv_doc_freq(ndocs_total, ndocs_per_word)
wx_to_weight = dict(zip(wx_list, idf_per_word))
logger.info('idf stats: ' +
ut.repr4(ut.get_stats(wx_to_weight.values())))
# Filter junk
Y_list_ = [Y for Y in Y_list if Y.qual != 'junk']
# =======================
# CHOOSE QUERY KERNEL
# =======================
params = {
'asmk': dict(alpha=3.0, thresh=0.0),
'bow': dict(),
'bow2': dict(),
}
# method = 'bow'
method = 'bow2'
method = 'asmk'
smk = SMK(wx_to_weight, method=method, **params[method])
# Specific info for the type of query
if method == 'asmk':
# Make residual vectors
if True:
# The stacked way is 50x faster
# TODO: extend for multi-assignment and record fxs
flat_query_vecs = np.vstack(query_vecs)
flat_query_wxs = np.vstack(query_wxs)
flat_query_offsets = np.array(
[0] + ut.cumsum(ut.lmap(len, query_wxs)))
flat_wxs_assign = flat_query_wxs
flat_offsets = flat_query_offsets
flat_vecs = flat_query_vecs
tup = smk_funcs.compute_stacked_agg_rvecs(
words, flat_wxs_assign, flat_vecs, flat_offsets)
all_agg_vecs, all_error_flags, agg_offset_list = tup
if int_rvec:
all_agg_vecs = smk_funcs.cast_residual_integer(
all_agg_vecs)
agg_rvecs_list = [
all_agg_vecs[left:right]
for left, right in ut.itertwo(agg_offset_list)
]
agg_flags_list = [
all_error_flags[left:right]
for left, right in ut.itertwo(agg_offset_list)
]
for X, agg_rvecs, agg_flags in zip(X_list, agg_rvecs_list,
agg_flags_list):
X.agg_rvecs = agg_rvecs
X.agg_flags = agg_flags[:, None]
flat_wxs_assign = idx_to_wxs
flat_offsets = offset_list
flat_vecs = all_vecs
tup = smk_funcs.compute_stacked_agg_rvecs(
words, flat_wxs_assign, flat_vecs, flat_offsets)
all_agg_vecs, all_error_flags, agg_offset_list = tup
if int_rvec:
all_agg_vecs = smk_funcs.cast_residual_integer(
all_agg_vecs)
agg_rvecs_list = [
all_agg_vecs[left:right]
for left, right in ut.itertwo(agg_offset_list)
]
agg_flags_list = [
all_error_flags[left:right]
for left, right in ut.itertwo(agg_offset_list)
]
for Y, agg_rvecs, agg_flags in zip(Y_list, agg_rvecs_list,
agg_flags_list):
Y.agg_rvecs = agg_rvecs
Y.agg_flags = agg_flags[:, None]
else:
# This non-stacked way is about 500x slower
_prog = ut.ProgPartial(label='agg Y rvecs',
bs=True,
adjust=True)
for Y in _prog(Y_list_):
make_agg_vecs(Y, words, Y.vecs)
_prog = ut.ProgPartial(label='agg X rvecs',
bs=True,
adjust=True)
for X in _prog(X_list):
make_agg_vecs(X, words, X.vecs)
elif method == 'bow2':
# Hack for orig tf-idf bow vector
nwords = len(words)
for X in ut.ProgIter(X_list, label='make bow vector'):
ensure_tf(X)
bow_vector(X, wx_to_weight, nwords)
for Y in ut.ProgIter(Y_list_, label='make bow vector'):
ensure_tf(Y)
bow_vector(Y, wx_to_weight, nwords)
if method != 'bow2':
for X in ut.ProgIter(X_list, 'compute X gamma'):
X.gamma = smk.gamma(X)
for Y in ut.ProgIter(Y_list_, 'compute Y gamma'):
Y.gamma = smk.gamma(Y)
# Execute matches (could go faster by enumerating candidates)
scores_list = []
for X in ut.ProgIter(X_list, label='query %s' % (smk, )):
scores = [smk.kernel(X, Y) for Y in Y_list_]
scores = np.array(scores)
scores = np.nan_to_num(scores)
scores_list.append(scores)
import sklearn.metrics
avep_list = []
_iter = list(zip(scores_list, X_list))
_iter = ut.ProgIter(_iter, label='evaluate %s' % (smk, ))
for scores, X in _iter:
truth = [X.nid == Y.nid for Y in Y_list_]
avep = sklearn.metrics.average_precision_score(truth, scores)
avep_list.append(avep)
avep_list = np.array(avep_list)
mAP = np.mean(avep_list)
logger.info('mAP = %r' % (mAP, ))
def load_oxford_2007():
"""
Loads data from
http://www.robots.ox.ac.uk:5000/~vgg/publications/2007/Philbin07/philbin07.pdf
>>> from wbia.algo.smk.script_smk import * # NOQA
"""
from os.path import join, basename, splitext
import pandas as pd
import vtool as vt
dbdir = ut.truepath('/raid/work/Oxford/')
data_fpath0 = join(dbdir, 'data_2007.pkl')
