-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathClustering External Indices with smile and spark.snb
553 lines (553 loc) · 44.1 KB
/
Clustering External Indices with smile and spark.snb
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
{
"metadata" : {
"name" : "Clustering External Indices with smile and spark",
"user_save_timestamp" : "1970-01-01T01:00:00.000Z",
"auto_save_timestamp" : "1970-01-01T01:00:00.000Z",
"language_info" : {
"name" : "scala",
"file_extension" : "scala",
"codemirror_mode" : "text/x-scala"
},
"trusted" : true,
"customLocalRepo" : "/tmp/repo",
"customRepos" : [ "spartakus % default % http://dl.bintray.com/spark-clustering-notebook/maven % maven" ],
"customDeps" : [ "com.github.haifengl % smile-scala_2.11 % 1.1.0" ],
"customImports" : null,
"customArgs" : null,
"customSparkConf" : null
},
"cells" : [ {
"metadata" : { },
"cell_type" : "markdown",
"source" : "#External Indices\n###Example using SMILE and SPARK"
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "This work was done during an internship (2016) at Computer Science Laboratory (Laboratoire d'Informatique de Paris Nord, LIPN) at the University of Paris 13, with CAO Anh Quan supervized by LEBBAH Mustapha (LIPN, Paris 13 university), AZZAG Hanene (LIPN, Paris 13 university), DOAN Nhat Quang (USTH, Vietnam). \n\nThe purpose of this program is to calculate the External Indices using SPARK which is used to measure how good is the clustering algorithm using labels. In this work, we implement popular external indices. This work is based on the Cluster Crit package in R\n\nThe clustering algorithms are based on SMILE [Smile (Statistical Machine Intelligence and Learning Engine)](https://github.com/haifengl/smile). Smile is a fast and comprehensive machine learning system. \n\nGet Smile from the [GitHub project releases page](https://github.com/haifengl/smile/releases). Downloads are pre-packaged for Mac and universal tarball."
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "import smile._\nimport smile.io._\nimport smile.util._\nimport smile.math._, Math._\nimport smile.math.distance._\nimport smile.math.kernel._\nimport smile.math.matrix._\nimport smile.stat.distribution._\nimport smile.data._\nimport smile.interpolation._\nimport smile.validation._\nimport smile.association._\nimport smile.regression._\nimport smile.classification._\nimport smile.feature._\nimport smile.clustering._\nimport smile.vq._\nimport smile.manifold._\nimport smile.mds._\nimport smile.sequence._\nimport smile.projection._\nimport smile.nlp._\nimport smile.plot._\nimport java.awt.Color\nimport smile.wavelet._\n\n// import smile.shell._\n",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "import smile._\nimport smile.io._\nimport smile.util._\nimport smile.math._\nimport Math._\nimport smile.math.distance._\nimport smile.math.kernel._\nimport smile.math.matrix._\nimport smile.stat.distribution._\nimport smile.data._\nimport smile.interpolation._\nimport smile.validation._\nimport smile.association._\nimport smile.regression._\nimport smile.classification._\nimport smile.feature._\nimport smile.clustering._\nimport smile.vq._\nimport smile.manifold._\nimport smile.mds._\nimport smile.sequence._\nimport smile.projection._\nimport smile.nlp._\nimport smile.plot._\nimport java.awt.Color\nimport smile.wavelet._\n"
}, {
"metadata" : { },
"data" : {
"text/html" : ""
},
"output_type" : "execute_result",
"execution_count" : 6
