Advertisement
Guest User

Split + RF

a guest
Feb 25th, 2020
82
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
XML 17.16 KB | None | 0 0
  1. <?xml version="1.0" encoding="UTF-8"?><process version="9.5.001">
  2.   <context>
  3.     <input/>
  4.     <output/>
  5.     <macros/>
  6.   </context>
  7.   <operator activated="true" class="process" compatibility="9.5.001" expanded="true" name="Process">
  8.     <parameter key="logverbosity" value="init"/>
  9.     <parameter key="random_seed" value="2001"/>
  10.     <parameter key="send_mail" value="never"/>
  11.     <parameter key="notification_email" value=""/>
  12.     <parameter key="process_duration_for_mail" value="30"/>
  13.     <parameter key="encoding" value="SYSTEM"/>
  14.     <process expanded="true">
  15.       <operator activated="true" class="retrieve" compatibility="9.5.001" expanded="true" height="68" name="Retrieve dev" width="90" x="45" y="34">
  16.         <parameter key="repository_entry" value="//MEST2020/Dados/dev"/>
  17.       </operator>
  18.       <operator activated="true" class="retrieve" compatibility="9.5.001" expanded="true" height="68" name="Retrieve new" width="90" x="45" y="187">
  19.         <parameter key="repository_entry" value="//MEST2020/Dados/new"/>
  20.       </operator>
  21.       <operator activated="true" class="subprocess" compatibility="9.5.001" expanded="true" height="82" name="Day Information (2)" width="90" x="179" y="187">
  22.         <process expanded="true">
  23.           <operator activated="true" class="subprocess" compatibility="9.5.001" expanded="true" height="82" name="Days To Numbers (2)" width="90" x="45" y="34">
  24.             <process expanded="true">
  25.               <operator activated="true" class="map" compatibility="9.5.001" expanded="true" height="82" name="Map (2)" width="90" x="45" y="34">
  26.                 <parameter key="attribute_filter_type" value="subset"/>
  27.                 <parameter key="attribute" value=""/>
  28.                 <parameter key="attributes" value="current_day|day_posted"/>
  29.                 <parameter key="use_except_expression" value="false"/>
  30.                 <parameter key="value_type" value="attribute_value"/>
  31.                 <parameter key="use_value_type_exception" value="false"/>
  32.                 <parameter key="except_value_type" value="time"/>
  33.                 <parameter key="block_type" value="attribute_block"/>
  34.                 <parameter key="use_block_type_exception" value="false"/>
  35.                 <parameter key="except_block_type" value="value_matrix_row_start"/>
  36.                 <parameter key="invert_selection" value="false"/>
  37.                 <parameter key="include_special_attributes" value="false"/>
  38.                 <list key="value_mappings">
  39.                   <parameter key="MONDAY" value="1"/>
  40.                   <parameter key="TUESDAY" value="2"/>
  41.                   <parameter key="WEDNESDAY" value="3"/>
  42.                   <parameter key="THURSDAY" value="4"/>
  43.                   <parameter key="FRIDAY" value="5"/>
  44.                   <parameter key="SATURDAY" value="6"/>
  45.                   <parameter key="SUNDAY" value="7"/>
  46.                 </list>
  47.                 <parameter key="consider_regular_expressions" value="false"/>
  48.                 <parameter key="add_default_mapping" value="false"/>
  49.               </operator>
  50.               <operator activated="true" class="parse_numbers" compatibility="9.5.001" expanded="true" height="82" name="Parse Numbers (2)" width="90" x="179" y="34">
  51.                 <parameter key="attribute_filter_type" value="subset"/>
  52.                 <parameter key="attribute" value=""/>
  53.                 <parameter key="attributes" value="current_day|day_posted"/>
  54.                 <parameter key="use_except_expression" value="false"/>
  55.                 <parameter key="value_type" value="nominal"/>
  56.                 <parameter key="use_value_type_exception" value="false"/>
  57.                 <parameter key="except_value_type" value="file_path"/>
  58.                 <parameter key="block_type" value="single_value"/>
  59.                 <parameter key="use_block_type_exception" value="false"/>
  60.                 <parameter key="except_block_type" value="single_value"/>
  61.                 <parameter key="invert_selection" value="false"/>
  62.                 <parameter key="include_special_attributes" value="false"/>
  63.                 <parameter key="decimal_character" value="."/>
  64.                 <parameter key="grouped_digits" value="false"/>
  65.                 <parameter key="grouping_character" value=","/>
  66.                 <parameter key="infinity_representation" value=""/>
  67.                 <parameter key="unparsable_value_handling" value="fail"/>
  68.               </operator>
  69.               <connect from_port="in 1" to_op="Map (2)" to_port="example set input"/>
  70.               <connect from_op="Map (2)" from_port="example set output" to_op="Parse Numbers (2)" to_port="example set input"/>
  71.               <connect from_op="Parse Numbers (2)" from_port="example set output" to_port="out 1"/>
  72.               <portSpacing port="source_in 1" spacing="0"/>
  73.               <portSpacing port="source_in 2" spacing="0"/>
  74.               <portSpacing port="sink_out 1" spacing="0"/>
  75.               <portSpacing port="sink_out 2" spacing="0"/>
  76.             </process>
  77.           </operator>
  78.           <operator activated="true" class="generate_attributes" compatibility="9.5.001" expanded="true" height="82" name="Day Difference (2)" width="90" x="179" y="34">
  79.             <list key="function_descriptions">
  80.               <parameter key="day_difference" value="if(current_day-day_posted&lt;0,current_day-day_posted+7,current_day-day_posted)"/>
  81.             </list>
  82.             <parameter key="keep_all" value="true"/>
  83.           </operator>
  84.           <connect from_port="in 1" to_op="Days To Numbers (2)" to_port="in 1"/>
  85.           <connect from_op="Days To Numbers (2)" from_port="out 1" to_op="Day Difference (2)" to_port="example set input"/>
  86.           <connect from_op="Day Difference (2)" from_port="example set output" to_port="out 1"/>
  87.           <portSpacing port="source_in 1" spacing="0"/>
  88.           <portSpacing port="source_in 2" spacing="0"/>
  89.           <portSpacing port="sink_out 1" spacing="0"/>
  90.           <portSpacing port="sink_out 2" spacing="0"/>
  91.         </process>
  92.       </operator>
  93.       <operator activated="true" class="subprocess" compatibility="9.5.001" expanded="true" height="82" name="Day Information" width="90" x="179" y="34">
  94.         <process expanded="true">
  95.           <operator activated="true" class="subprocess" compatibility="9.5.001" expanded="true" height="82" name="Days To Numbers" width="90" x="45" y="34">
  96.             <process expanded="true">
  97.               <operator activated="true" class="map" compatibility="9.5.001" expanded="true" height="82" name="Map" width="90" x="45" y="34">
  98.                 <parameter key="attribute_filter_type" value="subset"/>
  99.                 <parameter key="attribute" value=""/>
  100.                 <parameter key="attributes" value="current_day|day_posted"/>
  101.                 <parameter key="use_except_expression" value="false"/>
  102.                 <parameter key="value_type" value="attribute_value"/>
  103.                 <parameter key="use_value_type_exception" value="false"/>
  104.                 <parameter key="except_value_type" value="time"/>
  105.                 <parameter key="block_type" value="attribute_block"/>
  106.                 <parameter key="use_block_type_exception" value="false"/>
  107.                 <parameter key="except_block_type" value="value_matrix_row_start"/>
  108.                 <parameter key="invert_selection" value="false"/>
  109.                 <parameter key="include_special_attributes" value="false"/>
  110.                 <list key="value_mappings">
  111.                   <parameter key="MONDAY" value="1"/>
  112.                   <parameter key="TUESDAY" value="2"/>
  113.                   <parameter key="WEDNESDAY" value="3"/>
  114.                   <parameter key="THURSDAY" value="4"/>
  115.                   <parameter key="FRIDAY" value="5"/>
  116.                   <parameter key="SATURDAY" value="6"/>
  117.                   <parameter key="SUNDAY" value="7"/>
  118.                 </list>
  119.                 <parameter key="consider_regular_expressions" value="false"/>
  120.                 <parameter key="add_default_mapping" value="false"/>
  121.               </operator>
  122.               <operator activated="true" class="parse_numbers" compatibility="9.5.001" expanded="true" height="82" name="Parse Numbers" width="90" x="179" y="34">
  123.                 <parameter key="attribute_filter_type" value="subset"/>
  124.                 <parameter key="attribute" value=""/>
  125.                 <parameter key="attributes" value="current_day|day_posted"/>
  126.                 <parameter key="use_except_expression" value="false"/>
  127.                 <parameter key="value_type" value="nominal"/>
  128.                 <parameter key="use_value_type_exception" value="false"/>
  129.                 <parameter key="except_value_type" value="file_path"/>