if ut.checkpath(data_fpath0):
data = ut.load_data(data_fpath0)
return data
else:
word_dpath = join(dbdir, 'word_oxc1_hesaff_sift_16M_1M')
_word_fpath_list = ut.ls(word_dpath)
imgid_to_word_fpath = {
splitext(basename(word_fpath))[0]: word_fpath
for word_fpath in _word_fpath_list
}
readme_fpath = join(dbdir, 'README2.txt')
imgid_order = ut.readfrom(readme_fpath).split('\n')[20:-1]
imgid_order = imgid_order
data_uri_order = [x.replace('oxc1_', '') for x in imgid_order]
imgid_to_df = {}
for imgid in ut.ProgIter(imgid_order, label='reading kpts'):
word_fpath = imgid_to_word_fpath[imgid]
row_gen = (map(float,
line.strip('\n').split(' '))
for line in ut.read_lines_from(word_fpath)[2:])
rows = [(int(word_id), x, y, e11, e12, e22)
for (word_id, x, y, e11, e12, e22) in row_gen]
df = pd.DataFrame(
rows, columns=['word_id', 'x', 'y', 'e11', 'e12', 'e22'])
imgid_to_df[imgid] = df
df_list = ut.take(imgid_to_df, imgid_order)
nfeat_list = [len(df_) for df_ in df_list]
offset_list = [0] + ut.cumsum(nfeat_list)
shape = (offset_list[-1], 128)
# shape = (16334970, 128)
sift_fpath = join(dbdir, 'OxfordSIFTDescriptors',
'feat_oxc1_hesaff_sift.bin')
try:
file_ = open(sift_fpath, 'rb')
with ut.Timer('Reading SIFT binary file'):
nbytes = np.prod(shape)
all_vecs = np.fromstring(file_.read(nbytes), dtype=np.uint8)
all_vecs = all_vecs.reshape(shape)
finally:
file_.close()
kpts_list = [
df_.loc[:, ('x', 'y', 'e11', 'e12', 'e22')].values
for df_ in df_list
]
wordid_list = [df_.loc[:, 'word_id'].values for df_ in df_list]
kpts_Z = np.vstack(kpts_list)
idx_to_wx = np.hstack(wordid_list)
# assert len(np.unique(idx_to_wx)) == 1E6
# Reqd standard query order
query_files = sorted(
ut.glob(dbdir + '/oxford_groundtruth', '*_query.txt'))
query_uri_order = []
for qpath in query_files:
text = ut.readfrom(qpath, verbose=0)
query_uri = text.split(' ')[0].replace('oxc1_', '')
query_uri_order.append(query_uri)
logger.info('converting to invV')
all_kpts = vt.convert_kptsZ_to_kpts(kpts_Z)
data = {
'offset_list': offset_list,
'all_kpts': all_kpts,
'all_vecs': all_vecs,
'idx_to_wx': idx_to_wx,
'data_uri_order': data_uri_order,
'query_uri_order': query_uri_order,
}
ut.save_data(data_fpath0, data)
return data
def compute_stacked_agg_rvecs(words, flat_wxs_assign, flat_vecs, flat_offsets):
"""
More efficient version of agg on a stacked structure
Args:
words (ndarray): entire vocabulary of words
flat_wxs_assign (ndarray): maps a stacked index to word index
flat_vecs (ndarray): stacked SIFT descriptors
flat_offsets (ndarray): offset positions per annotation
Example:
>>> # DISABLE_DOCTEST
>>> from wbia.algo.smk.smk_funcs import * # NOQA
>>> data = testdata_rvecs(dim=2, nvecs=1000, nannots=10)
>>> words = data['words']
>>> flat_offsets = data['offset_list']
>>> flat_wxs_assign, flat_vecs = ut.take(data, ['idx_to_wx', 'vecs'])
>>> tup = compute_stacked_agg_rvecs(words, flat_wxs_assign, flat_vecs, flat_offsets)
>>> all_agg_vecs, all_error_flags, agg_offset_list = tup
>>> agg_rvecs_list = [all_agg_vecs[l:r] for l, r in ut.itertwo(agg_offset_list)]
>>> agg_flags_list = [all_error_flags[l:r] for l, r in ut.itertwo(agg_offset_list)]
>>> assert len(agg_flags_list) == len(flat_offsets) - 1
Example:
>>> # DISABLE_DOCTEST
>>> from wbia.algo.smk.smk_funcs import * # NOQA
>>> data = testdata_rvecs(dim=2, nvecs=100, nannots=5)
>>> words = data['words']
>>> flat_offsets = data['offset_list']
>>> flat_wxs_assign, flat_vecs = ut.take(data, ['idx_to_wx', 'vecs'])
>>> tup = compute_stacked_agg_rvecs(words, flat_wxs_assign, flat_vecs, flat_offsets)
>>> all_agg_vecs, all_error_flags, agg_offset_list = tup
>>> agg_rvecs_list = [all_agg_vecs[l:r] for l, r in ut.itertwo(agg_offset_list)]
>>> agg_flags_list = [all_error_flags[l:r] for l, r in ut.itertwo(agg_offset_list)]
