def build_matrix_str(allres):
hs = allres.hs
cx2_gx = hs.tables.cx2_gx
gx2_gname = hs.tables.gx2_gname
def cx2_gname(cx):
return [os.path.splitext(gname)[0] for gname in gx2_gname[cx2_gx]]
col_label_gname = cx2_gname(allres.col_label_cx)
row_label_gname = cx2_gname(allres.row_label_cx)
timestamp = helpers.get_timestamp(format_='comment') + '\n'
header = '\n'.join([
'# Result score matrix', '# Generated on: ' + timestamp,
'# Format: rows separated by newlines, cols separated by commas',
'# num_queries / rows = ' + repr(len(row_label_gname)),
'# num_indexed / cols = ' + repr(len(col_label_gname)),
'# row_labels = ' + repr(row_label_gname),
'# col_labels = ' + repr(col_label_gname)
])
row_strings = []
for row in allres.score_matrix:
row_str = map(lambda x: '%5.2f' % x, row)
row_strings.append(', '.join(row_str))
body = '\n'.join(row_strings)
matrix_str = '\n'.join([header, body])
allres.matrix_str = matrix_str
def build_matrix_str(allres):
hs = allres.hs
cx2_gx = hs.tables.cx2_gx
gx2_gname = hs.tables.gx2_gname
def cx2_gname(cx):
return [os.path.splitext(gname)[0] for gname in gx2_gname[cx2_gx]]
col_label_gname = cx2_gname(allres.col_label_cx)
row_label_gname = cx2_gname(allres.row_label_cx)
timestamp = helpers.get_timestamp(format_='comment') + '\n'
header = '\n'.join(
['# Result score matrix',
'# Generated on: ' + timestamp,
'# Format: rows separated by newlines, cols separated by commas',
'# num_queries / rows = ' + repr(len(row_label_gname)),
'# num_indexed / cols = ' + repr(len(col_label_gname)),
'# row_labels = ' + repr(row_label_gname),
'# col_labels = ' + repr(col_label_gname)])
row_strings = []
for row in allres.score_matrix:
row_str = map(lambda x: '%5.2f' % x, row)
row_strings.append(', '.join(row_str))
body = '\n'.join(row_strings)
matrix_str = '\n'.join([header, body])
allres.matrix_str = matrix_str
def backup_csv_tables(hs, force_backup=False):
internal_dir = hs.dirs.internal_dir
backup_dir = join(internal_dir, 'backup_v0.1.0')
if not exists(backup_dir) or force_backup:
helpers.ensuredir(backup_dir)
timestamp = helpers.get_timestamp(use_second=True)
def do_backup(fname):
src = join(internal_dir, fname)
dst_fname = ('%s_bak-' + timestamp + '%s') % splitext(fname)
dst = join(backup_dir, dst_fname)
if exists(src):
shutil.copy(src, dst)
do_backup(CHIP_TABLE_FNAME)
do_backup(NAME_TABLE_FNAME)
do_backup(IMAGE_TABLE_FNAME)
def backup_csv_tables(hs, force_backup=False):
internal_dir = hs.dirs.internal_dir
backup_dir = join(internal_dir, 'backup_v0.1.0')
if not exists(backup_dir) or force_backup:
helpers.ensuredir(backup_dir)
timestamp = helpers.get_timestamp(use_second=True)
def do_backup(fname):
src = join(internal_dir, fname)
dst_fname = ('%s_bak-' + timestamp + '%s') % splitext(fname)
dst = join(backup_dir, dst_fname)
if exists(src):
shutil.copy(src, dst)
do_backup(CHIP_TABLE_FNAME)
do_backup(NAME_TABLE_FNAME)
do_backup(IMAGE_TABLE_FNAME)
def __dump_text_report(allres, report_type):
if not 'report_type' in vars():
report_type = 'rankres_str'
print('[rr2] Dumping textfile: ' + report_type)
report_str = allres.__dict__[report_type]
# Get directories
result_dir = allres.hs.dirs.result_dir
timestamp_dir = join(result_dir, 'timestamped_results')
helpers.ensurepath(timestamp_dir)
helpers.ensurepath(result_dir)
