fix typos & add result.txt

assignment.py

@@ -12,7 +12,7 @@ amazonInputRDD = sc.textFile("datafiles/amazon-ratings.txt")
 nobelRDD = sc.textFile("datafiles/prize.json")
 
 ## The following converts the amazonInputRDD into 2-tuples with integers
-amazonBipartiteRDD = amazonInputRDD.map(lambda x: x.split(" ")).map(lambda x: (x[1], x[2]))
+amazonBipartiteRDD = amazonInputRDD.map(lambda x: x.split(" ")).map(lambda x: (x[0], x[1]))
 
 
 ### Task 1

functions.py

@@ -18,13 +18,13 @@ def task2_flatmap(x):
 def task3(nobelRDD):
         return dummyrdd
 
-def task4(logsRDD, l):
+def task4(logsRDD):
         return dummyrdd
 
 def task5(bipartiteGraphRDD):
         return dummyrdd
 
-def task6(logsRDD, day1, day2):
+def task6(logsRDD, time1, time2):
         return dummyrdd
 
 

results.txt

+=========================== Task 1
+(u"'Nay,'", u"'Nay,' said I, 'a good wit:' 'Just,' said she, 'it", 10)
+(u"'Tis", u"'Tis almost five o'clock, cousin; tis time you were", 9)
+(u"'Tis", u"'Tis even so. Hero and Margaret have by this", 9)
+(u"'Tis", u"'Tis no such matter. Then you do not love me?", 10)
+(u"'Tis", u"'Tis true, indeed; so your daughter says: 'Shall", 8)
+(u"'Tis", u"'Tis very true.", 3)
+(u"'Tis", u"'Tis well consented: presently away;", 5)
+(u"'twas", u"'twas not so, but, indeed, God forbid it should be", 10)
+(u'*ANTONIO*', u'*ANTONIO*', 1)
+(u'*ANTONIO*', u'*ANTONIO*', 1)
+=========================== Task 2
+[u'', u'Ahtisaari', u'Akasaki', u'Alexievich', u'Amano', u'Aumann', u'Axel', u'Barr\xe9-Sinoussi', u'Betzig', u'Beutler']
+=========================== Task 3
+(u'2004', [u'Gross', u'Politzer', u'Wilczek', u'Ciechanover', u'Hershko', u'Rose', u'Axel', u'Buck', u'Jelinek', u'Maathai', u'Kydland', u'Prescott'])
+(u'2005', [u'Glauber', u'Hall', u'H\xe4nsch', u'Chauvin', u'Grubbs', u'Schrock', u'Marshall', u'Warren', u'Pinter', u'', u'ElBaradei', u'Aumann', u'Schelling'])
+(u'2006', [u'Mather', u'Smoot', u'Kornberg', u'Fire', u'Mello', u'Pamuk', u'Yunus', u'', u'Phelps'])
+(u'2007', [u'Fert', u'Gr\xfcnberg', u'Ertl', u'Capecchi', u'Evans', u'Smithies', u'Lessing', u'', u'Gore Jr.', u'Hurwicz', u'Maskin', u'Myerson'])
+(u'2008', [u'Nambu', u'Kobayashi', u'Maskawa', u'Shimomura', u'Chalfie', u'Tsien', u'zur Hausen', u'Barr\xe9-Sinoussi', u'Montagnier', u'Le Cl\xe9zio', u'Ahtisaari', u'Krugman'])
+(u'2009', [u'Kao', u'Boyle', u'Smith', u'Ramakrishnan', u'Steitz', u'Yonath', u'Blackburn', u'Greider', u'Szostak', u'M\xfcller', u'Obama', u'Ostrom', u'Williamson'])
+(u'2010', [u'Geim', u'Novoselov', u'Heck', u'Negishi', u'Suzuki', u'Edwards', u'Vargas Llosa', u'Xiaobo', u'Diamond', u'Mortensen', u'Pissarides'])
+(u'2011', [u'Perlmutter', u'Schmidt', u'Riess', u'Shechtman', u'Beutler', u'Hoffmann', u'Steinman', u'Transtr\xf6mer', u'Johnson Sirleaf', u'Gbowee', u'Karman', u'Sargent', u'Sims'])
+(u'2012', [u'Haroche', u'Wineland', u'Lefkowitz', u'Kobilka', u'Gurdon', u'Yamanaka', u'Yan', u'', u'Roth', u'Shapley'])
+(u'2013', [u'Englert', u'Higgs', u'Karplus', u'Levitt', u'Warshel', u'Rothman', u'Schekman', u'S\xfcdhof', u'Munro', u'', u'Fama', u'Hansen', u'Shiller'])
