|
|
<?xml version="1.0" encoding="UTF-8"?><process version="10.5.000">
|
|
|
<context>
|
|
|
<input/>
|
|
|
<output/>
|
|
|
<macros/>
|
|
|
</context>
|
|
|
<operator activated="true" class="process" compatibility="10.5.000" expanded="true" name="Process" origin="GENERATED_TRAINING">
|
|
|
<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="subprocess" compatibility="10.5.000" expanded="true" height="82" name="ETL" origin="GENERATED_TRAINING" width="90" x="45" y="34">
|
|
|
<process expanded="true">
|
|
|
<operator activated="true" class="retrieve" compatibility="10.5.000" expanded="true" height="68" name="Retrieve Transaction Data" origin="GENERATED_TRAINING" width="90" x="45" y="34">
|
|
|
<parameter key="repository_entry" value="../../../../../Data/Hotel App Customer/Transaction Data"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="retrieve" compatibility="10.5.000" expanded="true" height="68" name="Retrieve Termination Data" origin="GENERATED_TRAINING" width="90" x="45" y="238">
|
|
|
<parameter key="repository_entry" value="../../../../../Data/Hotel App Customer/Termination Data"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="retrieve" compatibility="10.5.000" expanded="true" height="68" name="Retrieve Hotel App Joins data" origin="GENERATED_TRAINING" width="90" x="45" y="136">
|
|
|
<parameter key="repository_entry" value="../../../../../Data/Hotel App Customer/Hotel App Joins data"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="subprocess" compatibility="10.5.000" expanded="true" height="124" name="Data Prep" origin="GENERATED_TRAINING" width="90" x="179" y="85">
|
|
|
<process expanded="true">
|
|
|
<operator activated="true" class="numerical_to_polynominal" compatibility="10.5.000" expanded="true" height="82" name="Numerical to Polynominal (2)" origin="GENERATED_TRAINING" width="90" x="179" y="187">
|
|
|
<parameter key="attribute_filter_type" value="single"/>
|
|
|
<parameter key="attribute" value="CustomerId"/>
|
|
|
<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"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="subprocess" compatibility="10.5.000" expanded="true" height="103" name="Aggregate & Pivot" origin="GENERATED_TRAINING" width="90" x="45" y="34">
|
|
|
<process expanded="true">
|
|
|
<operator activated="true" class="aggregate" compatibility="10.5.000" expanded="true" height="82" name="Aggregate" origin="GENERATED_TRAINING" width="90" x="45" y="34">
|
|
|
<parameter key="use_default_aggregation" value="false"/>
|
|
|
<parameter key="attribute_filter_type" value="all"/>
|
|
|
<parameter key="attribute" value=""/>
|
|
|
<parameter key="attributes" value=""/>
|
|
|
<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"/>
|
|
|
<parameter key="default_aggregation_function" value="average"/>
|
|
|
<list key="aggregation_attributes">
|
|
|
<parameter key="TransactionValue" value="average"/>
|
|
|
<parameter key="TransactionValue" value="sum"/>
|
|
|
<parameter key="Date" value="maximum"/>
|
|
|
</list>
|
|
|
<parameter key="group_by_attributes" value="CustomerId"/>
|
|
|
<parameter key="count_all_combinations" value="false"/>
|
|
|
<parameter key="only_distinct" value="false"/>
|
|
|
<parameter key="ignore_missings" value="true"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="blending:pivot" compatibility="10.5.000" expanded="true" height="103" name="Pivot" origin="GENERATED_TRAINING" width="90" x="179" y="136">
|
|
|
<parameter key="group_by_attributes" value="CustomerId"/>
|
|
|
<parameter key="column_grouping_attribute" value="PaymentMethod"/>
|
|
|
<list key="aggregation_attributes">
|
|
|
<parameter key="PaymentMethod" value="count"/>
|
|
|
</list>
|
|
|
<parameter key="use_default_aggregation" value="false"/>
|
|
|
<parameter key="default_aggregation_function" value="first"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="concurrency:join" compatibility="10.5.000" expanded="true" height="82" name="Join" origin="GENERATED_TRAINING" width="90" x="313" y="34">
|
|
|
<parameter key="remove_double_attributes" value="true"/>
|
|
|
<parameter key="join_type" value="inner"/>
|
|
|
<parameter key="use_id_attribute_as_key" value="false"/>
|
|
|
<list key="key_attributes">
|
|
|
<parameter key="CustomerId" value="CustomerId"/>
|
|
|
</list>
|
