-
Notifications
You must be signed in to change notification settings - Fork 0
/
Model1.xml
637 lines (637 loc) · 44.6 KB
/
Model1.xml
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
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
<?xml version="1.0" encoding="UTF-8"?><process version="9.10.001">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="9.4.000" expanded="true" name="Process" origin="GENERATED_TUTORIAL">
<parameter key="logverbosity" value="init"/>
<parameter key="random_seed" value="2001"/>
<parameter key="send_mail" value="never"/>
<parameter key="notification_email" value=""/>
<parameter key="process_duration_for_mail" value="30"/>
<parameter key="encoding" value="SYSTEM"/>
<process expanded="true">
<operator activated="true" class="productivity:execute_process" compatibility="9.10.001" expanded="true" height="103" name="Execute Process" width="90" x="45" y="187">
<parameter key="process_location" value="//Local Repository/Thesis/Data Preparation/FinalDatasetPreprocessingUniqueSubjectID"/>
<parameter key="use_input" value="true"/>
<parameter key="store_output" value="false"/>
<parameter key="propagate_metadata_recursively" value="true"/>
<parameter key="cache_process" value="true"/>
<list key="macros"/>
<parameter key="fail_for_unknown_macros" value="true"/>
</operator>
<operator activated="true" class="subprocess" compatibility="9.10.001" expanded="true" height="166" name="Training Data Preparation" width="90" x="179" y="85">
<process expanded="true">
<operator activated="true" class="remove_correlated_attributes" compatibility="9.10.001" expanded="true" height="82" name="Remove Correlated Attributes" origin="EXPORTED_TURBOPREP" width="90" x="45" y="34">
<parameter key="correlation" value="0.9"/>
<parameter key="filter_relation" value="greater"/>
<parameter key="attribute_order" value="original"/>
<parameter key="use_absolute_correlation" value="true"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
<description align="center" color="transparent" colored="false" width="126">Remove columns with correlation > 0.900</description>
</operator>
<operator activated="true" class="subprocess" compatibility="9.10.001" expanded="true" height="103" name="Outlier elimination" width="90" x="179" y="34">
<process expanded="true">
<operator activated="true" class="normalize" compatibility="9.10.001" expanded="true" height="103" name="Normalize attributes" origin="EXPORTED_AUTOMODEL" width="90" x="45" y="34">
<parameter key="return_preprocessing_model" value="false"/>
<parameter key="create_view" value="false"/>
<parameter key="attribute_filter_type" value="all"/>
<parameter key="attribute" value="ID"/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="numeric"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="real"/>
<parameter key="block_type" value="value_series"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_series_end"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="false"/>
<parameter key="method" value="Z-transformation"/>
<parameter key="min" value="0.0"/>
<parameter key="max" value="1.0"/>
<parameter key="allow_negative_values" value="false"/>
<description align="center" color="transparent" colored="false" width="126">Standardize all columns.</description>
</operator>
<operator activated="true" class="anomalydetection:univariate_anomaly_detection" compatibility="3.3.000" expanded="true" height="82" name="Detect Outlier (Univariate)" width="90" x="179" y="34">
<parameter key="attribute_filter_type" value="all"/>
<parameter key="attribute" value="ID"/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="numeric"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="real"/>
<parameter key="block_type" value="value_series"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_series_end"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="false"/>
<parameter key="method" value="Histogram"/>
<parameter key="aggregation_method" value="Average"/>
<parameter key="show_individual_scores" value="false"/>
</operator>
<operator activated="true" class="anomalydetection:generate_anomaly_flag" compatibility="3.3.000" expanded="true" height="103" name="Generate Outlier Flag" width="90" x="313" y="34">
<parameter key="method" value="contamination"/>
<parameter key="define_score_column" value="true"/>
<parameter key="score_column" value="score"/>
<parameter key="contamination_threshold" value="0.001"/>
<parameter key="manual_threshold" value="1.0"/>
<parameter key="zscore_threshold" value="3.0"/>
</operator>
<operator activated="true" class="filter_examples" compatibility="9.10.001" expanded="true" height="103" name="Fliter out outliers" width="90" x="447" y="34">
<parameter key="parameter_expression" value=""/>
<parameter key="condition_class" value="custom_filters"/>
<parameter key="invert_filter" value="false"/>
<list key="filters_list">
<parameter key="filters_entry_key" value="outlier_flag.does_not_equal.Outlier"/>
</list>
<parameter key="filters_logic_and" value="true"/>
<parameter key="filters_check_metadata" value="true"/>
</operator>
<operator activated="true" class="select_attributes" compatibility="9.10.001" expanded="true" height="82" name="Select Attributes" width="90" x="648" y="34">
<parameter key="attribute_filter_type" value="subset"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value="outlier_flag|score|hadm_id"/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="attribute_value"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="time"/>
<parameter key="block_type" value="attribute_block"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_matrix_row_start"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="true"/>
</operator>
<operator activated="true" class="concurrency:join" compatibility="9.10.001" expanded="true" height="82" name="Join" width="90" x="782" y="85">
<parameter key="remove_double_attributes" value="false"/>
<parameter key="join_type" value="inner"/>
<parameter key="use_id_attribute_as_key" value="true"/>
<list key="key_attributes">
<parameter key="ID" value="ID"/>
</list>
<parameter key="keep_both_join_attributes" value="false"/>
</operator>
<operator activated="true" class="select_attributes" compatibility="9.10.001" expanded="true" height="82" name="Clean ExampleSet" origin="EXPORTED_AUTOMODEL" width="90" x="916" y="85">
<parameter key="attribute_filter_type" value="subset"/>
<parameter key="attribute" value="id"/>
<parameter key="attributes" value="outlier_flag|score"/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="attribute_value"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="time"/>
<parameter key="block_type" value="attribute_block"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_matrix_row_start"/>
<parameter key="invert_selection" value="true"/>
<parameter key="include_special_attributes" value="true"/>
<description align="center" color="transparent" colored="false" width="126">Remove outlier flag and score</description>
</operator>
<connect from_port="in 1" to_op="Normalize attributes" to_port="example set input"/>
<connect from_op="Normalize attributes" from_port="example set output" to_op="Detect Outlier (Univariate)" to_port="exa"/>
<connect from_op="Normalize attributes" from_port="original" to_op="Join" to_port="right"/>
<connect from_op="Detect Outlier (Univariate)" from_port="outlier" to_op="Generate Outlier Flag" to_port="example set"/>
<connect from_op="Generate Outlier Flag" from_port="example set" to_op="Fliter out outliers" to_port="example set input"/>
<connect from_op="Fliter out outliers" from_port="example set output" to_op="Select Attributes" to_port="example set input"/>
<connect from_op="Fliter out outliers" from_port="original" to_port="out 1"/>
<connect from_op="Select Attributes" from_port="example set output" to_op="Join" to_port="left"/>
<connect from_op="Join" from_port="join" to_op="Clean ExampleSet" to_port="example set input"/>
<connect from_op="Clean ExampleSet" from_port="example set output" to_port="out 2"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="source_in 2" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
<portSpacing port="sink_out 3" spacing="0"/>
</process>
</operator>
<operator activated="true" class="subprocess" compatibility="9.10.001" expanded="true" height="145" name="Auto FE" width="90" x="313" y="85">
<process expanded="true">
<operator activated="true" class="multiply" compatibility="9.10.001" expanded="true" height="103" name="Multiply Preprocessed dataset" width="90" x="45" y="34"/>
<operator activated="true" class="select_attributes" compatibility="9.10.001" expanded="true" height="82" name="Attribute Filtering" width="90" x="179" y="85">
<parameter key="attribute_filter_type" value="all"/>
<parameter key="attribute" value="scr_baseline"/>
<parameter key="attributes" value="age|gender|scr_baseline"/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="attribute_value"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="time"/>
<parameter key="block_type" value="attribute_block"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_matrix_row_start"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="false"/>
</operator>
<operator activated="true" class="sample" compatibility="9.10.001" expanded="true" height="82" name="Sample down for FE" width="90" x="313" y="85">
<parameter key="sample" value="relative"/>
<parameter key="balance_data" value="false"/>
<parameter key="sample_size" value="100"/>
<parameter key="sample_ratio" value="0.05"/>
<parameter key="sample_probability" value="0.1"/>
<list key="sample_size_per_class"/>
<list key="sample_ratio_per_class">
<parameter key="ckd" value="0.1"/>
<parameter key="notckd" value="0.1"/>
</list>
<list key="sample_probability_per_class"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
</operator>
<operator activated="true" class="model_simulator:automatic_feature_engineering" compatibility="9.10.001" expanded="true" height="103" name="FE" width="90" x="447" y="85">
<parameter key="mode" value="keep all original features"/>
<parameter key="balance for accuracy" value="1.0"/>
<parameter key="show progress dialog" value="true"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
<parameter key="use optimization heuristics" value="true"/>
<parameter key="maximum generations" value="30"/>
<parameter key="population size" value="10"/>
<parameter key="use multi-starts" value="true"/>
<parameter key="number of multi-starts" value="5"/>
<parameter key="generations until multi-start" value="10"/>
<parameter key="use time limit" value="true"/>
<parameter key="time limit in seconds" value="3600"/>
<parameter key="use subset for generation" value="false"/>
<parameter key="maximum function complexity" value="10"/>
<parameter key="use_plus" value="false"/>
<parameter key="use_diff" value="false"/>
<parameter key="use_mult" value="true"/>
<parameter key="use_div" value="true"/>
<parameter key="reciprocal_value" value="true"/>
<parameter key="use_square_roots" value="false"/>
<parameter key="use_exp" value="false"/>
<parameter key="use_log" value="false"/>
<parameter key="use_absolute_values" value="false"/>
<parameter key="use_sgn" value="false"/>
<parameter key="use_min" value="false"/>
<parameter key="use_max" value="false"/>
<process expanded="true">
<operator activated="true" class="concurrency:cross_validation" compatibility="9.10.001" expanded="true" height="145" name="FE Cross Validation" width="90" x="246" y="34">
<parameter key="split_on_batch_attribute" value="false"/>
<parameter key="leave_one_out" value="false"/>
<parameter key="number_of_folds" value="10"/>
<parameter key="sampling_type" value="stratified sampling"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
<parameter key="enable_parallel_execution" value="true"/>
<process expanded="true">
<operator activated="true" class="concurrency:parallel_random_forest" compatibility="9.10.001" expanded="true" height="103" name="FE Random Forest" width="90" x="112" y="34">
<parameter key="number_of_trees" value="100"/>
<parameter key="criterion" value="gini_index"/>
<parameter key="maximal_depth" value="15"/>
<parameter key="apply_pruning" value="false"/>
<parameter key="confidence" value="0.1"/>
<parameter key="apply_prepruning" value="false"/>
<parameter key="minimal_gain" value="0.01"/>
<parameter key="minimal_leaf_size" value="2"/>
<parameter key="minimal_size_for_split" value="4"/>
<parameter key="number_of_prepruning_alternatives" value="3"/>
<parameter key="random_splits" value="false"/>
<parameter key="guess_subset_ratio" value="true"/>
<parameter key="subset_ratio" value="0.2"/>
<parameter key="voting_strategy" value="confidence vote"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
<parameter key="enable_parallel_execution" value="true"/>
</operator>
<connect from_port="training set" to_op="FE Random Forest" to_port="training set"/>
<connect from_op="FE Random Forest" from_port="model" to_port="model"/>
<portSpacing port="source_training set" spacing="0"/>
