( Clustering) with (association rules)

Hi,

could you explain a bit more what you want to do?
In RapidMiner you can easily apply both algorithms with existing operators. But how do you want to combine them?

Best,
David

I want to do clustering (e.g Customer visit segmentation ) and I want to do association rules to search for associated products based on these segmentation

Hi @Ebte ,

in that case you can do the following:

Run the clusting with any algorithm you like (for example k-means or x-means, if you don't know a good number of clusters in advance).

Then you use the Loop Values operator to iterate over the different values of the new cluster attribute. Inside the loop you use the Filter Examples operator to select only those examples that lie in the same cluster, therefor you have to use the iteration_macro (check this video if you haven't used macros before: https://academy.rapidminer.com/learn/video/macros-introduction).
Then on those subsets you can create your association rules.

Check this sample process below as an example.

I hope that helps,
David

<?xml version="1.0" encoding="UTF-8"?><process version="9.1.000">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="6.0.002" expanded="true" name="Process" origin="GENERATED_TUTORIAL">
    <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="9.1.000" expanded="true" height="68" name="Iris" origin="GENERATED_TUTORIAL" width="90" x="45" y="136">
        <parameter key="repository_entry" value="//Samples/data/Iris"/>
      </operator>
      <operator activated="true" class="concurrency:k_means" compatibility="9.1.000" expanded="true" height="82" name="Clustering" width="90" x="179" y="136">
        <parameter key="add_cluster_attribute" value="true"/>
        <parameter key="add_as_label" value="false"/>
        <parameter key="remove_unlabeled" value="false"/>
        <parameter key="k" value="3"/>
        <parameter key="max_runs" value="10"/>
        <parameter key="determine_good_start_values" value="true"/>
        <parameter key="measure_types" value="NumericalMeasures"/>
        <parameter key="mixed_measure" value="MixedEuclideanDistance"/>
        <parameter key="nominal_measure" value="NominalDistance"/>
        <parameter key="numerical_measure" value="EuclideanDistance"/>
        <parameter key="divergence" value="SquaredEuclideanDistance"/>
        <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"/>
        <parameter key="max_optimization_steps" value="100"/>
        <parameter key="use_local_random_seed" value="false"/>
        <parameter key="local_random_seed" value="1992"/>
        <description align="center" color="green" colored="true" width="126">Make any type of clustering.&lt;br&gt;This creates a new attribute:&lt;br&gt;&amp;quot;cluster&amp;quot;</description>
      </operator>
      <operator activated="true" class="discretize_by_frequency" compatibility="7.1.001" expanded="true" height="103" name="Discretize by Frequency" origin="GENERATED_TUTORIAL" width="90" x="380" y="136">
        <parameter key="return_preprocessing_model" value="false"/>
        <parameter key="create_view" 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="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="use_sqrt_of_examples" value="false"/>
        <parameter key="number_of_bins" value="5"/>
        <parameter key="range_name_type" value="short"/>
        <parameter key="automatic_number_of_digits" value="true"/>
        <parameter key="number_of_digits" value="-1"/>
      </operator>
      <operator activated="true" class="nominal_to_binominal" compatibility="7.1.001" expanded="true" height="103" name="Nominal to Binominal" origin="GENERATED_TUTORIAL" width="90" x="514" y="136">
        <parameter key="return_preprocessing_model" value="false"/>
        <parameter key="create_view" 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="nominal"/>
        <parameter key="use_value_type_exception" value="false"/>
        <parameter key="except_value_type" value="file_path"/>
        <parameter key="block_type" value="single_value"/>
        <parameter key="use_block_type_exception" value="false"/>
        <parameter key="except_block_type" value="single_value"/>
        <parameter key="invert_selection" value="false"/>
        <parameter key="include_special_attributes" value="false"/>
        <parameter key="transform_binominal" value="true"/>
        <parameter key="use_underscore_in_name" value="true"/>
      </operator>
      <operator activated="true" class="concurrency:loop_values" compatibility="9.1.000" expanded="true" height="82" name="Loop Values" width="90" x="715" y="136">
        <parameter key="attribute" value="cluster"/>
        <parameter key="iteration_macro" value="loop_value"/>
        <parameter key="reuse_results" value="false"/>
        <parameter key="enable_parallel_execution" value="true"/>
        <process expanded="true">
          <operator activated="true" class="filter_examples" compatibility="9.1.000" expanded="true" height="103" name="Filter Examples" width="90" x="112" 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="cluster.equals.%{loop_value}"/>
            </list>
            <parameter key="filters_logic_and" value="true"/>
            <parameter key="filters_check_metadata" value="true"/>
            <description align="center" color="purple" colored="true" width="126">Select only those examples that belong to a certain cluster.&lt;br&gt;See the filter function where during run time the macro %{loop_value}&lt;br/&gt;is repleaced with &amp;quot;cluster_0&amp;quot;, &amp;quot;cluster_1&amp;quot; and &amp;quot;cluster_3&amp;quot;</description>
          </operator>
          <operator activated="true" class="concurrency:fp_growth" compatibility="9.1.000" expanded="true" height="82" name="FPGrowth" origin="GENERATED_TUTORIAL" width="90" x="447" y="85">
            <parameter key="input_format" value="items in dummy coded columns"/>
            <parameter key="item_separators" value="|"/>
            <parameter key="use_quotes" value="false"/>
            <parameter key="quotes_character" value="&quot;"/>
            <parameter key="escape_character" value="\"/>
            <parameter key="trim_item_names" value="true"/>
            <parameter key="min_requirement" value="support"/>
            <parameter key="min_support" value="0.1"/>
            <parameter key="min_frequency" value="100"/>
            <parameter key="min_items_per_itemset" value="1"/>
            <parameter key="max_items_per_itemset" value="0"/>
            <parameter key="max_number_of_itemsets" value="1000000"/>
            <parameter key="find_min_number_of_itemsets" value="false"/>
            <parameter key="min_number_of_itemsets" value="1"/>
            <parameter key="max_number_of_retries" value="15"/>
            <parameter key="requirement_decrease_factor" value="0.9"/>
            <enumeration key="must_contain_list"/>
          </operator>
          <operator activated="true" class="create_association_rules" compatibility="9.1.000" expanded="true" height="82" name="Create Association Rules" origin="GENERATED_TUTORIAL" width="90" x="581" y="85">
            <parameter key="criterion" value="confidence"/>
            <parameter key="min_confidence" value="0.8"/>
            <parameter key="min_criterion_value" value="0.8"/>
            <parameter key="gain_theta" value="2.0"/>
            <parameter key="laplace_k" value="1.0"/>
          </operator>
          <connect from_port="input 1" to_op="Filter Examples" to_port="example set input"/>
          <connect from_op="Filter Examples" from_port="example set output" to_op="FPGrowth" to_port="example set"/>
          <connect from_op="FPGrowth" from_port="frequent sets" to_op="Create Association Rules" to_port="item sets"/>
          <connect from_op="Create Association Rules" from_port="rules" 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"/>
          <description align="center" color="green" colored="true" height="106" resized="true" width="306" x="433" y="203">Create the association rules</description>
        </process>
        <description align="center" color="red" colored="true" width="126">Loop or iterate over the different values for the &amp;quot;cluster&amp;quot; attribute.&lt;br&gt;The iteration macro is then used to filter the examples inside</description>
      </operator>
      <connect from_op="Iris" from_port="output" to_op="Clustering" to_port="example set"/>
      <connect from_op="Clustering" from_port="clustered set" to_op="Discretize by Frequency" to_port="example set input"/>
      <connect from_op="Discretize by Frequency" 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="Loop Values" to_port="input 1"/>
      <connect from_op="Loop Values" from_port="output 1" to_port="result 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="90"/>
      <portSpacing port="sink_result 2" spacing="0"/>
      <description align="center" color="yellow" colored="false" height="96" resized="true" width="230" x="388" y="249">Just create some more attributes,&lt;br/&gt;by splitting the numerical values into ranges</description>
    </process>
  </operator>
</process>

