The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
Web Crawling
gunjanamit
Member Posts: 28 
Contributor II
I am trying to read two websites, tokenize the web pages data and then finding similarity.
But I am not getting results in the very first step - On reading web pages
My XML is
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.2.006">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.2.006" expanded="true" name="Process">
<process expanded="true" height="359" width="547">
<operator activated="true" class="read_excel" compatibility="5.2.006" expanded="true" height="60" name="Read Excel" width="90" x="57" y="26">
<parameter key="excel_file" value="C:\Users\guagg\Desktop\All\RapidMiner\read.xls"/>
<parameter key="imported_cell_range" value="A1:A3"/>
<parameter key="first_row_as_names" value="false"/>
<list key="annotations">
<parameter key="0" value="Comment"/>
</list>
<list key="data_set_meta_data_information">
<parameter key="0" value="Comments.true.file_path.attribute"/>
</list>
</operator>
<operator activated="true" class="web:retrieve_webpages" compatibility="5.2.000" expanded="true" height="60" name="Get Pages" width="90" x="179" y="120">
<parameter key="link_attribute" value="Comments"/>
</operator>
<operator activated="true" class="text:data_to_documents" compatibility="5.2.003" expanded="true" height="60" name="Data to Documents" width="90" x="246" y="30">
<parameter key="select_attributes_and_weights" value="true"/>
<list key="specify_weights"/>
</operator>
<operator activated="true" class="text:process_documents" compatibility="5.2.003" expanded="true" height="94" name="Process Documents" width="90" x="246" y="255">
<process expanded="true" height="360" width="695">
<operator activated="true" class="text:tokenize" compatibility="5.2.003" expanded="true" height="60" name="Tokenize" width="90" x="193" y="106"/>
<operator activated="true" class="text:transform_cases" compatibility="5.2.003" expanded="true" height="60" name="Transform Cases" width="90" x="306" y="104"/>
<operator activated="true" class="text:filter_stopwords_english" compatibility="5.2.003" expanded="true" height="60" name="Filter Stopwords (English)" width="90" x="422" y="104"/>
<connect from_port="document" to_op="Tokenize" to_port="document"/>
<connect from_op="Tokenize" from_port="document" to_op="Transform Cases" to_port="document"/>
<connect from_op="Transform Cases" from_port="document" to_op="Filter Stopwords (English)" to_port="document"/>
<connect from_op="Filter Stopwords (English)" 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="data_to_similarity" compatibility="5.2.006" expanded="true" height="76" name="Data to Similarity" width="90" x="380" y="165">
<parameter key="measure_types" value="NumericalMeasures"/>
<parameter key="numerical_measure" value="CosineSimilarity"/>
</operator>
<connect from_op="Read Excel" from_port="output" to_op="Get Pages" to_port="Example Set"/>
<connect from_op="Get Pages" from_port="Example Set" to_op="Data to Documents" to_port="example set"/>
<connect from_op="Data to Documents" from_port="documents" to_op="Process Documents" to_port="documents 1"/>
<connect from_op="Process Documents" from_port="example set" to_op="Data to Similarity" to_port="example set"/>
<connect from_op="Process Documents" from_port="word list" to_port="result 2"/>
<connect from_op="Data to Similarity" from_port="similarity" to_port="result 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="180"/>
<portSpacing port="sink_result 3" spacing="18"/>
</process>
</operator>
</process>
Please suggest....
But I am not getting results in the very first step - On reading web pages
My XML is
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.2.006">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.2.006" expanded="true" name="Process">
<process expanded="true" height="359" width="547">
<operator activated="true" class="read_excel" compatibility="5.2.006" expanded="true" height="60" name="Read Excel" width="90" x="57" y="26">
<parameter key="excel_file" value="C:\Users\guagg\Desktop\All\RapidMiner\read.xls"/>
<parameter key="imported_cell_range" value="A1:A3"/>
<parameter key="first_row_as_names" value="false"/>
<list key="annotations">
<parameter key="0" value="Comment"/>
</list>
<list key="data_set_meta_data_information">
<parameter key="0" value="Comments.true.file_path.attribute"/>
</list>
</operator>
<operator activated="true" class="web:retrieve_webpages" compatibility="5.2.000" expanded="true" height="60" name="Get Pages" width="90" x="179" y="120">
<parameter key="link_attribute" value="Comments"/>
</operator>
<operator activated="true" class="text:data_to_documents" compatibility="5.2.003" expanded="true" height="60" name="Data to Documents" width="90" x="246" y="30">
<parameter key="select_attributes_and_weights" value="true"/>
<list key="specify_weights"/>
</operator>
<operator activated="true" class="text:process_documents" compatibility="5.2.003" expanded="true" height="94" name="Process Documents" width="90" x="246" y="255">
<process expanded="true" height="360" width="695">
<operator activated="true" class="text:tokenize" compatibility="5.2.003" expanded="true" height="60" name="Tokenize" width="90" x="193" y="106"/>
<operator activated="true" class="text:transform_cases" compatibility="5.2.003" expanded="true" height="60" name="Transform Cases" width="90" x="306" y="104"/>
<operator activated="true" class="text:filter_stopwords_english" compatibility="5.2.003" expanded="true" height="60" name="Filter Stopwords (English)" width="90" x="422" y="104"/>
<connect from_port="document" to_op="Tokenize" to_port="document"/>
<connect from_op="Tokenize" from_port="document" to_op="Transform Cases" to_port="document"/>
<connect from_op="Transform Cases" from_port="document" to_op="Filter Stopwords (English)" to_port="document"/>
<connect from_op="Filter Stopwords (English)" 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="data_to_similarity" compatibility="5.2.006" expanded="true" height="76" name="Data to Similarity" width="90" x="380" y="165">
<parameter key="measure_types" value="NumericalMeasures"/>
<parameter key="numerical_measure" value="CosineSimilarity"/>
</operator>
<connect from_op="Read Excel" from_port="output" to_op="Get Pages" to_port="Example Set"/>
<connect from_op="Get Pages" from_port="Example Set" to_op="Data to Documents" to_port="example set"/>
<connect from_op="Data to Documents" from_port="documents" to_op="Process Documents" to_port="documents 1"/>
<connect from_op="Process Documents" from_port="example set" to_op="Data to Similarity" to_port="example set"/>
<connect from_op="Process Documents" from_port="word list" to_port="result 2"/>
<connect from_op="Data to Similarity" from_port="similarity" to_port="result 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="180"/>
<portSpacing port="sink_result 3" spacing="18"/>
</process>
</operator>
</process>
Please suggest....
0