+=========================== Task 4
+(u'128.187.140.171', [u'01/Jul/1995:00:27:49 -0400'])
+(u'129.188.154.200', [u'01/Jul/1995:01:09:05 -0400'])
+(u'129.193.116.41', [u'01/Jul/1995:00:19:11 -0400'])
+(u'129.59.205.2', [u'01/Jul/1995:00:22:32 -0400'])
+(u'129.79.164.64', [u'02/Jul/1995:02:25:32 -0400'])
+(u'129.94.144.152', [u'01/Jul/1995:00:10:39 -0400'])
+(u'130.231.92.40', [u'02/Jul/1995:03:08:46 -0400'])
+(u'130.54.33.130', [u'01/Jul/1995:01:08:08 -0400'])
+(u'131.112.168.40', [u'02/Jul/1995:01:36:03 -0400'])
+(u'131.128.2.155', [u'01/Jul/1995:01:12:09 -0400'])
+=========================== Task 5
+[(u'user81', (23, [[u'product108'], [u'product109'], [u'product110'], [u'product111'], [u'product112'], [u'product113'], [u'product114'], [u'product115'], [u'product116'], [u'product117'], [u'product118'], [u'product119'], [u'product120'], [u'product121'], [u'product122'], [u'product123'], [u'product124'], [u'product125'], [u'product126'], [u'product127'], [u'product128'], [u'product129'], [u'product130']])), (u'user274', (42, [[u'product109'], [u'product110'], [u'product111'], [u'product112'], [u'product113'], [u'product114'], [u'product115'], [u'product116'], [u'product83'], [u'product117'], [u'product118'], [u'product119'], [u'product120'], [u'product121'], [u'product122'], [u'product123'], [u'product123'], [u'product124'], [u'product125'], [u'product126'], [u'product56'], [u'product127'], [u'product128'], [u'product129'], [u'product130'], [u'product131'], [u'product132'], [u'product133'], [u'product134'], [u'product135'], [u'product136'], [u'product153'], [u'product137'], [u'product61'], [u'product138'], [u'product139'], [u'product140'], [u'product148'], [u'product141'], [u'product142'], [u'product143'], [u'product144']])), (u'user80', (39, [[u'product71'], [u'product72'], [u'product73'], [u'product74'], [u'product75'], [u'product76'], [u'product77'], [u'product78'], [u'product79'], [u'product80'], [u'product81'], [u'product82'], [u'product83'], [u'product84'], [u'product85'], [u'product86'], [u'product87'], [u'product88'], [u'product89'], [u'product90'], [u'product91'], [u'product92'], [u'product93'], [u'product94'], [u'product95'], [u'product96'], [u'product97'], [u'product98'], [u'product99'], [u'product100'], [u'product101'], [u'product101'], [u'product102'], [u'product103'], [u'product104'], [u'product105'], [u'product13'], [u'product106'], [u'product107']])), (u'user169', (11, [[u'product226'], [u'product227'], [u'product228'], [u'product229'], [u'product230'], [u'product231'], [u'product232'], [u'product233'], [u'product234'], [u'product235'], [u'product236']])), (u'user168', (15, [[u'product212'], [u'product213'], [u'product214'], [u'product215'], [u'product216'], [u'product217'], [u'product218'], [u'product219'], [u'product220'], [u'product221'], [u'product222'], [u'product220'], [u'product223'], [u'product224'], [u'product225']]))]
+=========================== Task 6
