A program to recognize and reward our most engaged community members
Try this example.
<?xml version="1.0" encoding="UTF-8"?><process version="7.4.000"> <context> <input/> <output/> <macros/> </context> <operator activated="true" class="process" compatibility="7.4.000" expanded="true" name="Process"> <parameter key="encoding" value="SYSTEM"/> <process expanded="true"> <operator activated="true" class="social_media:search_twitter" compatibility="7.3.000" expanded="true" height="68" name="Search Twitter" width="90" x="45" y="34"> <parameter key="connection" value="NewConnection"/> <parameter key="query" value="RapidMiner"/> <parameter key="language" value="en"/> </operator> <operator activated="true" class="select_attributes" compatibility="7.4.000" expanded="true" height="82" name="Select Attributes" width="90" x="179" y="34"> <parameter key="attribute_filter_type" value="subset"/> <parameter key="attributes" value="Retweet-Count|Text"/> </operator> <operator activated="true" class="nominal_to_text" compatibility="7.4.000" expanded="true" height="82" name="Nominal to Text" width="90" x="313" y="34"> <parameter key="attribute_filter_type" value="single"/> <parameter key="attribute" value="Text"/> </operator> <operator activated="true" class="set_role" compatibility="7.4.000" expanded="true" height="82" name="Set Role" width="90" x="447" y="34"> <parameter key="attribute_name" value="Retweet-Count"/> <parameter key="target_role" value="label"/> <list key="set_additional_roles"/> </operator> <operator activated="true" class="text:process_document_from_data" compatibility="7.4.001" expanded="true" height="82" name="Process Documents from Data" width="90" x="581" y="34"> <parameter key="prune_method" value="percentual"/> <list key="specify_weights"/> <process expanded="true"> <operator activated="true" class="text:tokenize" compatibility="7.4.001" expanded="true" height="68" name="Tokenize" width="90" x="45" y="34"/> <operator activated="true" class="text:filter_stopwords_english" compatibility="7.4.001" expanded="true" height="68" name="Filter Stopwords (English)" width="90" x="179" y="34"/> <operator activated="true" class="text:filter_by_length" compatibility="7.4.001" expanded="true" height="68" name="Filter Tokens (by Length)" width="90" x="313" y="34"> <parameter key="min_chars" value="2"/> </operator> <operator activated="true" class="text:stem_porter" compatibility="7.4.001" expanded="true" height="68" name="Stem (Porter)" width="90" x="447" y="34"/> <operator activated="true" class="text:transform_cases" compatibility="7.4.001" expanded="true" height="68" name="Transform Cases" width="90" x="581" y="34"/> <connect from_port="document" to_op="Tokenize" to_port="document"/> <connect from_op="Tokenize" from_port="document" to_op="Filter Stopwords (English)" to_port="document"/> <connect from_op="Filter Stopwords (English)" from_port="document" to_op="Filter Tokens (by Length)" to_port="document"/> <connect from_op="Filter Tokens (by Length)" from_port="document" to_op="Stem (Porter)" to_port="document"/> <connect from_op="Stem (Porter)" from_port="document" to_op="Transform Cases" to_port="document"/> <connect from_op="Transform Cases" from_port="document" to_port="document 1"/> <portSpacing port="source_document" spacing="0"/> <portSpacing port="sink_document 1" spacing="0"/> <portSpacing port="sink_document 2" spacing="0"/> </process> </operator> <operator activated="true" class="k_means" compatibility="7.4.000" expanded="true" height="82" name="Clustering" width="90" x="715" y="34"/> <connect from_op="Search Twitter" from_port="output" to_op="Select Attributes" to_port="example set input"/> <connect from_op="Select Attributes" from_port="example set output" to_op="Nominal to Text" to_port="example set input"/> <connect from_op="Nominal to Text" 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="Process Documents from Data" to_port="example set"/> <connect from_op="Process Documents from Data" from_port="example set" to_op="Clustering" to_port="example set"/> <connect from_op="Clustering" from_port="cluster model" to_port="result 1"/> <connect from_op="Clustering" from_port="clustered set" 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>
Did you search through the Community for a sample process or attempt one on your own?
yes I do my search but it alowas abut document clustering not word or Term clustering.
for my attempt I try to do the same thing in document clustering using the word output of Text processing operation as input of the K-means clustering operation but it still not good
