"sentiment analysis / text calssification problem"
Hello,
i am trying to implement a simple sentiment analysis (related to some videos and tutorials).
But it doens't work an di don't know why.
Could you pleas help me?
______________________________________________________________________
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.3.008">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.3.008" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="text:process_document_from_file" compatibility="5.3.000" expanded="true" height="76" name="Process Documents from Files" width="90" x="313" y="255">
<list key="text_directories">
<parameter key="bsp" value="C:\Users\michaelmoehring\Documents\St-Gallen\rapidminer\test"/>
</list>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="5.3.000" expanded="true" height="60" name="Tokenize" width="90" x="112" y="30">
<parameter key="language" value="German"/>
</operator>
<operator activated="true" class="text:transform_cases" compatibility="5.3.000" expanded="true" height="60" name="Transform Cases" width="90" x="246" y="30"/>
<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_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="retrieve" compatibility="5.3.008" expanded="true" height="60" name="Retrieve 424242" width="90" x="45" y="75">
<parameter key="repository_entry" value="424242"/>
</operator>
<operator activated="true" class="set_role" compatibility="5.3.008" expanded="true" height="76" name="Set Role" width="90" x="179" y="30">
<parameter key="attribute_name" value="wertung"/>
<parameter key="target_role" value="label"/>
<list key="set_additional_roles"/>
</operator>
<operator activated="true" class="x_validation" compatibility="5.3.008" expanded="true" height="112" name="Validation" width="90" x="313" y="30">
<parameter key="number_of_validations" value="5"/>
<process expanded="true">
<operator activated="true" class="k_nn" compatibility="5.3.008" expanded="true" height="76" name="k-NN" width="90" x="112" y="210">
<parameter key="k" value="20"/>
<parameter key="weighted_vote" value="true"/>
<parameter key="numerical_measure" value="CosineSimilarity"/>
</operator>
<connect from_port="training" to_op="k-NN" to_port="training set"/>
<connect from_op="k-NN" from_port="model" to_port="model"/>
<portSpacing port="source_training" spacing="0"/>
<portSpacing port="sink_model" spacing="0"/>
<portSpacing port="sink_through 1" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" class="apply_model" compatibility="5.3.008" expanded="true" height="76" name="Apply Model" width="90" x="45" y="30">
<list key="application_parameters"/>
</operator>
<operator activated="true" class="performance" compatibility="5.3.008" expanded="true" height="76" name="Performance" width="90" x="179" y="165"/>
<connect from_port="model" to_op="Apply Model" to_port="model"/>
<connect from_port="test set" to_op="Apply Model" to_port="unlabelled data"/>
<connect from_op="Apply Model" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
<connect from_op="Performance" from_port="performance" to_port="averagable 1"/>
<portSpacing port="source_model" spacing="0"/>
<portSpacing port="source_test set" spacing="0"/>
<portSpacing port="source_through 1" spacing="0"/>
<portSpacing port="sink_averagable 1" spacing="0"/>
<portSpacing port="sink_averagable 2" spacing="0"/>
</process>
</operator>
<operator activated="true" class="apply_model" compatibility="5.3.008" expanded="true" height="76" name="Apply Model (2)" width="90" x="514" y="165">
<list key="application_parameters"/>
</operator>
<connect from_op="Process Documents from Files" from_port="example set" to_op="Apply Model (2)" to_port="unlabelled data"/>
<connect from_op="Retrieve 424242" from_port="output" to_op="Set Role" to_port="example set input"/>
<connect from_op="Set Role" from_port="example set output" to_op="Validation" to_port="training"/>
<connect from_op="Validation" from_port="model" to_op="Apply Model (2)" to_port="model"/>
<connect from_op="Apply Model (2)" from_port="labelled data" to_port="result 1"/>
<connect from_op="Apply Model (2)" from_port="model" 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>
_______________________________________________________________________
The positive negative words a stored in the repository based on a csv with two coloums (word; positive/negative).
