how to classify using my own guidelines
mkq
New Altair Community Member
I wan to classify some posts based on my own guidelines. for example, I want some posts with some keywords are classified some class.
Tagged:
0
Answers
-
Hi mkq,
check this process. It is close to what you search for. It counts the occurences of specific words and assigns a score to it. Weights are possible:
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="6.5.002">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="6.5.002" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="generate_data_user_specification" compatibility="6.4.000" expanded="true" height="60" name="Generate Data by User Specification" width="90" x="45" y="255">
<list key="attribute_values">
<parameter key="SomeOtherWord" value="1"/>
<parameter key="text" value="1"/>
<parameter key="example" value="3"/>
</list>
<list key="set_additional_roles"/>
</operator>
<operator activated="false" class="retrieve" compatibility="6.5.002" expanded="true" height="60" name="Retrieve textstuff" width="90" x="112" y="750">
<parameter key="repository_entry" value="//Local Repository/Fourm/textstuff"/>
</operator>
<operator activated="false" class="subprocess" compatibility="6.5.002" expanded="true" height="94" name="Preprocess Dict" width="90" x="246" y="705">
<process expanded="true">
<operator activated="true" breakpoints="after" class="nominal_to_text" compatibility="6.5.002" expanded="true" height="76" name="Nominal to Text" width="90" x="112" y="30"/>
<operator activated="true" class="text:process_document_from_data" compatibility="6.5.000" expanded="true" height="76" name="Process Documents from Data" width="90" x="246" y="30">
<parameter key="vector_creation" value="Term Occurrences"/>
<list key="specify_weights"/>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="6.5.000" expanded="true" height="60" name="Tokenize" width="90" x="380" y="30">
<parameter key="mode" value="specify characters"/>
<parameter key="characters" value="\s"/>
</operator>
<connect from_port="document" to_op="Tokenize" to_port="document"/>
<connect from_op="Tokenize" 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="filter_example_range" compatibility="6.5.002" expanded="true" height="76" name="Filter Example Range" width="90" x="380" y="210">
<parameter key="first_example" value="1"/>
<parameter key="last_example" value="1"/>
</operator>
<operator activated="true" class="loop_attributes" compatibility="6.5.002" expanded="true" height="76" name="Loop Attributes" width="90" x="514" y="210">
<process expanded="true">
<operator activated="true" class="generate_attributes" compatibility="6.4.000" expanded="true" height="76" name="Generate Attributes (2)" width="90" x="313" y="30">
<list key="function_descriptions">
<parameter key="%{loop_attribute}" value="1"/>
</list>
</operator>
<connect from_port="example set" to_op="Generate Attributes (2)" to_port="example set input"/>
<connect from_op="Generate Attributes (2)" from_port="example set output" to_port="example set"/>
<portSpacing port="source_example set" spacing="0"/>
<portSpacing port="sink_example set" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
</process>
</operator>
<operator activated="true" class="generate_attributes" compatibility="6.4.000" expanded="true" height="76" name="Generate Attributes (3)" width="90" x="648" y="210">
<list key="function_descriptions">
<parameter key="label" value="1"/>
</list>
</operator>
<operator activated="true" class="set_role" compatibility="6.5.002" expanded="true" height="76" name="Set Role" width="90" x="782" y="30">
<parameter key="attribute_name" value="label"/>
<parameter key="target_role" value="label"/>
<list key="set_additional_roles"/>
</operator>
<connect from_port="in 1" to_op="Nominal to Text" to_port="example set input"/>
<connect from_op="Nominal to Text" 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="Filter Example Range" to_port="example set input"/>
<connect from_op="Process Documents from Data" from_port="word list" to_port="out 2"/>
<connect from_op="Filter Example Range" from_port="example set output" to_op="Loop Attributes" to_port="example set"/>
<connect from_op="Loop Attributes" from_port="example set" to_op="Generate Attributes (3)" to_port="example set input"/>
<connect from_op="Generate Attributes (3)" 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_port="out 1"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="source_in 2" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
<portSpacing port="sink_out 3" spacing="0"/>
</process>
</operator>
<operator activated="true" class="text:create_document" compatibility="6.5.000" expanded="true" height="60" name="Create Document" width="90" x="45" y="30">
<parameter key="text" value="This is an example text"/>
</operator>
<operator activated="true" class="multiply" compatibility="6.5.002" expanded="true" height="94" name="Multiply" width="90" x="179" y="255"/>
<operator activated="true" class="write_csv" compatibility="6.5.002" expanded="true" height="76" name="Write CSV" width="90" x="313" y="300">
<parameter key="column_separator" value=" "/>
<parameter key="quote_nominal_values" value="false"/>
</operator>
<operator activated="true" class="text:read_document" compatibility="6.5.000" expanded="true" height="60" name="Read Document" width="90" x="447" y="345"/>
<operator activated="true" class="generate_attributes" compatibility="6.4.000" expanded="true" height="76" name="Generate Attributes (4)" width="90" x="313" y="210">
<list key="function_descriptions">
<parameter key="label" value="1"/>
</list>
</operator>
<operator activated="true" class="set_role" compatibility="6.5.002" expanded="true" height="76" name="Set Role (2)" width="90" x="447" y="210">
<parameter key="attribute_name" value="label"/>
<parameter key="target_role" value="label"/>
<list key="set_additional_roles"/>
</operator>
<operator activated="true" class="vector_linear_regression" compatibility="6.5.002" expanded="true" height="76" name="Vector Linear Regression" width="90" x="581" y="210">
<parameter key="use_bias" value="false"/>
</operator>
<operator activated="true" class="text:process_documents" compatibility="6.5.000" expanded="true" height="94" name="Process Documents (2)" width="90" x="581" y="345">
<parameter key="vector_creation" value="Term Occurrences"/>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="6.5.000" expanded="true" height="60" name="Tokenize (3)" width="90" x="246" y="75"/>
<connect from_port="document" to_op="Tokenize (3)" to_port="document"/>
<connect from_op="Tokenize (3)" 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="text:process_documents" compatibility="6.5.000" expanded="true" height="94" name="Process Documents" width="90" x="648" y="30">
<parameter key="vector_creation" value="Term Occurrences"/>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="6.5.000" expanded="true" height="60" name="Tokenize (2)" width="90" x="246" y="75"/>
<connect from_port="document" to_op="Tokenize (2)" to_port="document"/>
<connect from_op="Tokenize (2)" 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="apply_model" compatibility="6.5.002" expanded="true" height="76" name="Apply Model" width="90" x="849" y="75">
<list key="application_parameters"/>
</operator>
<connect from_op="Generate Data by User Specification" from_port="output" to_op="Multiply" to_port="input"/>
<connect from_op="Create Document" from_port="output" to_op="Process Documents" to_port="documents 1"/>
<connect from_op="Multiply" from_port="output 1" to_op="Generate Attributes (4)" to_port="example set input"/>
<connect from_op="Multiply" from_port="output 2" to_op="Write CSV" to_port="input"/>
<connect from_op="Write CSV" from_port="file" to_op="Read Document" to_port="file"/>
<connect from_op="Read Document" from_port="output" to_op="Process Documents (2)" to_port="documents 1"/>
<connect from_op="Generate Attributes (4)" from_port="example set output" to_op="Set Role (2)" to_port="example set input"/>
<connect from_op="Set Role (2)" from_port="example set output" to_op="Vector Linear Regression" to_port="training set"/>
<connect from_op="Vector Linear Regression" from_port="model" to_op="Apply Model" to_port="model"/>
<connect from_op="Process Documents (2)" from_port="word list" to_op="Process Documents" to_port="word list"/>
<connect from_op="Process Documents" from_port="example set" to_op="Apply Model" to_port="unlabelled data"/>
<connect from_op="Apply Model" from_port="labelled data" 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>0 -
Thank you very much ! You help me a lot!
0
Altair Employee