  130.                 <parameter key="block_type" value="single_value"/>
  131.                 <parameter key="use_block_type_exception" value="false"/>
  132.                 <parameter key="except_block_type" value="single_value"/>
  133.                 <parameter key="invert_selection" value="false"/>
  134.                 <parameter key="include_special_attributes" value="false"/>
  135.                 <parameter key="decimal_character" value="."/>
  136.                 <parameter key="grouped_digits" value="false"/>
  137.                 <parameter key="grouping_character" value=","/>
  138.                 <parameter key="infinity_representation" value=""/>
  139.                 <parameter key="unparsable_value_handling" value="fail"/>
  140.               </operator>
  141.               <connect from_port="in 1" to_op="Map" to_port="example set input"/>
  142.               <connect from_op="Map" from_port="example set output" to_op="Parse Numbers" to_port="example set input"/>
  143.               <connect from_op="Parse Numbers" from_port="example set output" to_port="out 1"/>
  144.               <portSpacing port="source_in 1" spacing="0"/>
  145.               <portSpacing port="source_in 2" spacing="0"/>
  146.               <portSpacing port="sink_out 1" spacing="0"/>
  147.               <portSpacing port="sink_out 2" spacing="0"/>
  148.             </process>
  149.           </operator>
  150.           <operator activated="true" class="generate_attributes" compatibility="9.5.001" expanded="true" height="82" name="Day Difference" width="90" x="179" y="34">
  151.             <list key="function_descriptions">
  152.               <parameter key="day_difference" value="if(current_day-day_posted&lt;0,current_day-day_posted+7,current_day-day_posted)"/>
  153.             </list>
  154.             <parameter key="keep_all" value="true"/>
  155.           </operator>
  156.           <connect from_port="in 1" to_op="Days To Numbers" to_port="in 1"/>
  157.           <connect from_op="Days To Numbers" from_port="out 1" to_op="Day Difference" to_port="example set input"/>
  158.           <connect from_op="Day Difference" from_port="example set output" to_port="out 1"/>
  159.           <portSpacing port="source_in 1" spacing="0"/>
  160.           <portSpacing port="source_in 2" spacing="0"/>
  161.           <portSpacing port="sink_out 1" spacing="0"/>
  162.           <portSpacing port="sink_out 2" spacing="0"/>
  163.         </process>
  164.       </operator>
  165.       <operator activated="true" class="split_validation" compatibility="9.5.001" expanded="true" height="124" name="Validation" width="90" x="313" y="34">
  166.         <parameter key="create_complete_model" value="false"/>
  167.         <parameter key="split" value="relative"/>
  168.         <parameter key="split_ratio" value="0.4"/>
  169.         <parameter key="training_set_size" value="100"/>
  170.         <parameter key="test_set_size" value="-1"/>
  171.         <parameter key="sampling_type" value="automatic"/>
  172.         <parameter key="use_local_random_seed" value="false"/>
  173.         <parameter key="local_random_seed" value="1992"/>
  174.         <process expanded="true">
  175.           <operator activated="true" class="concurrency:parallel_random_forest" compatibility="9.5.001" expanded="true" height="103" name="Random Forest (2)" width="90" x="45" y="34">
  176.             <parameter key="number_of_trees" value="300"/>
  177.             <parameter key="criterion" value="gain_ratio"/>
  178.             <parameter key="maximal_depth" value="10"/>
  179.             <parameter key="apply_pruning" value="false"/>
  180.             <parameter key="confidence" value="0.1"/>
  181.             <parameter key="apply_prepruning" value="false"/>
  182.             <parameter key="minimal_gain" value="0.01"/>
  183.             <parameter key="minimal_leaf_size" value="2"/>
  184.             <parameter key="minimal_size_for_split" value="4"/>
  185.             <parameter key="number_of_prepruning_alternatives" value="3"/>
  186.             <parameter key="random_splits" value="false"/>
  187.             <parameter key="guess_subset_ratio" value="true"/>
  188.             <parameter key="subset_ratio" value="0.2"/>
  189.             <parameter key="voting_strategy" value="confidence vote"/>
  190.             <parameter key="use_local_random_seed" value="false"/>
  191.             <parameter key="local_random_seed" value="1992"/>
  192.             <parameter key="enable_parallel_execution" value="true"/>
  193.           </operator>
  194.           <connect from_port="training" to_op="Random Forest (2)" to_port="training set"/>