|
|
<parameter key="keep_both_join_attributes" value="false"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="replace_missing_values" compatibility="10.5.000" expanded="true" height="103" name="Replace Missing Values" origin="GENERATED_TRAINING" width="90" x="447" y="85">
|
|
|
<parameter key="return_preprocessing_model" value="false"/>
|
|
|
<parameter key="attribute_filter_type" value="subset"/>
|
|
|
<parameter key="attribute" value=""/>
|
|
|
<parameter key="attributes" value="count(PaymentMethod)_cash|count(PaymentMethod)_cheque|count(PaymentMethod)_credit card"/>
|
|
|
<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"/>
|
|
|
<parameter key="default" value="zero"/>
|
|
|
<list key="columns"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="concurrency:join" compatibility="10.5.000" expanded="true" height="82" name="Join (2)" origin="GENERATED_TRAINING" width="90" x="581" y="238">
|
|
|
<parameter key="remove_double_attributes" value="true"/>
|
|
|
<parameter key="join_type" value="inner"/>
|
|
|
<parameter key="use_id_attribute_as_key" value="false"/>
|
|
|
<list key="key_attributes">
|
|
|
<parameter key="CustomerId" value="CustomerId"/>
|
|
|
</list>
|
|
|
<parameter key="keep_both_join_attributes" value="false"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="blending:rename" compatibility="10.5.000" expanded="true" height="82" name="Rename" origin="GENERATED_TRAINING" width="90" x="715" y="85">
|
|
|
<list key="rename attributes">
|
|
|
<parameter key="average(TransactionValue)" value="AverageTransactionValue"/>
|
|
|
<parameter key="maximum(Date)" value="MostRecentTransactionDate"/>
|
|
|
<parameter key="sum(TransactionValue)" value="TotalTransactionValue"/>
|
|
|
<parameter key="Geschlecht" value="Gender"/>
|
|
|
</list>
|
|
|
<parameter key="from_attribute" value=""/>
|
|
|
<parameter key="to_attribute" value=""/>
|
|
|
</operator>
|
|
|
<connect from_port="in 1" to_op="Aggregate" to_port="example set input"/>
|
|
|
<connect from_port="in 2" to_op="Join (2)" to_port="right"/>
|
|
|
<connect from_op="Aggregate" from_port="example set output" to_op="Join" to_port="left"/>
|
|
|
<connect from_op="Aggregate" from_port="original" to_op="Pivot" to_port="input"/>
|
|
|
<connect from_op="Pivot" from_port="output" to_op="Join" to_port="right"/>
|
|
|
<connect from_op="Join" from_port="join" to_op="Replace Missing Values" to_port="example set input"/>
|
|
|
<connect from_op="Replace Missing Values" from_port="example set output" to_op="Join (2)" to_port="left"/>
|
|
|
<connect from_op="Join (2)" from_port="join" to_op="Rename" to_port="example set input"/>
|
|
|
<connect from_op="Rename" 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"/>
|
|
|
</process>
|
|
|
</operator>
|
|
|
<operator activated="true" class="numerical_to_polynominal" compatibility="10.5.000" expanded="true" height="82" name="Numerical to Polynominal" origin="GENERATED_TRAINING" width="90" x="179" y="34">
|
|
|
<parameter key="attribute_filter_type" value="single"/>
|
|
|
<parameter key="attribute" value="CustomerId"/>
|
|
|
<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"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="blending:set_role" compatibility="10.5.000" expanded="true" height="82" name="Set Role (2)" origin="GENERATED_TRAINING" width="90" x="313" y="34">
|
|
|
<list key="set_roles">
|
|
|
<parameter key="CustomerId" value="id"/>
|
|
|
</list>
|
|
|
</operator>
|
|
|
<operator activated="true" class="blending:set_role" compatibility="10.5.000" expanded="true" height="82" name="Set Role (3)" origin="GENERATED_TRAINING" width="90" x="313" y="187">
|
|
|
<list key="set_roles">
|
|
|
<parameter key="CustomerId" value="id"/>
|
|
|
</list>
|
|
|
</operator>
|
|
|
<operator activated="true" class="set_minus" compatibility="10.5.000" expanded="true" height="82" name="Set Minus to remove Termination Data" origin="GENERATED_TRAINING" width="90" x="447" y="85"/>
|
|
|
<connect from_port="in 1" to_op="Aggregate & Pivot" to_port="in 1"/>
|
|
|
<connect from_port="in 2" to_op="Aggregate & Pivot" to_port="in 2"/>
|
|
|
<connect from_port="in 3" to_op="Numerical to Polynominal (2)" to_port="example set input"/>
|
|
|
<connect from_op="Numerical to Polynominal (2)" from_port="example set output" to_op="Set Role (3)" to_port="example set input"/>