>>> assert len(agg_flags_list) == len(flat_offsets) - 1
"""
grouped_wxs = [
flat_wxs_assign[left:right] for left, right in ut.itertwo(flat_offsets)
]
# Assume single assignment, aggregate everything
# across the entire database
flat_offsets = np.array(flat_offsets)
idx_to_dx = (np.searchsorted(
flat_offsets, np.arange(len(flat_wxs_assign)), side='right') -
1).astype(np.int32)
if isinstance(flat_wxs_assign, np.ma.masked_array):
wx_list = flat_wxs_assign.T[0].compressed()
else:
wx_list = flat_wxs_assign.T[0].ravel()
unique_wx, groupxs = vt.group_indices(wx_list)
dim = flat_vecs.shape[1]
if isinstance(flat_wxs_assign, np.ma.masked_array):
dx_to_wxs = [np.unique(wxs.compressed()) for wxs in grouped_wxs]
else:
dx_to_wxs = [np.unique(wxs.ravel()) for wxs in grouped_wxs]
dx_to_nagg = [len(wxs) for wxs in dx_to_wxs]
num_agg_vecs = sum(dx_to_nagg)
# all_agg_wxs = np.hstack(dx_to_wxs)
agg_offset_list = np.array([0] + ut.cumsum(dx_to_nagg))
# Preallocate agg residuals for all dxs
all_agg_vecs = np.empty((num_agg_vecs, dim), dtype=np.float32)
all_agg_vecs[:, :] = np.nan
# precompute agg residual stack
i_to_dxs = vt.apply_grouping(idx_to_dx, groupxs)
subgroup = [vt.group_indices(dxs) for dxs in ut.ProgIter(i_to_dxs)]
i_to_unique_dxs = ut.take_column(subgroup, 0)
i_to_dx_groupxs = ut.take_column(subgroup, 1)
num_words = len(unique_wx)
# Overall this takes 5 minutes and 21 seconds
# I think the other method takes about 12 minutes
for i in ut.ProgIter(range(num_words), 'agg'):
wx = unique_wx[i]
xs = groupxs[i]
dxs = i_to_unique_dxs[i]
dx_groupxs = i_to_dx_groupxs[i]
word = words[wx:wx + 1]
offsets1 = agg_offset_list.take(dxs)
offsets2 = [np.where(dx_to_wxs[dx] == wx)[0][0] for dx in dxs]
offsets = np.add(offsets1, offsets2, out=offsets1)
# if __debug__:
# assert np.bincount(dxs).max() < 2
# offset = agg_offset_list[dxs[0]]
# assert np.all(dx_to_wxs[dxs[0]] == all_agg_wxs[offset:offset +
# dx_to_nagg[dxs[0]]])
# Compute residuals
rvecs = flat_vecs[xs] - word
vt.normalize(rvecs, axis=1, out=rvecs)
rvecs[np.all(np.isnan(rvecs), axis=1)] = 0
# Aggregate across same images
grouped_rvecs = vt.apply_grouping(rvecs, dx_groupxs, axis=0)
agg_rvecs_ = [rvec_group.sum(axis=0) for rvec_group in grouped_rvecs]
# agg_rvecs = np.vstack(agg_rvecs_)
all_agg_vecs[offsets, :] = agg_rvecs_
assert not np.any(np.isnan(all_agg_vecs))
logger.info('Apply normalization')
vt.normalize(all_agg_vecs, axis=1, out=all_agg_vecs)
all_error_flags = np.all(np.isnan(all_agg_vecs), axis=1)
all_agg_vecs[all_error_flags, :] = 0
# ndocs_per_word1 = np.array(ut.lmap(len, wx_to_unique_dxs))
# ndocs_total1 = len(flat_offsets) - 1
# idf1 = smk_funcs.inv_doc_freq(ndocs_total1, ndocs_per_word1)
tup = all_agg_vecs, all_error_flags, agg_offset_list
return tup
def make_score_tabular(
row_lbls, col_lbls, values, title=None, out_of=None, bold_best=False,
flip=False, bigger_is_better=True, multicol_lbls=None, FORCE_INT=False,
precision=None, SHORTEN_ROW_LBLS=False, col_align='l', col_sep='|',
multicol_sep='|', centerline=True, astable=False, table_position='',
AUTOFIX_LATEX=True, **kwargs):
r"""
makes a LaTeX tabular for displaying scores or errors
Args:
row_lbls (list of str):
col_lbls (list of str):
values (ndarray):
title (str): (default = None)
out_of (None): (default = None)
bold_best (bool): (default = True)
flip (bool): (default = False)
table_position (str) : eg '[h]'
Returns:
str: tabular_str
CommandLine:
python -m utool.util_latex --test-make_score_tabular:0 --show
python -m utool.util_latex --test-make_score_tabular:1 --show
python -m utool.util_latex --test-make_score_tabular:2 --show
Example:
>>> # DISABLE_DOCTEST
>>> from utool.util_latex import * # NOQA
>>> import utool as ut
>>> row_lbls = ['config1', 'config2']
>>> col_lbls = ['score \leq 1', 'metric2']
>>> values = np.array([[1.2, 2], [3.2, 4]])
