Options
Not getting the total occurences in the word list
Contributor II
I created a model that should give me the # of occurances of a word or n-gram. The model should only give the occurances of the words and n-grams that maches a wordlist.
When I ran the model and I check the output of the model I can see that the n-gram "not-clean" occurs 4 times. But when I check the wordlist of the output it gives only 1 occurrence.
This is because the model is not counting the # of occurances of the excel sheet but the # of occurances of the textfile
How can I change the model that is gives me the # occurances of he words and n-grams of the data in the excelfile?
Model:
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="6.0.003">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="6.0.002" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="text:process_document_from_file" compatibility="5.3.002" expanded="true" height="76" name="Process Documents from Files" width="90" x="45" y="165">
<list key="text_directories">
<parameter key="Most mentioned negative" value="C:\Improve Your Business\Qing\Rapidminer\Adjective lists\English\Hotels\most_mentioned_neg"/>
</list>
<parameter key="use_file_extension_as_type" value="false"/>
<parameter key="vector_creation" value="Term Occurrences"/>
<parameter key="add_meta_information" value="false"/>
<parameter key="keep_text" value="true"/>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize (4)" width="90" x="112" y="30">
<parameter key="mode" value="specify characters"/>
<parameter key="characters" value="."/>
</operator>
<operator activated="false" class="text:generate_n_grams_terms" compatibility="5.3.002" expanded="true" height="60" name="Generate n-Grams (2)" width="90" x="313" y="120"/>
<connect from_port="document" to_op="Tokenize (4)" to_port="document"/>
<connect from_op="Tokenize (4)" 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="read_excel" compatibility="6.0.003" expanded="true" height="60" name="Read Excel" width="90" x="45" y="30">
<parameter key="excel_file" value="C:\Improve Your Business\Qing\Rapidminer\English Demo\Hotel Qing Liverpool\Hotel\Hotel Qing Liverpool.xlsx"/>
<parameter key="sheet_number" value="8"/>
<parameter key="imported_cell_range" value="A1:A11"/>
<parameter key="first_row_as_names" value="false"/>
<list key="annotations">
<parameter key="0" value="Name"/>
</list>
<list key="data_set_meta_data_information">
<parameter key="0" value="tekst.true.text.attribute"/>
</list>
</operator>
<operator activated="true" class="text:process_document_from_data" compatibility="5.3.002" expanded="true" height="76" name="Process Documents from Data (2)" width="90" x="246" y="165">
<parameter key="vector_creation" value="Term Occurrences"/>
<parameter key="keep_text" value="true"/>
<list key="specify_weights"/>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize (2)" width="90" x="45" y="30">
<parameter key="characters" value="."/>
</operator>
<operator activated="true" class="text:transform_cases" compatibility="5.3.002" expanded="true" height="60" name="Transform Cases (2)" width="90" x="179" y="30"/>
<operator activated="true" class="text:generate_n_grams_terms" compatibility="5.3.002" expanded="true" height="60" name="Generate n-Grams (Terms)" width="90" x="380" y="30"/>
<connect from_port="document" to_op="Tokenize (2)" to_port="document"/>
<connect from_op="Tokenize (2)" from_port="document" to_op="Transform Cases (2)" to_port="document"/>
<connect from_op="Transform Cases (2)" 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="false" class="select_attributes" compatibility="6.0.003" expanded="true" height="76" name="Select Attributes (2)" width="90" x="313" y="345">
<parameter key="attribute_filter_type" value="no_missing_values"/>
<parameter key="attributes" value="Sentiment|id|Negative|Positive|text"/>
</operator>
<operator activated="false" class="filter_examples" compatibility="6.0.003" expanded="true" height="94" name="Filter Examples" width="90" x="514" y="345">
<parameter key="condition_class" value="no_missing_attributes"/>
<list key="filters_list"/>
</operator>
<operator activated="false" class="generate_aggregation" compatibility="6.0.003" expanded="true" height="76" name="Generate Aggregation" width="90" x="648" y="345">
<parameter key="attribute_name" value="Positive"/>
<parameter key="aggregation_function" value="product"/>
</operator>
<connect from_op="Process Documents from Files" from_port="word list" to_op="Process Documents from Data (2)" to_port="word list"/>
<connect from_op="Read Excel" from_port="output" to_op="Process Documents from Data (2)" to_port="example set"/>
<connect from_op="Process Documents from Data (2)" from_port="example set" to_port="result 1"/>
<connect from_op="Process Documents from Data (2)" from_port="word list" 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>
When I ran the model and I check the output of the model I can see that the n-gram "not-clean" occurs 4 times. But when I check the wordlist of the output it gives only 1 occurrence.