<portSpacing port="sink_model" spacing="0"/>
<portSpacing port="sink_through 1" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" class="apply_model" compatibility="7.1.001" expanded="true" height="82" name="FE Apply Model" origin="GENERATED_TUTORIAL" width="90" x="45" y="34">
<list key="application_parameters"/>
<parameter key="create_view" value="false"/>
</operator>
<operator activated="true" class="performance_binominal_classification" compatibility="9.10.001" expanded="true" height="82" name="FE Performance" width="90" x="179" y="34">
<parameter key="manually_set_positive_class" value="false"/>
<parameter key="main_criterion" value="first"/>
<parameter key="accuracy" value="false"/>
<parameter key="classification_error" value="true"/>
<parameter key="kappa" value="false"/>
<parameter key="AUC (optimistic)" value="false"/>
<parameter key="AUC" value="false"/>
<parameter key="AUC (pessimistic)" value="false"/>
<parameter key="precision" value="false"/>
<parameter key="recall" value="false"/>
<parameter key="lift" value="false"/>
<parameter key="fallout" value="false"/>
<parameter key="f_measure" value="false"/>
<parameter key="false_positive" value="false"/>
<parameter key="false_negative" value="false"/>
<parameter key="true_positive" value="false"/>
<parameter key="true_negative" value="false"/>
<parameter key="sensitivity" value="false"/>
<parameter key="specificity" value="false"/>
<parameter key="youden" value="false"/>
<parameter key="positive_predictive_value" value="false"/>
<parameter key="negative_predictive_value" value="false"/>
<parameter key="psep" value="false"/>
<parameter key="skip_undefined_labels" value="true"/>
<parameter key="use_example_weights" value="true"/>
</operator>
<connect from_port="model" to_op="FE Apply Model" to_port="model"/>
<connect from_port="test set" to_op="FE Apply Model" to_port="unlabelled data"/>
<connect from_op="FE Apply Model" from_port="labelled data" to_op="FE Performance" to_port="labelled data"/>
<connect from_op="FE Performance" from_port="performance" to_port="performance 1"/>
<portSpacing port="source_model" spacing="0"/>
<portSpacing port="source_test set" spacing="0"/>
<portSpacing port="source_through 1" spacing="0"/>
<portSpacing port="sink_test set results" spacing="0"/>
<portSpacing port="sink_performance 1" spacing="0"/>
<portSpacing port="sink_performance 2" spacing="0"/>
</process>
</operator>
<connect from_port="example set source" to_op="FE Cross Validation" to_port="example set"/>
<connect from_op="FE Cross Validation" from_port="performance 1" to_port="performance sink"/>
<portSpacing port="source_example set source" spacing="0"/>
<portSpacing port="sink_performance sink" spacing="0"/>
</process>
</operator>
<operator activated="true" class="multiply" compatibility="9.10.001" expanded="true" height="103" name="Multiply FeatureSet" width="90" x="581" y="85"/>
<operator activated="true" class="model_simulator:apply_feature_set" compatibility="9.10.001" expanded="true" height="82" name="Apply FE to TrainingData" width="90" x="715" y="34">
<parameter key="handle missings" value="true"/>
<parameter key="keep originals" value="false"/>
<parameter key="originals special role" value="true"/>
<parameter key="recreate missing attributes" value="true"/>
</operator>
<connect from_port="in 1" to_op="Multiply Preprocessed dataset" to_port="input"/>
<connect from_op="Multiply Preprocessed dataset" from_port="output 1" to_op="Apply FE to TrainingData" to_port="example set"/>
<connect from_op="Multiply Preprocessed dataset" from_port="output 2" to_op="Attribute Filtering" to_port="example set input"/>
<connect from_op="Attribute Filtering" from_port="example set output" to_op="Sample down for FE" to_port="example set input"/>
<connect from_op="Sample down for FE" from_port="example set output" to_op="FE" to_port="example set in"/>
<connect from_op="FE" from_port="feature set" to_op="Multiply FeatureSet" to_port="input"/>
<connect from_op="FE" from_port="population" to_port="out 4"/>
<connect from_op="FE" from_port="optimization log" to_port="out 2"/>
<connect from_op="Multiply FeatureSet" from_port="output 1" to_op="Apply FE to TrainingData" to_port="feature set"/>
<connect from_op="Multiply FeatureSet" from_port="output 2" to_port="out 3"/>
<connect from_op="Apply FE to TrainingData" from_port="example set" to_port="out 1"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="source_in 2" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
<portSpacing port="sink_out 3" spacing="0"/>
<portSpacing port="sink_out 4" spacing="0"/>
<portSpacing port="sink_out 5" spacing="0"/>
</process>
</operator>
<operator activated="true" class="subprocess" compatibility="9.10.001" expanded="true" height="82" name="Create Training Set" width="90" x="447" y="187">
<process expanded="true">
<operator activated="true" class="extract_macro" compatibility="9.10.001" expanded="true" height="68" name="Count CKD examples" width="90" x="112" y="34">
<parameter key="macro" value="ckdcount"/>
<parameter key="macro_type" value="statistics"/>
<parameter key="statistics" value="count"/>
<parameter key="attribute_name" value="ckd"/>
<parameter key="attribute_value" value="ckd"/>
<list key="additional_macros"/>
</operator>
<operator activated="true" class="sample" compatibility="9.10.001" expanded="true" height="82" name="Balanced Training Data" width="90" x="246" y="34">
<parameter key="sample" value="absolute"/>
<parameter key="balance_data" value="true"/>
<parameter key="sample_size" value="100"/>
<parameter key="sample_ratio" value="0.1"/>
<parameter key="sample_probability" value="0.1"/>
<list key="sample_size_per_class">
<parameter key="ckd" value="%{ckdcount}"/>
<parameter key="notckd" value="%{ckdcount}"/>
</list>
<list key="sample_ratio_per_class"/>
<list key="sample_probability_per_class"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
</operator>
<operator activated="false" class="sample" compatibility="9.10.001" expanded="true" height="82" name="Sample down training data" width="90" x="380" y="238">
<parameter key="sample" value="relative"/>
<parameter key="balance_data" value="false"/>
<parameter key="sample_size" value="100"/>
<parameter key="sample_ratio" value="0.5"/>
<parameter key="sample_probability" value="0.1"/>
<list key="sample_size_per_class"/>
<list key="sample_ratio_per_class"/>
<list key="sample_probability_per_class"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
</operator>
<operator activated="false" class="sample_stratified" compatibility="9.10.001" expanded="true" height="82" name="Sample (Stratified)" width="90" x="246" y="238">
<parameter key="sample" value="relative"/>
<parameter key="sample_size" value="100"/>
<parameter key="sample_ratio" value="0.5"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
</operator>
<connect from_port="in 1" to_op="Count CKD examples" to_port="example set"/>
<connect from_op="Count CKD examples" from_port="example set" to_op="Balanced Training Data" to_port="example set input"/>
<connect from_op="Balanced Training Data" from_port="example set output" to_port="out 1"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="source_in 2" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
</process>
</operator>
<connect from_port="in 1" to_op="Remove Correlated Attributes" to_port="example set input"/>
<connect from_op="Remove Correlated Attributes" from_port="example set output" to_op="Outlier elimination" to_port="in 1"/>
<connect from_op="Outlier elimination" from_port="out 1" to_port="out 1"/>
<connect from_op="Outlier elimination" from_port="out 2" to_op="Auto FE" to_port="in 1"/>
<connect from_op="Auto FE" from_port="out 1" to_op="Create Training Set" to_port="in 1"/>
<connect from_op="Auto FE" from_port="out 2" to_port="out 2"/>
<connect from_op="Auto FE" from_port="out 3" to_port="out 3"/>
<connect from_op="Auto FE" from_port="out 4" to_port="out 5"/>
<connect from_op="Create Training Set" from_port="out 1" to_port="out 4"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="source_in 2" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
<portSpacing port="sink_out 3" spacing="0"/>
<portSpacing port="sink_out 4" spacing="0"/>
<portSpacing port="sink_out 5" spacing="0"/>
<portSpacing port="sink_out 6" spacing="0"/>
</process>
</operator>
<operator activated="true" class="subprocess" compatibility="9.10.001" expanded="true" height="103" name="Test Data Preparation" width="90" x="380" y="187">
<process expanded="true">
<operator activated="true" class="model_simulator:apply_feature_set" compatibility="9.10.001" expanded="true" height="82" name="Apply FS to Scoring" width="90" x="112" y="34">
<parameter key="handle missings" value="false"/>
<parameter key="keep originals" value="false"/>
<parameter key="originals special role" value="true"/>
<parameter key="recreate missing attributes" value="false"/>
</operator>
<operator activated="true" class="extract_macro" compatibility="9.10.001" expanded="true" height="68" name="Count CKD in Scoring" width="90" x="246" y="34">
<parameter key="macro" value="ckdcount"/>
<parameter key="macro_type" value="statistics"/>
<parameter key="statistics" value="count"/>
<parameter key="attribute_name" value="ckd"/>
<parameter key="attribute_value" value="ckd"/>
<list key="additional_macros"/>
</operator>
<operator activated="true" class="sample" compatibility="9.10.001" expanded="true" height="82" name="Balanced Scoring Data" width="90" x="380" y="34">
<parameter key="sample" value="absolute"/>
<parameter key="balance_data" value="true"/>
<parameter key="sample_size" value="100"/>
<parameter key="sample_ratio" value="0.1"/>
<parameter key="sample_probability" value="0.1"/>
<list key="sample_size_per_class">
<parameter key="ckd" value="%{ckdcount}"/>
<parameter key="notckd" value="%{ckdcount}"/>
</list>
<list key="sample_ratio_per_class"/>
<list key="sample_probability_per_class"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
</operator>
<operator activated="false" class="sample_stratified" compatibility="9.10.001" expanded="true" height="82" name="Sample (Stratified) (2)" width="90" x="514" y="391">
<parameter key="sample" value="relative"/>
<parameter key="sample_size" value="100"/>
<parameter key="sample_ratio" value="0.5"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
</operator>
<operator activated="false" class="sample" compatibility="9.10.001" expanded="true" height="82" name="Sample down scoring data" width="90" x="380" y="340">
<parameter key="sample" value="relative"/>
<parameter key="balance_data" value="false"/>
<parameter key="sample_size" value="100"/>
<parameter key="sample_ratio" value="0.5"/>
<parameter key="sample_probability" value="0.1"/>
<list key="sample_size_per_class"/>
<list key="sample_ratio_per_class"/>
<list key="sample_probability_per_class"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
</operator>
<connect from_port="in 1" to_op="Apply FS to Scoring" to_port="example set"/>
<connect from_port="in 2" to_op="Apply FS to Scoring" to_port="feature set"/>
<connect from_op="Apply FS to Scoring" from_port="example set" to_op="Count CKD in Scoring" to_port="example set"/>
<connect from_op="Apply FS to Scoring" from_port="feature set" to_port="out 2"/>
<connect from_op="Count CKD in Scoring" from_port="example set" to_op="Balanced Scoring Data" to_port="example set input"/>
<connect from_op="Balanced Scoring Data" from_port="example set output" to_port="out 1"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="source_in 2" spacing="0"/>
<portSpacing port="source_in 3" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
<portSpacing port="sink_out 3" spacing="0"/>
</process>
</operator>
<operator activated="true" class="subprocess" compatibility="9.10.001" expanded="true" height="145" name="Training" origin="GENERATED_AUTOMODEL" width="90" x="380" y="34">
<process expanded="true">
<operator activated="true" class="concurrency:cross_validation" compatibility="9.10.001" expanded="true" height="145" name="Cross Validation" width="90" x="246" y="34">
<parameter key="split_on_batch_attribute" value="false"/>
<parameter key="leave_one_out" value="false"/>
<parameter key="number_of_folds" value="10"/>
<parameter key="sampling_type" value="stratified sampling"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
<parameter key="enable_parallel_execution" value="true"/>
<process expanded="true">
<operator activated="true" class="concurrency:parallel_random_forest" compatibility="9.10.001" expanded="true" height="103" name="Random Forest" width="90" x="45" y="34">
<parameter key="number_of_trees" value="100"/>
<parameter key="criterion" value="gini_index"/>
<parameter key="maximal_depth" value="15"/>
<parameter key="apply_pruning" value="false"/>
<parameter key="confidence" value="0.1"/>
<parameter key="apply_prepruning" value="false"/>
<parameter key="minimal_gain" value="0.01"/>
<parameter key="minimal_leaf_size" value="2"/>
<parameter key="minimal_size_for_split" value="4"/>
<parameter key="number_of_prepruning_alternatives" value="3"/>
<parameter key="random_splits" value="false"/>
<parameter key="guess_subset_ratio" value="true"/>
<parameter key="subset_ratio" value="0.2"/>
<parameter key="voting_strategy" value="confidence vote"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
<parameter key="enable_parallel_execution" value="true"/>
</operator>
<connect from_port="training set" to_op="Random Forest" to_port="training set"/>
<connect from_op="Random Forest" from_port="model" to_port="model"/>
<portSpacing port="source_training set" spacing="0"/>
<portSpacing port="sink_model" spacing="0"/>
<portSpacing port="sink_through 1" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" class="apply_model" compatibility="9.10.001" expanded="true" height="82" name="Apply Model" width="90" x="45" y="34">
<list key="application_parameters"/>
<parameter key="create_view" value="false"/>
</operator>
<operator activated="true" class="performance_binominal_classification" compatibility="9.10.001" expanded="true" height="82" name="Training Performance" width="90" x="179" y="34">
<parameter key="manually_set_positive_class" value="true"/>
<parameter key="positive_class" value="ckd"/>
<parameter key="main_criterion" value="AUC"/>
<parameter key="accuracy" value="false"/>
<parameter key="classification_error" value="false"/>
<parameter key="kappa" value="false"/>
<parameter key="AUC (optimistic)" value="false"/>
<parameter key="AUC" value="true"/>
<parameter key="AUC (pessimistic)" value="false"/>
<parameter key="precision" value="true"/>
<parameter key="recall" value="true"/>
<parameter key="lift" value="false"/>
<parameter key="fallout" value="false"/>
<parameter key="f_measure" value="true"/>
<parameter key="false_positive" value="false"/>
<parameter key="false_negative" value="false"/>
<parameter key="true_positive" value="false"/>
<parameter key="true_negative" value="false"/>
<parameter key="sensitivity" value="true"/>
<parameter key="specificity" value="true"/>
<parameter key="youden" value="false"/>
<parameter key="positive_predictive_value" value="false"/>
<parameter key="negative_predictive_value" value="false"/>
<parameter key="psep" value="false"/>
<parameter key="skip_undefined_labels" value="true"/>
<parameter key="use_example_weights" value="true"/>
</operator>
<connect from_port="model" to_op="Apply Model" to_port="model"/>
<connect from_port="test set" to_op="Apply Model" to_port="unlabelled data"/>
<connect from_op="Apply Model" from_port="labelled data" to_op="Training Performance" to_port="labelled data"/>
<connect from_op="Training Performance" from_port="performance" to_port="performance 1"/>
<portSpacing port="source_model" spacing="0"/>
<portSpacing port="source_test set" spacing="0"/>
<portSpacing port="source_through 1" spacing="0"/>
<portSpacing port="sink_test set results" spacing="0"/>
<portSpacing port="sink_performance 1" spacing="0"/>
<portSpacing port="sink_performance 2" spacing="0"/>
</process>
</operator>
<operator activated="true" class="weight_by_forest" compatibility="9.10.001" expanded="true" height="82" name="Weight by Tree Importance" width="90" x="380" y="238">
<parameter key="criterion" value="gain_ratio"/>
<parameter key="normalize_weights" value="true"/>
</operator>
<connect from_port="in 1" to_op="Cross Validation" to_port="example set"/>
<connect from_op="Cross Validation" from_port="model" to_op="Weight by Tree Importance" to_port="random forest"/>
<connect from_op="Cross Validation" from_port="example set" to_port="out 3"/>
<connect from_op="Cross Validation" from_port="performance 1" to_port="out 4"/>
<connect from_op="Weight by Tree Importance" from_port="weights" to_port="out 1"/>
<connect from_op="Weight by Tree Importance" from_port="random forest" to_port="out 2"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="source_in 2" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
<portSpacing port="sink_out 3" spacing="0"/>
<portSpacing port="sink_out 4" spacing="0"/>
<portSpacing port="sink_out 5" spacing="0"/>
</process>
</operator>
<operator activated="true" class="subprocess" compatibility="9.10.001" expanded="true" height="124" name="Scoring" width="90" x="514" y="136">
<process expanded="true">
<operator activated="true" class="apply_model" compatibility="9.10.001" expanded="true" height="82" name="Apply Model On Test Data" width="90" x="246" y="34">
<list key="application_parameters"/>
<parameter key="create_view" value="false"/>
</operator>
<operator activated="true" class="performance_binominal_classification" compatibility="9.10.001" expanded="true" height="82" name="Scoring Performance" width="90" x="447" y="136">
<parameter key="manually_set_positive_class" value="true"/>
<parameter key="positive_class" value="ckd"/>
<parameter key="main_criterion" value="AUC"/>
<parameter key="accuracy" value="false"/>
<parameter key="classification_error" value="false"/>
<parameter key="kappa" value="false"/>
<parameter key="AUC (optimistic)" value="false"/>
<parameter key="AUC" value="true"/>
<parameter key="AUC (pessimistic)" value="false"/>
<parameter key="precision" value="true"/>
<parameter key="recall" value="true"/>
<parameter key="lift" value="true"/>
<parameter key="fallout" value="false"/>
<parameter key="f_measure" value="true"/>
<parameter key="false_positive" value="false"/>
<parameter key="false_negative" value="false"/>
<parameter key="true_positive" value="false"/>
<parameter key="true_negative" value="false"/>
<parameter key="sensitivity" value="true"/>
<parameter key="specificity" value="true"/>
<parameter key="youden" value="false"/>
<parameter key="positive_predictive_value" value="false"/>
<parameter key="negative_predictive_value" value="false"/>
<parameter key="psep" value="false"/>
<parameter key="skip_undefined_labels" value="true"/>
<parameter key="use_example_weights" value="true"/>
</operator>
<connect from_port="in 1" to_op="Apply Model On Test Data" to_port="unlabelled data"/>
<connect from_port="in 2" to_op="Apply Model On Test Data" to_port="model"/>
<connect from_op="Apply Model On Test Data" from_port="labelled data" to_op="Scoring Performance" to_port="labelled data"/>
<connect from_op="Apply Model On Test Data" from_port="model" to_port="out 2"/>
<connect from_op="Scoring Performance" from_port="performance" to_port="out 1"/>
<connect from_op="Scoring Performance" from_port="example set" to_port="out 3"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="source_in 2" spacing="0"/>
<portSpacing port="source_in 3" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
<portSpacing port="sink_out 3" spacing="0"/>
<portSpacing port="sink_out 4" spacing="0"/>
</process>
</operator>
<connect from_op="Execute Process" from_port="result 1" to_op="Training Data Preparation" to_port="in 1"/>
<connect from_op="Execute Process" from_port="result 2" to_op="Test Data Preparation" to_port="in 1"/>
<connect from_op="Execute Process" from_port="result 3" to_port="result 11"/>
<connect from_op="Training Data Preparation" from_port="out 1" to_port="result 1"/>
<connect from_op="Training Data Preparation" from_port="out 2" to_port="result 2"/>
<connect from_op="Training Data Preparation" from_port="out 3" to_op="Test Data Preparation" to_port="in 2"/>
<connect from_op="Training Data Preparation" from_port="out 4" to_op="Training" to_port="in 1"/>
<connect from_op="Training Data Preparation" from_port="out 5" to_port="result 10"/>
<connect from_op="Test Data Preparation" from_port="out 1" to_op="Scoring" to_port="in 1"/>
<connect from_op="Test Data Preparation" from_port="out 2" to_port="result 9"/>
<connect from_op="Training" from_port="out 1" to_port="result 3"/>
<connect from_op="Training" from_port="out 2" to_op="Scoring" to_port="in 2"/>
<connect from_op="Training" from_port="out 3" to_port="result 4"/>
<connect from_op="Training" from_port="out 4" to_port="result 5"/>
<connect from_op="Scoring" from_port="out 1" to_port="result 6"/>
<connect from_op="Scoring" from_port="out 2" to_port="result 7"/>
<connect from_op="Scoring" from_port="out 3" to_port="result 8"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="0"/>
<portSpacing port="sink_result 3" spacing="0"/>
<portSpacing port="sink_result 4" spacing="0"/>
<portSpacing port="sink_result 5" spacing="0"/>
<portSpacing port="sink_result 6" spacing="0"/>
<portSpacing port="sink_result 7" spacing="0"/>
<portSpacing port="sink_result 8" spacing="0"/>
<portSpacing port="sink_result 9" spacing="0"/>
<portSpacing port="sink_result 10" spacing="0"/>
<portSpacing port="sink_result 11" spacing="0"/>
<portSpacing port="sink_result 12" spacing="0"/>
</process>
</operator>
</process>