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "#External Indices : Spark"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "import org.apache.spark.rdd.RDD\n\n/*\n * rdd1: the real cluster label\n * rdd2: the predicted cluster label\n *\n */\nclass ExternalIndex(var rdd1:RDD[String],var rdd2:RDD[String]) extends Serializable {\n \n val combinedRDD = rdd1.zip(rdd2)\n// combinedRDD.cache\n \n // Cartesian the combinedRDD with itself so we can use the map function to process on the pair of points\n val cart = combinedRDD.cartesian(combinedRDD)\n \n /*\n * Take in 2 pair of cluster label and return the yy,ny,nn,yn\n */\n private def notation(point1:(String,String),point2:(String,String)) = {\n if ( (point1._1 == point2._1) && (point1._2 == point2._2) ){\n (\"yy\",1)\n } else if ( (point1._1 == point2._1) && (point1._2 != point2._2) ){\n (\"yn\",1)\n } else if ( (point1._1 != point2._1) && (point1._2 == point2._2) ){\n (\"ny\",1)\n } else {\n (\"nn\",1)\n }\n }\n \n /*\n * Compute the confusion table\n */\n def confusionTable()= {\n this.combinedRDD.map(line => ( line ,1) ).reduceByKey(_+_)\n }\n \n def getNotations() = {\n val resultNotation = this.cart.map(v => this.notation(v._1,v._2))\n resultNotation.reduceByKey(_+_)\n }\n \n def purity()= {\n val table = this.confusionTable\n val cols = table.map( v => (v._1._2,v))\n val t = cols.map(v => (v._1,v._2._2))\n \n val sum = t.reduceByKey(_+_)\n val max = t.reduceByKey( (a,b) => if (a>b){a}else{b} )\n \n sum.join(max).map(v => v._2).map(a => a._2.toDouble/a._1 ).reduce(_+_)/sum.count\n }\n \n def nmi() = {\n val num_rows = combinedRDD.count();\n val t = this.confusionTable\n \n val cols = t.map(v => (v._1._2,v._2)).reduceByKey(_+_).collectAsMap\n val rows = t.map(v => (v._1._1,v._2)).reduceByKey(_+_).collectAsMap\n println(cols)\n val rightDenum = t.map(v => (v._1._2,v._2)).reduceByKey(_+_).map(v => cols.get(v._1).get * scala.math.log10((v._2.toDouble)/num_rows)).reduce(_+_);\n val leftDenum = t.map(v => (v._1._1,v._2)).reduceByKey(_+_).map(v => rows.get(v._1).get * scala.math.log10((v._2.toDouble)/num_rows) ).reduce(_+_) \n\n val numerator = -2 * t.map(v => scala.math.log10( ((v._2 * num_rows).toDouble / (rows.get(v._1._1).get * cols.get(v._1._2).get )) )*v._2).reduce(_+_)\n \n numerator/(leftDenum + rightDenum)\n }\n \n def precision():Double = {\n return this.yy.toDouble / (this.yy+this.ny)\n }\n def recall():Double = {\n return (this.yy.toDouble / (this.yy+this.yn))\n }\n \n \n def yy() = {\n val notations = this.getNotations\n if (notations.lookup(\"yy\").length == 0){\n 0.0\n } else {\n ((notations.lookup(\"yy\")(0) - combinedRDD.count())/2).toDouble\n }\n }\n \n def yn() = {\n val notations = this.getNotations\n if (notations.lookup(\"yn\").length == 0){\n 0.0\n } else {\n ((notations.lookup(\"yn\")(0))/2).toDouble\n }\n\n }\n \n def ny() = {\n val notations = this.getNotations\n if (notations.lookup(\"ny\").length == 0){\n 0.0\n } else {\n ((notations.lookup(\"ny\")(0))/2).toDouble\n }\n }\n \n def nn() = {\n val notations = this.getNotations\n if (notations.lookup(\"nn\").length == 0){\n 0.0\n } else {\n ((notations.lookup(\"nn\")(0))/2).toDouble\n }\n }\n def nt() = {\n this.yy + this.yn + this.nn + this.ny\n }\n \n def czekanowskiDice():Double = {\n return ((2*(this.yy)) / (2* this.yy + this.yn + this.ny ))\n }\n\n def rand():Double = {\n val notations = this.getNotations\n return ( (this.yy + this.nn) / this.nt )\n }\n def rogersTanimoto(): Double = {\n val denominator = this.yy + (2*(this.yn+this.ny))+this.nn\n return ((this.yy + this.nn) / denominator)\n }\n def folkesMallows():Double = {\n val denominator = (this.yy+ this.yn)*(this.ny+this.yy)\n return (this.yy / scala.math.sqrt(denominator))\n }\n// def hubert():Double = {\n// val yy_yn = this.yy + this.yn\n// val yy_ny = this.yy + this.ny\n// val nn_yn = this.nn + this.yn\n// val nn_ny = this.nn + this.ny\n// val denominator = math.sqrt(yy_yn) * math.sqrt(yy_ny) * math.sqrt(nn_yn) * math.sqrt(nn_ny)\n// ((this.nt*this.yy) - (yy_yn*yy_ny))/denominator\n// }\n def jaccard():Double = {\n this.yy/(this.yy + this.yn + this.ny)\n }\n def kulczynski():Double = {\n ((this.yy / (this.yy + this.ny)) + (this.yy / (this.yy+this.yn)))/2\n }\n def mcNemar():Double = {\n (((this.nn - this.ny) )/ scala.math.sqrt(this.nn + this.ny))\n }\n// def phi():Double = {\n// val num = (this.yy*this.nn)-(this.yn*this.ny)\n// val denum = (this.yy + this.yn)*(this.yy + this.ny)*(this.yn + this.nn)*(this.ny + this.nn)\n// num/denum\n// }\n def russelRao():Double = {\n this.yy / this.nt\n }\n def sokalSneath1():Double = {\n val denum = this.yy + (2*(this.yn + this.ny))\n this.yy / denum\n }\n def sokalSneath2():Double = {\n val denum = this.yy + this.nn + ((yn + ny)/2)\n (this.yy + this.nn)/ denum\n }\n}\n",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "import org.apache.spark.rdd.RDD\ndefined class ExternalIndex\n"
}, {
"metadata" : { },
"data" : {
"text/html" : ""
},
"output_type" : "execute_result",
"execution_count" : 9
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "#Hierarchical Clustering : Smile"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "val x = readCsv(\"DS2.csv\" ).unzip\nval clusters = hclust(pdist(x), \"complete\")\nval y_hier = clusters.partition(13)\nplot(x, y_hier, '.', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "x: Array[Array[Double]] = Array(Array(203.0, 69.0), Array(245.0, 214.0), Array(151.0, 108.0), Array(269.0, 84.0), Array(179.0, 221.0), Array(130.0, 104.0), Array(36.0, 301.0), Array(249.0, 74.0), Array(183.0, 243.0), Array(33.0, 69.0), Array(139.0, 342.0), Array(238.0, 268.0), Array(332.0, 148.0), Array(51.0, 268.0), Array(94.0, 38.0), Array(136.0, 255.0), Array(252.0, 218.0), Array(322.0, 327.0), Array(36.0, 339.0), Array(226.0, 74.0), Array(139.0, 207.0), Array(198.0, 80.0), Array(247.0, 113.0), Array(41.0, 292.0), Array(48.0, 163.0), Array(182.0, 187.0), Array(54.0, 322.0), Array(270.0, 188.0), Array(110.0, 342.0), Array(179.0, 231.0), Array(42.0, 296.0), Array(125.0, 75.0), Array(250.0, 39.0), Array(270.0, 82.0), Array(267.0, 214.0), Array(119.0, 39.0), Array(241.0, 192.0), Array(32..."
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame3,220,23,1000x843,layout=java.awt.BorderLayout,title=Smile Plot 4,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x821,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x821,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 17
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/hier.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "#K-Means : Smile"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "val clusters = kmeans(x, 13, runs = 20)\nval y_kmean = clusters.getClusterLabel\nplot(x, y_kmean, '.', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "clusters: smile.clustering.KMeans =\nK-Means distortion: 6522810,96585\nClusters of 5458 data points of dimension 2:\n 0\t 440 ( 8.1%)\n 1\t 372 ( 6.8%)\n 2\t 564 (10.3%)\n 3\t 551 (10.1%)\n 4\t 449 ( 8.2%)\n 5\t 391 ( 7.2%)\n 6\t 367 ( 6.7%)\n 7\t 346 ( 6.3%)\n 8\t 614 (11.2%)\n 9\t 329 ( 6.0%)\n 10\t 449 ( 8.2%)\n 11\t 287 ( 5.3%)\n 12\t 299 ( 5.5%)\n\ny_kmean: Array[Int] = Array(10, 0, 3, 2, 4, 3, 1, 2, 4, 6, 9, 0, 11, 1, 3, 4, 0, 7, 1, 10, 4, 10, 2, 1, 12, 8, 1, 0, 9, 4, 1, 3, 10, 2, 0, 3, 0, 11, 10, 2, 12, 2, 8, 4, 10, 11, 0, 0, 4, 11, 2, 5, 10, 2, 11, 6, 7, 4, 0, 0, 2, 8, 8, 9, 8, 0, 2, 1, 0, 11, 4, 2, 1, 12, 10, 10, 7, 5, 0, 9, 11, 7, 1, 6, 0, 4, 8, 3, 11, 2, 8, 5, 9, 12, 5, 3, 10, 9, 2, 7, 11, 1, 10, 0, 0, 3, 8, 1, 6, 11, 6, 2, 5, 5, 3, 6, 3, 10, 1, 1, 5, 0, 8, 5, 10, 7, 3, 7, 10, 3, 9..."
