def show_power_law_plots():
"""
CommandLine:
python -m ibeis.algo.hots.devcases --test-show_power_law_plots --show
Example:
>>> # DISABLE_DOCTEST
>>> #%pylab qt4
>>> from ibeis.all_imports import * # NOQA
>>> from ibeis.algo.hots.devcases import * # NOQA
>>> show_power_law_plots()
>>> pt.show_if_requested()
"""
import numpy as np
import plottool as pt
xdata = np.linspace(0, 1, 1000)
ydata = xdata
fnum = 1
powers = [.01, .1, .5, 1, 2, 30, 70, 100, 1000]
nRows, nCols = pt.get_square_row_cols(len(powers), fix=True)
pnum_next = pt.make_pnum_nextgen(nRows, nCols)
for p in powers:
plotkw = dict(fnum=fnum,
marker='g-',
linewidth=2,
pnum=pnum_next(),
title='p=%r' % (p, ))
ydata_ = ydata**p
pt.plot2(xdata, ydata_, **plotkw)
pt.set_figtitle('power laws y = x ** p')
def subindexer_time_experiment():
"""
builds plot of number of annotations vs indexer build time.
TODO: time experiment
"""
import ibeis
import utool as ut
import pyflann
import plottool as pt
ibs = ibeis.opendb(db='PZ_Master0')
daid_list = ibs.get_valid_aids()
count_list = []
time_list = []
flann_params = ibs.cfg.query_cfg.flann_cfg.get_flann_params()
for count in ut.ProgressIter(range(1, 301)):
daids_ = daid_list[:]
np.random.shuffle(daids_)
daids = daids_[0:count]
vecs = np.vstack(ibs.get_annot_vecs(daids))
with ut.Timer(verbose=False) as t:
flann = pyflann.FLANN()
flann.build_index(vecs, **flann_params)
count_list.append(count)
time_list.append(t.ellapsed)
count_arr = np.array(count_list)
time_arr = np.array(time_list)
pt.plot2(count_arr, time_arr, marker='-', equal_aspect=False,
x_label='num_annotations', y_label='FLANN build time')
def draw_precision_recall_curve(recall_domain,
p_interp,
title_pref=None,
fnum=1,
pnum=None,
color=None):
import plottool as pt
if color is None:
color = (0.4, 1.0, 0.4) if pt.is_default_dark_bg() else (0.1, 0.4, 0.4)
if recall_domain is None:
recall_domain = np.array([])
p_interp = np.array([])
if recall_domain is None:
ave_p = -1.0 # np.nan
else:
ave_p = p_interp.sum() / p_interp.size
pt.plot2(recall_domain,
p_interp,
marker='o--',
x_label='recall',
y_label='precision',
unitbox=True,
flipx=False,
color=color,
fnum=fnum,
pnum=pnum,
title='Interplated Precision Vs Recall\n' + 'avep = %.3f' % ave_p)
def draw_precision_recall_curve(recall_domain, p_interp, title_pref=None, fnum=1, pnum=None, color=None):
import plottool as pt
if color is None:
color = (0.4, 1.0, 0.4) if pt.is_default_dark_bg() else (0.1, 0.4, 0.4)
if recall_domain is None:
recall_domain = np.array([])
p_interp = np.array([])
if recall_domain is None:
ave_p = -1.0 # np.nan
else:
ave_p = p_interp.sum() / p_interp.size
pt.plot2(
recall_domain,
p_interp,
marker="o--",
x_label="recall",
y_label="precision",
unitbox=True,
flipx=False,
color=color,
fnum=fnum,
pnum=pnum,
title="Interplated Precision Vs Recall\n" + "avep = %.3f" % ave_p,
)
def show_power_law_plots():
"""
CommandLine:
python -m ibeis.algo.hots.devcases --test-show_power_law_plots --show
Example:
>>> # DISABLE_DOCTEST
>>> #%pylab qt4
>>> from ibeis.all_imports import * # NOQA
>>> from ibeis.algo.hots.devcases import * # NOQA
>>> show_power_law_plots()
>>> pt.show_if_requested()
"""
import numpy as np
import plottool as pt
xdata = np.linspace(0, 1, 1000)
ydata = xdata
fnum = 1
powers = [.01, .1, .5, 1, 2, 30, 70, 100, 1000]
nRows, nCols = pt.get_square_row_cols(len(powers), fix=True)
pnum_next = pt.make_pnum_nextgen(nRows, nCols)
for p in powers:
plotkw = dict(
fnum=fnum,
marker='g-',
linewidth=2,
pnum=pnum_next(),
title='p=%r' % (p,)
)
ydata_ = ydata ** p
pt.plot2(xdata, ydata_, **plotkw)
pt.set_figtitle('power laws y = x ** p')
def plotdata(data_list):
count_arr = ut.get_list_column(data_list, 1)
time_arr = ut.get_list_column(data_list, 2)
pt.plot2(count_arr,
time_arr,
marker='-o',
equal_aspect=False,
x_label='num_vectors',
y_label='FLANN build time')
def _plotpts(data, px, color=pt.BLUE, label='', marker='.', **kwargs):
#pt.figure(9003, docla=True, pnum=(1, 1, px))
pt.plot2(data.T[0],
data.T[1],
marker,
'',
color=color,
label=label,
**kwargs)
def draw_precision_recall_curve_(recall_range_, p_interp_curve, title_pref=None, fnum=1):
import plottool as pt
if recall_range_ is None:
recall_range_ = np.array([])
p_interp_curve = np.array([])
fig = pt.figure(fnum=fnum, docla=True, doclf=True) # NOQA
if recall_range_ is None:
ave_p = np.nan
else:
ave_p = p_interp_curve.sum() / p_interp_curve.size
pt.plot2(recall_range_, p_interp_curve, marker='o--',
x_label='recall', y_label='precision', unitbox=True,
flipx=False, color='r',
title='Interplated Precision Vs Recall\n' + 'avep = %r' % ave_p)
print('Interplated Precision')
print(ut.repr2(list(zip(recall_range_, p_interp_curve))))
def draw_precision_recall_curve_(recall_range_, p_interp_curve, title_pref=None, fnum=1):
import plottool as pt
if recall_range_ is None:
recall_range_ = np.array([])
p_interp_curve = np.array([])
fig = pt.figure(fnum=fnum, docla=True, doclf=True) # NOQA
if recall_range_ is None:
ave_p = np.nan
else:
ave_p = p_interp_curve.sum() / p_interp_curve.size
pt.plot2(recall_range_, p_interp_curve, marker='o--',
x_label='recall', y_label='precision', unitbox=True,
flipx=False, color='r',
title='Interplated Precision Vs Recall\n' + 'avep = %r' % ave_p)
print('Interplated Precision')
print(ut.list_str(list(zip(recall_range_, p_interp_curve))))
def flann_add_time_experiment():
"""
builds plot of number of annotations vs indexer build time.
TODO: time experiment
CommandLine:
python -m ibeis.algo.hots._neighbor_experiment --test-flann_add_time_experiment --db PZ_MTEST --show
python -m ibeis.algo.hots._neighbor_experiment --test-flann_add_time_experiment --db PZ_Master0 --show
utprof.py -m ibeis.algo.hots._neighbor_experiment --test-flann_add_time_experiment --show
valgrind --tool=memcheck --suppressions=valgrind-python.supp python -m ibeis.algo.hots._neighbor_experiment --test-flann_add_time_experiment --db PZ_MTEST --no-with-reindex
Example:
>>> # DISABLE_DOCTEST
>>> from ibeis.algo.hots._neighbor_experiment import * # NOQA
>>> import ibeis
>>> #ibs = ibeis.opendb('PZ_MTEST')
>>> result = flann_add_time_experiment()
>>> # verify results
>>> print(result)
>>> ut.show_if_requested()
"""
import ibeis
import utool as ut
import numpy as np
import plottool as pt
def make_flann_index(vecs, flann_params):
flann = pyflann.FLANN()
flann.build_index(vecs, **flann_params)
return flann