>>> title = 'title'
>>> out_of = 10
>>> bold_best = True
>>> flip = False
>>> tabular_str = make_score_tabular(row_lbls, col_lbls, values, title, out_of, bold_best, flip)
>>> result = tabular_str
>>> print(result)
>>> ut.quit_if_noshow()
>>> render_latex_text(tabular_str)
Example:
>>> # DISABLE_DOCTEST
>>> from utool.util_latex import * # NOQA
>>> import utool as ut
>>> row_lbls = ['config1']
>>> col_lbls = ['score \leq 1', 'metric2']
>>> values = np.array([[1.2, 2]])
>>> title = 'title'
>>> out_of = 10
>>> bold_best = True
>>> flip = False
>>> tabular_str = make_score_tabular(row_lbls, col_lbls, values, title, out_of, bold_best, flip)
>>> result = tabular_str
>>> print(result)
>>> ut.quit_if_noshow()
>>> render_latex_text(tabular_str)
Example:
>>> # DISABLE_DOCTEST
>>> from utool.util_latex import * # NOQA
>>> import utool as ut
>>> row_lbls = ['config1', 'config2']
>>> col_lbls = ['score \leq 1', 'metric2', 'foobar']
>>> multicol_lbls = [('spam', 1), ('eggs', 2)]
>>> values = np.array([[1.2, 2, -3], [3.2, 4, -2]])
>>> title = 'title'
>>> out_of = 10
>>> bold_best = True
>>> flip = False
>>> tabular_str = make_score_tabular(row_lbls, col_lbls, values, title, out_of, bold_best, flip, multicol_lbls=multicol_lbls)
>>> result = tabular_str
>>> print(result)
>>> ut.quit_if_noshow()
>>> render_latex_text(tabular_str)
"""
import utool as ut
if flip:
bigger_is_better = not bigger_is_better
flip_repltups = [
('<=', '>'),
('>', '<='),
('\\leq', '\\gt'),
('\\geq', '\\lt'),
('score', 'error')
]
col_lbls = [replace_all(lbl, flip_repltups) for lbl in col_lbls]
if title is not None:
title = replace_all(title, flip_repltups)
if out_of is not None:
values = out_of - values
# Abbreviate based on common substrings
common_rowlbl = None
if SHORTEN_ROW_LBLS:
if isinstance(row_lbls, list):
row_lbl_list = row_lbls
else:
row_lbl_list = row_lbls.flatten().tolist()
# Split the rob labels into the alg components
#algcomp_list = [lbl.split(')_') for lbl in row_lbl_list]
longest = long_substr(row_lbl_list)
common_strs = []
while len(longest) > 10:
common_strs += [longest]
row_lbl_list = [row.replace(longest, '...') for row in row_lbl_list]
longest = long_substr(row_lbl_list)
common_rowlbl = ('...'.join(common_strs)).replace(')_', ')_\n')
row_lbls = row_lbl_list
if len(row_lbl_list) == 1:
common_rowlbl = row_lbl_list[0]
row_lbls = ['0']
# Stack values into a tabular body
# TODO: need ability to specify datatypes
def ensurelist(row_values):
try:
return row_values.tolist()
except AttributeError:
return row_values
if False:
# Numpy formatting
def padvec(shape=(1, 1)):
pad = np.array([[' ' for c in range(shape[1])] for r in range(shape[0])])
return pad
col_lbls = ensure_rowvec(col_lbls)
row_lbls = ensure_colvec(row_lbls)
_0 = np.vstack([padvec(), row_lbls])
_1 = np.vstack([col_lbls, values])
body = np.hstack([_0, _1])
body = [[str_ for str_ in row] for row in body]
else:
assert len(row_lbls) == len(values)
body = [[' '] + col_lbls]
body += [[row_lbl] + ensurelist(row_values) for row_lbl, row_values in zip(row_lbls, values)]
#import utool as ut
# Fix things in each body cell
DO_PERCENT = True
try:
for r in range(len(body)):
for c in range(len(body[0])):
# In data land
if r > 0 and c > 0:
if precision is not None:
# Hack
if ut.is_float(body[r][c]):
fmtstr = '%.' + str(precision) + 'f'
body[r][c] = fmtstr % (float(body[r][c]),)
# Force integer
if FORCE_INT:
body[r][c] = str(int(float(body[r][c])))
body[r][c] = str(body[r][c])
# Remove bad formatting;
if AUTOFIX_LATEX:
body[r][c] = escape_latex(body[r][c])
except Exception as ex:
import utool as ut
print('len(row_lbls) = %r' % (len(row_lbls),))
print('len(col_lbls) = %r' % (len(col_lbls),))
print('len(values) = %r' % (values,))
print('ut.depth_profile(values) = %r' % (ut.depth_profile(values),))
util_dbg.printex(ex, keys=['r', 'c'])
raise
# Bold the best values
if bold_best:
best_col_scores = values.max(0) if bigger_is_better else values.min(0)
rows_to_bold = [np.where(values[:, colx] == best_col_scores[colx])[0]
for colx in range(len(values.T))]
for colx, rowx_list in enumerate(rows_to_bold):
for rowx in rowx_list:
body[rowx + 1][colx + 1] = '\\txtbf{' + body[rowx + 1][colx + 1] + '}'
# More fixing after the bold is in place
for r in range(len(body)):
for c in range(len(body[0])):
# In data land
if r > 0 and c > 0:
if out_of is not None:
body[r][c] = body[r][c] + '/' + str(out_of)
if DO_PERCENT:
percent = ' = %.1f%%' % float(100 * values[r - 1, c - 1] / out_of)
body[r][c] += escape_latex(percent)
# Align columns for pretty printing
body = np.array(body)
ALIGN_BODY = True
if ALIGN_BODY:
new_body_cols = []
for col in body.T:
colstrs = list(map(str, ensurelist(col)))
collens = list(map(len, colstrs))
maxlen = max(collens)
newcols = [str_ + (' ' * (maxlen - len(str_))) for str_ in colstrs]
new_body_cols += [newcols]
body = np.array(new_body_cols).T
# Build Body (and row layout)
HLINE_SEP = True
rowvalsep = ''
colvalsep = ' & '
endl = '\\\\\n'
hline = r'\hline'
#extra_rowsep_pos_list = [1] # rows to insert an extra hline after
extra_rowsep_pos_list = [] # rows to insert an extra hline after
if HLINE_SEP:
rowvalsep = hline + '\n'
# rowstr list holds blocks of rows
rowstr_list = [colvalsep.join(row) + endl for row in body]
#rowstr_list = [row[0] + rowlbl_sep + colvalsep.join(row[1:]) + endl for row in body]
#rowstr_list = [(
# ('' if len(row) == 0 else row[0])
# if len(row) <= 1 else
# row[0] + rowlblcol_sep + colvalsep.join(row[1:]) + endl)
# for row in body]
rowsep_list = [rowvalsep for row in rowstr_list[0:-1]] # should be len 1 less than rowstr_list
# Insert multicolumn names
if multicol_lbls is not None:
# TODO: label of the row labels
multicol_sep
multicols = [latex_multicolumn(multicol, size, 'c' + multicol_sep) for multicol, size in multicol_lbls]
multicol_str = latex_multirow('', 2) + colvalsep + colvalsep.join(multicols) + endl
ncols = sum([tup[1] for tup in multicol_lbls])
mcol_sep = '\\cline{2-%d}\n' % (ncols + 1,)
rowstr_list = [multicol_str] + rowstr_list
rowsep_list = [mcol_sep] + rowsep_list
#extra_rowsep_pos_list += [1]
# Insert title
if title is not None and not astable:
tex_title = latex_multicolumn(title, len(body[0])) + endl
rowstr_list = [tex_title] + rowstr_list
rowsep_list = [rowvalsep] + rowsep_list
#extra_rowsep_pos_list += [2]
# Apply an extra hline (for label)
#extra_rowsep_pos_list = []
for pos in sorted(extra_rowsep_pos_list)[::-1]:
rowstr_list.insert(pos, '')
rowsep_list.insert(pos, rowvalsep)
#tabular_body = rowvalsep.join(rowstr_list)
from six.moves import zip_longest
tabular_body = ''.join([row if sep is None else row + sep for row, sep in zip_longest(rowstr_list, rowsep_list)])
# Build Column Layout
col_align_list = [col_align] * len(body[0])
#extra_collayoutsep_pos_list = [1]
extra_collayoutsep_pos_list = []
for pos in sorted(extra_collayoutsep_pos_list)[::-1]:
col_align_list.insert(pos, '')
#col_layaout_sep_list = rowlblcol_sep # TODO
rowlblcol_sep = '|'
# Build build internal seprations between column alignments
# Defaults to just the normal col_sep
col_align_sep_list = [col_sep] * (len(col_align_list) - 1)
# Adjust for the separations between row labels and the actual row data
if len(col_align_sep_list) > 0:
col_align_sep_list[0] = rowlblcol_sep
# Continue multicolumn sepratation
if multicol_lbls is not None:
multicol_offsets = ut.cumsum(ut.get_list_column(multicol_lbls, 1))
for offset in multicol_offsets:
if offset < len(col_align_sep_list):
col_align_sep_list[offset] = multicol_sep
from six.moves import zip_longest
_tmp = [ut.filter_Nones(tup) for tup in zip_longest(col_align_list, col_align_sep_list)]