|
|
|
<connect from_op="Aggregate & Pivot" from_port="out 1" to_op="Numerical to Polynominal" to_port="example set input"/>
|
|
|
<connect from_op="Numerical to Polynominal" from_port="example set output" to_op="Set Role (2)" to_port="example set input"/>
|
|
|
<connect from_op="Set Role (2)" from_port="example set output" to_op="Set Minus to remove Termination Data" to_port="example set input"/>
|
|
|
<connect from_op="Set Role (3)" from_port="example set output" to_op="Set Minus to remove Termination Data" to_port="subtrahend"/>
|
|
|
<connect from_op="Set Minus to remove Termination 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="source_in 4" spacing="0"/>
|
|
|
<portSpacing port="sink_out 1" spacing="0"/>
|
|
|
<portSpacing port="sink_out 2" spacing="0"/>
|
|
|
</process>
|
|
|
</operator>
|
|
|
<operator activated="true" class="subprocess" compatibility="10.5.000" expanded="true" height="82" name="Feature Generation" origin="GENERATED_TRAINING" width="90" x="313" y="85">
|
|
|
<process expanded="true">
|
|
|
<operator activated="true" class="format_numbers" compatibility="10.5.000" expanded="true" height="82" name="Format Numbers" origin="GENERATED_TRAINING" width="90" x="45" y="34">
|
|
|
<parameter key="attribute_filter_type" value="single"/>
|
|
|
<parameter key="attribute" value="PostalCode"/>
|
|
|
<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="format_type" value="pattern"/>
|
|
|
<parameter key="pattern" value="00000"/>
|
|
|
<parameter key="locale" value="English (United States)"/>
|
|
|
<parameter key="use_grouping" value="false"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="blending:generate_columns" compatibility="10.5.000" expanded="true" height="82" name="Generate Attributes (2)" origin="GENERATED_TRAINING" width="90" x="179" y="34">
|
|
|
<list key="function_descriptions">
|
|
|
<parameter key="Churn Indicator" value="if(missing(DateChurn), "Loyal", "Churn")"/>
|
|
|
<parameter key="Age" value="date_diff(Birthday, date_now(), DATE_UNIT_YEAR,"America/Los_Angeles")"/>
|
|
|
</list>
|
|
|
<parameter key="keep_all_columns" value="true"/>
|
|
|
<parameter key="default_time_zone" value="America/New_York"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="filter_examples" compatibility="10.5.000" expanded="true" height="103" name="Filter Examples" origin="GENERATED_TRAINING" width="90" x="313" 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="Age.ge.16"/>
|
|
|
<parameter key="filters_entry_key" value="Age.le.100"/>
|
|
|
</list>
|
|
|
<parameter key="filters_logic_and" value="true"/>
|
|
|
<parameter key="filters_check_metadata" value="true"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="blending:set_role" compatibility="10.5.000" expanded="true" height="82" name="Set Role" origin="GENERATED_TRAINING" width="90" x="447" y="34">
|
|
|
<list key="set_roles">
|
|
|
<parameter key="Churn Indicator" value="label"/>
|
|
|
</list>
|
|
|
</operator>
|
|
|
<operator activated="true" class="blending:generate_columns" compatibility="10.5.000" expanded="true" height="82" name="Generate Attributes (3)" origin="GENERATED_TRAINING" width="90" x="581" y="34">
|
|
|
<list key="function_descriptions">
|
|
|
<parameter key="PostalCode" value="prefix(PostalCode, 1)"/>
|
|
|
<parameter key="MostRecentTransactionDate" value="date_diff(MostRecentTransactionDate, date_now(), DATE_UNIT_DAY, "America/Los_Angeles")"/>
|
|
|
</list>
|
|
|
<parameter key="keep_all_columns" value="true"/>
|
|
|
<parameter key="default_time_zone" value="America/New_York"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="blending:select_attributes" compatibility="10.5.000" expanded="true" height="82" name="Select Attributes" origin="GENERATED_TRAINING" width="90" x="246" y="289">
|
|
|
<parameter key="type" value="exclude attributes"/>
|
|
|
<parameter key="attribute_filter_type" value="a subset"/>
|
|
|
<parameter key="select_attribute" value=""/>
|
|
|
<parameter key="select_subset" value="Birthday␞DateChurn␞First Name␞id␞HashCode"/>
|
|
|
<parameter key="also_apply_to_special_attributes_(id,_label..)" value="false"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="generate_aggregation" compatibility="10.5.000" expanded="true" height="82" name="Generate Aggregation" origin="GENERATED_TRAINING" width="90" x="380" y="289">
