def augmentation_evaluation(df_train, df_test, policy, p=None):
tfs = [
TransformationFunction.change_addr,
TransformationFunction.change_business,
TransformationFunction.change_o,
TransformationFunction.randomly_delete,
TransformationFunction.randomly_add
]
if policy == "random":
random_policy = RandomPolicy(len(tfs),
sequence_length=2,
n_per_original=2,
keep_original=True)
tf_applier = PandasTFApplier(tfs, random_policy)
df_train_augmented = tf_applier.apply(df_train)
Y_train_augmented = df_train_augmented["label"].values
print(f"Original training set size: {len(df_train)}")
print(f"Augmented training set size: {len(df_train_augmented)}")
return df_train_augmented, Y_train_augmented
if policy == "mean":
if p is None:
p = [0.1, 0.1, 0.1, 0.35, 0.35]
mean_field_policy = MeanFieldPolicy(
len(tfs),
sequence_length=
2, # how many TFs to apply uniformly at random per data point
n_per_original=
2, # how many augmented data points to generate per original data point
keep_original=True,
p=p, # specify a sampling distribution for the TFs
)
tf_applier = PandasTFApplier(tfs, mean_field_policy)
df_train_augmented = tf_applier.apply(df_train)
Y_train_augmented = df_train_augmented["label"].values
print(f"Original training set size: {len(df_train)}")
print(f"Augmented training set size: {len(df_train_augmented)}")
return df_train_augmented, Y_train_augmented
# In some cases, we can do better than uniform random sampling.
# We might have domain knowledge that some TFs should be applied more frequently than others,
# or have trained an [automated data augmentation model](https://snorkel.org/tanda/)
# that learned a sampling distribution for the TFs.
# Snorkel supports this use case with a
# [`MeanFieldPolicy`](https://snorkel.readthedocs.io/en/master/packages/_autosummary/augmentation/snorkel.augmentation.MeanFieldPolicy.html),
# which allows you to specify a sampling distribution for the TFs.
# We give higher probabilities to the `replace_[X]_with_synonym` TFs, since those provide more information to the model.
# %%
from snorkel.augmentation import MeanFieldPolicy
mean_field_policy = MeanFieldPolicy(
len(tfs),
sequence_length=2,
n_per_original=2,
keep_original=True,
p=[0.05, 0.05, 0.3, 0.3, 0.3],
)
# %% [markdown]
# To apply one or more TFs that we've written to a collection of data points according to our policy, we use a
# [`PandasTFApplier`](https://snorkel.readthedocs.io/en/master/packages/_autosummary/augmentation/snorkel.augmentation.PandasTFApplier.html)
# because our data points are represented with a Pandas DataFrame.
# %% {"tags": ["md-exclude-output"]}
from snorkel.augmentation import PandasTFApplier
tf_applier = PandasTFApplier(tfs, mean_field_policy)
df_train_augmented = tf_applier.apply(df_train)
Y_train_augmented = df_train_augmented["label"].values
def test_mean_field_policy(self):
policy = MeanFieldPolicy(2, sequence_length=2, p=[1, 0])
n_samples = 100
samples = [policy.generate() for _ in range(n_samples)]
self.assertEqual(samples.count([0, 0]), n_samples)