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
"Two Documents Similarity using Cross distance"
Contributor I- texti am using rapidminer to compare the similarity between two text fields in two sheets in same excel file using cross distance, as i want to compart one request will all referernce to return the similarity value by cosine similarity, the problem is the distance returns as question mark '?' without knowing the reason
<?xml version="1.0" encoding="UTF-8"?><process version="8.2.001">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="8.2.001" 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="8.2.001" expanded="true" height="68" name="Read Excel" width="90" x="45" y="391">
<parameter key="excel_file" value="/Users/macbook/Desktop/ULS/Change Management in ULS/WASP_Requirements.xlsx"/>
<parameter key="sheet_selection" value="sheet number"/>
<parameter key="sheet_number" value="1"/>
<parameter key="imported_cell_range" value="A1:B72"/>
<parameter key="encoding" value="SYSTEM"/>
<parameter key="first_row_as_names" value="false"/>
<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="A.true.polynominal.id"/>
<parameter key="1" value="B.true.polynominal.attribute"/>
</list>
<parameter key="read_not_matching_values_as_missings" value="true"/>
<parameter key="datamanagement" value="double_array"/>
<parameter key="data_management" value="auto"/>
</operator>
<operator activated="true" class="remove_duplicates" compatibility="8.2.001" expanded="true" height="103" name="Remove Duplicates" width="90" x="45" y="493">
<parameter key="attribute_filter_type" value="all"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="attribute_value"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="time"/>
<parameter key="block_type" value="attribute_block"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_matrix_row_start"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="false"/>
<parameter key="treat_missing_values_as_duplicates" value="false"/>
</operator>
<operator activated="true" class="set_role" compatibility="8.2.001" expanded="true" height="82" name="Set Role" width="90" x="179" y="391">
<parameter key="attribute_name" value="A"/>
<parameter key="target_role" value="id"/>
<list key="set_additional_roles">
<parameter key="B" value="regular"/>
<parameter key="A" value="id"/>
</list>
</operator>
<operator activated="true" class="nominal_to_text" compatibility="8.2.001" expanded="true" height="82" name="Nominal to Text" width="90" x="179" y="493">
<parameter key="attribute_filter_type" value="all"/>
<parameter key="attribute" value=""/>
<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" class="text:process_document_from_data" compatibility="8.1.000" expanded="true" height="82" name="Process Documents from Data" width="90" x="313" y="391">
<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="true"/>
<parameter key="prune_method" value="absolute"/>
<parameter key="prune_below_percent" value="3.0"/>
<parameter key="prune_above_percent" value="30.0"/>
<parameter key="prune_below_absolute" value="2"/>
<parameter key="prune_above_absolute" value="9999"/>
<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="false"/>
<list key="specify_weights">
<parameter key="B" value="1.0"/>
</list>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="8.1.000" expanded="true" height="68" name="Tokenize" width="90" x="112" y="34">
<parameter key="mode" value="linguistic tokens"/>
<parameter key="characters" value=".:"/>
<parameter key="language" value="English"/>
<parameter key="max_token_length" value="3"/>
</operator>
<operator activated="true" class="text:filter_stopwords_english" compatibility="8.1.000" expanded="true" height="68" name="Filter Stopwords (English)" width="90" x="112" y="136"/>
<operator activated="true" class="text:transform_cases" compatibility="8.1.000" expanded="true" height="68" name="Transform Cases" width="90" x="112" y="238">
<parameter key="transform_to" value="lower case"/>
</operator>