# Write to timestamp and result dir
timestamp = helpers.get_timestamp()
csv_timestamp_fname = report_type + allres.title_suffix + timestamp + '.csv'
csv_timestamp_fpath = join(timestamp_dir, csv_timestamp_fname)
csv_fname = report_type + allres.title_suffix + '.csv'
csv_fpath = join(result_dir, csv_fname)
helpers.write_to(csv_fpath, report_str)
helpers.write_to(csv_timestamp_fpath, report_str)
def __dump_text_report(allres, report_type):
if not 'report_type' in vars():
report_type = 'rankres_str'
print('[rr2] Dumping textfile: ' + report_type)
report_str = allres.__dict__[report_type]
# Get directories
result_dir = allres.hs.dirs.result_dir
timestamp_dir = join(result_dir, 'timestamped_results')
helpers.ensurepath(timestamp_dir)
helpers.ensurepath(result_dir)
# Write to timestamp and result dir
timestamp = helpers.get_timestamp()
csv_timestamp_fname = report_type + allres.title_suffix + timestamp + '.csv'
csv_timestamp_fpath = join(timestamp_dir, csv_timestamp_fname)
csv_fname = report_type + allres.title_suffix + '.csv'
csv_fpath = join(result_dir, csv_fname)
helpers.write_to(csv_fpath, report_str)
helpers.write_to(csv_timestamp_fpath, report_str)
def translate_python_to_cython(input_lines):
try:
from hscom import helpers as util
timestamp = util.get_timestamp()
except Exception:
timestamp = '???'
pass
output_lines = ['# THIS FILE WAS AUTOGENERATED ON %s\n' % timestamp]
MODE = None
PYX_MAP = {}
translate_nLines = 0
for in_line in input_lines:
MODE, in_line = pyx_preprocess(MODE, in_line, PYX_MAP)
if MODE is None:
# No cython annotations
output_lines.append(in_line)
elif MODE == START_TAG:
# Start unannotating cython code;
in_line = translate_cython_line(in_line, PYX_MAP)
output_lines.append(in_line)
elif MODE == ELSE_TAG:
# Exclude from cython
pass
elif MODE == DEFINE_TAG:
# Skip the python define
if in_line.find('#') == -1 and in_line.find('):') != -1:
MODE = None
translate_nLines = 0
# Translate the cython define
elif in_line.find('#') == 0:
translate_nLines = 1
elif MODE == CDEF_TAG:
translate_nLines = 1
MODE = None
# We are translating the next N lines
if translate_nLines > 0:
translate_nLines -= 1
in_line = translate_cython_line(in_line, PYX_MAP)
output_lines.append(in_line)
return output_lines
def build_rankres_str(allres):
'Builds csv files showing the cxs/scores/ranks of the query results'
hs = allres.hs
#SV = allres.SV
#qcx2_res = allres.qcx2_res
cx2_cid = hs.tables.cx2_cid
#cx2_nx = hs.tables.cx2_nx
test_samp = hs.test_sample_cx
train_samp = hs.train_sample_cx
indx_samp = hs.indexed_sample_cx
# Get organized data for csv file
(qcx2_top_true_rank,
qcx2_top_true_score,
qcx2_top_true_cx) = allres.top_true_qcx_arrays
(qcx2_bot_true_rank,
qcx2_bot_true_score,
qcx2_bot_true_cx) = allres.bot_true_qcx_arrays
(qcx2_top_false_rank,
qcx2_top_false_score,
qcx2_top_false_cx) = allres.top_false_qcx_arrays
# Number of groundtruth per query
qcx2_numgt = np.zeros(len(cx2_cid)) - 2
for qcx in test_samp:
qcx2_numgt[qcx] = len(hs.get_other_indexed_cxs(qcx))
# Easy to digest results
num_chips = len(test_samp)
num_nonquery = len(np.setdiff1d(indx_samp, test_samp))
# Find the test samples WITH ground truth
test_samp_with_gt = np.array(test_samp)[qcx2_numgt[test_samp] > 0]
if len(test_samp_with_gt) == 0:
warnings.warn('[rr2] there were no queries with ground truth')