col_layout = ''.join(ut.flatten(_tmp))
#if len(col_align_list) > 1:
# col_layout = col_align_list[0] + rowlblcol_sep + col_sep.join(col_align_list[1:])
#else:
# col_layout = col_sep.join(col_align_list)
tabular_head = (r'\begin{tabular}{|%s|}' % col_layout) + '\n'
tabular_tail = r'\end{tabular}'
if centerline:
tabular_head = r'\centerline{' + '\n' + tabular_head
tabular_tail = tabular_tail + '}'
if astable:
#tabular_head = r'\begin{centering}' + '\n' + tabular_head
tabular_head = r'\centering' + '\n' + tabular_head
tabular_head = r'\begin{table}' + table_position + '\n' + tabular_head
lblstr = latex_sanitize_command_name(kwargs.get('label', title))
caption = title
if AUTOFIX_LATEX:
caption = escape_latex(caption)
caption = '\n% ---\n' + caption + '\n% ---\n'
#tabular_head = r'\end{centering}' + '\n' + tabular_head
tabular_tail = tabular_tail + '\n\caption[%s]{%s}\n\label{tbl:%s}\n\end{table}' % (lblstr, caption, lblstr)
tabular_str = rowvalsep.join([tabular_head, tabular_body, tabular_tail])
topsep = '\\hline\n' if True else '\\toprule\n'
botsep = '\\hline\n' if True else '\\bottomrule\n'
tabular_str = tabular_head + topsep + tabular_body + botsep + tabular_tail
if common_rowlbl is not None:
#tabular_str += escape_latex('\n\nThe following parameters were held fixed:\n' + common_rowlbl)
pass
return tabular_str
def make_score_tabular(row_lbls,
col_lbls,
values,
title=None,
out_of=None,
bold_best=False,
flip=False,
bigger_is_better=True,
multicol_lbls=None,
FORCE_INT=False,
precision=None,
SHORTEN_ROW_LBLS=False,
col_align='l',
col_sep='|',
multicol_sep='|',
centerline=True,
astable=False,
table_position='',
AUTOFIX_LATEX=True,
**kwargs):
r"""
makes a LaTeX tabular for displaying scores or errors
Args:
row_lbls (list of str):
col_lbls (list of str):
values (ndarray):
title (str): (default = None)
out_of (None): (default = None)
bold_best (bool): (default = True)
flip (bool): (default = False)
table_position (str) : eg '[h]'
Returns:
str: tabular_str
CommandLine:
python -m utool.util_latex --test-make_score_tabular:0 --show
python -m utool.util_latex --test-make_score_tabular:1 --show
python -m utool.util_latex --test-make_score_tabular:2 --show
Example:
>>> # DISABLE_DOCTEST
>>> from utool.util_latex import * # NOQA
>>> import utool as ut
>>> row_lbls = ['config1', 'config2']
>>> col_lbls = ['score \leq 1', 'metric2']
>>> values = np.array([[1.2, 2], [3.2, 4]])
>>> title = 'title'
>>> out_of = 10
>>> bold_best = True
>>> flip = False
>>> tabular_str = make_score_tabular(row_lbls, col_lbls, values, title, out_of, bold_best, flip)
>>> result = tabular_str
>>> print(result)
>>> ut.quit_if_noshow()
>>> render_latex_text(tabular_str)
Example:
>>> # DISABLE_DOCTEST
>>> from utool.util_latex import * # NOQA
>>> import utool as ut
>>> row_lbls = ['config1']
>>> col_lbls = ['score \leq 1', 'metric2']
>>> values = np.array([[1.2, 2]])
>>> title = 'title'
>>> out_of = 10
>>> bold_best = True
>>> flip = False
>>> tabular_str = make_score_tabular(row_lbls, col_lbls, values, title, out_of, bold_best, flip)
>>> result = tabular_str
>>> print(result)
>>> ut.quit_if_noshow()
>>> render_latex_text(tabular_str)
Example:
>>> # DISABLE_DOCTEST
>>> from utool.util_latex import * # NOQA
>>> import utool as ut
>>> row_lbls = ['config1', 'config2']
>>> col_lbls = ['score \leq 1', 'metric2', 'foobar']
>>> multicol_lbls = [('spam', 1), ('eggs', 2)]
>>> values = np.array([[1.2, 2, -3], [3.2, 4, -2]])
>>> title = 'title'
>>> out_of = 10
>>> bold_best = True
>>> flip = False
>>> tabular_str = make_score_tabular(row_lbls, col_lbls, values, title, out_of, bold_best, flip, multicol_lbls=multicol_lbls)
>>> result = tabular_str
>>> print(result)
>>> ut.quit_if_noshow()
>>> render_latex_text(tabular_str)
"""
import utool as ut
if flip:
bigger_is_better = not bigger_is_better
flip_repltups = [('<=', '>'), ('>', '<='), ('\\leq', '\\gt'),
('\\geq', '\\lt'), ('score', 'error')]
col_lbls = [replace_all(lbl, flip_repltups) for lbl in col_lbls]
if title is not None:
title = replace_all(title, flip_repltups)
if out_of is not None:
values = out_of - values
# Abbreviate based on common substrings
common_rowlbl = None
if SHORTEN_ROW_LBLS:
if isinstance(row_lbls, list):
row_lbl_list = row_lbls
else:
row_lbl_list = row_lbls.flatten().tolist()
# Split the rob labels into the alg components
#algcomp_list = [lbl.split(')_') for lbl in row_lbl_list]
longest = long_substr(row_lbl_list)
common_strs = []
while len(longest) > 10:
common_strs += [longest]
row_lbl_list = [
row.replace(longest, '...') for row in row_lbl_list
]
longest = long_substr(row_lbl_list)
common_rowlbl = ('...'.join(common_strs)).replace(')_', ')_\n')
row_lbls = row_lbl_list
if len(row_lbl_list) == 1:
common_rowlbl = row_lbl_list[0]
row_lbls = ['0']
# Stack values into a tabular body
# TODO: need ability to specify datatypes
def ensurelist(row_values):
try:
return row_values.tolist()
except AttributeError:
return row_values
if False:
# Numpy formatting
def padvec(shape=(1, 1)):
pad = np.array([[' ' for c in range(shape[1])]
for r in range(shape[0])])
return pad
col_lbls = ensure_rowvec(col_lbls)
row_lbls = ensure_colvec(row_lbls)
_0 = np.vstack([padvec(), row_lbls])
_1 = np.vstack([col_lbls, values])
body = np.hstack([_0, _1])
body = [[str_ for str_ in row] for row in body]
else:
assert len(row_lbls) == len(values)
body = [[' '] + col_lbls]
body += [[row_lbl] + ensurelist(row_values)
for row_lbl, row_values in zip(row_lbls, values)]
#import utool as ut
# Fix things in each body cell
DO_PERCENT = True
try:
for r in range(len(body)):
for c in range(len(body[0])):
# In data land
if r > 0 and c > 0:
if precision is not None:
# Hack
if ut.is_float(body[r][c]):
fmtstr = '%.' + str(precision) + 'f'
body[r][c] = fmtstr % (float(body[r][c]), )
# Force integer
if FORCE_INT:
body[r][c] = str(int(float(body[r][c])))
body[r][c] = str(body[r][c])
# Remove bad formatting;
if AUTOFIX_LATEX:
body[r][c] = escape_latex(body[r][c])
except Exception as ex:
import utool as ut
print('len(row_lbls) = %r' % (len(row_lbls), ))
print('len(col_lbls) = %r' % (len(col_lbls), ))
print('len(values) = %r' % (values, ))
print('ut.depth_profile(values) = %r' % (ut.depth_profile(values), ))
util_dbg.printex(ex, keys=['r', 'c'])
raise
# Bold the best values
if bold_best:
best_col_scores = values.max(0) if bigger_is_better else values.min(0)
rows_to_bold = [
np.where(values[:, colx] == best_col_scores[colx])[0]
for colx in range(len(values.T))
]
for colx, rowx_list in enumerate(rows_to_bold):
for rowx in rowx_list:
body[rowx + 1][colx +
1] = '\\txtbf{' + body[rowx + 1][colx + 1] + '}'
# More fixing after the bold is in place
for r in range(len(body)):
for c in range(len(body[0])):
# In data land
if r > 0 and c > 0:
if out_of is not None:
body[r][c] = body[r][c] + '/' + str(out_of)
if DO_PERCENT:
percent = ' = %.1f%%' % float(
100 * values[r - 1, c - 1] / out_of)
body[r][c] += escape_latex(percent)
# Align columns for pretty printing
body = np.array(body)
ALIGN_BODY = True
if ALIGN_BODY:
new_body_cols = []
for col in body.T:
colstrs = list(map(str, ensurelist(col)))
collens = list(map(len, colstrs))
maxlen = max(collens)
newcols = [str_ + (' ' * (maxlen - len(str_))) for str_ in colstrs]
new_body_cols += [newcols]
body = np.array(new_body_cols).T
# Build Body (and row layout)
HLINE_SEP = True
rowvalsep = ''
colvalsep = ' & '
endl = '\\\\\n'
hline = r'\hline'
#extra_rowsep_pos_list = [1] # rows to insert an extra hline after
extra_rowsep_pos_list = [] # rows to insert an extra hline after
if HLINE_SEP:
rowvalsep = hline + '\n'
