explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-31 16:07:41 +03:00
Code Issues Packages Projects Releases Wiki Activity

cleanup + reword

Browse Source
This commit is contained in:
Peter Baumgartner 2022-09-08 11:57:15 -04:00
parent c09d99a069
commit 5c3337b81b
1 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
spacy/cli/debug_data.py
View File

@ -676,17 +676,19 @@ def debug_data(
trees_train: Set[str] = gold_train_data["lemmatizer_trees"] trees_train: Set[str] = gold_train_data["lemmatizer_trees"]
trees_dev: Set[str] = gold_dev_data["lemmatizer_trees"] trees_dev: Set[str] = gold_dev_data["lemmatizer_trees"]
# This is necessary context if someone is attempting to interpret whether the # This is necessary context when someone is attempting to interpret whether the
# number of trees exclusively in the dev set is meaningful. # number of trees exclusively in the dev set is meaningful.
msg.info(f"{len(trees_train)} lemmatizer trees generated from training data.") msg.info(f"{len(trees_train)} lemmatizer trees generated from training data.")
msg.info(f"{len(trees_dev)} lemmatizer trees generated from dev data.") msg.info(f"{len(trees_dev)} lemmatizer trees generated from dev data.")
dev_not_train = trees_dev - trees_train dev_not_train = trees_dev - trees_train
if len(dev_not_train) != 0: if len(dev_not_train) != 0:
msg.warn( msg.warn(
f"{len(dev_not_train)} lemmatizer trees were found exclusively in the dev data." f"{len(dev_not_train)} lemmatizer trees were found exclusively in the dev data."
) )
else: else:
# Would we ever expect this case? It seems like it would be pretty rare. # Would we ever expect this case? It seems like it would be pretty rare,
# and we might actually want a warning?
msg.good("All trees in dev data present in training data.") msg.good("All trees in dev data present in training data.")
if gold_train_data["n_low_cardinality_lemmas"] > 0: if gold_train_data["n_low_cardinality_lemmas"] > 0:
@ -694,14 +696,14 @@ def debug_data(
f"{gold_train_data['n_low_cardinality_lemmas']} docs with 1 or 0 unique lemmas." f"{gold_train_data['n_low_cardinality_lemmas']} docs with 1 or 0 unique lemmas."
) )
else: else:
msg.good("Training docs have sufficient unique lemmas") msg.good("All training docs meet lemma uniqueness requirements.")
if gold_train_data["n_low_cardinality_lemmas"] > 0: if gold_train_data["n_low_cardinality_lemmas"] > 0:
msg.warn( msg.warn(
f"{gold_dev_data['n_low_cardinality_lemmas']} docs with 1 or 0 unique lemmas." f"{gold_dev_data['n_low_cardinality_lemmas']} docs with 1 or 0 unique lemmas."
) )
else: else:
msg.good("Dev docs have sufficient unique lemmas") msg.good("All dev docs meet lemma uniqueness requirements.")
msg.divider("Summary") msg.divider("Summary")
good_counts = msg.counts[MESSAGES.GOOD] good_counts = msg.counts[MESSAGES.GOOD]