Added: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv1_cc.txt
URL: 
http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv1_cc.txt?rev=1148501&view=auto
==============================================================================
--- 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv1_cc.txt
 (added)
+++ 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv1_cc.txt
 Tue Jul 19 19:44:48 2011
@@ -0,0 +1,500 @@
+238val_238
+86val_86
+311val_311
+27val_27
+165val_165
+409val_409
+255val_255
+278val_278
+98val_98
+484val_484
+265val_265
+193val_193
+401val_401
+150val_150
+273val_273
+224val_224
+369val_369
+66val_66
+128val_128
+213val_213
+146val_146
+406val_406
+429val_429
+374val_374
+152val_152
+469val_469
+145val_145
+495val_495
+37val_37
+327val_327
+281val_281
+277val_277
+209val_209
+15val_15
+82val_82
+403val_403
+166val_166
+417val_417
+430val_430
+252val_252
+292val_292
+219val_219
+287val_287
+153val_153
+193val_193
+338val_338
+446val_446
+459val_459
+394val_394
+237val_237
+482val_482
+174val_174
+413val_413
+494val_494
+207val_207
+199val_199
+466val_466
+208val_208
+174val_174
+399val_399
+396val_396
+247val_247
+417val_417
+489val_489
+162val_162
+377val_377
+397val_397
+309val_309
+365val_365
+266val_266
+439val_439
+342val_342
+367val_367
+325val_325
+167val_167
+195val_195
+475val_475
+17val_17
+113val_113
+155val_155
+203val_203
+339val_339
+0val_0
+455val_455
+128val_128
+311val_311
+316val_316
+57val_57
+302val_302
+205val_205
+149val_149
+438val_438
+345val_345
+129val_129
+170val_170
+20val_20
+489val_489
+157val_157
+378val_378
+221val_221
+92val_92
+111val_111
+47val_47
+72val_72
+4val_4
+280val_280
+35val_35
+427val_427
+277val_277
+208val_208
+356val_356
+399val_399
+169val_169
+382val_382
+498val_498
+125val_125
+386val_386
+437val_437
+469val_469
+192val_192
+286val_286
+187val_187
+176val_176
+54val_54
+459val_459
+51val_51
+138val_138
+103val_103
+239val_239
+213val_213
+216val_216
+430val_430
+278val_278
+176val_176
+289val_289
+221val_221
+65val_65
+318val_318
+332val_332
+311val_311
+275val_275
+137val_137
+241val_241
+83val_83
+333val_333
+180val_180
+284val_284
+12val_12
+230val_230
+181val_181
+67val_67
+260val_260
+404val_404
+384val_384
+489val_489
+353val_353
+373val_373
+272val_272
+138val_138
+217val_217
+84val_84
+348val_348
+466val_466
+58val_58
+8val_8
+411val_411
+230val_230
+208val_208
+348val_348
+24val_24
+463val_463
+431val_431
+179val_179
+172val_172
+42val_42
+129val_129
+158val_158
+119val_119
+496val_496
+0val_0
+322val_322
+197val_197
+468val_468
+393val_393
+454val_454
+100val_100
+298val_298
+199val_199
+191val_191
+418val_418
+96val_96
+26val_26
+165val_165
+327val_327
+230val_230
+205val_205
+120val_120
+131val_131
+51val_51
+404val_404
+43val_43
+436val_436
+156val_156
+469val_469
+468val_468
+308val_308
+95val_95
+196val_196
+288val_288
+481val_481
+457val_457
+98val_98
+282val_282
+197val_197
+187val_187
+318val_318
+318val_318
+409val_409
+470val_470
+137val_137
+369val_369
+316val_316
+169val_169
+413val_413
+85val_85
+77val_77
+0val_0
+490val_490
+87val_87
+364val_364
+179val_179
+118val_118
+134val_134
+395val_395
+282val_282
+138val_138
+238val_238
+419val_419
+15val_15
+118val_118
+72val_72
+90val_90
+307val_307
+19val_19
+435val_435
+10val_10
+277val_277
+273val_273
+306val_306
+224val_224
+309val_309
+389val_389
+327val_327
+242val_242
+369val_369
+392val_392
+272val_272
+331val_331
+401val_401
+242val_242
+452val_452
+177val_177
+226val_226
+5val_5
+497val_497
+402val_402
+396val_396
+317val_317
+395val_395
+58val_58
+35val_35
+336val_336
+95val_95
+11val_11
+168val_168
+34val_34
+229val_229
+233val_233
+143val_143
+472val_472
+322val_322
+498val_498
+160val_160
+195val_195
+42val_42
+321val_321
+430val_430
+119val_119
+489val_489
+458val_458
+78val_78
+76val_76
+41val_41
+223val_223
+492val_492
+149val_149
+449val_449
+218val_218
+228val_228
+138val_138
+453val_453
+30val_30
+209val_209
+64val_64
+468val_468
+76val_76
+74val_74
+342val_342
+69val_69
+230val_230
+33val_33
+368val_368
+103val_103
+296val_296
+113val_113
+216val_216
+367val_367
+344val_344
+167val_167
+274val_274
+219val_219
+239val_239
+485val_485
+116val_116
+223val_223
+256val_256
+263val_263
+70val_70
+487val_487
+480val_480
+401val_401
+288val_288
+191val_191
+5val_5
+244val_244
+438val_438
+128val_128
+467val_467
+432val_432
+202val_202
+316val_316
+229val_229
+469val_469
+463val_463
+280val_280
+2val_2
+35val_35
+283val_283
+331val_331
+235val_235
+80val_80
+44val_44
+193val_193
+321val_321
+335val_335
+104val_104
+466val_466
+366val_366
+175val_175
+403val_403
+483val_483
+53val_53
+105val_105
+257val_257
+406val_406
+409val_409
+190val_190
+406val_406
+401val_401
+114val_114
+258val_258
+90val_90
+203val_203
+262val_262
+348val_348
+424val_424
+12val_12
+396val_396
+201val_201
+217val_217
+164val_164
+431val_431
+454val_454
+478val_478
+298val_298
+125val_125
+431val_431
+164val_164
+424val_424
+187val_187
+382val_382
+5val_5
+70val_70
+397val_397
+480val_480
+291val_291
+24val_24
+351val_351
+255val_255
+104val_104
+70val_70
+163val_163
+438val_438
+119val_119
+414val_414
+200val_200
+491val_491
+237val_237
+439val_439
+360val_360
+248val_248
+479val_479
+305val_305
+417val_417
+199val_199
+444val_444
+120val_120
+429val_429
+169val_169
+443val_443
+323val_323
+325val_325
+277val_277
+230val_230
+478val_478
+178val_178
+468val_468
+310val_310
+317val_317
+333val_333
+493val_493
+460val_460
+207val_207
+249val_249
+265val_265
+480val_480
+83val_83
+136val_136
+353val_353
+172val_172
+214val_214
+462val_462
+233val_233
+406val_406
+133val_133
+175val_175
+189val_189
+454val_454
+375val_375
+401val_401
+421val_421
+407val_407
+384val_384
+256val_256
+26val_26
+134val_134
+67val_67
+384val_384
+379val_379
+18val_18
+462val_462
+492val_492
+100val_100
+298val_298
+9val_9
+341val_341
+498val_498
+146val_146
+458val_458
+362val_362
+186val_186
+285val_285
+348val_348
+167val_167
+18val_18
+273val_273
+183val_183
+281val_281
+344val_344
+97val_97
+469val_469
+315val_315
+84val_84
+28val_28
+37val_37
+448val_448
+152val_152
+348val_348
+307val_307
+194val_194
+414val_414
+477val_477
+222val_222
+126val_126
+90val_90
+169val_169
+403val_403
+400val_400
+200val_200
+97val_97