# rowstr list holds blocks of rows
rowstr_list = [colvalsep.join(row) + endl for row in body]
#rowstr_list = [row[0] + rowlbl_sep + colvalsep.join(row[1:]) + endl for row in body]
#rowstr_list = [(
# ('' if len(row) == 0 else row[0])
# if len(row) <= 1 else
# row[0] + rowlblcol_sep + colvalsep.join(row[1:]) + endl)
# for row in body]
rowsep_list = [rowvalsep for row in rowstr_list[0:-1]
] # should be len 1 less than rowstr_list
# Insert multicolumn names
if multicol_lbls is not None:
# TODO: label of the row labels
multicol_sep
multicols = [
latex_multicolumn(multicol, size, 'c' + multicol_sep)
for multicol, size in multicol_lbls
]
multicol_str = latex_multirow(
'', 2) + colvalsep + colvalsep.join(multicols) + endl
ncols = sum([tup[1] for tup in multicol_lbls])
mcol_sep = '\\cline{2-%d}\n' % (ncols + 1, )
rowstr_list = [multicol_str] + rowstr_list
rowsep_list = [mcol_sep] + rowsep_list
#extra_rowsep_pos_list += [1]
# Insert title
if title is not None and not astable:
tex_title = latex_multicolumn(title, len(body[0])) + endl
rowstr_list = [tex_title] + rowstr_list
rowsep_list = [rowvalsep] + rowsep_list
#extra_rowsep_pos_list += [2]
# Apply an extra hline (for label)
#extra_rowsep_pos_list = []
for pos in sorted(extra_rowsep_pos_list)[::-1]:
rowstr_list.insert(pos, '')
rowsep_list.insert(pos, rowvalsep)
#tabular_body = rowvalsep.join(rowstr_list)
from six.moves import zip_longest
tabular_body = ''.join([
row if sep is None else row + sep
for row, sep in zip_longest(rowstr_list, rowsep_list)
])
# Build Column Layout
col_align_list = [col_align] * len(body[0])
#extra_collayoutsep_pos_list = [1]
extra_collayoutsep_pos_list = []
for pos in sorted(extra_collayoutsep_pos_list)[::-1]:
col_align_list.insert(pos, '')
#col_layaout_sep_list = rowlblcol_sep # TODO
rowlblcol_sep = '|'
# Build build internal seprations between column alignments
# Defaults to just the normal col_sep
col_align_sep_list = [col_sep] * (len(col_align_list) - 1)
# Adjust for the separations between row labels and the actual row data
if len(col_align_sep_list) > 0:
col_align_sep_list[0] = rowlblcol_sep
# Continue multicolumn sepratation
if multicol_lbls is not None:
multicol_offsets = ut.cumsum(ut.get_list_column(multicol_lbls, 1))
for offset in multicol_offsets:
if offset < len(col_align_sep_list):
col_align_sep_list[offset] = multicol_sep
from six.moves import zip_longest
_tmp = [
ut.filter_Nones(tup)
for tup in zip_longest(col_align_list, col_align_sep_list)
]
col_layout = ''.join(ut.flatten(_tmp))
#if len(col_align_list) > 1:
# col_layout = col_align_list[0] + rowlblcol_sep + col_sep.join(col_align_list[1:])
#else:
# col_layout = col_sep.join(col_align_list)
tabular_head = (r'\begin{tabular}{|%s|}' % col_layout) + '\n'
tabular_tail = r'\end{tabular}'
if centerline:
tabular_head = r'\centerline{' + '\n' + tabular_head
tabular_tail = tabular_tail + '}'
if astable:
#tabular_head = r'\begin{centering}' + '\n' + tabular_head
tabular_head = r'\centering' + '\n' + tabular_head
tabular_head = r'\begin{table}' + table_position + '\n' + tabular_head
lblstr = latex_sanitize_command_name(kwargs.get('label', title))
caption = title
if AUTOFIX_LATEX:
caption = escape_latex(caption)
caption = '\n% ---\n' + caption + '\n% ---\n'
#tabular_head = r'\end{centering}' + '\n' + tabular_head
tabular_tail = tabular_tail + '\n\caption[%s]{%s}\n\label{tbl:%s}\n\end{table}' % (
lblstr, caption, lblstr)
tabular_str = rowvalsep.join([tabular_head, tabular_body, tabular_tail])
topsep = '\\hline\n' if True else '\\toprule\n'
botsep = '\\hline\n' if True else '\\bottomrule\n'
tabular_str = tabular_head + topsep + tabular_body + botsep + tabular_tail
if common_rowlbl is not None:
#tabular_str += escape_latex('\n\nThe following parameters were held fixed:\n' + common_rowlbl)
pass
return tabular_str