def test_debug_data_compile_gold():
nlp = English()
pred = Doc(nlp.vocab, words=["Token", ".", "New", "York", "City"])
ref = Doc(
nlp.vocab,
words=["Token", ".", "New York City"],
sent_starts=[True, False, True],
ents=["O", "O", "B-ENT"],
)
eg = Example(pred, ref)
data = _compile_gold([eg], ["ner"], nlp, True)
assert data["boundary_cross_ents"] == 0
pred = Doc(nlp.vocab, words=["Token", ".", "New", "York", "City"])
ref = Doc(
nlp.vocab,
words=["Token", ".", "New York City"],
sent_starts=[True, False, True],
ents=["O", "B-ENT", "I-ENT"],
)
eg = Example(pred, ref)
data = _compile_gold([eg], ["ner"], nlp, True)
assert data["boundary_cross_ents"] == 1
def test_ensure_print_span_characteristics_wont_fail():
"""Test if interface between two methods aren't destroyed if refactored"""
nlp = English()
spans_key = "sc"
pred = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
pred.spans[spans_key] = [Span(pred, 3, 6, "ORG"), Span(pred, 5, 6, "GPE")]
ref = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
ref.spans[spans_key] = [Span(ref, 3, 6, "ORG"), Span(ref, 5, 6, "GPE")]
eg = Example(pred, ref)
examples = [eg]
data = _compile_gold(examples, ["spancat"], nlp, True)
span_characteristics = _get_span_characteristics(
examples=examples, compiled_gold=data, spans_key=spans_key
)
_print_span_characteristics(span_characteristics)
def test_get_span_characteristics_return_value():
nlp = English()
spans_key = "sc"
pred = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
pred.spans[spans_key] = [Span(pred, 3, 6, "ORG"), Span(pred, 5, 6, "GPE")]
ref = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
ref.spans[spans_key] = [Span(ref, 3, 6, "ORG"), Span(ref, 5, 6, "GPE")]
eg = Example(pred, ref)
examples = [eg]
data = _compile_gold(examples, ["spancat"], nlp, True)
span_characteristics = _get_span_characteristics(
examples=examples, compiled_gold=data, spans_key=spans_key
)
assert {"sd", "bd", "lengths"}.issubset(span_characteristics.keys())
assert span_characteristics["min_length"] == 1
assert span_characteristics["max_length"] == 3
def test_debug_data_compile_gold_for_spans():
nlp = English()
spans_key = "sc"
pred = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
pred.spans[spans_key] = [Span(pred, 3, 6, "ORG"), Span(pred, 5, 6, "GPE")]
ref = Doc(nlp.vocab, words=["Welcome", "to", "the", "Bank", "of", "China", "."])
ref.spans[spans_key] = [Span(ref, 3, 6, "ORG"), Span(ref, 5, 6, "GPE")]
eg = Example(pred, ref)
data = _compile_gold([eg], ["spancat"], nlp, True)
assert data["spancat"][spans_key] == Counter({"ORG": 1, "GPE": 1})
assert data["spans_length"][spans_key] == {"ORG": [3], "GPE": [1]}
assert data["spans_per_type"][spans_key] == {
"ORG": [Span(ref, 3, 6, "ORG")],
"GPE": [Span(ref, 5, 6, "GPE")],
}
assert data["sb_per_type"][spans_key] == {
"ORG": {"start": [ref[2:3]], "end": [ref[6:7]]},
"GPE": {"start": [ref[4:5]], "end": [ref[6:7]]},
}