Added: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv1kv2.cogroup.txt
URL: 
http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv1kv2.cogroup.txt?rev=1148501&view=auto
==============================================================================
--- 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv1kv2.cogroup.txt
 (added)
+++ 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv1kv2.cogroup.txt
 Tue Jul 19 19:44:48 2011
@@ -0,0 +1,1000 @@
+0val_0
+0val_0
+0val_0
+10
+10
+11
+0val_10
+110
+0val_100
+0val_100
+1100
+1100
+1101
+1102
+0val_103
+0val_103
+0val_104
+0val_104
+1104
+1104
+1104
+0val_105
+1105
+1105
+1106
+0val_11
+111
+111
+111
+1110
+0val_111
+0val_113
+0val_113
+0val_114
+1114
+1114
+1114
+0val_116
+1116
+1117
+1117
+0val_118
+0val_118
+1118
+1118
+1118
+0val_119
+0val_119
+0val_119
+1119
+1119
+1119
+0val_12
+0val_12
+112
+0val_120
+0val_120
+1120
+1121
+1121
+1122
+1122
+1122
+1123
+1123
+0val_125
+0val_125
+1125
+0val_126
+1126
+1126
+0val_128
+0val_128
+0val_128
+1128
+1128
+0val_129
+0val_129
+1129
+1129
+0val_131
+1132
+1132
+0val_133
+1133
+0val_134
+0val_134
+1134
+1135
+1135
+1135
+0val_136
+1136
+0val_137
+0val_137
+1137
+0val_138
+0val_138
+0val_138
+0val_138
+1138
+1138
+1140
+0val_143
+1143
+1144
+0val_145
+0val_146
+0val_146
+1147
+1147
+0val_149
+0val_149
+1149
+0val_15
+0val_15
+115
+115
+0val_150
+1151
+1151
+0val_152
+0val_152
+1152
+1152
+1152
+0val_153
+1153
+1153
+0val_155
+0val_156
+1156
+1156
+0val_157
+1157
+1157
+0val_158
+116
+116
+0val_160
+1160
+1161
+1161
+1161
+1161
+0val_162
+1162
+0val_163
+0val_164
+0val_164
+1164
+1164
+0val_165
+0val_165
+1165
+0val_166
+0val_167
+0val_167
+0val_167
+1167
+0val_168
+1168
+0val_169
+0val_169
+0val_169
+0val_169
+0val_17
+0val_170
+1170
+0val_172
+0val_172
+1172
+0val_174
+0val_174
+1174
+1174
+0val_175
+0val_175
+1175
+1175
+0val_176
+0val_176
+0val_177
+1177
+1177
+0val_178
+1178
+1178
+0val_179
+0val_179
+1179
+0val_18
+0val_18
+0val_180
+0val_181
+1182
+0val_183
+1183
+1184
+1185
+0val_186
+0val_187
+0val_187
+0val_187
+0val_189
+1189
+0val_19
+119
+0val_190
+0val_191
+0val_191
+1191
+0val_192
+1192
+0val_193
+0val_193
+0val_193
+0val_194
+0val_195
+0val_195
+0val_196
+1196
+1196
+1196
+0val_197
+0val_197
+1197
+0val_199
+0val_199
+0val_199
+1199
+0val_2
+12
+0val_20
+120
+120
+0val_200
+0val_200
+0val_201
+0val_202
+0val_203
+0val_203
+1204
+0val_205
+0val_205
+1205
+1206
+1206
+1206
+0val_207
+0val_207
+0val_208
+0val_208
+0val_208
+0val_209
+0val_209
+1209
+1209
+121
+121
+121
+121
+1212
+0val_213
+0val_213
+1213
+0val_214
+1215
+0val_216
+0val_216
+1216
+0val_217
+0val_217
+1217
+1217
+0val_218
+0val_219
+0val_219
+122
+0val_221
+0val_221
+0val_222
+1222
+0val_223
+0val_223
+0val_224
+0val_224
+1224
+0val_226
+1226
+1226
+1226
+1226
+1227
+0val_228
+1228
+0val_229
+0val_229
+123
+0val_230
+0val_230
+0val_230
+0val_230
+0val_230
+1231
+0val_233
+0val_233
+0val_235
+1235
+0val_237
+0val_237
+0val_238
+0val_238
+1238
+0val_239
+0val_239
+1239
+1239
+0val_24
+0val_24
+1240
+0val_241
+1241
+1241
+1241
+1241
+0val_242
+0val_242
+1242
+1243
+1243
+0val_244
+1244
+1244
+1244
+1245
+1245
+1246
+1246
+0val_247
+0val_248
+1248
+0val_249
+1249
+1249
+0val_252
+1252
+1254
+0val_255
+0val_255
+0val_256
+0val_256
+1256
+0val_257
+1257
+1257
+0val_258
+1258
+1259
+1259
+0val_26
+0val_26
+0val_260
+1260
+1260
+1261
+0val_262
+1262
+1262
+0val_263
+1264
+1264
+0val_265
+0val_265
+1265
+0val_266
+1267
+1268
+0val_27
+1271
+0val_272
+0val_272
+1272
+0val_273
+0val_273
+0val_273
+1273
+0val_274
+1274
+0val_275
+1275
+1275
+1276
+0val_277
+0val_277
+0val_277
+0val_277
+1277
+1277
+0val_278
+0val_278
+1278
+0val_28
+0val_280
+0val_280
+0val_281
+0val_281
+1281
+1281
+1281
+0val_282
+0val_282
+0val_283
+0val_284
+1284
+1284
+0val_285
+1285
+0val_286
+1286
+0val_287
+1287
+1287
+0val_288
+0val_288
+0val_289
+1289
+129
+129
+0val_291
+1291
+1291
+0val_292
+1292
+1292
+1293
+1293
+1295
+1295
+0val_296
+1296
+0val_298
+0val_298
+0val_298
+13
+0val_30
+130
+1300
+1300
+0val_302
+1302
+1303
+1303
+1304
+0val_305
+1305
+0val_306
+1306
+0val_307
+0val_307
+0val_308
+1308
+1308