Thank you so much!
Greetings
i am trying to implement a simple sentiment analysis (related to some videos and tutorials).
But it doens't work an di don't know why.
Could you pleas help me?
______________________________________________________________________
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.3.008">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="5.3.008" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="text:process_document_from_file" compatibility="5.3.000" expanded="true" height="76" name="Process Documents from Files" width="90" x="313" y="255">
<list key="text_directories">
<parameter key="bsp" value="C:\Users\michaelmoehring\Documents\St-Gallen\rapidminer\test"/>
</list>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="5.3.000" expanded="true" height="60" name="Tokenize" width="90" x="112" y="30">
<parameter key="language" value="German"/>
</operator>
<operator activated="true" class="text:transform_cases" compatibility="5.3.000" expanded="true" height="60" name="Transform Cases" width="90" x="246" y="30"/>
<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_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="retrieve" compatibility="5.3.008" expanded="true" height="60" name="Retrieve 424242" width="90" x="45" y="75">
<parameter key="repository_entry" value="424242"/>
</operator>
<operator activated="true" class="set_role" compatibility="5.3.008" expanded="true" height="76" name="Set Role" width="90" x="179" y="30">
<parameter key="attribute_name" value="wertung"/>
<parameter key="target_role" value="label"/>
<list key="set_additional_roles"/>
</operator>
<operator activated="true" class="x_validation" compatibility="5.3.008" expanded="true" height="112" name="Validation" width="90" x="313" y="30">
<parameter key="number_of_validations" value="5"/>
<process expanded="true">
<operator activated="true" class="k_nn" compatibility="5.3.008" expanded="true" height="76" name="k-NN" width="90" x="112" y="210">
<parameter key="k" value="20"/>
<parameter key="weighted_vote" value="true"/>
<parameter key="numerical_measure" value="CosineSimilarity"/>
</operator>
<connect from_port="training" to_op="k-NN" to_port="training set"/>
<connect from_op="k-NN" from_port="model" to_port="model"/>
<portSpacing port="source_training" spacing="0"/>
<portSpacing port="sink_model" spacing="0"/>
<portSpacing port="sink_through 1" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" class="apply_model" compatibility="5.3.008" expanded="true" height="76" name="Apply Model" width="90" x="45" y="30">
<list key="application_parameters"/>
</operator>
<operator activated="true" class="performance" compatibility="5.3.008" expanded="true" height="76" name="Performance" width="90" x="179" y="165"/>
<connect from_port="model" to_op="Apply Model" to_port="model"/>
<connect from_port="test set" to_op="Apply Model" to_port="unlabelled data"/>
<connect from_op="Apply Model" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
<connect from_op="Performance" from_port="performance" to_port="averagable 1"/>
<portSpacing port="source_model" spacing="0"/>
<portSpacing port="source_test set" spacing="0"/>
<portSpacing port="source_through 1" spacing="0"/>
<portSpacing port="sink_averagable 1" spacing="0"/>
<portSpacing port="sink_averagable 2" spacing="0"/>
</process>
</operator>
<operator activated="true" class="apply_model" compatibility="5.3.008" expanded="true" height="76" name="Apply Model (2)" width="90" x="514" y="165">
<list key="application_parameters"/>
</operator>
<connect from_op="Process Documents from Files" from_port="example set" to_op="Apply Model (2)" to_port="unlabelled data"/>
<connect from_op="Retrieve 424242" from_port="output" to_op="Set Role" to_port="example set input"/>
<connect from_op="Set Role" from_port="example set output" to_op="Validation" to_port="training"/>
<connect from_op="Validation" from_port="model" to_op="Apply Model (2)" to_port="model"/>
<connect from_op="Apply Model (2)" from_port="labelled data" to_port="result 1"/>
<connect from_op="Apply Model (2)" from_port="model" 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>
_______________________________________________________________________
The positive negative words a stored in the repository based on a csv with two coloums (word; positive/negative).
Thank you so much!
Greetings