JasonKessler

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',

JasonKessler

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

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

reviews_df = pd.read_csv('https://github.com/JasonKessler/ICLR18ReviewVis/raw/master/iclr2018_reviews.csv.bz2')
reviews_df['parse'] = reviews_df['review'].apply(spacy.load('en', parser=False))

# Create Corpus based on accept/reject/workshop decision
full_corpus = st.CorpusFromParsedDocuments(
          reviews_df, category_col='decision', parsed_col='parse').build()

# A two-category corpus to use for plotting, with unigrams which only occur in bigrams removed.
# Terms used in <5 documents are removed as well.
corpus = st.CompactTerms(full_corpus.remove_categories(['Workshop']), 

JasonKessler

reviews_df = pd.read_csv('https://github.com/JasonKessler/ICLR18ReviewVis/raw/master/iclr2018_reviews.csv.bz2')
reviews_df['parse'] = reviews_df['review'].apply(spacy.load('en', parser=False))
full_corpus = st.CorpusFromParsedDocuments(reviews_df, category_col='decision', parsed_col='parse').build()
corpus = full_corpus.remove_categories(['Workshop'])
priors = (st.PriorFactory(full_corpus, term_ranker=st.OncePerDocFrequencyRanker)
          .use_all_categories().align_to_target(corpus).get_priors())
html = st.produce_frequency_explorer(
  corpus, 
  category='Accept', 
  not_categories=['Reject'],

JasonKessler

import bisect
class ECDFPurePy(object):
    '''
    ECDF with linear interpolation
    '''
    def __init__(self, raw_list, min_possible, max_possible, resolution=1000):
        '''
        raw: sorted list or generator of numbers
        '''
        self.resolution_ = resolution

JasonKessler

import pandas as pd
import scattertext as st
import spacy

reviews_df = pd.read_csv('https://github.com/JasonKessler/ICLR18ReviewVis/raw/master/iclr2018_reviews.csv.bz2')
reviews_df['parse'] = reviews_df['review'].apply(spacy.load('en'))
corpus = (st.CorpusFromParsedDocuments(reviews_df, category_col = 'rating_bin', parsed_col = 'parse')
          .build().remove_categories(['Neutral']))
html = st.produce_scattertext_explorer(corpus, 
                                       category='Positive', not_categories=['Negative'],

JasonKessler

title,authors,decision_raw,forum,confidence,rating,review
Improving Discriminator-Generator Balance in Generative Adversarial Networks,['Simen Selseng and Björn Gambäck'],Reject,SyBPtQfAZ,4: The reviewer is confident but not absolutely certain that the evaluation is correct,3: Clear rejection,"The paper proposes a variety of modifications to improve GAN training and evaluates them using a variant of the Generative Adversarial Metric.

The first proposed approach, Static Reusable Noise, proposes sampling a fixed set of latent noise vectors instead of producing them via online sampling. It is motivated by the observation that the generator encounters different noise samples at each iteration of training while for real data the discriminator sees only a fixed number of samples. This does not seem to be a particularly convincing argument. One could argue likewise that this makes the discriminator's job easier as it only has to track the finite amount of samples the generator can produce instead of the full distri

JasonKessler

url = 'https://openreview.net/notes?invitation=ICLR.cc%2F2018%2FConference%2F-%2FBlind_Submission&offset=0&limit=1000'
df = pd.DataFrame(requests.get(url).json()['notes']) # Each row in this data frame is a paper.
forum_content = []
for i, forum_id in list(enumerate(df.forum)): # Each forum_id is a review, comment, or acceptance decision about a paper.
  forum_content.append(requests.get('https://openreview.net/notes?forum={}&trash=true'.format(forum_id)).json())
  time.sleep(.3)
df['forumContent'] = pd.Series(forum_content)

df['title'] = df.content.apply(lambda x: x['title'])
df['authors'] = df.content.apply(lambda x: x['authors'])

JasonKessler

url = 'https://openreview.net/notes?invitation=ICLR.cc%2F2018%2FConference%2F-%2FBlind_Submission&offset=0&limit=1000'
df = pd.DataFrame(requests.get(url).json()['notes']) # Each row in this data frame is a paper.
forum_content = []
for i, forum_id in list(enumerate(df.forum)): # Each forum_id is a review, comment, or acceptance decision about a paper.
  forum_content.append(requests.get('https://openreview.net/notes?forum={}&trash=true'.format(forum_id)).json())
  time.sleep(.3)
df['forumContent'] = pd.Series(forum_content)