+(u'128.187.140.171', ([], [u'/ksc.html', u'/images/ksclogo-medium.gif', u'/images/NASA-logosmall.gif', u'/images/MOSAIC-logosmall.gif', u'/images/USA-logosmall.gif', u'/images/WORLD-logosmall.gif', u'/shuttle/countdown/', u'/shuttle/countdown/count.gif', u'/images/KSC-logosmall.gif', u'/cgi-bin/imagemap/countdown?97,140', u'/cgi-bin/imagemap/countdown?375,269']))
+(u'129.188.154.200', ([], [u'/facts/about_ksc.html', u'/images/launchpalms-small.gif', u'/images/NASA-logosmall.gif', u'/images/KSC-logosmall.gif', u'/', u'/images/ksclogo-medium.gif', u'/images/MOSAIC-logosmall.gif', u'/images/USA-logosmall.gif', u'/images/WORLD-logosmall.gif', u'/shuttle/missions/sts-71/mission-sts-71.html', u'/shuttle/missions/sts-71/sts-71-patch-small.gif', u'/images/launch-logo.gif', u'/shuttle/missions/sts-71/movies/movies.html', u'/shuttle/missions/sts-71/movies/', u'/icons/blank.xbm', u'/icons/menu.xbm', u'/icons/movie.xbm', u'/icons/text.xbm', u'/shuttle/missions/sts-71/', u'/shuttle/missions/sts-71/images/', u'/icons/image.xbm', u'/icons/image.xbm', u'/shuttle/missions', u'/shuttle/missions/', u'/shuttle', u'/shuttle/', u'/shuttle/missions/sts-71/movies/sts-71-launch.mpg', u'/shuttle/movies/', u'/shuttle', u'/shuttle/', u'/', u'/shuttle/missions/sts-71/images/images.html', u'/shuttle/missions/sts-71/movies/movies.html', u'/htbin/wais.pl', u'/shuttle/movies/astronauts.mpg', u'/htbin/wais.pl?mpeg', u'/shuttle/countdown/lps/mpeg.html', u'/shuttle/countdown/lps/back.gif', u'/htbin/cdt_main.pl', u'/shuttle/countdown/countdown.html', u'/shuttle/countdown/count.gif', u'/shuttle/missions/sts-71/movies/movies.html', u'/shuttle/missions/sts-71/sts-71-patch.jpg', u'/shuttle/missions/sts-71/movies/sts-71-launch.mpg']))
+(u'129.193.116.41', ([], [u'/shuttle/countdown/', u'/shuttle/countdown/count.gif', u'/images/NASA-logosmall.gif', u'/images/KSC-logosmall.gif', u'/cgi-bin/imagemap/countdown?370,276']))
+(u'129.59.205.2', ([], [u'/shuttle/countdown/', u'/images/NASA-logosmall.gif', u'/images/KSC-logosmall.gif', u'/shuttle/countdown/count.gif', u'/cgi-bin/imagemap/countdown?89,176', u'/shuttle/missions/sts-71/images/images.html', u'/shuttle/missions/sts-71/images/KSC-95EC-0904.jpg']))
+(u'129.79.164.64', ([], [u'/shuttle/countdown/liftoff.html', u'/images/NASA-logosmall.gif', u'/shuttle/countdown/video/livevideo.gif', u'/shuttle/missions/sts-71/movies/sts-71-mir-dock-2.mpg', u'/shuttle/missions/sts-71/movies/sts-71-launch-3.mpg']))
+(u'129.94.144.152', ([u'/', u'/images/ksclogo-medium.gif'], [u'/images/shuttle-patch-small.gif', u'/shuttle/technology/sts-newsref/stsref-toc.html', u'/images/KSC-logosmall.gif', u'/images/launch-logo.gif', u'/shuttle/technology/sts-newsref/sts-cron.html', u'/images/shuttle-patch-logo.gif', u'/images/KSC-logosmall.gif', u'/shuttle/missions/51-l/mission-51-l.html', u'/images/launch-logo.gif', u'/shuttle/missions/51-l/51-l-patch-small.gif', u'/shuttle/missions/51-l/51-l-info.html']))
+(u'130.231.92.40', ([], [u'/shuttle/missions/sts-71/mission-sts-71.html']))
+(u'130.54.33.130', ([], [u'/', u'/images/ksclogo-medium.gif', u'/images/NASA-logosmall.gif', u'/images/MOSAIC-logosmall.gif', u'/images/USA-logosmall.gif', u'/images/WORLD-logosmall.gif']))
