explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Feat/debug data warn spread ents (#9960)

Browse Source 
* added check for crossing boundaries

* formatted blacked

* Rephrasing slightly

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
This commit is contained in:
Duygu Altinok 2022-01-04 18:22:10 +01:00 committed by GitHub
parent 56dcb39fb7
commit 55cf492218
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy/cli/debug_data.py
View File

@ -203,6 +203,7 @@ def debug_data(
has_low_data_warning = False
has_no_neg_warning = False
has_ws_ents_error = False
has_boundary_cross_ents_warning = False
msg.divider("Named Entity Recognition")
msg.info(f"{len(model_labels)} label(s)")
@ -242,12 +243,20 @@ def debug_data(
msg.warn(f"No examples for texts WITHOUT new label '{label}'")
has_no_neg_warning = True
if gold_train_data["boundary_cross_ents"]:
msg.warn(
f"{gold_train_data['boundary_cross_ents']} entity span(s) crossing sentence boundaries"
)
has_boundary_cross_ents_warning = True
if not has_low_data_warning:
msg.good("Good amount of examples for all labels")
if not has_no_neg_warning:
msg.good("Examples without occurrences available for all labels")
if not has_ws_ents_error:
msg.good("No entities consisting of or starting/ending with whitespace")
if not has_boundary_cross_ents_warning:
msg.good("No entities crossing sentence boundaries")
if has_low_data_warning:
msg.text(
@ -565,6 +574,7 @@ def _compile_gold(
"words": Counter(),
"roots": Counter(),
"ws_ents": 0,
"boundary_cross_ents": 0,
"n_words": 0,
"n_misaligned_words": 0,
"words_missing_vectors": Counter(),
@ -602,6 +612,8 @@ def _compile_gold(
if label.startswith(("B-", "U-")):
combined_label = label.split("-")[1]
data["ner"][combined_label] += 1
if gold[i].is_sent_start and label.startswith(("I-", "L-")):
data["boundary_cross_ents"] += 1
elif label == "-":
data["ner"]["-"] += 1
if "textcat" in factory_names or "textcat_multilabel" in factory_names: