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
text mining problem
Mohamad1367
Member Posts: 22 Learner III
hi dear community
i have a question about filter stop word (dictionary) operator that i asked in previous post but didn't answer anyone. when i apply this operator after tokenizing the eaxample set i don't recieve filtered output what is the cause of this problem?
i have a question about filter stop word (dictionary) operator that i asked in previous post but didn't answer anyone. when i apply this operator after tokenizing the eaxample set i don't recieve filtered output what is the cause of this problem?
Tagged:
0
Answers
Lindon Ventures
Data Science Consulting from Certified RapidMiner Experts
متاسفانه روال پردازش شما در سیستم بنده کار نمیکند. در حال حاضر مشکل چی هست؟
سارا
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="9.7.000" expanded="true" name="Process">
<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="read_excel" compatibility="9.7.000" expanded="true" height="68" name="Read Excel" width="90" x="45" y="34">
<parameter key="excel_file" value="C:\Users\Administrator\Desktop\test.xlsx"/>
<parameter key="sheet_selection" value="sheet number"/>
<parameter key="sheet_number" value="1"/>
<parameter key="imported_cell_range" value="A1"/>
<parameter key="encoding" value="SYSTEM"/>
<parameter key="first_row_as_names" value="true"/>
<list key="annotations"/>
<parameter key="date_format" value=""/>
<parameter key="time_zone" value="SYSTEM"/>
<parameter key="locale" value="English (United States)"/>
<parameter key="read_all_values_as_polynominal" value="false"/>
<list key="data_set_meta_data_information">
<parameter key="0" value="opinion.true.polynominal.attribute"/>
<parameter key="1" value="label.true.integer.attribute"/>
</list>
<parameter key="read_not_matching_values_as_missings" value="false"/>
<parameter key="datamanagement" value="double_array"/>
<parameter key="data_management" value="auto"/>
</operator>
<operator activated="true" class="nominal_to_text" compatibility="9.7.000" expanded="true" height="82" name="Nominal to Text" width="90" x="179" y="34">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="opinion"/>
<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"/>
</operator>
<operator activated="true" breakpoints="after" class="rosette_text_toolkit:rosette_tokenize" compatibility="1.11.000" expanded="true" height="68" name="Tokenize (2)" width="90" x="313" y="34">
<parameter key="Connection" value="NewConnection"/>
<parameter key="Source Language" value="Persian"/>
<parameter key="Attribute Selector" value="opinion"/>
<parameter key="Filter stopwords" value="false"/>
</operator>
<operator activated="true" class="text:process_document_from_data" compatibility="9.3.001" expanded="true" height="82" name="Process Documents from Data" width="90" x="447" y="34">
<parameter key="create_word_vector" value="true"/>
<parameter key="vector_creation" value="TF-IDF"/>
<parameter key="add_meta_information" value="true"/>
<parameter key="keep_text" value="false"/>
<parameter key="prune_method" value="none"/>
<parameter key="prune_below_percent" value="3.0"/>
<parameter key="prune_above_percent" value="30.0"/>
<parameter key="prune_below_rank" value="0.05"/>
<parameter key="prune_above_rank" value="0.95"/>
<parameter key="datamanagement" value="double_sparse_array"/>
<parameter key="data_management" value="auto"/>
<parameter key="select_attributes_and_weights" value="true"/>
<list key="specify_weights">
<parameter key="Token" value="1.0"/>
</list>
<process expanded="true">
<operator activated="true" class="open_file" compatibility="9.7.000" expanded="true" height="68" name="Open File" width="90" x="112" y="187">
<parameter key="resource_type" value="file"/>
<parameter key="filename" value="C:/Users/Administrator/Desktop/stopwords.txt"/>
</operator>
<operator activated="true" class="text:filter_stopwords_dictionary" compatibility="9.3.001" expanded="true" height="82" name="Filter Stopwords (Dictionary)" width="90" x="246" y="34">
<parameter key="file" value="C:\Users\lione\Downloads\stopwords.txt"/>
<parameter key="case_sensitive" value="false"/>
<parameter key="encoding" value="SYSTEM"/>
</operator>
<connect from_port="document" to_op="Filter Stopwords (Dictionary)" to_port="document"/>
<connect from_op="Open File" from_port="file" to_op="Filter Stopwords (Dictionary)" to_port="file"/>
<connect from_op="Filter Stopwords (Dictionary)" 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>
<connect from_op="Read Excel" from_port="output" to_op="Nominal to Text" to_port="example set input"/>
<connect from_op="Nominal to Text" from_port="example set output" to_op="Tokenize (2)" to_port="example set"/>
<connect from_op="Tokenize (2)" from_port="example set" to_op="Process Documents from Data" to_port="example set"/>
<connect from_op="Process Documents from Data" from_port="example set" 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"/>
</process>
</operator>
</process>
شرمنده
https://academy.rapidminer.com/learn/video/applying-a-model-to-categorize-documents
https://academy.rapidminer.com/learn/video/document-similarity-and-clustering
https://rapidminer.com/wp-content/uploads/2015/11/Text-Mining-with-RapidMiner.pdf
هنگ کرده