db = ut.get_argval('--db')
ibs = ibeis.opendb(db=db)
# Input
if ibs.get_dbname() == 'PZ_MTEST':
initial = 1
reindex_stride = 16
addition_stride = 4
max_ceiling = 120
elif ibs.get_dbname() == 'PZ_Master0':
#ibs = ibeis.opendb(db='GZ_ALL')
initial = 32
reindex_stride = 32
addition_stride = 16
max_ceiling = 300001
else:
assert False
#max_ceiling = 32
all_daids = ibs.get_valid_aids()
max_num = min(max_ceiling, len(all_daids))
flann_params = ibs.cfg.query_cfg.flann_cfg.get_flann_params()
# Output
count_list, time_list_reindex = [], []
count_list2, time_list_addition = [], []
# Setup
#all_randomize_daids_ = ut.deterministic_shuffle(all_daids[:])
all_randomize_daids_ = all_daids
# ensure all features are computed
ibs.get_annot_vecs(all_randomize_daids_)
def reindex_step(count, count_list, time_list_reindex):
daids = all_randomize_daids_[0:count]
vecs = np.vstack(ibs.get_annot_vecs(daids))
with ut.Timer(verbose=False) as t:
flann = make_flann_index(vecs, flann_params) # NOQA
count_list.append(count)
time_list_reindex.append(t.ellapsed)
def addition_step(count, flann, count_list2, time_list_addition):
daids = all_randomize_daids_[count:count + 1]
vecs = np.vstack(ibs.get_annot_vecs(daids))
with ut.Timer(verbose=False) as t:
flann.add_points(vecs)
count_list2.append(count)
time_list_addition.append(t.ellapsed)
def make_initial_index(initial):
daids = all_randomize_daids_[0:initial + 1]
vecs = np.vstack(ibs.get_annot_vecs(daids))
flann = make_flann_index(vecs, flann_params)
return flann
WITH_REINDEX = not ut.get_argflag('--no-with-reindex')
if WITH_REINDEX:
# Reindex Part
reindex_lbl = 'Reindexing'
_reindex_iter = range(1, max_num, reindex_stride)
reindex_iter = ut.ProgressIter(_reindex_iter, lbl=reindex_lbl, freq=1)
for count in reindex_iter:
reindex_step(count, count_list, time_list_reindex)
# Add Part
flann = make_initial_index(initial)
addition_lbl = 'Addition'
_addition_iter = range(initial + 1, max_num, addition_stride)
addition_iter = ut.ProgressIter(_addition_iter, lbl=addition_lbl)
for count in addition_iter:
addition_step(count, flann, count_list2, time_list_addition)
print('---')
print('Reindex took time_list_reindex %.2s seconds' % sum(time_list_reindex))
print('Addition took time_list_reindex %.2s seconds' % sum(time_list_addition))
print('---')
statskw = dict(precision=2, newlines=True)
print('Reindex stats ' + ut.get_stats_str(time_list_reindex, **statskw))
print('Addition stats ' + ut.get_stats_str(time_list_addition, **statskw))
print('Plotting')
#with pt.FigureContext:
next_fnum = iter(range(0, 2)).next # python3 PY3
pt.figure(fnum=next_fnum())
if WITH_REINDEX:
pt.plot2(count_list, time_list_reindex, marker='-o', equal_aspect=False,
x_label='num_annotations', label=reindex_lbl + ' Time', dark=False)
#pt.figure(fnum=next_fnum())
pt.plot2(count_list2, time_list_addition, marker='-o', equal_aspect=False,
x_label='num_annotations', label=addition_lbl + ' Time')
pt
pt.legend()
def augment_nnindexer_experiment():
"""
References:
http://answers.opencv.org/question/44592/flann-index-training-fails-with-segfault/
CommandLine:
utprof.py -m ibeis.algo.hots._neighbor_experiment --test-augment_nnindexer_experiment
