def summarize_(corpus: Corpus) -> PartialSummary:
"""
Provides automated input and output summaries for Corpus
"""
table_summary = summarize.dispatch(Table)(corpus)
extras = ((f"<br/><nobr>Tokens: {sum(map(len, corpus.tokens))}, "
f"Types: {len(corpus.dictionary)}</nobr>")
if corpus.has_tokens() else
"<br/><nobr>Corpus is not preprocessed</nobr>")
return PartialSummary(table_summary.summary,
table_summary.details + extras)
def test_corpus_not_preprocessed(self):
"""Check if details part of the summary is formatted correctly"""
corpus = Corpus.from_file("book-excerpts")
n_features = len(corpus.domain.variables) + len(corpus.domain.metas)
details = (
f"<nobr>{len(corpus)} instances, {n_features} variables</nobr><br/>"
f"<nobr>Features: — (no missing values)</nobr><br/>"
f"<nobr>Target: categorical</nobr><br/>"
f"<nobr>Metas: string</nobr><br/>"
f"<nobr>Corpus is not preprocessed</nobr>")
summary = summarize.dispatch(Corpus)(corpus)
self.assertEqual(140, summary.summary)
self.assertEqual(details, summary.details)
def test_corpus_preprocessed(self):
"""Check if details part of the summary is formatted correctly"""
corpus = Corpus.from_file("book-excerpts")
corpus = RegexpTokenizer()(corpus)
n_features = len(corpus.domain.variables) + len(corpus.domain.metas)
details = (
f"<nobr><b><u>book-excerpts</u></b>: "
f"{len(corpus)} instances, {n_features} variables</nobr><br/>"
f"<nobr>Features: — (no missing values)</nobr><br/>"
f"<nobr>Target: categorical</nobr><br/>"
f"<nobr>Metas: string</nobr><br/>"
f"<nobr>Tokens: 128020, Types: 11712</nobr>")
summary = summarize.dispatch(Corpus)(corpus)
self.assertEqual(140, summary.summary)
self.assertEqual(details, summary.details)