Thank you so much,

David_A 

hi @Ebte the links that are at the top of the page when you wrote your post are very helpful - they explain all about using XML (like David shared).



You can get back to this page by clicking on "Ask a Question" at the top of any community page.

Scott

Thank you @sgenzer

Can you help me with this?

hi @Ebte so yes, it's saying that you need more computer RAM to run the process you're trying to run, or reduce down the size of your data set via sampling, etc.. How much RAM do you have? What's the size of your data set?

hi @sgenzer
my computer memery is 8GB
dataset : 
Number of examples = 1363 ,
5 attributes:       

8GB is the bare minimum for RapidMiner. That said, try restarting RM (it will clear out all memory entirely) and/or use the "free memory" operator in a few places. It may help. Or just get more RAM

Scott

@sgenzer Ok thank you

Hi @Ebte,

I'm travelling at the moment, so it might take a bit of time to invest your issue.

On a first guess: the FPGrowth algorithm can be quite memory intense. You could try to uncheck the "run in parallel" check box of the Loop Values operator. So it might run a bit slower, but does not require so much memory.

Best regards,
David

Ok @David_A  Thank you ..
' I will try.. '

FP Growth is a real memory hog!  You might not be able to run it at all with only 8Gb RAM even on a relatively small dataset such as yours.  You could also consider setting up a RapidMiner Cloud account and paying for the credits to run just that part of the process which is most memory intensive, then storing the output in a Repository, and doing the rest of the analysis locally.