-
Notifications
You must be signed in to change notification settings - Fork 0
/
BAN-706-043-Final-Project-Martinez-Suarez-Julio-Mod-14-kNN-Numerical.rmp
82 lines (82 loc) · 4.89 KB
/
BAN-706-043-Final-Project-Martinez-Suarez-Julio-Mod-14-kNN-Numerical.rmp
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
<?xml version="1.0" encoding="UTF-8"?><process version="9.10.006">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="9.10.006" expanded="true" name="Process">
<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="read_excel" compatibility="9.10.006" expanded="true" height="68" name="Read Excel (2)" width="90" x="45" y="85">
<parameter key="excel_file" value="C:\Users\julio\OneDrive\Documents\UNR - Master\BAN-706\Module-014-BAN-706\HabermansSurvivalData.xlsx"/>
<parameter key="sheet_selection" value="sheet number"/>
<parameter key="sheet_number" value="1"/>
<parameter key="imported_cell_range" value="A1"/>
<parameter key="encoding" value="SYSTEM"/>
<parameter key="first_row_as_names" value="true"/>
<list key="annotations"/>
<parameter key="date_format" value=""/>
<parameter key="time_zone" value="SYSTEM"/>
<parameter key="locale" value="English (United States)"/>
<parameter key="read_all_values_as_polynominal" value="false"/>
<list key="data_set_meta_data_information">
<parameter key="0" value="Age.true.integer.attribute"/>
<parameter key="1" value="Year of Operation.true.integer.attribute"/>
<parameter key="2" value="Number of positive axillary nodes detected.true.integer.attribute"/>
<parameter key="3" value="Survival status.true.integer.label"/>
</list>
<parameter key="read_not_matching_values_as_missings" value="false"/>
</operator>
<operator activated="true" class="split_data" compatibility="9.10.006" expanded="true" height="82" name="Split Data" width="90" x="246" y="85">
<enumeration key="partitions">
<parameter key="ratio" value="0.7"/>
<parameter key="ratio" value="0.3"/>
</enumeration>
<parameter key="sampling_type" value="stratified sampling"/>
<parameter key="use_local_random_seed" value="true"/>
<parameter key="local_random_seed" value="1992"/>
</operator>
<operator activated="true" class="k_nn" compatibility="9.10.006" expanded="true" height="82" name="k-NN" width="90" x="447" y="34">
<parameter key="k" value="3"/>
<parameter key="weighted_vote" value="true"/>
<parameter key="measure_types" value="MixedMeasures"/>
<parameter key="mixed_measure" value="MixedEuclideanDistance"/>
<parameter key="nominal_measure" value="NominalDistance"/>
<parameter key="numerical_measure" value="EuclideanDistance"/>
<parameter key="divergence" value="GeneralizedIDivergence"/>
<parameter key="kernel_type" value="radial"/>
<parameter key="kernel_gamma" value="1.0"/>
<parameter key="kernel_sigma1" value="1.0"/>
<parameter key="kernel_sigma2" value="0.0"/>
<parameter key="kernel_sigma3" value="2.0"/>
<parameter key="kernel_degree" value="3.0"/>
<parameter key="kernel_shift" value="1.0"/>
<parameter key="kernel_a" value="1.0"/>
<parameter key="kernel_b" value="0.0"/>
</operator>
<operator activated="true" class="apply_model" compatibility="9.10.006" expanded="true" height="82" name="Apply Model (2)" width="90" x="581" y="34">
<list key="application_parameters"/>
<parameter key="create_view" value="false"/>
</operator>
<operator activated="true" class="performance" compatibility="9.10.006" expanded="true" height="82" name="Performance k-NN" width="90" x="715" y="289">
<parameter key="use_example_weights" value="true"/>
</operator>
<connect from_op="Read Excel (2)" from_port="output" to_op="Split Data" to_port="example set"/>
<connect from_op="Split Data" from_port="partition 1" to_op="k-NN" to_port="training set"/>
<connect from_op="k-NN" from_port="model" to_op="Apply Model (2)" to_port="model"/>
<connect from_op="k-NN" from_port="exampleSet" to_op="Apply Model (2)" to_port="unlabelled data"/>
<connect from_op="Apply Model (2)" from_port="labelled data" to_op="Performance k-NN" to_port="labelled data"/>
<connect from_op="Apply Model (2)" from_port="model" to_port="result 2"/>
<connect from_op="Performance k-NN" from_port="performance" to_port="result 1"/>
<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"/>
</process>
</operator>
</process>