🎉Community Raffle - Win $25

An exclusive raffle opportunity for active members like you! Complete your profile, answer questions and get your first accepted badge to enter the raffle.
Join and Win

Implement pairwise_count with execute R

User: "TobiasNehrig"
New Altair Community Member
Updated by Jocelyn

Hi Experts,

 

I‘d like to implement in an execute R Operator the widyr function pairwise_count() like in https://www.tidytextmining.com/nasa.html#word-co-ocurrences-and-correlations. For this I crawl some pages and process them. But somehow it won’t function. I’ve this error message:

Dec 22, 2017 3:45:59 PM INFO: [1] "Failed to execute the script."

Dec 22, 2017 3:45:59 PM INFO: [1] "replacement has 0 rows, data has 2"

 

This is how my process looks like:

 

 

<?xml version="1.0" encoding="UTF-8"?><process version="8.0.001">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="8.0.001" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="subprocess" compatibility="8.0.001" expanded="true" height="82" name="Crawler Spon" width="90" x="45" y="34">
<process expanded="true">
<operator activated="true" class="web:crawl_web_modern" compatibility="7.3.000" expanded="true" height="68" name="Crawl Web" width="90" x="112" y="34">
<parameter key="url" value="http://www.spiegel.de"/>
<list key="crawling_rules">
<parameter key="store_with_matching_url" value=".+www.spiegel.+"/>
<parameter key="follow_link_with_matching_url" value=".+spiegel.+|.+de.+"/>
</list>
<parameter key="max_crawl_depth" value="10"/>
<parameter key="retrieve_as_html" value="true"/>
<parameter key="add_content_as_attribute" value="true"/>
<parameter key="max_pages" value="5"/>
<parameter key="delay" value="100"/>
<parameter key="max_concurrent_connections" value="200"/>
<parameter key="max_connections_per_host" value="100"/>
<parameter key="user_agent" value="Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:55.0) Gecko/20100101 Firefox/55.0"/>
</operator>
<operator activated="true" class="web:retrieve_webpages" compatibility="7.3.000" expanded="true" height="68" name="Get Pages" width="90" x="246" y="34">
<parameter key="link_attribute" value="Link"/>
<parameter key="page_attribute" value="link"/>
<parameter key="random_user_agent" value="true"/>
</operator>
<connect from_op="Crawl Web" from_port="example set" to_op="Get Pages" to_port="Example Set"/>
<connect from_op="Get Pages" from_port="Example Set" 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="text:process_document_from_data" compatibility="7.5.000" expanded="true" height="82" name="Process Documents from Data Spon" width="90" x="179" y="34">
<parameter key="vector_creation" value="Term Frequency"/>
<parameter key="add_meta_information" value="false"/>
<parameter key="keep_text" value="true"/>
<parameter key="prune_method" value="absolute"/>
<parameter key="prune_below_absolute" value="2"/>
<parameter key="prune_above_absolute" value="99999"/>
<parameter key="data_management" value="memory-optimized"/>
<parameter key="select_attributes_and_weights" value="true"/>
<list key="specify_weights">
<parameter key="link" value="1.0"/>
</list>
<process expanded="true">
<operator activated="true" class="web:extract_html_text_content" compatibility="7.3.000" expanded="true" height="68" name="Extract Content" width="90" x="45" y="34">
<parameter key="minimum_text_block_length" value="2"/>
</operator>
<operator activated="true" class="text:tokenize" compatibility="7.5.000" expanded="true" height="68" name="Tokenize Token" width="90" x="179" y="34">
<parameter key="mode" value="linguistic tokens"/>
<parameter key="language" value="German"/>
</operator>
<operator activated="true" class="text:filter_tokens_by_content" compatibility="7.5.000" expanded="true" height="68" name="Filter Tokens a-zA-Z" width="90" x="313" y="34">
<parameter key="condition" value="matches"/>
<parameter key="regular_expression" value="[a-zA-Z]+"/>
</operator>
<operator activated="true" class="text:transform_cases" compatibility="7.5.000" expanded="true" height="68" name="Transform Cases" width="90" x="447" y="34"/>
<connect from_port="document" to_op="Extract Content" to_port="document"/>
<connect from_op="Extract Content" from_port="document" to_op="Tokenize Token" to_port="document"/>
<connect from_op="Tokenize Token" from_port="document" to_op="Filter Tokens a-zA-Z" to_port="document"/>
<connect from_op="Filter Tokens a-zA-Z" 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="select_attributes" compatibility="8.0.001" expanded="true" height="82" name="Select Attributes (2)" width="90" x="313" y="34">
<parameter key="attribute_filter_type" value="subset"/>
<parameter key="attributes" value="text"/>
</operator>
<operator activated="true" class="r_scripting:execute_r" compatibility="7.2.000" expanded="true" height="82" name="Execute R" width="90" x="447" 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;library(dplyr)&#10;library(tidytext)&#10;library(widyr)&#10;set.seed(2017)&#10;&#10;test &lt;- data %&gt;%&#10;pairwise_count(word, text, sort= TRUE)&#10;print(test)&#10; return(list(test))&#10;}&#10;"/>
</operator>
<connect from_op="Crawler Spon" from_port="out 1" to_op="Process Documents from Data Spon" to_port="example set"/>
<connect from_op="Process Documents from Data Spon" from_port="example set" to_op="Select Attributes (2)" to_port="example set input"/>
<connect from_op="Select Attributes (2)" from_port="example set output" to_op="Execute R" to_port="input 1"/>
<connect from_op="Select Attributes (2)" from_port="original" to_port="result 2"/>
<connect from_op="Execute R" from_port="output 1" to_port="result 1"/>
<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>

 

Maybe there is someone who can help me to tackle that problem.

 

Regards

Tobias

 

Find more posts tagged with