python -m ibeis.algo.hots._neighbor_experiment --test-augment_nnindexer_experiment
python -m ibeis.algo.hots._neighbor_experiment --test-augment_nnindexer_experiment --db PZ_MTEST --diskshow --adjust=.1 --save "augment_experiment_{db}.png" --dpath='.' --dpi=180 --figsize=9,6
python -m ibeis.algo.hots._neighbor_experiment --test-augment_nnindexer_experiment --db PZ_Master0 --diskshow --adjust=.1 --save "augment_experiment_{db}.png" --dpath='.' --dpi=180 --figsize=9,6 --nosave-flann --show
python -m ibeis.algo.hots._neighbor_experiment --test-augment_nnindexer_experiment --db PZ_Master0 --diskshow --adjust=.1 --save "augment_experiment_{db}.png" --dpath='.' --dpi=180 --figsize=9,6 --nosave-flann --show
python -m ibeis.algo.hots._neighbor_experiment --test-augment_nnindexer_experiment --db PZ_Master0 --diskshow --adjust=.1 --save "augment_experiment_{db}.png" --dpath='.' --dpi=180 --figsize=9,6 --nosave-flann --no-api-cache --nocache-uuids
python -m ibeis.algo.hots._neighbor_experiment --test-augment_nnindexer_experiment --db PZ_MTEST --show
python -m ibeis.algo.hots._neighbor_experiment --test-augment_nnindexer_experiment --db PZ_Master0 --show
# RUNS THE SEGFAULTING CASE
python -m ibeis.algo.hots._neighbor_experiment --test-augment_nnindexer_experiment --db PZ_Master0 --show
# Debug it
gdb python
run -m ibeis.algo.hots._neighbor_experiment --test-augment_nnindexer_experiment --db PZ_Master0 --show
gdb python
run -m ibeis.algo.hots._neighbor_experiment --test-augment_nnindexer_experiment --db PZ_Master0 --diskshow --adjust=.1 --save "augment_experiment_{db}.png" --dpath='.' --dpi=180 --figsize=9,6
Example:
>>> # DISABLE_DOCTEST
>>> from ibeis.algo.hots._neighbor_experiment import * # NOQA
>>> # execute function
>>> augment_nnindexer_experiment()
>>> # verify results
>>> ut.show_if_requested()
"""
import ibeis
# build test data
#ibs = ibeis.opendb('PZ_MTEST')
ibs = ibeis.opendb(defaultdb='PZ_Master0')
if ibs.get_dbname() == 'PZ_MTEST':
initial = 1
addition_stride = 4
max_ceiling = 100
elif ibs.get_dbname() == 'PZ_Master0':
initial = 128
#addition_stride = 64
#addition_stride = 128
addition_stride = 256
max_ceiling = 10000
#max_ceiling = 4000
#max_ceiling = 2000
#max_ceiling = 600
else:
assert False
all_daids = ibs.get_valid_aids(species='zebra_plains')
qreq_ = ibs.new_query_request(all_daids, all_daids)
max_num = min(max_ceiling, len(all_daids))
# Clear Caches
ibs.delete_flann_cachedir()
neighbor_index_cache.clear_memcache()
neighbor_index_cache.clear_uuid_cache(qreq_)
# Setup
all_randomize_daids_ = ut.deterministic_shuffle(all_daids[:])
# ensure all features are computed
#ibs.get_annot_vecs(all_randomize_daids_, ensure=True)
#ibs.get_annot_fgweights(all_randomize_daids_, ensure=True)
nnindexer_list = []
addition_lbl = 'Addition'
_addition_iter = list(range(initial + 1, max_num, addition_stride))
addition_iter = iter(ut.ProgressIter(_addition_iter, lbl=addition_lbl,
freq=1, autoadjust=False))
time_list_addition = []
#time_list_reindex = []
addition_count_list = []
tmp_cfgstr_list = []
#for _ in range(80):
# next(addition_iter)
try:
memtrack = ut.MemoryTracker(disable=False)
for count in addition_iter:
aid_list_ = all_randomize_daids_[0:count]