This is because the model is not counting the # of occurances of the excel sheet but the # of occurances of the textfile
How can I change the model that is gives me the # occurances of he words and n-grams of the data in the excelfile?
Model:
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="6.0.003">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="6.0.002" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="text:process_document_from_file" compatibility="5.3.002" expanded="true" height="76" name="Process Documents from Files" width="90" x="45" y="165">
<list key="text_directories">
<parameter key="Most mentioned negative" value="C:\Improve Your Business\Qing\Rapidminer\Adjective lists\English\Hotels\most_mentioned_neg"/>
</list>
<parameter key="use_file_extension_as_type" value="false"/>
<parameter key="vector_creation" value="Term Occurrences"/>
<parameter key="add_meta_information" value="false"/>
<parameter key="keep_text" value="true"/>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize (4)" width="90" x="112" y="30">
<parameter key="mode" value="specify characters"/>
<parameter key="characters" value="."/>
</operator>
<operator activated="false" class="text:generate_n_grams_terms" compatibility="5.3.002" expanded="true" height="60" name="Generate n-Grams (2)" width="90" x="313" y="120"/>
<connect from_port="document" to_op="Tokenize (4)" to_port="document"/>
<connect from_op="Tokenize (4)" 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="read_excel" compatibility="6.0.003" expanded="true" height="60" name="Read Excel" width="90" x="45" y="30">
<parameter key="excel_file" value="C:\Improve Your Business\Qing\Rapidminer\English Demo\Hotel Qing Liverpool\Hotel\Hotel Qing Liverpool.xlsx"/>
<parameter key="sheet_number" value="8"/>
<parameter key="imported_cell_range" value="A1:A11"/>
<parameter key="first_row_as_names" value="false"/>
<list key="annotations">
<parameter key="0" value="Name"/>
</list>
<list key="data_set_meta_data_information">
<parameter key="0" value="tekst.true.text.attribute"/>
</list>
</operator>
<operator activated="true" class="text:process_document_from_data" compatibility="5.3.002" expanded="true" height="76" name="Process Documents from Data (2)" width="90" x="246" y="165">
<parameter key="vector_creation" value="Term Occurrences"/>
<parameter key="keep_text" value="true"/>
<list key="specify_weights"/>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize (2)" width="90" x="45" y="30">
<parameter key="characters" value="."/>
</operator>
<operator activated="true" class="text:transform_cases" compatibility="5.3.002" expanded="true" height="60" name="Transform Cases (2)" width="90" x="179" y="30"/>
<operator activated="true" class="text:generate_n_grams_terms" compatibility="5.3.002" expanded="true" height="60" name="Generate n-Grams (Terms)" width="90" x="380" y="30"/>
<connect from_port="document" to_op="Tokenize (2)" to_port="document"/>
<connect from_op="Tokenize (2)" from_port="document" to_op="Transform Cases (2)" to_port="document"/>
<connect from_op="Transform Cases (2)" 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="false" class="select_attributes" compatibility="6.0.003" expanded="true" height="76" name="Select Attributes (2)" width="90" x="313" y="345">
<parameter key="attribute_filter_type" value="no_missing_values"/>
<parameter key="attributes" value="Sentiment|id|Negative|Positive|text"/>
</operator>
<operator activated="false" class="filter_examples" compatibility="6.0.003" expanded="true" height="94" name="Filter Examples" width="90" x="514" y="345">
<parameter key="condition_class" value="no_missing_attributes"/>
<list key="filters_list"/>
</operator>
<operator activated="false" class="generate_aggregation" compatibility="6.0.003" expanded="true" height="76" name="Generate Aggregation" width="90" x="648" y="345">
<parameter key="attribute_name" value="Positive"/>
<parameter key="aggregation_function" value="product"/>
</operator>
<connect from_op="Process Documents from Files" from_port="word list" to_op="Process Documents from Data (2)" to_port="word list"/>
<connect from_op="Read Excel" from_port="output" to_op="Process Documents from Data (2)" to_port="example set"/>
<connect from_op="Process Documents from Data (2)" from_port="example set" to_port="result 1"/>
<connect from_op="Process Documents from Data (2)" from_port="word list" 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>
0