|
|
|
<parameter key="attribute_name" value="TotalCount"/>
|
|
|
<parameter key="attribute_filter_type" value="regular_expression"/>
|
|
|
<parameter key="attribute" value=""/>
|
|
|
<parameter key="attributes" value=""/>
|
|
|
<parameter key="regular_expression" value="count.+"/>
|
|
|
<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"/>
|
|
|
<parameter key="aggregation_function" value="sum"/>
|
|
|
<parameter key="concatenation_separator" value="|"/>
|
|
|
<parameter key="keep_all" value="true"/>
|
|
|
<parameter key="ignore_missings" value="true"/>
|
|
|
<parameter key="ignore_missing_attributes" value="false"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="rename_by_replacing" compatibility="10.5.000" expanded="true" height="82" name="Rename by Replacing" origin="GENERATED_TRAINING" width="90" x="514" y="289">
|
|
|
<parameter key="attribute_filter_type" value="all"/>
|
|
|
<parameter key="attribute" value=""/>
|
|
|
<parameter key="attributes" value=""/>
|
|
|
<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"/>
|
|
|
<parameter key="replace_what" value="\W"/>
|
|
|
</operator>
|
|
|
<connect from_port="in 1" to_op="Format Numbers" to_port="example set input"/>
|
|
|
<connect from_op="Format Numbers" from_port="example set output" to_op="Generate Attributes (2)" to_port="table input"/>
|
|
|
<connect from_op="Generate Attributes (2)" from_port="table output" to_op="Filter Examples" to_port="example set input"/>
|
|
|
<connect from_op="Filter Examples" 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="Generate Attributes (3)" to_port="table input"/>
|
|
|
<connect from_op="Generate Attributes (3)" from_port="table output" to_op="Select Attributes" to_port="example set input"/>
|
|
|
<connect from_op="Select Attributes" from_port="example set output" to_op="Generate Aggregation" to_port="example set input"/>
|
|
|
<connect from_op="Generate Aggregation" from_port="example set output" to_op="Rename by Replacing" to_port="example set input"/>
|
|
|
<connect from_op="Rename by Replacing" 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>
|
|
|
<operator activated="true" class="concurrency:loop_attributes" compatibility="10.5.000" expanded="true" height="82" name="Loop Attributes" origin="GENERATED_TRAINING" width="90" x="447" y="85">
|
|
|
<parameter key="attribute_filter_type" value="regular_expression"/>
|
|
|
<parameter key="attribute" value=""/>
|
|
|
<parameter key="attributes" value=""/>
|
|
|
<parameter key="regular_expression" value="count.+"/>
|
|
|
<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"/>
|
|
|
<parameter key="attribute_name_macro" value="loop_attribute"/>
|
|
|
<parameter key="reuse_results" value="true"/>
|
|
|
<parameter key="enable_parallel_execution" value="true"/>
|
|
|
<process expanded="true">
|
|
|
<operator activated="true" class="blending:generate_columns" compatibility="10.5.000" expanded="true" height="82" name="Generate Attributes" origin="GENERATED_TRAINING" width="90" x="179" y="34">
|
|
|
<list key="function_descriptions">
|
|
|
<parameter key="%{loop_attribute}" value="eval(%{loop_attribute})/TotalCount"/>
|
|
|
</list>
|
|
|
<parameter key="keep_all_columns" value="true"/>
|
|
|
<parameter key="default_time_zone" value="America/New_York"/>
|
|
|
</operator>
|
|
|
<connect from_port="input 1" to_op="Generate Attributes" to_port="table input"/>
|
|
|
<connect from_op="Generate Attributes" from_port="table output" to_port="output 1"/>
|
|
|
<portSpacing port="source_input 1" spacing="0"/>
|
|
|
<portSpacing port="source_input 2" spacing="0"/>
|
|
|
<portSpacing port="sink_output 1" spacing="0"/>
|
|
|
<portSpacing port="sink_output 2" spacing="0"/>
|
|
|
</process>
|
|
|
</operator>
|
|
|
<connect from_op="Retrieve Transaction Data" from_port="output" to_op="Data Prep" to_port="in 1"/>
|
|
|
<connect from_op="Retrieve Termination Data" from_port="output" to_op="Data Prep" to_port="in 3"/>
|
|
|
<connect from_op="Retrieve Hotel App Joins data" from_port="output" to_op="Data Prep" to_port="in 2"/>
|
|
|
<connect from_op="Data Prep" from_port="out 1" to_op="Feature Generation" to_port="in 1"/>
|
|
|