  195.           <connect from_op="Random Forest (2)" from_port="model" to_port="model"/>
  196.           <connect from_op="Random Forest (2)" from_port="exampleSet" to_port="through 1"/>
  197.           <portSpacing port="source_training" spacing="0"/>
  198.           <portSpacing port="sink_model" spacing="0"/>
  199.           <portSpacing port="sink_through 1" spacing="0"/>
  200.           <portSpacing port="sink_through 2" spacing="0"/>
  201.         </process>
  202.         <process expanded="true">
  203.           <operator activated="true" class="apply_model" compatibility="9.5.001" expanded="true" height="82" name="Apply Model" width="90" x="112" y="34">
  204.             <list key="application_parameters"/>
  205.             <parameter key="create_view" value="false"/>
  206.           </operator>
  207.           <operator activated="true" class="performance" compatibility="9.5.001" expanded="true" height="82" name="Performance" width="90" x="246" y="34">
  208.             <parameter key="use_example_weights" value="true"/>
  209.           </operator>
  210.           <connect from_port="model" to_op="Apply Model" to_port="model"/>
  211.           <connect from_port="test set" to_op="Apply Model" to_port="unlabelled data"/>
  212.           <connect from_op="Apply Model" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
  213.           <connect from_op="Performance" from_port="performance" to_port="averagable 1"/>
  214.           <portSpacing port="source_model" spacing="0"/>
  215.           <portSpacing port="source_test set" spacing="0"/>
  216.           <portSpacing port="source_through 1" spacing="0"/>
  217.           <portSpacing port="source_through 2" spacing="0"/>
  218.           <portSpacing port="sink_averagable 1" spacing="0"/>
  219.           <portSpacing port="sink_averagable 2" spacing="0"/>
  220.         </process>
  221.       </operator>
  222.       <operator activated="true" class="apply_model" compatibility="9.5.001" expanded="true" height="82" name="Apply Model (2)" width="90" x="447" y="136">
  223.         <list key="application_parameters"/>
  224.         <parameter key="create_view" value="false"/>
  225.       </operator>
  226.       <operator activated="true" class="select_attributes" compatibility="9.5.001" expanded="true" height="82" name="Select Attributes" width="90" x="581" y="136">
  227.         <parameter key="attribute_filter_type" value="subset"/>
  228.         <parameter key="attribute" value=""/>
  229.         <parameter key="attributes" value="ID|prediction(has_new_comments)"/>
  230.         <parameter key="use_except_expression" value="false"/>
  231.         <parameter key="value_type" value="attribute_value"/>
  232.         <parameter key="use_value_type_exception" value="false"/>
  233.         <parameter key="except_value_type" value="time"/>
  234.         <parameter key="block_type" value="attribute_block"/>
  235.         <parameter key="use_block_type_exception" value="false"/>
  236.         <parameter key="except_block_type" value="value_matrix_row_start"/>
  237.         <parameter key="invert_selection" value="false"/>
  238.         <parameter key="include_special_attributes" value="true"/>
  239.       </operator>
  240.       <operator activated="true" class="rename" compatibility="9.5.001" expanded="true" height="82" name="Rename" width="90" x="715" y="136">
  241.         <parameter key="old_name" value="prediction(has_new_comments)"/>
  242.         <parameter key="new_name" value="has_new_comments"/>
  243.         <list key="rename_additional_attributes"/>
  244.       </operator>
  245.       <connect from_op="Retrieve dev" from_port="output" to_op="Day Information" to_port="in 1"/>
  246.       <connect from_op="Retrieve new" from_port="output" to_op="Day Information (2)" to_port="in 1"/>
  247.       <connect from_op="Day Information (2)" from_port="out 1" to_op="Apply Model (2)" to_port="unlabelled data"/>
  248.       <connect from_op="Day Information" from_port="out 1" to_op="Validation" to_port="training"/>
  249.       <connect from_op="Validation" from_port="model" to_op="Apply Model (2)" to_port="model"/>
  250.       <connect from_op="Apply Model (2)" from_port="labelled data" to_op="Select Attributes" to_port="example set input"/>
  251.       <connect from_op="Select Attributes" from_port="example set output" to_op="Rename" to_port="example set input"/>
  252.       <connect from_op="Rename" from_port="example set output" to_port="result 1"/>
  253.       <portSpacing port="source_input 1" spacing="0"/>
  254.       <portSpacing port="sink_result 1" spacing="0"/>
  255.       <portSpacing port="sink_result 2" spacing="0"/>
  256.     </process>
  257.   </operator>
  258. </process>
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement