🎉 🎉 RAPIDMINER 9.10 IS OUT!!! 🎉🎉

Download the latest version helping analytics teams accelerate time-to-value for streaming and IIOT use cases.

CLICK HERE TO DOWNLOAD

"Reading a Word Vector into Execute R"

carlcarl Member Posts: 30  Guru
edited June 2019 in Help

After creating a word vector, with a column of words and a column of total occurrences, what line of code would I then need to read that data into the Execute R operator?

 

<?xml version="1.0" encoding="UTF-8"?><process version="7.3.001">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="7.3.001" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="open_file" compatibility="7.3.001" expanded="true" height="68" name="Open File" width="90" x="45" y="34">
<parameter key="filename" value="/Users/carl/Documents/government-strategy.pdf"/>
</operator>
<operator activated="true" class="text:read_document" compatibility="7.3.000" expanded="true" height="68" name="Read Document" width="90" x="179" y="34">
<parameter key="content_type" value="pdf"/>
</operator>
<operator activated="true" class="text:tokenize" compatibility="7.3.000" expanded="true" height="68" name="Tokenize" width="90" x="313" y="34"/>
<operator activated="true" class="text:filter_stopwords_english" compatibility="7.3.000" expanded="true" height="68" name="Filter Stopwords (English)" width="90" x="447" y="34"/>
<operator activated="true" class="text:transform_cases" compatibility="7.3.000" expanded="true" height="68" name="Transform Cases" width="90" x="581" y="34"/>
<operator activated="true" class="text:filter_by_length" compatibility="7.3.000" expanded="true" height="68" name="Filter Tokens (by Length)" width="90" x="715" y="34"/>
<operator activated="true" class="text:stem_snowball" compatibility="7.3.000" expanded="true" height="68" name="Stem (Snowball)" width="90" x="849" y="34"/>
<operator activated="true" class="text:process_documents" compatibility="7.3.000" expanded="true" height="103" name="Process Documents" width="90" x="983" y="34">
<parameter key="vector_creation" value="Term Occurrences"/>
<parameter key="add_meta_information" value="false"/>
<parameter key="prune_below_absolute" value="0"/>
<parameter key="prune_above_absolute" value="10"/>
<process expanded="true">
<connect 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="r_scripting:execute_r" compatibility="7.2.000" expanded="true" height="103" name="Execute R" width="90" x="1117" y="34">
<parameter key="script" value="# rm_main is a mandatory function, &#10;# the number of arguments has to be the number of input ports (can be none)&#10;rm_main = function(data)&#10;{&#10; &#10; &#10; wordcloud(data, scale=c(5,0.5), max.words=100, random.order=FALSE, &#10; rot.per=0.35, use.r.layout=FALSE, colors=brewer.pal(8, “Dark2”))&#10;&#10; # connect 2 output ports to see the results&#10; return(list(data,data2))&#10;}&#10;"/>
</operator>
<connect from_op="Open File" from_port="file" to_op="Read Document" to_port="file"/>
<connect from_op="Read Document" from_port="output" 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="Transform Cases" to_port="document"/>
<connect from_op="Transform Cases" 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 (Snowball)" to_port="document"/>
<connect from_op="Stem (Snowball)" from_port="document" to_op="Process Documents" to_port="documents 1"/>
<connect from_op="Process Documents" from_port="example set" to_op="Execute R" to_port="input 1"/>
<connect from_op="Process Documents" from_port="word list" to_op="Execute R" to_port="input 2"/>
<connect from_op="Execute R" from_port="output 1" to_port="result 1"/>
<connect from_op="Execute R" from_port="output 2" 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>

Best Answer

  • bhupendra_patilbhupendra_patil Administrator, Employee, Member Posts: 168  RM Data Scientist
    Solution Accepted

    Hey @carl

     

    You can  use the 'wordlist to data" operator and then connect that to your Execute R  operator, that should make it available as a datatable in rm_main inside the execute R.

    keep in mind the order matter. So if you connect to first port on execute R, then "data" will ahve your wordlist

    rm_main = function(data)
    {

    ..

