late commit of data used for theses, and WAC5 paper

canola/README.txt

@@ -0,0 +1,37 @@
+agreement/
+Fleiss Multi-pi calculation of agreement on the basis of:
+Artstein, Ron, and Massimo Poesio. "Inter-Coder Agreement for Computational Linguistics." Computational Linguistics 34, no. 4 (2008): 555-596. http://www.mitpressjournals.org/doi/abs/10.1162/coli.07-034-R2
+
+
+pagedata.py, analyse_pagedata.r, and stats*/
+./pagedata.py stats page.csv user.csv userpage.csv pagenodeusertags.csv
+ IN stats/: stats directory from an app's -merge -stats run
+ OUT page.csv user.csv userpage.csv pagenodeusertags.csv:
+    cf. page.csv.txt, user.csv.txt, userpage.csv.txt
+    pagenodeusertags.csv: needed for agreement
+
+ all sorts of measures of the quality/difficulty/etc. of submissions/pages
+
+
+timings/
+take deltas between submissions and calculate durations users saw pages
+
+
+dumps_2nd/
+JS-enabled re-dumps of pages for merging 
+(during merge user submissions are compared to a 'master document' for
+differences in text and structure. however, the user submissions' were done with
+JS enabled (i.e. some might contain additional DOM nodes). therefore, the master
+needs to be re-loaded with JS enabled.)
+
+dumps_2nd.fl
+pageids
+
+
+mkstats.sh
+ for pageid in (cat dumps_2nd.fl); do ./mkstats.sh $pageid; done
+    merge user submissions (from dumps_2ns) and produce stats/
+
+
+submissions.tar.bz2
+DB dumps of user submissions