# Request an indexer which could be an augmented version of an existing indexer.
with ut.Timer(verbose=False) as t:
memtrack.report('BEFORE AUGMENT')
nnindexer_ = neighbor_index_cache.request_augmented_ibeis_nnindexer(qreq_, aid_list_)
memtrack.report('AFTER AUGMENT')
nnindexer_list.append(nnindexer_)
addition_count_list.append(count)
time_list_addition.append(t.ellapsed)
tmp_cfgstr_list.append(nnindexer_.cfgstr)
print('===============\n\n')
print(ut.list_str(time_list_addition))
print(ut.list_str(list(map(id, nnindexer_list))))
print(ut.list_str(tmp_cfgstr_list))
print(ut.list_str(list([nnindxer.cfgstr for nnindxer in nnindexer_list])))
IS_SMALL = False
if IS_SMALL:
nnindexer_list = []
reindex_label = 'Reindex'
# go backwards for reindex
_reindex_iter = list(range(initial + 1, max_num, addition_stride))[::-1]
reindex_iter = ut.ProgressIter(_reindex_iter, lbl=reindex_label)
time_list_reindex = []
#time_list_reindex = []
reindex_count_list = []
for count in reindex_iter:
print('\n+===PREDONE====================\n')
# check only a single size for memory leaks
#count = max_num // 16 + ((x % 6) * 1)
#x += 1
aid_list_ = all_randomize_daids_[0:count]
# Call the same code, but force rebuilds
memtrack.report('BEFORE REINDEX')
with ut.Timer(verbose=False) as t:
nnindexer_ = neighbor_index_cache.request_augmented_ibeis_nnindexer(
qreq_, aid_list_, force_rebuild=True, memtrack=memtrack)
memtrack.report('AFTER REINDEX')
ibs.print_cachestats_str()
print('[nnindex.MEMCACHE] size(NEIGHBOR_CACHE) = %s' % (
ut.get_object_size_str(neighbor_index_cache.NEIGHBOR_CACHE.items()),))
print('[nnindex.MEMCACHE] len(NEIGHBOR_CACHE) = %s' % (
len(neighbor_index_cache.NEIGHBOR_CACHE.items()),))
print('[nnindex.MEMCACHE] size(UUID_MAP_CACHE) = %s' % (
ut.get_object_size_str(neighbor_index_cache.UUID_MAP_CACHE),))
print('totalsize(nnindexer) = ' + ut.get_object_size_str(nnindexer_))
memtrack.report_type(neighbor_index_cache.NeighborIndex)
ut.print_object_size_tree(nnindexer_, lbl='nnindexer_')
if IS_SMALL:
nnindexer_list.append(nnindexer_)
reindex_count_list.append(count)
time_list_reindex.append(t.ellapsed)
#import cv2
#import matplotlib as mpl
#print(mem_top.mem_top(limit=30, width=120,
# #exclude_refs=[cv2.__dict__, mpl.__dict__]
# ))
print('L___________________\n\n\n')
print(ut.list_str(time_list_reindex))
if IS_SMALL:
print(ut.list_str(list(map(id, nnindexer_list))))
print(ut.list_str(list([nnindxer.cfgstr for nnindxer in nnindexer_list])))
except KeyboardInterrupt:
print('\n[train] Caught CRTL+C')
resolution = ''
from six.moves import input
while not (resolution.isdigit()):
print('\n[train] What do you want to do?')
print('[train] 0 - Continue')
print('[train] 1 - Embed')
print('[train] ELSE - Stop network training')
resolution = input('[train] Resolution: ')
resolution = int(resolution)
# We have a resolution
if resolution == 0:
print('resuming training...')
elif resolution == 1:
ut.embed()
import plottool as pt
next_fnum = iter(range(0, 1)).next # python3 PY3
pt.figure(fnum=next_fnum())
if len(addition_count_list) > 0:
pt.plot2(addition_count_list, time_list_addition, marker='-o', equal_aspect=False,
x_label='num_annotations', label=addition_lbl + ' Time')
if len(reindex_count_list) > 0:
pt.plot2(reindex_count_list, time_list_reindex, marker='-o', equal_aspect=False,
x_label='num_annotations', label=reindex_label + ' Time')
pt.set_figtitle('Augmented indexer experiment')
pt.legend()
def draw_roc_curve(
fpr,
tpr,
fnum=None,
pnum=None,