<connect from_op="Feature Generation" from_port="out 1" to_op="Loop Attributes" to_port="input 1"/>
|
|
|
<connect from_op="Loop Attributes" from_port="output 1" to_port="out 1"/>
|
|
|
<portSpacing port="source_in 1" spacing="0"/>
|
|
|
<portSpacing port="sink_out 1" spacing="0"/>
|
|
|
<portSpacing port="sink_out 2" spacing="0"/>
|
|
|
</process>
|
|
|
</operator>
|
|
|
<operator activated="true" class="concurrency:cross_validation" compatibility="10.1.003" expanded="true" height="145" name="Cross Validation" origin="GENERATED_TRAINING" width="90" x="179" 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="automatic"/>
|
|
|
<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_decision_tree" compatibility="10.5.000" expanded="true" height="103" name="Decision Tree" origin="GENERATED_TRAINING" width="90" x="112" y="34">
|
|
|
<parameter key="criterion" value="gain_ratio"/>
|
|
|
<parameter key="maximal_depth" value="10"/>
|
|
|
<parameter key="apply_pruning" value="true"/>
|
|
|
<parameter key="confidence" value="0.25"/>
|
|
|
<parameter key="apply_prepruning" value="true"/>
|
|
|
<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"/>
|
|
|
</operator>
|
|
|
<connect from_port="training set" to_op="Decision Tree" to_port="training set"/>
|
|
|
<connect from_op="Decision Tree" 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"/>
|
|
|
<description align="left" color="orange" colored="true" height="280" resized="true" width="303" x="10" y="163">Demo 6a &#8211; Building &amp; Storing Model<br><br>1. Embed Lesson 5 process result<br>2. Introduce the Cross Validation Operator (insert building block)<br>3. In the Cross Validation sub-process, define Decision Tree parameters<br>4. Apply Model &amp; Evaluate Performance<br>(Consider using Performance(Binominal Classification) despite any warnings<br>5. Store the Model<br></description>
|
|
|
</process>
|
|
|
<process expanded="true">
|
|
|
<operator activated="true" class="apply_model" compatibility="10.5.000" expanded="true" height="82" name="Apply Model" origin="GENERATED_TRAINING" width="90" x="45" y="34">
|
|
|
<list key="application_parameters"/>
|
|
|
</operator>
|
|
|
<operator activated="true" class="performance_binominal_classification" compatibility="10.5.000" expanded="true" height="82" name="Performance" origin="GENERATED_TRAINING" width="90" x="179" y="34">
|
|
|
<parameter key="manually_set_positive_class" value="false"/>
|
|
|
<parameter key="main_criterion" value="AUC"/>
|
|
|
<parameter key="accuracy" value="true"/>
|
|
|
<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="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="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="Performance" to_port="labelled data"/>
|
|
|
<connect from_op="Performance" from_port="performance" to_port="performance 1"/>
|
|
|
<connect from_op="Performance" from_port="example set" to_port="test set results"/>
|
|
|
<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="store" compatibility="10.5.000" expanded="true" height="68" name="Store" width="90" x="380" y="34">
|
|
|
<parameter key="repository_entry" value="//Local Repository/data/mylearning/atl"/>
|
|
|
</operator>
|
|
|
<connect from_op="ETL" from_port="out 1" to_op="Cross Validation" to_port="example set"/>
|
|
|
<connect from_op="Cross Validation" from_port="model" to_op="Store" to_port="input"/>
|
|
|
<connect from_op="Cross Validation" from_port="test result set" to_port="result 2"/>
|
|
|
<connect from_op="Cross Validation" from_port="performance 1" to_port="result 3"/>
|
|
|
<connect from_op="Store" from_port="through" to_port="result 1"/>
|
|
|
<portSpacing port="source_input 1" spacing="0"/>
|
|
|
<portSpacing port="sink_result 1" spacing="0"/>
|
|
|
<portSpacing port="sink_result 2" spacing="21"/>
|
|
|
<portSpacing port="sink_result 3" spacing="0"/>
|
|
|
<portSpacing port="sink_result 4" spacing="0"/>
|
|
|
<description align="left" color="orange" colored="true" height="93" resized="true" width="650" x="10" y="274">You may find the lesson <a href="https://academy.rapidminer.com/learn/video/deployment-intro">here!<br></a><br>1. Inspect the ETL and Cross Validation subprocesses<br>2. Store the Model in your own repository as Results/Models/DTModel</description>
|
|
|
</process>
|
|
|
</operator>
|
|
|
</process>
|
|
|
|
