Jason S. Kessler JasonKessler

Building tools to help people make sense of large collections of text. Views and software are my own.

JasonKessler / dense_iclr_scattertext_accept_reject.py

Last active March 9, 2018 22:58

	import pandas as pd
	import scattertext as st

	reviews_df = pd.read_csv('https://github.com/JasonKessler/ICLR18ReviewVis/raw/master/iclr2018_reviews.csv.bz2')
	reviews_df['parse'] = reviews_df['review'].apply(st.whitespace_nlp_with_sentences)
	corpus = (st.CorpusFromParsedDocuments(reviews_df, category_col = 'decision', parsed_col = 'parse')
	.build().remove_categories(['Workshop']))
	html = st.produce_scattertext_explorer(corpus,
	category='Accept', not_categories=['Reject'],
	transform = st.Scalers.dense_rank,

JasonKessler / acceptance_vs_polarity_four_square.py

Created March 20, 2018 00:45

	four_square_corpus = (st.CorpusFromParsedDocuments(reviews_df, category_col = 'category', parsed_col = 'parse')
	.build()
	.get_unigram_corpus()
	.compact(st.ClassPercentageCompactor(term_count=1)))
	four_square_axes = st.FourSquareAxes(four_square_corpus,
	left_categories=['Accept, Positive'],
	right_categories=['Accept, Negative'],
	top_categories=['Reject, Positive'],
	bottom_categories=['Reject, Negative'],
	labels = {'a': 'Positive',

JasonKessler / acceptance_vs_polarity_four_square_phrases.py

Created March 20, 2018 01:03

	four_square_corpus_phrases = (st.CorpusFromParsedDocuments(reviews_df, category_col = 'category', parsed_col = 'parse',
	feats_from_spacy_doc=st.PhraseMachinePhrases())
	.build().compact(st.ClassPercentageCompactor(term_count=1)))
	four_square_axes = st.FourSquareAxes(four_square_corpus_phrases,
	left_categories=['Accept, Positive'],
	right_categories=['Accept, Negative'],
	top_categories=['Reject, Positive'],
	bottom_categories=['Reject, Negative'],
	labels = {'a': 'Positive',
	'b': 'Review that was Contrary to Accpetance Decision',