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame1,220,23,1000x843,layout=java.awt.BorderLayout,title=Smile Plot 2,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x821,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x821,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 13
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/kmean1.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "#G-Means : Smile"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "val clusters = gmeans(x,13)\nval y_gmean = clusters.getClusterLabel\nplot(x, y_gmean, '.', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "clusters: smile.clustering.GMeans =\nG-Means distortion: 7489294,82453\nClusters of 5458 data points of dimension 2:\n 0\t 276 ( 5.1%)\n 1\t 454 ( 8.3%)\n 2\t 383 ( 7.0%)\n 3\t 322 ( 5.9%)\n 4\t 279 ( 5.1%)\n 5\t 177 ( 3.2%)\n 6\t 242 ( 4.4%)\n 7\t 742 (13.6%)\n 8\t 603 (11.0%)\n 9\t 346 ( 6.3%)\n 10\t 460 ( 8.4%)\n 11\t 687 (12.6%)\n 12\t 487 ( 8.9%)\n\ny_gmean: Array[Int] = Array(7, 1, 11, 7, 9, 11, 10, 7, 9, 12, 4, 1, 0, 10, 11, 5, 1, 3, 10, 7, 9, 7, 7, 10, 12, 8, 10, 1, 4, 9, 10, 11, 7, 7, 1, 11, 1, 6, 11, 6, 12, 6, 8, 9, 7, 0, 1, 1, 1, 0, 6, 2, 7, 7, 0, 11, 0, 9, 1, 1, 6, 8, 8, 4, 8, 1, 7, 10, 9, 0, 9, 7, 10, 12, 7, 7, 3, 2, 1, 4, 0, 3, 10, 12, 1, 9, 8, 8, 0, 6, 8, 2, 4, 12, 2, 11, 11, 4, 7, 3, 0, 4, 7, 1, 1, 11, 8, 10, 12, 6, 12, 7, 2, 2, 11, 12, 11, 7, 10, 10, 2, 1, 8, 2, 7, 3, 11, 3, 7..."
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame2,220,23,1000x843,layout=java.awt.BorderLayout,title=Smile Plot 3,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x821,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x821,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 14
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/gmean1.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "#External Indices : Spark"
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "We will compute 12 internal indices:\n* Czekanowski Dice \n* Rand Index\n* Rogers Tanimoto \n* Folkes Mallows \n* Jaccard \n* Kulczynski\n* McNemar\n* Russel Rao\n* Sokal Sneath 1\n* Sokal Sneath 2\n* Recall\n* Precision"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "val realLabels = sc.parallelize(readCsv(\"labels.csv\").unzip.map(_(0).toInt.toString))",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "realLabels: org.apache.spark.rdd.RDD[String] = ParallelCollectionRDD[0] at parallelize at <console>:198\n"
}, {
"metadata" : { },
"data" : {
"text/html" : "ParallelCollectionRDD[0] at parallelize at <console>:198"
},
"output_type" : "execute_result",
"execution_count" : 18
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "##Hierarchical Clustering"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "val predict_hier = sc.parallelize(y_hier).map(_.toString)\nval id_hier = new ExternalIndex(realLabels,predict_hier)\nprintln(\"czekanowskiDice=\"+id_hier.czekanowskiDice)\nprintln(\"rand=\"+id_hier.rand)\nprintln(\"rogersTanimoto=\"+id_hier.rogersTanimoto)\nprintln(\"folkesMallows=\"+id_hier.folkesMallows)\nprintln(\"jaccard=\"+id_hier.jaccard)\nprintln(\"kulczynski=\"+id_hier.kulczynski)\nprintln(\"mcNemar=\"+id_hier.mcNemar)\nprintln(\"russelRao=\"+id_hier.russelRao)\nprintln(\"sokalSneath1=\"+id_hier.sokalSneath1)\nprintln(\"sokalSneath2=\"+id_hier.sokalSneath2)\nprintln(\"recall=\"+id_hier.recall)\nprintln(\"precision=\"+id_hier.precision)\n",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "czekanowskiDice=0.3749675958471351\nrand=0.8528303462904255\nrogersTanimoto=0.7434212921625402\nfolkesMallows=0.3867034566432036\njaccard=0.23074468846829366\nkulczynski=0.39880663032217223\n"
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "##K-means"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : true
},
"cell_type" : "code",
"source" : "val predict_kmean = sc.parallelize(y_kmean).map(_.toString)\nval id_kmean = new ExternalIndex(realLabels,predict_kmean)\nprintln(\"czekanowskiDice=\"+id_kmean.czekanowskiDice)\nprintln(\"rand=\"+id_kmean.rand)\nprintln(\"rogersTanimoto=\"+id_kmean.rogersTanimoto)\nprintln(\"folkesMallows=\"+id_kmean.folkesMallows)\nprintln(\"jaccard=\"+id_kmean.jaccard)\nprintln(\"kulczynski=\"+id_kmean.kulczynski)\nprintln(\"mcNemar=\"+id_kmean.mcNemar)\nprintln(\"russelRao=\"+id_kmean.russelRao)\nprintln(\"sokalSneath1=\"+id_kmean.sokalSneath1)\nprintln(\"sokalSneath2=\"+id_kmean.sokalSneath2)\nprintln(\"recall=\"+id_kmean.recall)\nprintln(\"precision=\"+id_kmean.precision)",
"outputs" : [ ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "##G-means"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : true
},
"cell_type" : "code",
"source" : "val predict_gmean = sc.parallelize(y_gmean).map(_.toString)\nval id_gmean = new ExternalIndex(realLabels,predict_gmean)\nprintln(\"czekanowskiDice=\"+id_gmean.czekanowskiDice)\nprintln(\"rand=\"+id_gmean.rand)\nprintln(\"rogersTanimoto=\"+id_gmean.rogersTanimoto)\nprintln(\"folkesMallows=\"+id_gmean.folkesMallows)\nprintln(\"jaccard=\"+id_gmean.jaccard)\nprintln(\"kulczynski=\"+id_gmean.kulczynski)\nprintln(\"mcNemar=\"+id_gmean.mcNemar)\nprintln(\"russelRao=\"+id_gmean.russelRao)\nprintln(\"sokalSneath1=\"+id_gmean.sokalSneath1)\nprintln(\"sokalSneath2=\"+id_gmean.sokalSneath2)\nprintln(\"recall=\"+id_gmean.recall)\nprintln(\"precision=\"+id_gmean.precision)",
"outputs" : [ ]
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "val indices = Array(id_hier,id_kmean,id_gmean)\nval czekanowskiDice = indices.map(_.czekanowskiDice()).zipWithIndex.map(x => Array(x._2+0.72,x._1))\nval rand = indices.map(_.rand()).zipWithIndex.map(x => Array(x._2+0.72,x._1))\nval rogersTanimoto = indices.map(_.rogersTanimoto()).zipWithIndex.map(x => Array(x._2+0.72,x._1))\nval folkesMallows = indices.map(_.folkesMallows()).zipWithIndex.map(x => Array(x._2+0.72,x._1))\nval jaccard = indices.map(_.jaccard()).zipWithIndex.map(x => Array(x._2+0.72,x._1))\nval kulczynski = indices.map(_.kulczynski()).zipWithIndex.map(x => Array(x._2+0.72,x._1))\nval mcNemar = indices.map(_.mcNemar()).zipWithIndex.map(x => Array(x._2+0.72,x._1))\nval russelRao = indices.map(_.russelRao()).zipWithIndex.map(x => Array(x._2+0.72,x._1))\nval sokalSneath1 = indices.map(_.sokalSneath1()).zipWithIndex.map(x => Array(x._2+0.72,x._1))\nval sokalSneath2 = indices.map(_.sokalSneath2()).zipWithIndex.map(x => Array(x._2+0.72,x._1))\nval recall = indices.map(_.recall()).zipWithIndex.map(x => Array(x._2+0.72,x._1))\nval precision = indices.map(_.precision()).zipWithIndex.map(x => Array(x._2+0.72,x._1))\n",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "indices: Array[ExternalIndex] = Array(ExternalIndex@7c65cee1, ExternalIndex@1b62b7ad, ExternalIndex@130f5d6d)\nczekanowskiDice: Array[Array[Double]] = Array(Array(0.72, 0.3749675958471351), Array(1.72, 0.43770910076750547), Array(2.7199999999999998, 0.496179725296113))\nrand: Array[Array[Double]] = Array(Array(0.72, 0.8528303462904255), Array(1.72, 0.8720090372426338), Array(2.7199999999999998, 0.8813644340076281))\nrogersTanimoto: Array[Array[Double]] = Array(Array(0.72, 0.7434212921625402), Array(1.72, 0.7730638507165107), Array(2.7199999999999998, 0.787892376035573))\nfolkesMallows: Array[Array[Double]] = Array(Array(0.72, 0.3867034566432036), Array(1.72, 0.45697890547427916), Array(2.7199999999999998, 0.5117003528947278))\njaccard: Array[Array[Double]] = Array(Array(0.72, 0.2307446884682..."