    ..}

     

    if you connect it as second port, then apples will have the wordlist. Let me know if this helps

    rm_main = function(data,apples)
    {

    ..

    ..}

     

Answers

  • carlcarl Member Posts: 30  Guru

    Many thanks Bhupendra ... it is at least executing now.  This is my very first attempt at a little R script!

     

    I do get an execution failure though, so guess I'm missing something in the code to recognize the wordlist as a table?

     

    Error and sample data attached below:

     

     

    Wordlist.jpegError.jpeg<?xml version="1.0" encoding="UTF-8"?><process version="7.3.001">
    <context>
    <input/>
    <output/>
    <macros/>
    </context>
    <operator activated="true" class="process" compatibility="7.3.001" expanded="true" name="Process">
    <process expanded="true">
    <operator activated="true" class="open_file" compatibility="7.3.001" expanded="true" height="68" name="Open File" width="90" x="45" y="34">
    <parameter key="filename" value="/Users/carl/Documents/test.pdf"/>
    </operator>
    <operator activated="true" class="text:read_document" compatibility="7.3.000" expanded="true" height="68" name="Read Document" width="90" x="179" y="34">
    <parameter key="content_type" value="pdf"/>
    </operator>
    <operator activated="true" class="text:tokenize" compatibility="7.3.000" expanded="true" height="68" name="Tokenize" width="90" x="313" y="34"/>
    <operator activated="true" class="text:filter_stopwords_english" compatibility="7.3.000" expanded="true" height="68" name="Filter Stopwords (English)" width="90" x="447" y="34"/>
    <operator activated="true" class="text:transform_cases" compatibility="7.3.000" expanded="true" height="68" name="Transform Cases" width="90" x="581" y="34"/>
    <operator activated="true" class="text:filter_by_length" compatibility="7.3.000" expanded="true" height="68" name="Filter Tokens (by Length)" width="90" x="715" y="34"/>
    <operator activated="true" class="text:stem_snowball" compatibility="7.3.000" expanded="true" height="68" name="Stem (Snowball)" width="90" x="849" y="34"/>
    <operator activated="true" class="text:process_documents" compatibility="7.3.000" expanded="true" height="103" name="Process Documents" width="90" x="983" y="34">
    <parameter key="vector_creation" value="Term Occurrences"/>
    <parameter key="add_meta_information" value="false"/>
    <parameter key="prune_below_absolute" value="0"/>
    <parameter key="prune_above_absolute" value="10"/>
    <process expanded="true">
    <connect 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" breakpoints="after" class="text:wordlist_to_data" compatibility="7.3.000" expanded="true" height="82" name="WordList to Data" width="90" x="1117" y="34"/>
    <operator activated="true" class="r_scripting:execute_r" compatibility="7.2.000" expanded="true" height="103" name="Execute R" width="90" x="1251" y="34">
    <parameter key="script" value="rm_main = function(data)&#10;{&#10; wordcloud::wordcloud(data, scale=c(5,0.5), max.words=100, random.order=FALSE,&#10; rot.per=0.35, use.r.layout=FALSE, colors=&quot;Dark2&quot;)&#10;}"/>
    </operator>
    <connect from_op="Open File" from_port="file" to_op="Read Document" to_port="file"/>
    <connect from_op="Read Document" from_port="output" 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="Transform Cases" to_port="document"/>
    <connect from_op="Transform Cases" 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 (Snowball)" to_port="document"/>
    <connect from_op="Stem (Snowball)" from_port="document" to_op="Process Documents" to_port="documents 1"/>
    <connect from_op="Process Documents" from_port="word list" to_op="WordList to Data" to_port="word list"/>
    <connect from_op="WordList to Data" from_port="example set" to_op="Execute R" to_port="input 1"/>
    <connect from_op="Execute R" from_port="output 1" to_port="result 1"/>
    <connect from_op="Execute R" from_port="output 2" 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>

     

Sign In or Register to comment.