+0val_309
+0val_309
+1309
+131
+0val_310
+1310
+1310
+1310
+0val_311
+0val_311
+0val_311
+1313
+1314
+0val_315
+0val_316
+0val_316
+0val_316
+0val_317
+0val_317
+1317
+0val_318
+0val_318
+0val_318
+1318
+132
+0val_321
+0val_321
+0val_322
+0val_322
+1322
+0val_323
+1323
+1324
+0val_325
+0val_325
+1326
+0val_327
+0val_327
+0val_327
+1328
+1328
+0val_33
+133
+1330
+0val_331
+0val_331
+1331
+1331
+0val_332
+0val_333
+0val_333
+1333
+1334
+0val_335
+1335
+1335
+0val_336
+1336
+1337
+0val_338
+1338
+0val_339
+0val_34
+1340
+0val_341
+1341
+1341
+1341
+0val_342
+0val_342
+1342
+1343
+0val_344
+0val_344
+1344
+0val_345
+1347
+1347
+0val_348
+0val_348
+0val_348
+0val_348
+0val_348
+1348
+1349
+1349
+1349
+1349
+0val_35
+0val_35
+0val_35
+135
+135
+135
+0val_351
+1351
+1351
+1352
+1352
+0val_353
+0val_353
+1353
+1355
+1355
+0val_356
+1356
+1356
+1358
+0val_360
+1360
+0val_362
+1363
+1363
+1363
+0val_364
+1364
+0val_365
+0val_366
+0val_367
+0val_367
+1367
+1367
+0val_368
+0val_369
+0val_369
+0val_369
+1369
+0val_37
+0val_37
+1371
+1371
+1371
+1371
+0val_373
+1373
+0val_374
+1374
+0val_375
+1375
+1375
+1375
+1375
+1375
+1376
+0val_377
+0val_378
+1378
+0val_379
+1379
+1381
+0val_382
+0val_382
+1382
+1382
+0val_384
+0val_384
+0val_384
+1384
+1384
+1384
+1385
+1385
+0val_386
+1386
+1386
+1388
+0val_389
+1389
+1389
+1390
+1390
+1390
+1391
+1391
+0val_392
+1392
+1392
+0val_393
+1393
+1393
+0val_394
+0val_395
+0val_395
+1395
+1395
+0val_396
+0val_396
+0val_396
+0val_397
+0val_397
+1398
+0val_399
+0val_399
+1399
+1399
+0val_4
+14
+140
+140
+0val_400
+0val_401
+0val_401
+0val_401
+0val_401
+0val_401
+1401
+0val_402
+1402
+1402
+1402
+0val_403
+0val_403
+0val_403
+0val_404
+0val_404
+1404
+1404
+1404
+1405
+0val_406
+0val_406
+0val_406
+0val_406
+1406
+0val_407
+1407
+1407
+1407
+1408
+1408
+0val_409
+0val_409
+0val_409
+1409
+1409
+0val_41
+1410
+0val_411
+1411
+1412
+1412
+0val_413
+0val_413
+1413
+0val_414
+0val_414
+1414
+1415
+1416
+0val_417
+0val_417
+0val_417
+0val_418
+0val_419
+0val_42
+0val_42
+142
+142
+142
+0val_421
+1421
+1421
+1423
+0val_424
+0val_424
+1424
+1425
+1426
+0val_427
+1427
+1427
+1428
+0val_429
+0val_429
+1429
+1429
+0val_43
+0val_430
+0val_430
+0val_430
+1430
+0val_431
+0val_431
+0val_431
+1431
+0val_432
+1432
+0val_435
+1435
+0val_436
+1436
+0val_437
+1437
+0val_438
+0val_438
+0val_438
+1438
+1438
+0val_439
+0val_439
+1439
+1439
+0val_44
+1440
+1440
+1441
+1442
+0val_443
+1443
+1443
+1443
+0val_444
+0val_446
+1446
+1446
+1447
+0val_448
+1448
+0val_449
+1450
+1450
+1451
+0val_452
+0val_453
+1453
+0val_454
+0val_454
+0val_454
+1454
+1454
+0val_455
+1455
+1455
+0val_457
+1457
+1457
+0val_458
+0val_458
+0val_459
+0val_459
+1459
+146
+0val_460
+1461
+0val_462
+0val_462
+1462
+0val_463
+0val_463
+1463
+0val_466
+0val_466
+0val_466
+0val_467
+1467
+0val_468
+0val_468
+0val_468
+0val_468
+1468
+1468
+1468
+0val_469
+0val_469
+0val_469
+0val_469
+0val_469
+1469
+0val_47
+147
+0val_470
+1470
+0val_472
+1473
+1474
+1474
+0val_475
+1475
+1476
+1476
+0val_477
+1477
+0val_478
+0val_478
+1478
+1478
+0val_479
+148
+148
+0val_480
+0val_480
+0val_480
+1480
+1480
+0val_481
+1481
+0val_482
+1482
+0val_483
+0val_484
+1484
+0val_485
+1485
+1485
+1486
+0val_487
+1487
+1488
+0val_489
+0val_489
+0val_489
+0val_489
+1489
+149
+149
+0val_490
+1490
+0val_491
+1491
+1491
+0val_492
+0val_492
+1492
+1492
+0val_493
+0val_494
+1494
+1494
+0val_495
+1495
+0val_496
+1496
+0val_497
+1497
+1497
+0val_498
+0val_498
+0val_498
+0val_5
+0val_5
+0val_5
+15
+150
+0val_51
+0val_51
+151
+152
+152
+152
+152
+0val_53
+153
+0val_54
+156
+0val_57
+0val_58
+0val_58
+158
+158
+159
+16
+16
+160
+161
+162
+162
+163
+0val_64
+0val_65
+165
+165
+0val_66
+0val_67
+0val_67
+168
+0val_69
+169
+0val_70
+0val_70
+0val_70
+170
+171
+0val_72
+0val_72
+0val_74
+175
+0val_76
+0val_76
+176
+176
+176
+0val_77
+177
+177
+0val_78
+178
+0val_8
+18
+0val_80
+180
+0val_82
+182
+182
+0val_83
+0val_83
+0val_84
+0val_84
+0val_85
+185
+0val_86
+186
+0val_87
+187
+187
+189
+189
+189
+0val_9
+0val_90
+0val_90
+0val_90
+191
+0val_92
+193
+193
+193
+194
+0val_95
+0val_95
+0val_96
+0val_97
+0val_97
+197
+197
+0val_98
+0val_98
+199

