medium-files/model3-split-sample.rmp at main · andreharak/medium-files · GitHub

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
<?xml version="1.0" encoding="UTF-8"?><process version="9.10.001">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.10.001" 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="retrieve" compatibility="9.10.001" expanded="true" height="68" name="Retrieve dataset1_hr" width="90" x="112" y="34">
        <parameter key="repository_entry" value="dataset1_hr"/>
      </operator>
      <operator activated="true" class="numerical_to_binominal" compatibility="9.10.001" expanded="true" height="82" name="Numerical to Binominal" width="90" x="313" y="34">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="left"/>
        <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="true"/>
        <parameter key="min" value="0.0"/>
        <parameter key="max" value="0.0"/>
        <description align="center" color="transparent" colored="false" width="126">Transform the target variable into binomial</description>
      </operator>
      <operator activated="true" class="set_role" compatibility="9.10.001" expanded="true" height="82" name="Set Role" width="90" x="447" y="34">
        <parameter key="attribute_name" value="left"/>
        <parameter key="target_role" value="label"/>
        <list key="set_additional_roles"/>
        <description align="center" color="transparent" colored="false" width="126">Set the variable &amp;quot;Left&amp;quot; as target variable</description>
      </operator>
      <operator activated="true" class="split_data" compatibility="9.10.001" expanded="true" height="103" name="Split Data" width="90" x="581" y="34">
        <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="false"/>
        <parameter key="local_random_seed" value="1992"/>
        <description align="center" color="transparent" colored="false" width="126">Split the data into 70% training set and 30% test set</description>
      </operator>
      <operator activated="true" class="concurrency:parallel_random_forest" compatibility="9.10.001" expanded="true" height="103" name="Random Forest" width="90" x="849" y="34">
        <parameter key="number_of_trees" value="100"/>
        <parameter key="criterion" value="gain_ratio"/>
        <parameter key="maximal_depth" value="10"/>
        <parameter key="apply_pruning" value="true"/>
        <parameter key="confidence" value="0.1"/>
        <parameter key="apply_prepruning" value="true"/>
        <parameter key="minimal_gain" value="0.01"/>
        <parameter key="minimal_leaf_size" value="100"/>
        <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>
      <operator activated="true" class="apply_model" compatibility="9.10.001" expanded="true" height="82" name="Apply Model" width="90" x="983" y="238">
        <list key="application_parameters"/>
        <parameter key="create_view" value="false"/>
      </operator>
      <operator activated="true" class="weight_by_forest" compatibility="9.10.001" expanded="true" height="82" name="Weight by Tree Importance" width="90" x="1117" y="340">
        <parameter key="criterion" value="gain_ratio"/>
        <parameter key="normalize_weights" value="false"/>
      </operator>
      <operator activated="true" class="performance_classification" compatibility="9.10.001" expanded="true" height="82" name="Performance" width="90" x="1117" y="238">
        <parameter key="main_criterion" value="root_mean_squared_error"/>
        <parameter key="accuracy" value="true"/>
        <parameter key="classification_error" value="false"/>
        <parameter key="kappa" value="false"/>
        <parameter key="weighted_mean_recall" value="false"/>
        <parameter key="weighted_mean_precision" value="false"/>
        <parameter key="spearman_rho" value="false"/>
        <parameter key="kendall_tau" value="false"/>
        <parameter key="absolute_error" value="false"/>
        <parameter key="relative_error" value="false"/>
        <parameter key="relative_error_lenient" value="false"/>
        <parameter key="relative_error_strict" value="false"/>
        <parameter key="normalized_absolute_error" value="false"/>
        <parameter key="root_mean_squared_error" value="true"/>
        <parameter key="root_relative_squared_error" value="false"/>
        <parameter key="squared_error" value="false"/>
        <parameter key="correlation" value="false"/>
        <parameter key="squared_correlation" value="true"/>
        <parameter key="cross-entropy" value="false"/>
        <parameter key="margin" value="false"/>
        <parameter key="soft_margin_loss" value="false"/>
        <parameter key="logistic_loss" value="false"/>
        <parameter key="skip_undefined_labels" value="true"/>
        <parameter key="use_example_weights" value="true"/>
        <list key="class_weights"/>
      </operator>
      <connect from_op="Retrieve dataset1_hr" from_port="output" to_op="Numerical to Binominal" to_port="example set input"/>
      <connect from_op="Numerical to Binominal" from_port="example set output" to_op="Set Role" to_port="example set input"/>
      <connect from_op="Set Role" from_port="example set output" to_op="Split Data" to_port="example set"/>
      <connect from_op="Split Data" from_port="partition 1" to_op="Random Forest" to_port="training set"/>
      <connect from_op="Split Data" from_port="partition 2" to_op="Apply Model" to_port="unlabelled data"/>
      <connect from_op="Random Forest" from_port="model" to_op="Apply Model" to_port="model"/>
      <connect from_op="Random Forest" from_port="exampleSet" to_port="result 1"/>
      <connect from_op="Random Forest" from_port="weights" to_port="result 2"/>
      <connect from_op="Apply Model" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
      <connect from_op="Apply Model" from_port="model" to_op="Weight by Tree Importance" to_port="random forest"/>
      <connect from_op="Weight by Tree Importance" from_port="weights" to_port="result 5"/>
      <connect from_op="Performance" from_port="performance" to_port="result 3"/>
      <connect from_op="Performance" from_port="example set" to_port="result 4"/>
      <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"/>
    </process>
  </operator>
</process>