#train_nxs_set = set(cx2_nx[train_samp])
flag_cxs_fn = hs.flag_cxs_with_name_in_sample
def ranks_less_than_(thresh, intrain=None):
#Find the number of ranks scoring more than thresh
# Get statistics with respect to the training set
if len(test_samp_with_gt) == 0:
test_cxs_ = np.array([])
elif intrain is None: # report all
test_cxs_ = test_samp_with_gt
else: # report either or
in_train_flag = flag_cxs_fn(test_samp_with_gt, train_samp)
if intrain is False:
in_train_flag = True - in_train_flag
test_cxs_ = test_samp_with_gt[in_train_flag]
# number of test samples with ground truth
num_with_gt = len(test_cxs_)
if num_with_gt == 0:
return [], ('NoGT', 'NoGT', -1, 'NoGT')
# find tests with ranks greater and less than thresh
testcx2_ttr = qcx2_top_true_rank[test_cxs_]
greater_cxs = test_cxs_[np.where(testcx2_ttr > thresh)[0]]
num_greater = len(greater_cxs)
num_less = num_with_gt - num_greater
num_greater = num_with_gt - num_less
frac_less = 100.0 * num_less / num_with_gt
fmt_tup = (num_less, num_with_gt, frac_less, num_greater)
return greater_cxs, fmt_tup
greater5_cxs, fmt5_tup = ranks_less_than_(5)
greater1_cxs, fmt1_tup = ranks_less_than_(1)
#
gt5_intrain_cxs, fmt5_in_tup = ranks_less_than_(5, intrain=True)
gt1_intrain_cxs, fmt1_in_tup = ranks_less_than_(1, intrain=True)
#
gt5_outtrain_cxs, fmt5_out_tup = ranks_less_than_(5, intrain=False)
gt1_outtrain_cxs, fmt1_out_tup = ranks_less_than_(1, intrain=False)
#
allres.greater1_cxs = greater1_cxs
allres.greater5_cxs = greater5_cxs
#print('greater5_cxs = %r ' % (allres.greater5_cxs,))
#print('greater1_cxs = %r ' % (allres.greater1_cxs,))
# CSV Metadata
header = '# Experiment allres.title_suffix = ' + allres.title_suffix + '\n'
header += helpers.get_timestamp(format_='comment') + '\n'
# Scalar summary
scalar_summary = '# Num Query Chips: %d \n' % num_chips
scalar_summary += '# Num Query Chips with at least one match: %d \n' % len(test_samp_with_gt)
scalar_summary += '# Num NonQuery Chips: %d \n' % num_nonquery
scalar_summary += '# Ranks <= 5: %r/%r = %.1f%% (missed %r)\n' % (fmt5_tup)
scalar_summary += '# Ranks <= 1: %r/%r = %.1f%% (missed %r)\n\n' % (fmt1_tup)
scalar_summary += '# InTrain Ranks <= 5: %r/%r = %.1f%% (missed %r)\n' % (fmt5_in_tup)
scalar_summary += '# InTrain Ranks <= 1: %r/%r = %.1f%% (missed %r)\n\n' % (fmt1_in_tup)
scalar_summary += '# OutTrain Ranks <= 5: %r/%r = %.1f%% (missed %r)\n' % (fmt5_out_tup)
scalar_summary += '# OutTrain Ranks <= 1: %r/%r = %.1f%% (missed %r)\n\n' % (fmt1_out_tup)
header += scalar_summary
# Experiment parameters
#header += '# Full Parameters: \n' + helpers.indent(params.param_string(), '#') + '\n\n'
# More Metadata
header += textwrap.dedent('''
# Rank Result Metadata:
# QCX = Query chip-index
# QGNAME = Query images name
# NUMGT = Num ground truth matches
# TT = top true
# BT = bottom true
# TF = top false''').strip()
# Build the CSV table
test_sample_gx = hs.tables.cx2_gx[test_samp]
test_sample_gname = hs.tables.gx2_gname[test_sample_gx]
test_sample_gname = [g.replace('.jpg', '') for g in test_sample_gname]
column_labels = ['QCX', 'NUM GT',
'TT CX', 'BT CX', 'TF CX',
'TT SCORE', 'BT SCORE', 'TF SCORE',
'TT RANK', 'BT RANK', 'TF RANK',
'QGNAME', ]
column_list = [
test_samp, qcx2_numgt[test_samp],
qcx2_top_true_cx[test_samp], qcx2_bot_true_cx[test_samp],
