d04904cdd1df7afba9859868f4e487d3a2332070,demo_semiotic.py,,,#,6

Before Change

import scattertext as st

newsgroups_train = fetch_20newsgroups(subset="train", remove=("headers", "footers", "quotes"))

vectorizer = TfidfVectorizer()
tfidf_X = vectorizer.fit_transform(newsgroups_train.data)

corpus = st.CorpusFromScikit(
	X=CountVectorizer(vocabulary=vectorizer.vocabulary_).fit_transform(newsgroups_train.data),
	y=newsgroups_train.target,
	feature_vocabulary=vectorizer.vocabulary_,
	category_names=newsgroups_train.target_names,
	raw_texts=newsgroups_train.data
).build()

semiotic_square = st.SemioticSquare(
	corpus,
	category_a="alt.atheism",

After Change

movie_df = st.SampleCorpora.RottenTomatoes.get_data()

corpus = st.CorpusFromPandas(
	movie_df,
	category_col="category",
	text_col="text",
	nlp=st.whitespace_nlp_with_sentences
).build().get_unigram_corpus()

semiotic_square = st.SemioticSquare(
	corpus,
	category_a="fresh",

Instances