canola/agreement/A_o.csv

@@ -0,0 +1,220 @@
+"page_id","A_o","nodes"
+"1",768,0.572981366459628,46
+"2",769,0.932330827067669,19
+"3",762,0.734314671814674,592
+"4",763,0.82920634920635,75
+"5",760,0.798872180451126,152
+"6",766,0.824595469255664,103
+"7",767,0.975,10
+"8",764,0.907782101167315,771
+"9",765,0.827272727272727,20
+"10",909,0.69951124144673,682
+"11",692,0.686906201416479,827
+"12",693,0.416574585635362,362
+"13",691,0.78510101010101,396
+"14",696,0.79644541167935,919
+"15",697,0.797892434635642,958
+"16",694,0.717703913248468,404
+"17",695,0.863636363636364,44
+"18",698,0.893681318681318,130
+"19",699,0.853433226651149,491
+"20",819,0.670138888888889,24
+"21",810,0.497821350762528,306
+"22",811,0.958159541188738,274
+"23",812,0.965111111111111,100
+"24",814,0.883587786259542,131
+"25",815,0.795975855130785,355
+"26",816,0.928205128205128,39
+"27",817,0.911111111111111,15
+"28",719,0.852891396332864,709
+"29",718,0.677704194260485,151
+"30",717,0.866961217476683,291
+"31",716,0.802327084680017,1105
+"32",713,0.731646825396824,144
+"33",712,0.547850208044383,103
+"34",710,0.816073354908307,103
+"35",884,0.597452934662238,86
+"36",910,0.855072463768116,23
+"37",892,0.860650510204082,112
+"38",829,0.880952380952381,40
+"39",828,0.88827045969903,231
+"40",825,0.951351351351351,111
+"41",824,0.747820254862507,142
+"42",827,0.85007072135785,101
+"43",826,0.825396825396826,78
+"44",821,0.954451345755694,23
+"45",820,0.946458185264155,201
+"46",823,1,1678
+"47",822,0.934455075332673,433
+"48",890,0.760204081632653,56
+"49",862,0.71082474226804,194
+"50",709,0.881592039800995,268
+"51",891,0.797407407407403,300
+"52",706,0.981723237597911,383
+"53",707,0.793425324675325,88
+"54",701,0.872184936614467,149
+"55",702,0.867817896389324,910
+"56",703,0.611567635903919,226
+"57",894,0.842188114915386,121
+"58",895,0.812301587301588,120
+"59",797,0.872596153846153,416
+"60",796,0.880128205128205,104
+"61",795,0.760609984174939,331
+"62",794,0.760828625235405,59
+"63",793,0.995595926231764,173
+"64",792,0.88135593220339,59
+"65",791,0.883390705679862,166
+"66",790,0.747666905958363,199
+"67",838,0.798708635996771,413
+"68",839,0.906666666666667,25
+"69",799,0.685045948203844,171
+"70",798,0.430588235294117,340
+"71",919,0.939605110336818,205
+"72",918,0.966611932129174,435
+"73",915,0.709474463360475,772
+"74",914,0.858309037900875,245
+"75",917,0.74025974025974,99
+"76",916,0.843406593406594,26
+"77",911,0.918871252204584,108
+"78",847,0.978888888888889,120
+"79",913,0.602851605758583,344
+"80",912,0.587687687687687,74
+"81",902,0.932222222222222,240
+"82",920,0.873626373626374,13
+"83",923,0.922448979591837,49
+"84",921,0.699423247559893,161
+"85",904,0.601937984496124,172
+"86",846,0.936507936507937,72
+"87",922,0.770325203252032,738
+"88",784,0.85576923076923,156
+"89",785,0.988095238095238,88
+"90",786,0.874611801242236,92
+"91",787,0.736873156342183,339
+"92",780,0.928021978021978,130
+"93",781,0.87379679144385,17
+"94",782,0.93840579710145,69
+"95",783,0.883928571428571,20
+"96",896,0.96996699669967,202
+"97",903,0.744047619047619,320
+"98",788,0.82494201118843,349
+"99",789,0.738977072310406,81
+"100",849,0.885593220338983,59
+"101",848,0.886238532110092,109
+"102",883,0.990446796002352,243
+"103",882,0.98447204968944,46
+"104",900,0.976954732510288,81
+"105",881,0.983823529411765,136
+"106",880,0.911525974025974,44
+"107",901,0.875407697325505,219
+"108",887,0.902702702702703,37
+"109",854,0.482880755608029,121
+"110",855,0.573573573573572,222
+"111",856,0.801401869158878,107
+"112",857,0.683947772657449,124
+"113",850,0.93125,32
+"114",852,0.59572192513369,187
+"115",853,0.601970443349754,203
+"116",832,0.495601173020528,341
+"117",858,0.857875457875456,130
+"118",859,0.930059523809524,48
+"119",731,0.98168498168498,624
+"120",730,0.898419203747073,122
+"121",733,0.812748015873016,192
+"122",732,0.637852593266605,314
+"123",735,0.993188854489164,323
+"124",734,0.920845159255755,151
+"125",737,0.836563876651982,227
+"126",736,0.787569573283857,154
+"127",739,0.874800637958533,19
+"128",738,0.93703007518797,76
+"129",753,0.993002915451895,245
+"130",752,0.96805304400241,79
+"131",751,0.947115384615385,104
+"132",750,0.831645569620252,316
+"133",757,0.54006968641115,41
+"134",756,0.90033167495854,134
+"135",755,0.875,102
+"136",754,0.47212741751991,293
+"137",833,0.888180272108843,112
+"138",758,0.89413616686344,121
+"139",845,0.877972709551655,342
+"140",844,0.729504172803142,97
+"141",843,0.88118811881188,101
+"142",842,0.881834215167549,63
+"143",869,0.574032738095238,128
+"144",868,0.82781954887218,190
+"145",907,0.838850174216028,82
+"146",841,0.682297346419483,131
+"147",830,0.933333333333334,123
+"148",861,0.858,300
+"149",860,0.631541725601131,101
+"150",863,0.74749373433584,76
+"151",840,0.753720238095238,64
+"152",865,0.773476702508961,93
+"153",867,0.971988795518207,85
+"154",866,0.921933621933623,330
+"155",726,0.927960927960928,39
+"156",727,0.895470383275261,246
+"157",724,0.910675381263616,102
+"158",725,0.977927651747394,233
+"159",722,0.949465500485909,343
+"160",723,1,373
+"161",721,0.743023255813954,172
+"162",728,0.69373942470389,788
+"163",729,0.967169476486247,322
+"164",740,0.9562358276644,315
+"165",741,0.827731092436975,34
+"166",742,0.868725868725869,37
+"167",743,0.798295454545455,88
+"168",744,0.884575569358178,92
+"169",745,0.730817217716782,229
+"170",885,0.880770628862232,393
+"171",747,0.927721088435374,84
+"172",748,0.66988416988417,296
+"173",749,0.86002886002886,33
+"174",889,0.927849927849928,33
+"175",888,0.902439024390244,41
+"176",905,0.554887218045109,475
+"177",878,0.92517006802721,28
+"178",879,0.90922619047619,48
+"179",876,0.897875816993464,68
+"180",877,0.996842936069456,181
+"181",874,0.898210290827742,596
+"182",875,0.877536231884058,368
+"183",872,0.858490566037736,106
+"184",873,0.972963951935915,107
+"185",906,0.92746913580247,216
+"186",871,0.92781954887218,95
+"187",775,0.57040110650069,482
+"188",774,0.83236409608091,565
+"189",777,0.942359855334539,316
+"190",893,0.851906158357771,31
+"191",771,0.924459494660065,349
+"192",770,0.816065723413966,313
+"193",773,0.936692506459948,86
+"194",772,0.715608465608466,54
+"195",898,0.956898964455636,1191
+"196",899,0.78125,32
+"197",779,0.832794656324068,221
+"198",778,0.574222222222223,300
+"199",803,0.823979591836735,84
+"200",831,0.693739967897272,445
+"201",802,0.787545787545788,52
+"202",836,0.736507936507937,147
+"203",801,0.924761904761905,100
+"204",837,0.780842911877395,87
+"205",800,0.840555555555555,150
+"206",834,0.931216931216931,108
+"207",835,0.899431818181818,64
+"208",809,0.899185823754789,232
+"209",808,0.849324804548684,134
+"210",689,0.756594724220624,417
+"211",688,0.967120181405896,63
+"212",685,0.816445182724252,86
+"213",684,0.739718614718615,198
+"214",687,0.782679738562092,85
+"215",686,0.442090395480226,59
+"216",807,0.727838827838828,260
+"217",806,0.9,32
+"218",805,0.705722639933168,228
+"219",804,0.983739837398374,41