Added: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv2.txt
URL: 
http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv2.txt?rev=1148501&view=auto
==============================================================================
--- 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv2.txt
 (added)
+++ 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv2.txt
 Tue Jul 19 19:44:48 2011
@@ -0,0 +1,500 @@
+474val_475
+281val_282
+179val_180
+291val_292
+62val_63
+271val_272
+217val_218
+135val_136
+167val_168
+468val_469
+423val_424
+413val_414
+245val_246
+455val_456
+425val_426
+241val_242
+177val_178
+272val_273
+231val_232
+448val_449
+287val_288
+246val_247
+440val_441
+31val_32
+373val_374
+447val_448
+443val_444
+175val_176
+278val_279
+296val_297
+147val_148
+428val_429
+126val_127
+249val_250
+21val_22
+273val_274
+441val_442
+106val_107
+371val_372
+153val_154
+356val_357
+217val_218
+490val_491
+33val_34
+35val_36
+421val_422
+243val_244
+402val_403
+128val_129
+10val_11
+226val_227
+133val_134
+333val_334
+15val_16
+110val_111
+391val_392
+343val_344
+275val_276
+0val_1
+485val_486
+293val_294
+240val_241
+241val_242
+286val_287
+85val_86
+408val_409
+477val_478
+455val_456
+99val_100
+335val_336
+476val_477
+482val_483
+367val_368
+59val_60
+48val_49
+424val_425
+226val_227
+494val_495
+488val_489
+94val_95
+485val_486
+393val_394
+349val_350
+11val_12
+161val_162
+123val_124
+409val_410
+50val_51
+265val_266
+402val_403
+128val_129
+468val_469
+314val_315
+497val_498
+224val_225
+63val_64
+344val_345
+4val_5
+277val_278
+135val_136
+3val_4
+206val_207
+101val_102
+331val_332
+114val_115
+209val_210
+281val_282
+56val_57
+239val_240
+389val_390
+114val_115
+254val_255
+235val_236
+390val_391
+165val_166
+304val_305
+264val_265
+196val_197
+238val_239
+20val_21
+11val_12
+492val_493
+129val_130
+257val_258
+71val_72
+289val_290
+453val_454
+421val_422
+82val_83
+58val_59
+5val_6
+86val_87
+249val_250
+438val_439
+360val_361
+323val_324
+222val_223
+42val_43
+467val_468
+411val_412
+175val_176
+429val_430
+338val_339
+281val_282
+68val_69
+185val_186
+16val_17
+147val_148
+119val_120
+492val_493
+473val_474
+376val_377
+347val_348
+120val_121
+213val_214
+306val_307
+393val_394
+427val_428
+291val_292
+426val_427
+132val_133
+446val_447
+386val_387
+65val_66
+121val_122
+388val_389
+184val_185
+375val_376
+284val_285
+191val_192
+129val_130
+246val_247
+197val_198
+491val_492
+369val_370
+262val_263
+122val_123
+438val_439
+351val_352
+390val_391
+352val_353
+23val_24
+226val_227
+328val_329
+382val_383
+342val_343
+349val_350
+480val_481
+102val_103
+497val_498
+487val_488
+480val_481
+331val_332
+409val_410
+475val_476
+463val_464
+183val_184
+177val_178
+399val_400
+15val_16
+318val_319
+149val_150
+392val_393
+77val_78
+275val_276
+476val_477
+258val_259
+174val_175
+252val_253
+114val_115
+87val_88
+161val_162
+75val_76
+264val_265
+48val_49
+336val_337
+340val_341
+390val_391
+443val_444
+484val_485
+407val_408
+189val_190
+305val_306
+367val_368
+6val_7
+260val_261
+2val_3
+349val_350
+170val_171
+51val_52
+355val_356
+363val_364
+164val_165
+118val_119
+310val_311
+104val_105
+19val_20
+80val_81
+117val_118
+326val_327
+47val_48
+121val_122
+241val_242
+450val_451
+140val_141
+212val_213
+308val_309
+30val_31
+405val_406
+239val_240
+119val_120
+358val_359
+11val_12
+49val_50
+143val_144
+153val_154
+341val_342
+21val_22
+105val_106
+157val_158
+416val_417
+199val_200
+375val_376
+42val_43
+89val_90
+363val_364
+395val_396
+347val_348
+386val_387
+77val_78
+454val_455
+293val_294
+364val_365
+20val_21
+89val_90
+461val_462
+52val_53
+40val_41
+8val_9
+168val_169
+384val_385
+313val_314
+324val_325
+310val_311
+206val_207
+381val_382
+404val_405
+206val_207
+385val_386
+259val_260
+226val_227
+262val_263
+69val_70
+303val_304
+245val_246
+260val_261
+328val_329
+322val_323
+122val_123
+241val_242
+469val_470
+404val_405
+384val_385
+76val_77
+116val_117
+42val_43
+104val_105
+481val_482
+303val_304
+93val_94
+277val_278
+406val_407
+451val_452
+53val_54
+32val_33
+132val_133
+192val_193
+58val_59
+351val_352
+70val_71
+443val_444
+356val_357
+399val_400
+205val_206
+352val_353
+52val_53
+21val_22
+317val_318
+330val_331
+209val_210
+138val_139
+429val_430
+160val_161
+267val_268
+454val_455
+257val_258
+76val_77
+174val_175
+412val_413
+16val_17
+375val_376
+489val_490
+295val_296
+105val_106
+204val_205
+126val_127
+274val_275
+439val_440
+374val_375
+494val_495
+216val_217
+457val_458
+93val_94
+470val_471
+196val_197
+302val_303
+119val_120
+375val_376
+391val_392
+287val_288
+450val_451
+375val_376
+437val_438
+12val_13
+398val_399
+35val_36
+334val_335
+384val_385
+435val_436
+60val_61
+29val_30
+442val_443
+151val_152
+52val_53
+404val_405
+446val_447
+300val_301
+0val_1
+268val_269
+491val_492
+392val_393
+21val_22
+295val_296
+93val_94
+104val_105
+436val_437
+61val_62
+407val_408
+439val_440
+156val_157
+341val_342
+118val_119
+335val_336
+172val_173
+244val_245
+6val_7
+284val_285
+164val_165
+136val_137
+349val_350
+371val_372
+462val_463
+123val_124
+432val_433
+496val_497
+355val_356
+144val_145
+87val_88
+408val_409
+152val_153
+382val_383
+348val_349
+122val_123
+427val_428
+292val_293
+182val_183
+474val_475
+353val_354
+310val_311
+52val_53
+486val_487
+152val_153
+378val_379
+414val_415
+261val_262
+65val_66
+371val_372
+256val_257
+292val_293
+412val_413
+97val_98
+495val_496
+385val_386
+40val_41
+49val_50
+389val_390
+259val_260
+97val_98
+478val_479
+125val_126
+243val_244
+151val_152
+178val_179
+100val_101
+415val_416
+401val_402
+156val_157
+228val_229
+363val_364
+117val_118
+22val_23
+248val_249
+459val_460
+402val_403
+62val_63
+137val_138
+162val_163
+244val_245
+276val_277
+46val_47
+341val_342
+78val_79
+379val_380
+215val_216
+134val_135
+196val_197
+410val_411
+157val_158
+431val_432
+82val_83
+440val_441
+100val_101
+407val_408
+371val_372
+308val_309
+430val_431
+309val_310
+135val_136
+161val_162
+468val_469
+152val_153
+138val_139
+76val_77
+161val_162
+300val_301
+337val_338
+91val_92
+478val_479
+118val_119
+1val_2
+89val_90
+178val_179
+457val_458
+29val_30
+242val_243
+285val_286
+35val_36
+227val_228
+395val_396
+244val_245

