distStats = calcFeatures.getPaperDistStats(paper)
simStats = calcFeatures.getSimStats(paper, tfidf)
paperTable.append({
"paperId":
paper.id,
###true values
"avgRating":
paper.avgRating,
"accepted":
paper.accepted,
###nationalities of authors
"modeAuthorCountry":
calcFeatures.getAuthorCountryMode(paper),
"maxAuthorCountry":
maxAuthor.country,
"primaryAuthorCountry":
paper.primaryAuthor.country,
###affiliation of team of authors
"isIndustry":
int(affiliation == 'industry'),
"isAcademic":
int(affiliation == 'academic'),
"isMixed":
int(affiliation == 'mixed'),
###past paper counts of authors
"avgPaperCount":
"accepted": paper.accepted,
"reviewerAverage": reviewer.avgRating,
"paperAverage": paper.avgRating,
"reviewerRatingDiff": review.overallRating - reviewer.avgRating,
"paperRatingDiff": review.overallRating - paper.avgRating,
"paperId": paper.id,
"userId": reviewer.id,
"reviewLength": len(
("%s %s %s" % (
review.ratings["strengths"],
review.ratings["weaknesses"],
review.ratings["comments"])).split()),
"externalReviewer": review.externalReviewer,
"reviewerCountry": reviewer.country,
"authorCountryMode": calcFeatures.getAuthorCountryMode(paper),
"primaryAuthorCountry": paper.primaryAuthor.country,
"reviewerIsAcademic": reviewer.isAcademic,
"paperAcademicOrIndustry": calcFeatures.getAcademicOrIndustry(paper),
"maxAuthorIsAcademic": paper.maxAuthor.isAcademic,
}
ratingTable.append(ratingStats)
if id % 100 == 0 and id > 0:
print id
DataFrame(ratingTable).to_pickle("savedFrames/ratingPrediction/ratingTable")
