Hi all,
after preparation of data for FP-Growth (binary representation) my example set looks like this:
The next step is transforming the data from nominal to binomial with the help of Nominal to Binomial.
<operator activated="true" breakpoints="after" class="nominal_to_binominal" compatibility="7.2.001" expanded="true" height="103" name="Nominal to Binominal" width="90" x="715" y="34">
<parameter key="create_view" value="true"/>
<parameter key="regular_expression" value="[0-9]+"/>
</operator>
This is the input to Nominal to Binomial:
The operator Nominal to Binomial runs without any error messages - but unfortunately without a result set also..
When ticking the parameter transform binomial*, RapidMiner splits one column into two, which is not what I need for the subsequent FP-Growth operator. *desperate attempt via try-and-error
Any suggestions? ...please..
The whole process (if necessary):
<?xml version="1.0" encoding="UTF-8"?><process version="7.2.001">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="7.2.001" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" breakpoints="after" class="subprocess" compatibility="7.2.001" expanded="true" height="82" name="Pivot data" width="90" x="45" y="34">
<process expanded="true">
<operator activated="true" class="jdbc_connectors:read_database" compatibility="7.2.001" expanded="true" height="68" name="Read Database" width="90" x="179" y="136">
<parameter key="connection" value="DB_Name"/>
<parameter key="query" value="SELECT * FROM "DB_SCHEMA"."TBLBIT" WHERE ROWNUM < 100000"/>
<enumeration key="parameters"/>
</operator>
<operator activated="false" class="jdbc_connectors:stream_database" compatibility="7.2.001" expanded="true" height="68" name="Stream Database" width="90" x="179" y="34">
<parameter key="connection" value="DB_NAME"/>
<parameter key="table_name" value="ZZ_RM_TEST"/>
<parameter key="recreate_index" value="true"/>
</operator>
<operator activated="true" breakpoints="after" class="select_attributes" compatibility="7.2.001" expanded="true" height="82" name="Select Attributes" width="90" x="313" y="34">
<parameter key="attribute_filter_type" value="subset"/>
<parameter key="attributes" value="|TBLUNIQUELRU_ID|BITID|EVENT"/>
</operator>
<operator activated="true" class="filter_examples" compatibility="7.2.001" expanded="true" height="103" name="Filter Examples" width="90" x="447" y="34">
<list key="filters_list">
<parameter key="filters_entry_key" value="BITID.is_not_missing."/>
</list>
</operator>
<operator activated="true" breakpoints="after" class="pivot" compatibility="7.2.001" expanded="true" height="82" name="Pivot" width="90" x="581" y="34">
<parameter key="group_attribute" value="TBLUNIQUELRU_ID"/>
<parameter key="index_attribute" value="BITID"/>
<parameter key="consider_weights" value="false"/>
<parameter key="skip_constant_attributes" value="false"/>
</operator>
<connect from_op="Read Database" from_port="output" to_op="Select Attributes" to_port="example set input"/>
<connect from_op="Select Attributes" from_port="example set output" to_op="Filter Examples" to_port="example set input"/>
<connect from_op="Filter Examples" from_port="example set output" to_op="Pivot" to_port="example set input"/>
<connect from_op="Pivot" from_port="example set output" 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="subprocess" compatibility="7.2.001" expanded="true" height="82" name="Rename" width="90" x="179" y="34">
<process expanded="true">
<operator activated="true" class="rename_by_replacing" compatibility="7.2.001" expanded="true" height="82" name="Rename Att. EVENT_" width="90" x="45" y="34">
<parameter key="regular_expression" value="EVENT_"/>
<parameter key="replace_what" value="EVENT_"/>
</operator>
<operator activated="true" class="rename_by_replacing" compatibility="7.2.001" expanded="true" height="82" name="Rename Attr. .0" width="90" x="179" y="34">
<parameter key="attribute_filter_type" value="regular_expression"/>
<parameter key="regular_expression" value="[0-9]*[.][0]"/>
<parameter key="replace_what" value="[.]0"/>
</operator>
<operator activated="false" class="replace" compatibility="7.2.001" expanded="true" height="82" name="Replace TINF" width="90" x="313" y="136">
<parameter key="regular_expression" value="' '[0-9][.][0-9]"/>
<parameter key="replace_what" value="TINF"/>
<parameter key="replace_by" value="Y"/>
</operator>
<operator activated="true" class="replace" compatibility="7.2.001" expanded="true" height="82" name="Replace [A-Z]" width="90" x="447" y="34">
<parameter key="regular_expression" value="' '[0-9][.][0-9]"/>
<parameter key="replace_what" value="[A-Z]+"/>
<parameter key="replace_by" value="Y"/>
</operator>
<operator activated="false" class="replace" compatibility="7.2.001" expanded="true" height="82" name="Replace TPSD" width="90" x="447" y="187">
<parameter key="regular_expression" value="' '[0-9][.][0-9]"/>
<parameter key="replace_what" value="TPSD"/>
<parameter key="replace_by" value="Y"/>
</operator>
<operator activated="false" class="replace" compatibility="7.2.001" expanded="true" height="82" name="Replace PWRO" width="90" x="581" y="187">
<parameter key="regular_expression" value="' '[0-9][.][0-9]"/>
<parameter key="replace_what" value="PWRO"/>
<parameter key="replace_by" value="Y"/>
</operator>
<operator activated="false" breakpoints="after" class="replace" compatibility="7.2.001" expanded="true" height="82" name="Replace TFLD" width="90" x="715" y="187">
<parameter key="regular_expression" value="' '[0-9][.][0-9]"/>
<parameter key="replace_what" value="TFLD"/>
<parameter key="replace_by" value="Y"/>
</operator>
<operator activated="true" breakpoints="after" class="replace_missing_values" compatibility="7.2.001" expanded="true" height="103" name="Replace Missing Values" width="90" x="983" y="34">
<parameter key="create_view" value="true"/>
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="TBLUNIQUELRU_ID"/>
<parameter key="regular_expression" value="[0-9]+"/>
<parameter key="value_type" value="nominal"/>
<parameter key="invert_selection" value="true"/>
<parameter key="default" value="none"/>
<list key="columns">
<parameter key="Infinity" value="zero"/>
</list>
</operator>
<operator activated="false" class="replace_infinite_values" compatibility="7.2.001" expanded="true" height="103" name="Replace Infinite Values" width="90" x="916" y="187">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="TBLUNIQUELRU_ID"/>
<parameter key="invert_selection" value="true"/>
<parameter key="default" value="none"/>
<list key="columns"/>
</operator>
<connect from_port="in 1" to_op="Rename Att. EVENT_" to_port="example set input"/>
<connect from_op="Rename Att. EVENT_" from_port="example set output" to_op="Rename Attr. .0" to_port="example set input"/>
<connect from_op="Rename Attr. .0" from_port="example set output" to_op="Replace [A-Z]" to_port="example set input"/>
<connect from_op="Replace [A-Z]" from_port="example set output" to_op="Replace Missing Values" to_port="example set input"/>
<connect from_op="Replace TPSD" from_port="example set output" to_op="Replace PWRO" to_port="example set input"/>
<connect from_op="Replace PWRO" from_port="example set output" to_op="Replace TFLD" to_port="example set input"/>
<connect from_op="Replace Missing Values" 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="false" class="set_role" compatibility="7.2.001" expanded="true" height="82" name="Set Role" width="90" x="179" y="187">
<parameter key="attribute_name" value="TBLUNIQUELRU_ID"/>
<parameter key="target_role" value="id"/>
<list key="set_additional_roles"/>
</operator>
<operator activated="false" class="select_attributes" compatibility="7.2.001" expanded="true" height="82" name="Select Attributes (3)" width="90" x="313" y="187">
<parameter key="attribute_filter_type" value="regular_expression"/>
<parameter key="regular_expression" value="['?' ]"/>
<parameter key="invert_selection" value="true"/>
</operator>
<operator activated="true" breakpoints="after" class="replace_missing_values" compatibility="7.2.001" expanded="true" height="103" name="Replace Missing Values (2)" width="90" x="313" y="34">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="TBLUNIQUELRU_ID"/>
<parameter key="invert_selection" value="true"/>
<parameter key="default" value="value"/>
<list key="columns"/>
<parameter key="replenishment_value" value="N"/>
</operator>
<operator activated="true" breakpoints="after" class="select_attributes" compatibility="7.2.001" expanded="true" height="82" name="Select Attributes (2)" width="90" x="447" y="34">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="TBLUNIQUELRU_ID"/>
<parameter key="attributes" value="TBLUNIQUELRU_ID||Infinity"/>
<parameter key="invert_selection" value="true"/>
</operator>
<operator activated="false" breakpoints="after" class="replace" compatibility="7.2.001" expanded="true" height="82" name="Replace '?'" width="90" x="581" y="238">
<parameter key="regular_expression" value="((.*[.])(0))"/>
<parameter key="replace_what" value="\?"/>
<parameter key="replace_by" value="'?'"/>
</operator>
<operator activated="true" breakpoints="after" class="nominal_to_binominal" compatibility="7.2.001" expanded="true" height="103" name="Nominal to Binominal" width="90" x="715" y="34">
<parameter key="create_view" value="true"/>
<parameter key="regular_expression" value="[0-9]+"/>
</operator>
<operator activated="true" breakpoints="before,after" class="fp_growth" compatibility="7.2.001" expanded="true" height="82" name="FP-Growth" width="90" x="849" y="34"/>
<connect from_op="Pivot data" from_port="out 1" to_op="Rename" to_port="in 1"/>
<connect from_op="Rename" from_port="out 1" to_op="Replace Missing Values (2)" to_port="example set input"/>
<connect from_op="Replace Missing Values (2)" from_port="example set output" to_op="Select Attributes (2)" to_port="example set input"/>
<connect from_op="Select Attributes (2)" from_port="example set output" to_op="Nominal to Binominal" to_port="example set input"/>
<connect from_op="Nominal to Binominal" from_port="example set output" to_op="FP-Growth" to_port="example set"/>
<connect from_op="FP-Growth" from_port="example set" to_port="result 1"/>
<connect from_op="FP-Growth" from_port="frequent sets" to_port="result 2"/>
<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>