Added: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv3.txt
URL: 
http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv3.txt?rev=1148501&view=auto
==============================================================================
--- 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv3.txt
 (added)
+++ 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv3.txt
 Tue Jul 19 19:44:48 2011
@@ -0,0 +1,25 @@
+238val_238
+
+311val_311
+val_27
+val_165
+val_409
+255val_255
+278val_278
+98val_98
+val_484
+val_265
+val_193
+401val_401
+150val_150
+273val_273
+224
+369
+66val_66
+128
+213val_213
+146val_146
+406val_406
+
+
+

Added: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv4.txt
URL: 
http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv4.txt?rev=1148501&view=auto
==============================================================================
Binary file - no diff available.

Propchange: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv4.txt
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv5.txt
URL: 
http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv5.txt?rev=1148501&view=auto
==============================================================================
--- 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv5.txt
 (added)
+++ 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv5.txt
 Tue Jul 19 19:44:48 2011
@@ -0,0 +1,24 @@
+238val_238
+238val_239
+86val_86
+238val_240
+311val_311
+27val_27
+165val_165
+213val_213
+409val_409
+255val_255
+278val_278
+98val_98
+484val_484
+265val_265
+213val_214
+193val_193
+401val_401
+150val_150
+273val_273
+224val_224
+369val_369
+66val_66
+128val_128
+213val_213

Added: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv6.txt
URL: 
http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv6.txt?rev=1148501&view=auto
==============================================================================
--- 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv6.txt
 (added)
+++ 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/kv6.txt
 Tue Jul 19 19:44:48 2011
@@ -0,0 +1,100 @@
+00
+01
+02
+03
+04
+05
+06
+07
+08
+09
+010
+011
+012
+013
+014
+015
+016
+017
+018
+019
+020
+021
+022
+023
+024
+025
+026
+027
+028
+029
+030
+031
+032
+033
+034
+035
+036
+037
+038
+039
+040
+041
+042
+043
+044
+045
+046
+047
+048
+049
+10
+11
+12
+13
+14
+15
+16
+17
+18
+19
+110
+111
+112
+113
+114
+115
+116
+117
+118
+119
+120
+121
+122
+123
+124
+125
+126
+127
+128
+129
+130
+131
+132
+133
+134
+135
+136
+137
+138
+139
+140
+141
+142
+143
+144
+145
+146
+147
+148
+149

Added: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/lt100.sorted.txt
URL: 
http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/lt100.sorted.txt?rev=1148501&view=auto
==============================================================================
--- 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/lt100.sorted.txt
 (added)
+++ 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/lt100.sorted.txt
 Tue Jul 19 19:44:48 2011
@@ -0,0 +1,84 @@
+0val_0
+0val_0
+0val_0
+10val_10
+11val_11
+12val_12
+12val_12
+15val_15
+15val_15
+17val_17
+18val_18
+18val_18
+19val_19
+2val_2
+20val_20
+24val_24
+24val_24
+26val_26
+26val_26
+27val_27
+28val_28
+30val_30
+33val_33
+34val_34
+35val_35
+35val_35
+35val_35
+37val_37
+37val_37
+4val_4
+41val_41
+42val_42
+42val_42
+43val_43
+44val_44
+47val_47
+5val_5
+5val_5
+5val_5
+51val_51
+51val_51
+53val_53
+54val_54
+57val_57
+58val_58
+58val_58
+64val_64
+65val_65
+66val_66
+67val_67
+67val_67
+69val_69
+70val_70
+70val_70
+70val_70
+72val_72
+72val_72
+74val_74
+76val_76
+76val_76
+77val_77
+78val_78
+8val_8
+80val_80
+82val_82
+83val_83
+83val_83
+84val_84
+84val_84
+85val_85
+86val_86
+87val_87
+9val_9
+90val_90
+90val_90
+90val_90
+92val_92
+95val_95
+95val_95
+96val_96
+97val_97
+97val_97
+98val_98
+98val_98

Added: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/lt100.txt
URL: 
http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/lt100.txt?rev=1148501&view=auto
==============================================================================
--- 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/lt100.txt
 (added)
+++ 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/lt100.txt
 Tue Jul 19 19:44:48 2011
@@ -0,0 +1,84 @@
+86val_86
+27val_27
+98val_98
+66val_66
+37val_37
+15val_15
+82val_82
+17val_17
+0val_0
+57val_57
+20val_20
+92val_92
+47val_47
+72val_72
+4val_4
+35val_35
+54val_54
+51val_51
+65val_65
+83val_83
+12val_12
+67val_67
+84val_84
+58val_58
+8val_8
+24val_24
+42val_42
+0val_0
+96val_96
+26val_26
+51val_51
+43val_43
+95val_95
+98val_98
+85val_85
+77val_77
+0val_0
+87val_87
+15val_15
+72val_72
+90val_90
+19val_19
+10val_10
+5val_5
+58val_58
+35val_35
+95val_95
+11val_11
+34val_34
+42val_42
+78val_78
+76val_76
+41val_41
+30val_30
+64val_64
+76val_76
+74val_74
+69val_69
+33val_33
+70val_70
+5val_5
+2val_2
+35val_35
+80val_80
+44val_44
+53val_53
+90val_90
+12val_12
+5val_5
+70val_70
+24val_24
+70val_70
+83val_83
+26val_26
+67val_67
+18val_18
+9val_9
+18val_18
+97val_97
+84val_84
+28val_28
+37val_37
+90val_90
+97val_97

Added: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/lt100.txt.deflate
URL: 
http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/lt100.txt.deflate?rev=1148501&view=auto
==============================================================================
--- 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/lt100.txt.deflate
 (added)
+++ 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/lt100.txt.deflate
 Tue Jul 19 19:44:48 2011
@@ -0,0 +1,3 @@
+xœMR;nDASZŸføŸÓDéSçü=ï.Ó!ƒÁ*¾þ~~¿+ ùDšèz¢.³0f-!û‰d£”\…
0+‰õ›ÈN(!]hַ™õD˃‚±¿mlBÛ±…‘ ˜3Ý8Ý ì!Š`ßH¹u¸t³
+ʜ:œL׏î¦ã>û`¤qMwÎtCSGïk[E¬6’:röQDêÞßxo–õ‚4³
!&g—9™¡JýÙí/ÉÍBÒWœ?β… 
7üªKb骋†qfHrstr¨^*‹5µà¯3Ÿ»°Ã¶Ûýç’ï^Ó}®6ØüÀ\k~@èY
+”Ý7ª¾?E™Õº¾}´
ã?úÍÙ
\ No newline at end of file

Added: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/README
URL: 
http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/README?rev=1148501&view=auto
==============================================================================
--- 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/README
 (added)
+++ 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/README
 Tue Jul 19 19:44:48 2011
@@ -0,0 +1,145 @@
+SUMMARY & USAGE LICENSE
+=============================================
+
+MovieLens data sets were collected by the GroupLens Research Project
+at the University of Minnesota.
+ 
+This data set consists of:
+       * 100,000 ratings (1-5) from 943 users on 1682 movies. 
+       * Each user has rated at least 20 movies. 
+        * Simple demographic info for the users (age, gender, occupation, zip)
+
+The data was collected through the MovieLens web site
+(movielens.umn.edu) during the seven-month period from September 19th, 
+1997 through April 22nd, 1998. This data has been cleaned up - users
+who had less than 20 ratings or did not have complete demographic
+information were removed from this data set. Detailed descriptions of
+the data file can be found at the end of this file.
+
+Neither the University of Minnesota nor any of the researchers
+involved can guarantee the correctness of the data, its suitability
+for any particular purpose, or the validity of results based on the
+use of the data set.  The data set may be used for any research
+purposes under the following conditions:
+
+     * The user may not state or imply any endorsement from the
+       University of Minnesota or the GroupLens Research Group.
+
+     * The user must acknowledge the use of the data set in
+       publications resulting from the use of the data set, and must
+       send us an electronic or paper copy of those publications.
+
+     * The user may not redistribute the data without separate
+       permission.
+
+     * The user may not use this information for any commercial or
+       revenue-bearing purposes without first obtaining permission
+       from a faculty member of the GroupLens Research Project at the
+       University of Minnesota.
+
+If you have any further questions or comments, please contact Jon Herlocker
+<[email protected]>. 
+
+ACKNOWLEDGEMENTS
+==============================================
+
+Thanks to Al Borchers for cleaning up this data and writing the
+accompanying scripts.
+
+PUBLISHED WORK THAT HAS USED THIS DATASET
+==============================================
+
+Herlocker, J., Konstan, J., Borchers, A., Riedl, J.. An Algorithmic
+Framework for Performing Collaborative Filtering. Proceedings of the
+1999 Conference on Research and Development in Information
+Retrieval. Aug. 1999.
+
+FURTHER INFORMATION ABOUT THE GROUPLENS RESEARCH PROJECT
+==============================================
+
+The GroupLens Research Project is a research group in the Department
+of Computer Science and Engineering at the University of Minnesota.
+Members of the GroupLens Research Project are involved in many
+research projects related to the fields of information filtering,
+collaborative filtering, and recommender systems. The project is lead
+by professors John Riedl and Joseph Konstan. The project began to
+explore automated collaborative filtering in 1992, but is most well
+known for its world wide trial of an automated collaborative filtering
+system for Usenet news in 1996.  The technology developed in the
+Usenet trial formed the base for the formation of Net Perceptions,
+Inc., which was founded by members of GroupLens Research. Since then
+the project has expanded its scope to research overall information
+filtering solutions, integrating in content-based methods as well as
+improving current collaborative filtering technology.
+
+Further information on the GroupLens Research project, including
+research publications, can be found at the following web site:
+        
+        http://www.grouplens.org/
+
+GroupLens Research currently operates a movie recommender based on
+collaborative filtering:
+
+        http://www.movielens.org/
+
+DETAILED DESCRIPTIONS OF DATA FILES
+==============================================
+
+Here are brief descriptions of the data.
+
+ml-data.tar.gz   -- Compressed tar file.  To rebuild the u data files do this:
+                gunzip ml-data.tar.gz
+                tar xvf ml-data.tar
+                mku.sh
+
+u.data     -- The full u data set, 100000 ratings by 943 users on 1682 items.
+              Each user has rated at least 20 movies.  Users and items are
+              numbered consecutively from 1.  The data is randomly
+              ordered. This is a tab separated list of 
+                user id | item id | rating | timestamp. 
+              The time stamps are unix seconds since 1/1/1970 UTC   
+
+u.info     -- The number of users, items, and ratings in the u data set.
+
+u.item     -- Information about the items (movies); this is a tab separated
+              list of
+              movie id | movie title | release date | video release date |
+              IMDb URL | unknown | Action | Adventure | Animation |
+              Children's | Comedy | Crime | Documentary | Drama | Fantasy |
+              Film-Noir | Horror | Musical | Mystery | Romance | Sci-Fi |
+              Thriller | War | Western |
+              The last 19 fields are the genres, a 1 indicates the movie
+              is of that genre, a 0 indicates it is not; movies can be in
+              several genres at once.
+              The movie ids are the ones used in the u.data data set.
+
+u.genre    -- A list of the genres.
+
+u.user     -- Demographic information about the users; this is a tab
+              separated list of
+              user id | age | gender | occupation | zip code
+              The user ids are the ones used in the u.data data set.
+
+u.occupation -- A list of the occupations.
+
+u1.base    -- The data sets u1.base and u1.test through u5.base and u5.test
+u1.test       are 80%/20% splits of the u data into training and test data.
+u2.base       Each of u1, ..., u5 have disjoint test sets; this if for
+u2.test       5 fold cross validation (where you repeat your experiment
+u3.base       with each training and test set and average the results).
+u3.test       These data sets can be generated from u.data by mku.sh.
+u4.base
+u4.test
+u5.base
+u5.test
+
+ua.base    -- The data sets ua.base, ua.test, ub.base, and ub.test
+ua.test       split the u data into a training set and a test set with
+ub.base       exactly 10 ratings per user in the test set.  The sets
+ub.test       ua.test and ub.test are disjoint.  These data sets can
+              be generated from u.data by mku.sh.
+
+allbut.pl  -- The script that generates training and test sets where
+              all but n of a users ratings are in the training data.
+
+mku.sh     -- A shell script to generate all the u data sets from u.data.