+(u'131.112.168.40', ([], [u'/shuttle/missions/missions.html', u'/images/launchmedium.gif', u'/images/NASA-logosmall.gif', u'/images/KSC-logosmall.gif', u'/history/history.html', u'/history/apollo/images/apollo-small.gif', u'/history/rocket-history.txt', u'/shuttle/missions/sts-1/mission-sts-1.html', u'/shuttle/missions/sts-1/sts-1-patch-small.gif', u'/images/launch-logo.gif', u'/shuttle/resources/orbiters/columbia.html', u'/shuttle/resources/orbiters/columbia-logo.gif', u'/images/ksclogosmall.gif', u'/shuttle/resources/orbiters/endeavour.html', u'/shuttle/resources/orbiters/endeavour-logo.gif', u'/images/ksclogosmall.gif', u'/shuttle/resources/orbiters/orbiters-logo.gif', u'/shuttle/missions/sts-49/mission-sts-49.html', u'/shuttle/missions/sts-49/sts-49-patch-small.gif']))
+(u'131.128.2.155', ([], [u'/shuttle/missions/sts-71/movies/crew-arrival-t38.mpg', u'/shuttle/missions/sts-71/mission-sts-71.html', u'/shuttle/missions/sts-71/sts-71-patch-small.gif', u'/images/launch-logo.gif', u'/images/KSC-logosmall.gif', u'/shuttle/countdown/', u'/shuttle/countdown/count.gif', u'/images/NASA-logosmall.gif', u'/cgi-bin/imagemap/countdown?98,208', u'/shuttle/countdown/tour.html', u'/images/KSC-94EC-412-small.gif', u'/facilities/crawler.html', u'/images/crawler-logo.gif', u'/images/ksclogosmall.gif', u'/images/kscmap-tiny.gif', u'/images/rollout.gif', u'/images/crawler-logo.gif', u'/cgi-bin/imagemap/countdown?105,146', u'/cgi-bin/imagemap/countdown?377,274']))
+=========================== Task 7
+(u'chemistry:Aaron', 1)
+(u'chemistry:Ada E.', 1)
+(u'chemistry:Akira', 1)
+(u'chemistry:Arieh', 1)
+(u'chemistry:Avram', 1)
+(u'chemistry:Aziz', 1)
+(u'chemistry:Bernard L.', 1)
+(u'chemistry:Brian K.', 1)
+(u'chemistry:Dan', 1)
+(u'chemistry:Ei-ichi', 1)
+=========================== Task 8
+Found 146 edges to add to the matching
+[(u'user10', u'product229'), (u'user100', u'product130'), (u'user101', u'product151'), (u'user102', u'product164'), (u'user103', u'product174'), (u'user104', u'product192'), (u'user105', u'product206'), (u'user106', u'product0'), (u'user107', u'product119'), (u'user108', u'product133'), (u'user109', u'product157'), (u'user11', u'product251'), (u'user110', u'product167'), (u'user111', u'product182'), (u'user113', u'product19'), (u'user114', u'product71'), (u'user115', u'product100'), (u'user116', u'product104'), (u'user117', u'product117'), (u'user118', u'product127'), (u'user119', u'product147'), (u'user120', u'product162'), (u'user121', u'product126'), (u'user122', u'product201'), (u'user123', u'product211'), (u'user124', u'product219'), (u'user125', u'product114'), (u'user127', u'product15'), (u'user128', u'product35'), (u'user129', u'product191'), (u'user13', u'product1'), (u'user130', u'product57'), (u'user131', u'product63'), (u'user133', u'product102'), (u'user135', u'product163'), (u'user136', u'product176'), (u'user138', u'product10'), (u'user139', u'product24'), (u'user14', u'product31'), (u'user140', u'product39'), (u'user141', u'product22'), (u'user142', u'product65'), (u'user143', u'product81'), (u'user145', u'product110'), (u'user146', u'product109'), (u'user148', u'product186'), (u'user15', u'product58'), (u'user151', u'product140'), (u'user152', u'product11'), (u'user154', u'product165'), (u'user155', u'product173'), (u'user157', u'product26'), (u'user158', u'product40'), (u'user161', u'product123'), (u'user166', u'product115'), (u'user167', u'product190'), (u'user168', u'product212'), (u'user169', u'product226'), (u'user17', u'product101'), (u'user170', u'product12'), (u'user171', u'product246'), (u'user172', u'product145'), (u'user173', u'product184'), (u'user18', u'product118'), (u'user182', u'product32'), (u'user183', u'product243'), (u'user184', u'product61'), (u'user186', u'product107'), (u'user187', u'product116'), (u'user189', u'product49'), (u'user19', u'product224'), (u'user190', u'product53'), (u'user191', u'product67'), (u'user193', u'product121'), (u'user196', u'product112'), (u'user197', u'product153'), (u'user198', u'product170'), (u'user199', u'product177'), (u'user200', u'product199'), (u'user201', u'product210'), (u'user203', u'product236'), (u'user204', u'product248'), (u'user206', u'product266'), (u'user208', u'product14'), (u'user212', u'product134'), (u'user215', u'product16'), (u'user217', u'product194'), (u'user22', u'product21'), (u'user220', u'product225'), (u'user222', u'product263'), (u'user227', u'product18'), (u'user228', u'product27'), (u'user229', u'product42'), (u'user23', u'product33'), (u'user231', u'product82'), (u'user233', u'product138'), (u'user234', u'product155'), (u'user236', u'product181'), (u'user238', u'product209'), (u'user239', u'product217')]
+Found 51 edges to add to the matching
+[(u'user112', u'product13'), (u'user12', u'product275'), (u'user132', u'product79'), (u'user134', u'product154'), (u'user137', u'product193'), (u'user144', u'product103'), (u'user147', u'product220'), (u'user150', u'product41'), (u'user159', u'product113'), (u'user162', u'product135'), (u'user164', u'product83'), (u'user174', u'product158'), (u'user175', u'product3'), (u'user177', u'product20'), (u'user178', u'product66'), (u'user181', u'product28'), (u'user194', u'product171'), (u'user20', u'product284'), (u'user205', u'product252'), (u'user209', u'product183'), (u'user211', u'product120'), (u'user213', u'product159'), (u'user216', u'product54'), (u'user219', u'product202'), (u'user221', u'product244'), (u'user225', u'product125'), (u'user230', u'product60'), (u'user235', u'product168'), (u'user237', u'product195'), (u'user254', u'product198'), (u'user267', u'product175'), (u'user268', u'product187'), (u'user271', u'product230'), (u'user275', u'product146'), (u'user279', u'product29'), (u'user280', u'product144'), (u'user284', u'product143'), (u'user287', u'product196'), (u'user38', u'product95'), (u'user44', u'product178'), (u'user47', u'product141'), (u'user52', u'product222'), (u'user56', u'product280'), (u'user58', u'product50'), (u'user67', u'product80'), (u'user85', u'product78'), (u'user88', u'product172'), (u'user9', u'product149'), (u'user91', u'product279'), (u'user93', u'product23'), (u'user97', u'product128')]