}, {
"metadata" : { },
"data" : {
"text/html" : ""
},
"output_type" : "execute_result",
"execution_count" : 20
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<table>\n <tr style=\"color:white\">\n <th></th>\n <th>Hierarchical Clustering</th>\n <th>K-means</th>\n <th>G-means</th>\n <tr>\n <tr>\n <td>Czekanowski Dice</td>\n <td>0.3749675958471351</td>\n <td>0.43770910076750547</td>\n <td>0.496179725296113</td>\n <tr>\n <tr>\n <td>Rand</td>\n <td>0.8528303462904255</td>\n <td>0.8720090372426338</td>\n <td>0.8813644340076281</td>\n <tr>\n <tr>\n <td>Rogers Tanimoto</td>\n <td>0.7434212921625402</td>\n <td>0.7730638507165107</td>\n <td>0.787892376035573</td>\n <tr>\n <tr>\n <td>Folkes Mallows</td>\n <td>0.3867034566432036</td>\n <td>0.45697890547427916</td>\n <td>0.5117003528947278</td>\n <tr>\n <tr>\n <td>Jaccard</td>\n <td>0.23074468846829366</td>\n <td>0.2801713182753215</td>\n <td>0.3299461602177257</td>\n <tr>\n <tr>\n <td>Kulczynski</td>\n <td>0.39880663032217223</td>\n <td>0.4770970484330702</td>\n <td>0.5277064696594125</td>\n <tr>\n <tr>\n <td>Mc Nemar</td>\n <td>3190.862945221066</td>\n <td>3303.7038279166877</td>\n <td>3310.000908699689</td>\n <tr>\n <tr>\n <td>Russel Rao</td>\n <td>0.0441447922271548</td>\n <td>0.04981657118349509</td>\n <td>0.05841821528425071</td>\n <tr>\n <tr>\n <td>Sokal Sneath 1</td>\n <td>0.13041910173412447</td>\n <td>0.16290652740734624</td>\n <td>0.1975661816152831</td>\n <tr>\n <tr>\n <td>Sokal Sneath 2</td>\n <td>0.9205703565875718</td>\n <td>0.93162908927732</td>\n <td>0.9369417408727888</td>\n <tr>\n <tr>\n <td>Recall</td>\n <td>0.30130193808060035</td>\n <td>0.34001359365067435</td>\n <td>0.39872249015881106</td>\n <tr>\n <tr>\n <td>Precision</td>\n <td>0.49631132256374405</td>\n <td>0.614180503215466</td>\n <td>0.656690449160014</td>\n <tr>\n\n</table>"
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "##Draw\n###From Left to Right\n* Hierarchical Clustering\n* K-means\n* G-means"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "plot(czekanowskiDice, Array(0,0,0), 'Q', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "res121: smile.plot.Window = Window(javax.swing.JFrame[frame47,244,23,1000x877,invalid,layout=java.awt.BorderLayout,title=Smile Plot 48,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x978,invalid,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,0x0,invalid,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])\n"
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame47,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 48,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 65
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/1.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "plot(rand, Array(0,0,0), 'Q', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "res77: smile.plot.Window = Window(javax.swing.JFrame[frame28,244,23,1000x877,invalid,layout=java.awt.BorderLayout,title=Smile Plot 29,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,invalid,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777675,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,0x0,invalid,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])\n"
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame28,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 29,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 43
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/2.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "plot(rogersTanimoto, Array(0,0,0), 'Q', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "res81: smile.plot.Window = Window(javax.swing.JFrame[frame30,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 31,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=11,maximumSize=,minimumSize=,preferredSize=])\n"
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame30,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 31,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 45
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/3.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "plot(folkesMallows, Array(0,0,0), 'Q', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "res87: smile.plot.Window = Window(javax.swing.JFrame[frame32,244,23,1000x877,invalid,layout=java.awt.BorderLayout,title=Smile Plot 33,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x978,invalid,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,0x0,invalid,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])\n"
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame32,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 33,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 48
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/4.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "plot(jaccard, Array(0,0,0), 'Q', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "res93: smile.plot.Window = Window(javax.swing.JFrame[frame34,244,23,1000x877,invalid,layout=java.awt.BorderLayout,title=Smile Plot 35,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,invalid,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,0x0,invalid,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])\n"
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame34,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 35,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 51
