print "Calculating Features"
calcFeatures.calcAuthorsPastPapers(loader)
calcFeatures.calcTopConfsJoursCount(loader)
calcFeatures.computeAverages(loader)
calcFeatures.computeDistances(loader.reviews)
print "Constructing Paper Table"
paperTable = []
for id, paper in loader.papers.iteritems():
maxAuthor = sorted(paper.authors, key=lambda a: len(a.pastPapers))[-1]
maxTopAuthor = sorted(paper.authors, key=lambda a: a.topPastPapers)[-1]
maxKDDAuthor = sorted(paper.authors, key=lambda a: a.topKDDPast)[-1]
numAuthors = len(paper.authors)
affiliation = calcFeatures.getAcademicOrIndustry(paper)
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
calcFeatures.calcAuthorsPastPapers(loader)
calcFeatures.calcTopConfsJoursCount(loader)
calcFeatures.computeAverages(loader)
calcFeatures.computeDistances(loader.reviews)
print "Constructing Paper Table"
paperTable = []
for id, paper in loader.papers.iteritems():
maxAuthor = sorted(paper.authors, key=lambda a: len(a.pastPapers))[-1]
maxTopAuthor = sorted(paper.authors, key=lambda a: a.topPastPapers)[-1]
maxKDDAuthor = sorted(paper.authors, key=lambda a: a.topKDDPast)[-1]
numAuthors = len(paper.authors)
affiliation = calcFeatures.getAcademicOrIndustry(paper)
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,
"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")
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")