Added: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/allbut.pl
URL: 
http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/allbut.pl?rev=1148501&view=auto
==============================================================================
--- 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/allbut.pl
 (added)
+++ 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/allbut.pl
 Tue Jul 19 19:44:48 2011
@@ -0,0 +1,34 @@
+#!/usr/local/bin/perl
+
+# get args
+if (@ARGV < 3) {
+       print STDERR "Usage: $0 base_name start stop max_test [ratings ...]\n";
+       exit 1;
+}
+$basename = shift;
+$start = shift;
+$stop = shift;
+$maxtest = shift;
+
+# open files
+open( TESTFILE, ">$basename.test" ) or die "Cannot open $basename.test for 
writing\n";
+open( BASEFILE, ">$basename.base" ) or die "Cannot open $basename.base for 
writing\n";
+
+# init variables
+$testcnt = 0;
+
+while (<>) {
+       ($user) = split;
+       if (! defined $ratingcnt{$user}) {
+               $ratingcnt{$user} = 0;
+       }
+       ++$ratingcnt{$user};
+       if (($testcnt < $maxtest || $maxtest <= 0)
+       && $ratingcnt{$user} >= $start && $ratingcnt{$user} <= $stop) {
+               ++$testcnt;
+               print TESTFILE;
+       }
+       else {
+               print BASEFILE;
+       }
+}

Propchange: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/allbut.pl
------------------------------------------------------------------------------
    svn:executable = *

Added: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/mku.sh
URL: 
http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/mku.sh?rev=1148501&view=auto
==============================================================================
--- 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/mku.sh
 (added)
+++ 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/mku.sh
 Tue Jul 19 19:44:48 2011
@@ -0,0 +1,25 @@
+#!/bin/sh
+
+trap `rm -f tmp.$$; exit 1` 1 2 15
+
+for i in 1 2 3 4 5
+do
+       head -`expr $i \* 20000` u.data | tail -20000 > tmp.$$
+       sort -t"        " -k 1,1n -k 2,2n tmp.$$ > u$i.test
+       head -`expr \( $i - 1 \) \* 20000` u.data > tmp.$$
+       tail -`expr \( 5 - $i \) \* 20000` u.data >> tmp.$$
+       sort -t"        " -k 1,1n -k 2,2n tmp.$$ > u$i.base
+done
+
+allbut.pl ua 1 10 100000 u.data
+sort -t"       " -k 1,1n -k 2,2n ua.base > tmp.$$
+mv tmp.$$ ua.base
+sort -t"       " -k 1,1n -k 2,2n ua.test > tmp.$$
+mv tmp.$$ ua.test
+
+allbut.pl ub 11 20 100000 u.data
+sort -t"       " -k 1,1n -k 2,2n ub.base > tmp.$$
+mv tmp.$$ ub.base
+sort -t"       " -k 1,1n -k 2,2n ub.test > tmp.$$
+mv tmp.$$ ub.test
+

Propchange: 
incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/seed_data_files/ml-data/mku.sh
------------------------------------------------------------------------------
    svn:executable = *


Reply via email to