qcx2_top_false_cx[test_samp], qcx2_top_true_score[test_samp],
qcx2_bot_true_score[test_samp], qcx2_top_false_score[test_samp],
qcx2_top_true_rank[test_samp], qcx2_bot_true_rank[test_samp],
qcx2_top_false_rank[test_samp], test_sample_gname, ]
column_type = [int, int, int, int, int,
float, float, float, int, int, int, str, ]
rankres_str = ld2.make_csv_table(column_labels, column_list, header, column_type)
# Put some more data at the end
problem_true_pairs = zip(allres.problem_true.qcxs, allres.problem_true.cxs)
problem_false_pairs = zip(allres.problem_false.qcxs, allres.problem_false.cxs)
problem_str = '\n'.join( [
'#Problem Cases: ',
'# problem_true_pairs = ' + repr(problem_true_pairs),
'# problem_false_pairs = ' + repr(problem_false_pairs)])
rankres_str += '\n' + problem_str
# Attach results to allres structure
allres.rankres_str = rankres_str
allres.scalar_summary = scalar_summary
allres.problem_false_pairs = problem_false_pairs
allres.problem_true_pairs = problem_true_pairs
allres.problem_false_pairs = problem_false_pairs
allres.problem_true_pairs = problem_true_pairs
def build_rankres_str(allres):
'Builds csv files showing the cxs/scores/ranks of the query results'
hs = allres.hs
#SV = allres.SV
#qcx2_res = allres.qcx2_res
cx2_cid = hs.tables.cx2_cid
#cx2_nx = hs.tables.cx2_nx
test_samp = hs.test_sample_cx
train_samp = hs.train_sample_cx
indx_samp = hs.indexed_sample_cx
# Get organized data for csv file
(qcx2_top_true_rank, qcx2_top_true_score,
qcx2_top_true_cx) = allres.top_true_qcx_arrays
(qcx2_bot_true_rank, qcx2_bot_true_score,
qcx2_bot_true_cx) = allres.bot_true_qcx_arrays
(qcx2_top_false_rank, qcx2_top_false_score,
qcx2_top_false_cx) = allres.top_false_qcx_arrays
# Number of groundtruth per query
qcx2_numgt = np.zeros(len(cx2_cid)) - 2
for qcx in test_samp:
qcx2_numgt[qcx] = len(hs.get_other_indexed_cxs(qcx))
# Easy to digest results
num_chips = len(test_samp)
num_nonquery = len(np.setdiff1d(indx_samp, test_samp))
# Find the test samples WITH ground truth
test_samp_with_gt = np.array(test_samp)[qcx2_numgt[test_samp] > 0]
if len(test_samp_with_gt) == 0:
warnings.warn('[rr2] there were no queries with ground truth')
#train_nxs_set = set(cx2_nx[train_samp])
flag_cxs_fn = hs.flag_cxs_with_name_in_sample
def ranks_less_than_(thresh, intrain=None):
#Find the number of ranks scoring more than thresh
# Get statistics with respect to the training set
if len(test_samp_with_gt) == 0:
test_cxs_ = np.array([])
elif intrain is None: # report all
test_cxs_ = test_samp_with_gt
else: # report either or
in_train_flag = flag_cxs_fn(test_samp_with_gt, train_samp)
if intrain is False:
in_train_flag = True - in_train_flag
test_cxs_ = test_samp_with_gt[in_train_flag]
# number of test samples with ground truth
num_with_gt = len(test_cxs_)
if num_with_gt == 0:
return [], ('NoGT', 'NoGT', -1, 'NoGT')
# find tests with ranks greater and less than thresh
testcx2_ttr = qcx2_top_true_rank[test_cxs_]
greater_cxs = test_cxs_[np.where(testcx2_ttr > thresh)[0]]
num_greater = len(greater_cxs)
num_less = num_with_gt - num_greater
num_greater = num_with_gt - num_less
frac_less = 100.0 * num_less / num_with_gt
fmt_tup = (num_less, num_with_gt, frac_less, num_greater)
return greater_cxs, fmt_tup
greater5_cxs, fmt5_tup = ranks_less_than_(5)