marker="-",
target_tpr=None,
target_fpr=None,
thresholds=None,
color=None,
show_operating_point=False,
):
r"""
Args:
fpr (?):
tpr (?):
fnum (int): figure number(default = None)
pnum (tuple): plot number(default = None)
marker (str): (default = '-x')
target_tpr (None): (default = None)
target_fpr (None): (default = None)
thresholds (None): (default = None)
color (None): (default = None)
show_operating_point (bool): (default = False)
CommandLine:
python -m vtool.confusion --exec-draw_roc_curve --show --lightbg
Example:
>>> # DISABLE_DOCTEST
>>> from vtool.confusion import * # NOQA
>>> scores, labels = testdata_scores_labels()
>>> confusions = get_confusion_metrics(scores, labels)
>>> fpr = confusions.fpr
>>> tpr = confusions.tpr
>>> thresholds = confusions.thresholds
>>> fnum = None
>>> pnum = None
>>> marker = '-x'
>>> target_tpr = .85
>>> target_fpr = None
>>> color = None
>>> show_operating_point = True
>>> draw_roc_curve(fpr, tpr, fnum, pnum, marker, target_tpr, target_fpr,
>>> thresholds, color, show_operating_point)
>>> ut.show_if_requested()
"""
import plottool as pt
if fnum is None:
fnum = pt.next_fnum()
if color is None:
color = (0.4, 1.0, 0.4) if pt.is_default_dark_bg() else (0.1, 0.4, 0.4)
roc_auc = sklearn.metrics.auc(fpr, tpr)
title_suffix = ""
if target_fpr is not None:
# func = scipy.interpolate.interp1d(fpr, tpr, kind='linear', assume_sorted=False)
# func = scipy.interpolate.interp1d(xdata, ydata, kind='nearest', assume_sorted=False)
# interp_vals[interp_mask] = func(pt[interp_mask])
target_fpr = np.clip(target_fpr, 0, 1)
interp_tpr = interpolate_replbounds(fpr, tpr, target_fpr)
choice_tpr = interp_tpr
choice_fpr = target_fpr
elif target_tpr is not None:
target_tpr = np.clip(target_tpr, 0, 1)
interp_fpr = interpolate_replbounds(tpr, fpr, target_tpr)
choice_tpr = target_tpr
choice_fpr = interp_fpr
else:
choice_tpr = None
choice_fpr = None
if choice_fpr is not None:
choice_thresh = 0
if thresholds is not None:
try:
index = np.nonzero(tpr >= choice_tpr)[0][0]
except IndexError:
index = len(thresholds) - 1
choice_thresh = thresholds[index]
# percent = ut.scalar_str(choice_tpr * 100).split('.')[0]
# title_suffix = ', FPR%s=%05.2f%%' % (percent, choice_fpr)
title_suffix = ""
if show_operating_point:
title_suffix = ", fpr=%.2f, tpr=%.2f, thresh=%.2f" % (choice_fpr, choice_tpr, choice_thresh)
else:
title_suffix = ""
# if recall_domain is None:
# ave_p = np.nan
# else:
# ave_p = p_interp.sum() / p_interp.size
title = "Receiver operating characteristic\n" + "AUC=%.3f" % (roc_auc,)
title += title_suffix
pt.plot2(
fpr,
tpr,
marker=marker,
x_label="False Positive Rate",
y_label="True Positive Rate",
unitbox=True,
flipx=False,
color=color,
fnum=fnum,
pnum=pnum,
title=title,
)
if False:
# Interp does not work right because of duplicate values
# in xdomain
line_ = np.linspace(0.11, 0.9, 20)
# np.append([np.inf], np.diff(fpr)) > 0
# np.append([np.inf], np.diff(tpr)) > 0
unique_tpr_idxs = np.nonzero(np.append([np.inf], np.diff(tpr)) > 0)[0]
unique_fpr_idxs = np.nonzero(np.append([np.inf], np.diff(fpr)) > 0)[0]
pt.plt.plot(line_, interpolate_replbounds(fpr[unique_fpr_idxs], tpr[unique_fpr_idxs], line_), "b-x")
pt.plt.plot(interpolate_replbounds(tpr[unique_tpr_idxs], fpr[unique_tpr_idxs], line_), line_, "r-x")
if choice_fpr is not None:
pt.plot(choice_fpr, choice_tpr, "o", color=pt.PINK)
def draw_roc_curve(fpr,
tpr,
fnum=None,
pnum=None,
marker='-',
target_tpr=None,
target_fpr=None,
thresholds=None,
color=None,