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/5.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "plot(kulczynski, Array(0,0,0), 'Q', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "res97: smile.plot.Window = Window(javax.swing.JFrame[frame36,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 37,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=8203,maximumSize=,minimumSize=,preferredSize=])\n"
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame36,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 37,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 53
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/6.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "plot(mcNemar, Array(0,0,0), 'Q', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "res99: smile.plot.Window = Window(javax.swing.JFrame[frame37,244,23,1000x877,invalid,layout=java.awt.BorderLayout,title=Smile Plot 38,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,invalid,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,0x0,invalid,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])\n"
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame37,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 38,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 54
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/7.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "plot(russelRao, Array(0,0,0), 'Q', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "res101: smile.plot.Window = Window(javax.swing.JFrame[frame38,244,23,1000x877,invalid,layout=java.awt.BorderLayout,title=Smile Plot 39,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,invalid,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,0x0,invalid,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])\n"
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame38,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 39,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 55
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/8.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "plot(sokalSneath1, Array(0,0,0), 'Q', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "res103: smile.plot.Window = Window(javax.swing.JFrame[frame39,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 40,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])\n"
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame39,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 40,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 56
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/9.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "plot(sokalSneath2, Array(0,0,0), 'Q', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "res105: smile.plot.Window = Window(javax.swing.JFrame[frame40,244,23,1000x877,invalid,layout=java.awt.BorderLayout,title=Smile Plot 41,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,invalid,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777675,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,0x0,invalid,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])\n"
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame40,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 41,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 57
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/10.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "plot(recall, Array(0,0,0), 'Q', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "res107: smile.plot.Window = Window(javax.swing.JFrame[frame41,244,23,1000x877,invalid,layout=java.awt.BorderLayout,title=Smile Plot 42,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,invalid,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,0x0,invalid,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])\n"
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame41,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 42,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 58
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/11.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : false
},
"cell_type" : "code",
"source" : "plot(precision, Array(0,0,0), 'Q', Palette.COLORS)",
"outputs" : [ {
"name" : "stdout",
"output_type" : "stream",
"text" : "res117: smile.plot.Window = Window(javax.swing.JFrame[frame45,244,23,1000x877,invalid,layout=java.awt.BorderLayout,title=Smile Plot 46,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x978,invalid,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,0x0,invalid,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])\n"
}, {
"metadata" : { },
"data" : {
"text/html" : "Window(javax.swing.JFrame[frame45,244,23,1000x877,layout=java.awt.BorderLayout,title=Smile Plot 46,resizable,normal,defaultCloseOperation=DISPOSE_ON_CLOSE,rootPane=javax.swing.JRootPane[,0,22,1000x855,layout=javax.swing.JRootPane$RootLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=16777673,maximumSize=,minimumSize=,preferredSize=],rootPaneCheckingEnabled=true],smile.plot.PlotCanvas[,0,0,1000x855,layout=java.awt.BorderLayout,alignmentX=0.0,alignmentY=0.0,border=,flags=9,maximumSize=,minimumSize=,preferredSize=])"
},
"output_type" : "execute_result",
"execution_count" : 63
} ]
}, {
"metadata" : { },
"cell_type" : "markdown",
"source" : "<img src=\"https://s3-ap-southeast-1.amazonaws.com/cmstorage/test/12.png\" style=\"width:80%;height:auto\"/>"
}, {
"metadata" : {
"trusted" : true,
"input_collapsed" : false,
"collapsed" : true
},
"cell_type" : "code",
"source" : "",
"outputs" : [ ]
} ],
"nbformat" : 4
}