greater1_cxs, fmt1_tup = ranks_less_than_(1)
#
gt5_intrain_cxs, fmt5_in_tup = ranks_less_than_(5, intrain=True)
gt1_intrain_cxs, fmt1_in_tup = ranks_less_than_(1, intrain=True)
#
gt5_outtrain_cxs, fmt5_out_tup = ranks_less_than_(5, intrain=False)
gt1_outtrain_cxs, fmt1_out_tup = ranks_less_than_(1, intrain=False)
#
allres.greater1_cxs = greater1_cxs
allres.greater5_cxs = greater5_cxs
#print('greater5_cxs = %r ' % (allres.greater5_cxs,))
#print('greater1_cxs = %r ' % (allres.greater1_cxs,))
# CSV Metadata
header = '# Experiment allres.title_suffix = ' + allres.title_suffix + '\n'
header += helpers.get_timestamp(format_='comment') + '\n'
# Scalar summary
scalar_summary = '# Num Query Chips: %d \n' % num_chips
scalar_summary += '# Num Query Chips with at least one match: %d \n' % len(
test_samp_with_gt)
scalar_summary += '# Num NonQuery Chips: %d \n' % num_nonquery
scalar_summary += '# Ranks <= 5: %r/%r = %.1f%% (missed %r)\n' % (fmt5_tup)
scalar_summary += '# Ranks <= 1: %r/%r = %.1f%% (missed %r)\n\n' % (
fmt1_tup)
scalar_summary += '# InTrain Ranks <= 5: %r/%r = %.1f%% (missed %r)\n' % (
fmt5_in_tup)
scalar_summary += '# InTrain Ranks <= 1: %r/%r = %.1f%% (missed %r)\n\n' % (
fmt1_in_tup)
scalar_summary += '# OutTrain Ranks <= 5: %r/%r = %.1f%% (missed %r)\n' % (
fmt5_out_tup)
scalar_summary += '# OutTrain Ranks <= 1: %r/%r = %.1f%% (missed %r)\n\n' % (
fmt1_out_tup)
header += scalar_summary
# Experiment parameters
#header += '# Full Parameters: \n' + helpers.indent(params.param_string(), '#') + '\n\n'
# More Metadata
header += textwrap.dedent('''
# Rank Result Metadata:
# QCX = Query chip-index
# QGNAME = Query images name
# NUMGT = Num ground truth matches
# TT = top true
# BT = bottom true
# TF = top false''').strip()
# Build the CSV table
test_sample_gx = hs.tables.cx2_gx[test_samp]
test_sample_gname = hs.tables.gx2_gname[test_sample_gx]
test_sample_gname = [g.replace('.jpg', '') for g in test_sample_gname]
column_labels = [
'QCX',
'NUM GT',
'TT CX',
'BT CX',
'TF CX',
'TT SCORE',
'BT SCORE',
'TF SCORE',
'TT RANK',
'BT RANK',
'TF RANK',
'QGNAME',
]
column_list = [
test_samp,
qcx2_numgt[test_samp],
qcx2_top_true_cx[test_samp],
qcx2_bot_true_cx[test_samp],
qcx2_top_false_cx[test_samp],
qcx2_top_true_score[test_samp],
qcx2_bot_true_score[test_samp],
qcx2_top_false_score[test_samp],
qcx2_top_true_rank[test_samp],
qcx2_bot_true_rank[test_samp],
qcx2_top_false_rank[test_samp],
test_sample_gname,
]
column_type = [
int,
int,
int,
int,
int,
float,
float,
float,
int,
int,
int,
str,
]
rankres_str = ld2.make_csv_table(column_labels, column_list, header,
column_type)
# Put some more data at the end
problem_true_pairs = zip(allres.problem_true.qcxs, allres.problem_true.cxs)
problem_false_pairs = zip(allres.problem_false.qcxs,
allres.problem_false.cxs)
problem_str = '\n'.join([
'#Problem Cases: ',
'# problem_true_pairs = ' + repr(problem_true_pairs),
'# problem_false_pairs = ' + repr(problem_false_pairs)
])
rankres_str += '\n' + problem_str
# Attach results to allres structure
allres.rankres_str = rankres_str
allres.scalar_summary = scalar_summary
allres.problem_false_pairs = problem_false_pairs
allres.problem_true_pairs = problem_true_pairs
allres.problem_false_pairs = problem_false_pairs
allres.problem_true_pairs = problem_true_pairs