moreo
/
QuaPy
1
0
Fork 1
Code Issues Pull Requests Releases Wiki Activity

copying a modification from devel

This commit is contained in:
Alejandro Moreo Fernandez 2024-02-28 08:49:19 +01:00
parent 3932cf22ce
commit 29eaa54d82
1 changed files with 7 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
quapy/data/base.py
View File

@ -108,8 +108,7 @@ class LabelledCollection:
"""
Returns an index to be used to extract a random sample of desired size and desired prevalence values. If the
prevalence values are not specified, then returns the index of a uniform sampling.
For each class, the sampling is drawn with replacement if the requested prevalence is larger than
the actual prevalence of the class, or without replacement otherwise.
For each class, the sampling is drawn with replacement.
:param size: integer, the requested size
:param prevs: the prevalence for each class; the prevalence value for the last class can be lead empty since
@ -153,7 +152,7 @@ class LabelledCollection:
for class_, n_requested in n_requests.items():
n_candidates = len(self.index[class_])
index_sample = self.index[class_][
np.random.choice(n_candidates, size=n_requested, replace=(n_requested > n_candidates))
np.random.choice(n_candidates, size=n_requested, replace=True)
] if n_requested > 0 else []
indexes_sample.append(index_sample)
@ -168,8 +167,7 @@ class LabelledCollection:
def uniform_sampling_index(self, size, random_state=None):
"""
Returns an index to be used to extract a uniform sample of desired size. The sampling is drawn
with replacement if the requested size is greater than the number of instances, or without replacement
otherwise.
with replacement.
:param size: integer, the size of the uniform sample
:param random_state: if specified, guarantees reproducibility of the split.
@ -179,13 +177,12 @@ class LabelledCollection:
ng = RandomState(seed=random_state)
else:
ng = np.random
return ng.choice(len(self), size, replace=size > len(self))
return ng.choice(len(self), size, replace=True)
def sampling(self, size, *prevs, shuffle=True, random_state=None):
"""
Return a random sample (an instance of :class:`LabelledCollection`) of desired size and desired prevalence
values. For each class, the sampling is drawn without replacement if the requested prevalence is larger than
the actual prevalence of the class, or with replacement otherwise.
values. For each class, the sampling is drawn with replacement.
:param size: integer, the requested size
:param prevs: the prevalence for each class; the prevalence value for the last class can be lead empty since
@ -202,8 +199,7 @@ class LabelledCollection:
def uniform_sampling(self, size, random_state=None):
"""
Returns a uniform sample (an instance of :class:`LabelledCollection`) of desired size. The sampling is drawn
with replacement if the requested size is greater than the number of instances, or without replacement
otherwise.
with replacement.
:param size: integer, the requested size
:param random_state: if specified, guarantees reproducibility of the split.
@ -236,24 +232,11 @@ class LabelledCollection:
:return: two instances of :class:`LabelledCollection`, the first one with `train_prop` elements, and the
second one with `1-train_prop` elements
"""
instances = self.instances
labels = self.labels
remainder = None
for idx in np.argwhere(self.counts()==1):
class_with_1 = self.classes_[idx.item()]
if remainder is None:
remainder = LabelledCollection(instances[labels==class_with_1], [class_with_1], classes=self.classes_)
else:
remainder += LabelledCollection(instances[labels==class_with_1], [class_with_1], classes=self.classes_)
instances = instances[labels!=class_with_1]
labels = labels[labels!=class_with_1]
tr_docs, te_docs, tr_labels, te_labels = train_test_split(
instances, labels, train_size=train_prop, stratify=labels, random_state=random_state
self.instances, self.labels, train_size=train_prop, stratify=self.labels, random_state=random_state
)
training = LabelledCollection(tr_docs, tr_labels, classes=self.classes_)
test = LabelledCollection(te_docs, te_labels, classes=self.classes_)
if remainder is not None:
training += remainder
return training, test
def split_random(self, train_prop=0.6, random_state=None):