def confusion_matrix_2017_new(y_true, y_pred, labels=None, sample_weight=None):
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)
if labels is None:
labels = unique_labels(y_true, y_pred)
else:
labels = np.asarray(labels)
if np.all([l not in y_true for l in labels]):
raise ValueError("At least one label specified must be in y_true")
if sample_weight is None:
sample_weight = np.ones(y_true.shape[0], dtype=np.int64)
else:
sample_weight = np.asarray(sample_weight)
check_consistent_length(sample_weight, y_true, y_pred)
n_labels = labels.size
# If labels are not consecitive integers starting from zero, then
# yt, yp must be converted into index form
need_index_conversion = not (
labels.dtype.kind in {'i', 'u', 'b'} and
labels.min() == 0 and np.all(np.diff(labels) == 1) and
y_true.min() >= 0 and y_pred.min() >= 0
)
if need_index_conversion:
label_to_ind = dict((y, x) for x, y in enumerate(labels))
y_pred = np.array([label_to_ind.get(x, n_labels + 1) for x in y_pred])
y_true = np.array([label_to_ind.get(x, n_labels + 1) for x in y_true])
# eliminate items in y_true, y_pred not in labels
isvalid = np.logical_and(y_pred < n_labels, y_true < n_labels)
if not np.all(isvalid):
y_pred = y_pred[isvalid]
y_true = y_true[isvalid]
# also eliminate weights of eliminated items
sample_weight = sample_weight[isvalid]
# Choose the accumulator dtype to always have high precision
if sample_weight.dtype.kind in {'i', 'u', 'b'}:
dtype = np.int64
else:
dtype = np.float64
CM = coo_matrix((sample_weight, (y_true, y_pred)),
shape=(n_labels, n_labels), dtype=dtype,
).toarray()
return CM
def quick_cm(y_true, y_pred, labels, sample_weight):
n_labels = len(labels)
C = coo_matrix(
(sample_weight, (y_true, y_pred)), shape=(n_labels, n_labels)
).toarray()
return C
def confusion_matrix_2021(y_true, y_pred, *, labels=None, sample_weight=None,
normalize=None):
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)
if labels is None:
labels = unique_labels(y_true, y_pred)
else:
labels = np.asarray(labels)
n_labels = labels.size
if n_labels == 0:
raise ValueError("'labels' should contains at least one label.")
elif y_true.size == 0:
return np.zeros((n_labels, n_labels), dtype=int)
elif np.all([l not in y_true for l in labels]):
raise ValueError("At least one label specified must be in y_true")
if sample_weight is None:
sample_weight = np.ones(y_true.shape[0], dtype=np.int64)
else:
sample_weight = np.asarray(sample_weight)
check_consistent_length(y_true, y_pred, sample_weight)
if normalize not in ['true', 'pred', 'all', None]:
raise ValueError("normalize must be one of {'true', 'pred', "
"'all', None}")
n_labels = labels.size
label_to_ind = {y: x for x, y in enumerate(labels)}
# convert yt, yp into index
y_pred = np.array([label_to_ind.get(x, n_labels + 1) for x in y_pred])
y_true = np.array([label_to_ind.get(x, n_labels + 1) for x in y_true])
# intersect y_pred, y_true with labels, eliminate items not in labels
ind = np.logical_and(y_pred < n_labels, y_true < n_labels)
y_pred = y_pred[ind]
y_true = y_true[ind]
# also eliminate weights of eliminated items
sample_weight = sample_weight[ind]
# Choose the accumulator dtype to always have high precision
if sample_weight.dtype.kind in {'i', 'u', 'b'}:
dtype = np.int64
else:
dtype = np.float64
cm = coo_matrix((sample_weight, (y_true, y_pred)),
shape=(n_labels, n_labels), dtype=dtype,
).toarray()
with np.errstate(all='ignore'):
if normalize == 'true':
cm = cm / cm.sum(axis=1, keepdims=True)
elif normalize == 'pred':
cm = cm / cm.sum(axis=0, keepdims=True)
elif normalize == 'all':
cm = cm / cm.sum()
cm = np.nan_to_num(cm)
return cm
def mwe_check_sample_weight():
import ubelt as ub
from sklearn.utils.validation import _check_sample_weight
import numpy as np
results = []
ns = np.logspace(1, 6, 100).astype(np.int)
for n in ub.ProgIter(ns, desc='time-tradeoff', verbose=3):
print('n = {!r}'.format(n))
y_true = np.random.randint(0, 100, n).astype(np.int64)
y_pred = np.random.randint(0, 100, n).astype(np.int64)
sample_weight = np.random.rand(n)
import timerit
ti = timerit.Timerit(9, bestof=3, verbose=2)
for timer in ti.reset('old-sample-weight-given'):
with timer:
np.asarray(sample_weight)
results.append({
'n': n,
'label': ti.label,
'time': ti.mean(),
})
for timer in ti.reset('new-sample-weight-given'):
with timer:
_check_sample_weight(sample_weight, y_true, dtype=np.int64)
results.append({
'n': n,
'label': ti.label,
'time': ti.mean(),
})
for timer in ti.reset('old-sample-weight-default'):
with timer:
np.ones(y_true.shape[0], dtype=np.int64)
results.append({
'n': n,
'label': ti.label,
'time': ti.mean(),
})
for timer in ti.reset('new-sample-weight-default'):
with timer:
_check_sample_weight(None, y_true, dtype=np.int64)
results.append({
'n': n,
'label': ti.label,
'time': ti.mean(),
})
import pandas as pd
df = pd.DataFrame(results)
import kwplot
import seaborn as sns
kwplot.autoplt()
sns.set()
ax = sns.lineplot(data=df, x='n', y='time', hue='label')
ax.set_yscale('log')
ax.set_xscale('log')
from sklearn.utils.validation import _check_sample_weight
import numpy as np
results = []
ns = np.logspace(1, 6, 100).astype(np.int)
for n in ub.ProgIter(ns, desc='time-tradeoff', verbose=3):
print('n = {!r}'.format(n))
n_labels = 100
y_true = np.random.randint(0, n_labels, n).astype(np.int64)
y_pred = np.random.randint(0, n_labels, n).astype(np.int64)
sample_weight = np.ones(y_true.shape[0], dtype=np.int64)
for timer in ti.reset('use-old-uint8-sample-weight-default'):
with timer:
if sample_weight.dtype.kind in {'i', 'u', 'b'}:
dtype = np.int64
else:
dtype = np.float64
cm = coo_matrix((sample_weight, (y_true, y_pred)),
shape=(n_labels, n_labels), dtype=dtype,
).toarray()
results.append({
'n': n,
'label': ti.label,
'time': ti.mean(),
})
sample_weight = _check_sample_weight(None, y_true, dtype=np.int64)
for timer in ti.reset('use-new-float64-sample-weight-default'):
with timer:
if sample_weight.dtype.kind in {'i', 'u', 'b'}:
dtype = np.int64
else:
dtype = np.float64
cm = coo_matrix((sample_weight, (y_true, y_pred)),
shape=(n_labels, n_labels), dtype=dtype,
).toarray()
results.append({
'n': n,
'label': ti.label,
'time': ti.mean(),
})
import pandas as pd
df = pd.DataFrame(results)
import kwplot
import seaborn as sns
kwplot.autoplt()
sns.set()
ax = sns.lineplot(data=df, x='n', y='time', hue='label')
ax.set_yscale('log')
ax.set_xscale('log')