Skip to content

armgit / dspy

Public Imported from GitHub
0

DSPy: The framework for programming—not prompting—language models

Python

minor fix on dataset (#1868)

Chen Qiane2e84ee2ae36
diff --git a/dspy/datasets/dataset.py b/dspy/datasets/dataset.py
index c420f1908..0c2b3ce7e 100644
--- a/dspy/datasets/dataset.py
+++ b/dspy/datasets/dataset.py
@@ -20,49 +20,44 @@ class Dataset:
self.name = self.__class__.__name__
def reset_seeds(self, train_seed=None, train_size=None, eval_seed=None, dev_size=None, test_size=None):
- self.train_size = train_size if train_size is not None else self.train_size
- self.train_seed = train_seed if train_seed is not None else self.train_seed
- self.dev_size = dev_size if dev_size is not None else self.dev_size
- self.dev_seed = eval_seed if eval_seed is not None else self.dev_seed
- self.test_size = test_size if test_size is not None else self.test_size
- self.test_seed = eval_seed if eval_seed is not None else self.test_seed
-
- if hasattr(self, '_train_'):
+ self.train_size = train_size or self.train_size
+ self.train_seed = train_seed or self.train_seed
+ self.dev_size = dev_size or self.dev_size
+ self.dev_seed = eval_seed or self.dev_seed
+ self.test_size = test_size or self.test_size
+ self.test_seed = eval_seed or self.test_seed
+
+ if hasattr(self, "_train_"):
del self._train_
-
- if hasattr(self, '_dev_'):
+
+ if hasattr(self, "_dev_"):
del self._dev_
-
- if hasattr(self, '_test_'):
+
+ if hasattr(self, "_test_"):
del self._test_
@property
def train(self):
- if not hasattr(self, '_train_'):
- self._train_ = self._shuffle_and_sample('train', self._train, self.train_size, self.train_seed)
+ if not hasattr(self, "_train_"):
+ self._train_ = self._shuffle_and_sample("train", self._train, self.train_size, self.train_seed)
return self._train_
@property
def dev(self):
- if not hasattr(self, '_dev_'):
- self._dev_ = self._shuffle_and_sample('dev', self._dev, self.dev_size, self.dev_seed)
+ if not hasattr(self, "_dev_"):
+ self._dev_ = self._shuffle_and_sample("dev", self._dev, self.dev_size, self.dev_seed)
return self._dev_
-
+
@property
def test(self):
- if not hasattr(self, '_test_'):
- self._test_ = self._shuffle_and_sample('test', self._test, self.test_size, self.test_seed)
+ if not hasattr(self, "_test_"):
+ self._test_ = self._shuffle_and_sample("test", self._test, self.test_size, self.test_seed)
return self._test_
def _shuffle_and_sample(self, split, data, size, seed=0):
- '''
- The setting (seed=s, size=N) is always a subset
- of the setting (seed=s, size=M) for N < M.
- '''
-
data = list(data)
# Shuffle the data irrespective of the requested size.
@@ -84,15 +79,18 @@ class Dataset:
# a uuid field that would respect this in some way. This means that we need a more refined concept that
# uuid (each example is unique) and more like a group_uuid.
- # rng = random.Random(seed)
- # rng.shuffle(data)
-
return output
-
+
@classmethod
- def prepare_by_seed(cls, train_seeds=[1,2,3,4,5], train_size=16, dev_size=1000,
- divide_eval_per_seed=True, eval_seed=2023, **kwargs):
-
+ def prepare_by_seed(
+ cls,
+ train_seeds=[1, 2, 3, 4, 5],
+ train_size=16,
+ dev_size=1000,
+ divide_eval_per_seed=True,
+ eval_seed=2023,
+ **kwargs,
+ ):
data_args = dotdict(train_size=train_size, eval_seed=eval_seed, dev_size=dev_size, test_size=0, **kwargs)
dataset = cls(**data_args)
@@ -106,12 +104,12 @@ class Dataset:
data_args.train_seed = train_seed
dataset.reset_seeds(**data_args)
- eval_sets.append(eval_set[eval_offset:eval_offset+examples_per_seed])
+ eval_sets.append(eval_set[eval_offset : eval_offset + examples_per_seed])
train_sets.append(dataset.train)
assert len(eval_sets[-1]) == examples_per_seed, len(eval_sets[-1])
assert len(train_sets[-1]) == train_size, len(train_sets[-1])
-
+
if divide_eval_per_seed:
eval_offset += examples_per_seed