Hello,
I'm new in RapidMiner and I need some help please!
I have a process in RM witch find similarity between some records. This process run successfully!
I run this process in java, but I cant get the results.
In java code run the process and get the result in IOContainer object.
Then get data of first outpout port with
SimilarityMeasureObject result = (SimilarityMeasureObject)ioResult.getElementAt(0);
How can get the results of this process??
Thank you!!!
The RM process
<?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="read_database" compatibility="5.3.008" expanded="true" height="60" name="Read Database" width="90" x="45" y="75">
<parameter key="connection" value="diplomatii"/>
<parameter key="query" value="SELECT `comment` FROM `web`"/>
<enumeration key="parameters"/>
</operator>
<operator activated="true" class="nominal_to_text" compatibility="5.3.008" expanded="true" height="76" name="Nominal to Text" width="90" x="179" y="75"/>
<operator activated="true" class="text:process_document_from_data" compatibility="5.3.000" expanded="true" height="76" name="Process Documents from Data" width="90" x="313" y="75">
<parameter key="prune_method" value="percentual"/>
<parameter key="prune_above_percent" value="60.0"/>
<parameter key="select_attributes_and_weights" value="true"/>
<list key="specify_weights">
<parameter key="comment" value="1.0"/>
</list>
<process expanded="true">
<operator activated="true" class="text:replace_tokens" compatibility="5.3.000" expanded="true" height="60" name="Replace Tokens" width="90" x="45" y="75">
<list key="replace_dictionary">
<parameter key="[-!"#$%&'()*+,./:;<=>?@\[\\\]_`{|}~]" value=" "/>
</list>
</operator>
<operator activated="true" class="text:tokenize" compatibility="5.3.000" expanded="true" height="60" name="Tokenize" width="90" x="179" y="75">
<parameter key="mode" value="linguistic tokens"/>
</operator>
<operator activated="true" class="text:transform_cases" compatibility="5.3.000" expanded="true" height="60" name="Transform Cases" width="90" x="313" y="75">
<parameter key="transform_to" value="upper case"/>
</operator>
<operator activated="true" class="text:filter_by_length" compatibility="5.3.000" expanded="true" height="60" name="Filter Tokens (by Length)" width="90" x="179" y="210"/>
<operator activated="true" class="text:filter_stopwords_dictionary" compatibility="5.3.000" expanded="true" height="76" name="Filter Stopwords (Dictionary)" width="90" x="313" y="210">
<parameter key="file" value="C:\Users\Dimitris\Desktop\greek stopwords.txt"/>
</operator>
<operator activated="true" class="text:filter_stopwords_english" compatibility="5.3.000" expanded="true" height="60" name="Filter Stopwords (English)" width="90" x="447" y="210"/>
<operator activated="true" class="text:stem_snowball" compatibility="5.3.000" expanded="true" height="60" name="Stem (Snowball)" width="90" x="581" y="210"/>
<operator activated="true" class="text:generate_n_grams_terms" compatibility="5.3.000" expanded="true" height="60" name="Generate n-Grams (Terms)" width="90" x="648" y="75">
<parameter key="max_length" value="3"/>
</operator>
<connect from_port="document" to_op="Replace Tokens" to_port="document"/>
<connect from_op="Replace Tokens" 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 Tokens (by Length)" to_port="document"/>
<connect from_op="Filter Tokens (by Length)" from_port="document" to_op="Filter Stopwords (Dictionary)" to_port="document"/>
<connect from_op="Filter Stopwords (Dictionary)" from_port="document" to_op="Filter Stopwords (English)" to_port="document"/>
<connect from_op="Filter Stopwords (English)" from_port="document" to_op="Stem (Snowball)" to_port="document"/>
<connect from_op="Stem (Snowball)" from_port="document" to_op="Generate n-Grams (Terms)" to_port="document"/>
<connect from_op="Generate n-Grams (Terms)" 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="5.3.008" expanded="true" height="76" name="Data to Similarity" width="90" x="447" y="75">
<parameter key="measure_types" value="NumericalMeasures"/>
<parameter key="numerical_measure" value="CosineSimilarity"/>
</operator>
<connect from_op="Read Database" 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="Process Documents from Data" to_port="example set"/>
<connect from_op="Process Documents from Data" from_port="example set" to_op="Data to Similarity" to_port="example set"/>
<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="0"/>
</process>
</operator>
</process>