show_operating_point=False):
r"""
Args:
fpr (?):
tpr (?):
fnum (int): figure number(default = None)
pnum (tuple): plot number(default = None)
marker (str): (default = '-x')
target_tpr (None): (default = None)
target_fpr (None): (default = None)
thresholds (None): (default = None)
color (None): (default = None)
show_operating_point (bool): (default = False)
CommandLine:
python -m vtool.confusion --exec-draw_roc_curve --show --lightbg
Example:
>>> # DISABLE_DOCTEST
>>> from vtool.confusion import * # NOQA
>>> scores, labels = testdata_scores_labels()
>>> confusions = get_confusion_metrics(scores, labels)
>>> fpr = confusions.fpr
>>> tpr = confusions.tpr
>>> thresholds = confusions.thresholds
>>> fnum = None
>>> pnum = None
>>> marker = '-x'
>>> target_tpr = .85
>>> target_fpr = None
>>> color = None
>>> show_operating_point = True
>>> draw_roc_curve(fpr, tpr, fnum, pnum, marker, target_tpr, target_fpr,
>>> thresholds, color, show_operating_point)
>>> ut.show_if_requested()
"""
import plottool as pt
if fnum is None:
fnum = pt.next_fnum()
if color is None:
color = (0.4, 1.0, 0.4) if pt.is_default_dark_bg() else (0.1, 0.4, 0.4)
roc_auc = sklearn.metrics.auc(fpr, tpr)
title_suffix = ''
if target_fpr is not None:
#func = scipy.interpolate.interp1d(fpr, tpr, kind='linear', assume_sorted=False)
#func = scipy.interpolate.interp1d(xdata, ydata, kind='nearest', assume_sorted=False)
#interp_vals[interp_mask] = func(pt[interp_mask])
target_fpr = np.clip(target_fpr, 0, 1)
interp_tpr = interpolate_replbounds(fpr, tpr, target_fpr)
choice_tpr = interp_tpr
choice_fpr = target_fpr
elif target_tpr is not None:
target_tpr = np.clip(target_tpr, 0, 1)
interp_fpr = interpolate_replbounds(tpr, fpr, target_tpr)
choice_tpr = target_tpr
choice_fpr = interp_fpr
else:
choice_tpr = None
choice_fpr = None
if choice_fpr is not None:
choice_thresh = 0
if thresholds is not None:
try:
index = np.nonzero(tpr >= choice_tpr)[0][0]
except IndexError:
index = len(thresholds) - 1
choice_thresh = thresholds[index]
#percent = ut.scalar_str(choice_tpr * 100).split('.')[0]
#title_suffix = ', FPR%s=%05.2f%%' % (percent, choice_fpr)
title_suffix = ''
if show_operating_point:
title_suffix = ', fpr=%.2f, tpr=%.2f, thresh=%.2f' % (
choice_fpr, choice_tpr, choice_thresh)
else:
title_suffix = ''
#if recall_domain is None:
# ave_p = np.nan
#else:
# ave_p = p_interp.sum() / p_interp.size
title = 'Receiver operating characteristic\n' + 'AUC=%.3f' % (roc_auc, )
title += title_suffix
pt.plot2(fpr,
tpr,
marker=marker,
x_label='False Positive Rate',
y_label='True Positive Rate',
unitbox=True,
flipx=False,
color=color,
fnum=fnum,
pnum=pnum,
title=title)
if False:
# Interp does not work right because of duplicate values
# in xdomain
line_ = np.linspace(.11, .9, 20)
#np.append([np.inf], np.diff(fpr)) > 0
#np.append([np.inf], np.diff(tpr)) > 0
unique_tpr_idxs = np.nonzero(np.append([np.inf], np.diff(tpr)) > 0)[0]
unique_fpr_idxs = np.nonzero(np.append([np.inf], np.diff(fpr)) > 0)[0]
pt.plt.plot(
line_,
interpolate_replbounds(fpr[unique_fpr_idxs], tpr[unique_fpr_idxs],
line_), 'b-x')
pt.plt.plot(
interpolate_replbounds(tpr[unique_tpr_idxs], fpr[unique_tpr_idxs],
line_), line_, 'r-x')
if choice_fpr is not None:
pt.plot(choice_fpr, choice_tpr, 'o', color=pt.PINK)
def plotdata(data_list):
count_arr = ut.get_list_column(data_list, 1)
time_arr = ut.get_list_column(data_list, 2)
pt.plot2(count_arr, time_arr, marker='-o', equal_aspect=False,
x_label='num_vectors', y_label='FLANN build time')