<operator activated="true" class="wordnet:open_wordnet_dictionary" compatibility="5.3.000" expanded="true" height="68" name="Open WordNet Dictionary" width="90" x="313" y="391">
<parameter key="resource_type" value="directory"/>
<parameter key="directory" value="/Users/macbook/Downloads/WordNet-3.0/dict"/>
</operator>
<operator activated="true" class="wordnet:stem_wordnet" compatibility="5.3.000" expanded="true" height="82" name="Stem (WordNet)" width="90" x="313" y="238">
<parameter key="allow_ambiguity" value="true"/>
<parameter key="keep_unmatched_stems" value="true"/>
<parameter key="keep_unmatched_tokens" value="true"/>
<parameter key="work_on_type_noun" value="true"/>
<parameter key="work_on_type_verb" value="true"/>
<parameter key="work_on_type_adjective" value="true"/>
<parameter key="work_on_type_adverb" value="true"/>
</operator>
<operator activated="true" class="wordnet:find_synonym_wordnet" compatibility="5.3.000" expanded="true" height="82" name="Find Synonyms (WordNet)" width="90" x="447" y="238">
<parameter key="use_prefix" value="false"/>
<parameter key="synset_word_prefix" value="syn:"/>
<parameter key="maximum_recursion_depth" value="1"/>
<parameter key="multiple_meanings_per_word_policy" value="Take only first meaning"/>
<parameter key="multiple_synsets_policy" value="Take only first synset per meaning"/>
<parameter key="multiple_synset_words_policy" value="Take only first synset word"/>
<parameter key="concatenation" value="Concatenate result per synset"/>
<parameter key="keep_original_tokens" value="true"/>
<parameter key="keep_unmatched_tokens" value="true"/>
<parameter key="take_ID_instead_of_words" value="false"/>
<parameter key="work_on_type_noun" value="true"/>
<parameter key="work_on_type_verb" value="true"/>
<parameter key="work_on_type_adjective" value="true"/>
<parameter key="work_on_type_adverb" value="true"/>
</operator>
<connect from_port="document" to_op="Tokenize" to_port="document"/>
<connect from_op="Tokenize" from_port="document" to_op="Filter Stopwords (English)" to_port="document"/>
<connect from_op="Filter Stopwords (English)" from_port="document" to_op="Transform Cases" to_port="document"/>
<connect from_op="Transform Cases" from_port="document" to_op="Stem (WordNet)" to_port="document"/>
<connect from_op="Open WordNet Dictionary" from_port="dictionary" to_op="Stem (WordNet)" to_port="dictionary"/>
<connect from_op="Stem (WordNet)" from_port="document" to_op="Find Synonyms (WordNet)" to_port="document"/>
<connect from_op="Stem (WordNet)" from_port="dictionary" to_op="Find Synonyms (WordNet)" to_port="dictionary"/>
<connect from_op="Find Synonyms (WordNet)" 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="concurrency:k_means" compatibility="8.2.001" expanded="true" height="82" name="Clustering" width="90" x="782" y="34">
<parameter key="add_cluster_attribute" value="true"/>
<parameter key="add_as_label" value="false"/>
<parameter key="remove_unlabeled" value="false"/>
<parameter key="k" value="40"/>
<parameter key="max_runs" value="10"/>
<parameter key="determine_good_start_values" value="true"/>
<parameter key="measure_types" value="BregmanDivergences"/>
<parameter key="mixed_measure" value="MixedEuclideanDistance"/>
<parameter key="nominal_measure" value="NominalDistance"/>
<parameter key="numerical_measure" value="EuclideanDistance"/>
<parameter key="divergence" value="SquaredEuclideanDistance"/>
<parameter key="kernel_type" value="radial"/>
<parameter key="kernel_gamma" value="1.0"/>
<parameter key="kernel_sigma1" value="1.0"/>
<parameter key="kernel_sigma2" value="0.0"/>
<parameter key="kernel_sigma3" value="2.0"/>
<parameter key="kernel_degree" value="3.0"/>
<parameter key="kernel_shift" value="1.0"/>
<parameter key="kernel_a" value="1.0"/>
<parameter key="kernel_b" value="0.0"/>
<parameter key="max_optimization_steps" value="100"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
</operator>
<operator activated="true" class="read_excel" compatibility="8.2.001" expanded="true" height="68" name="Read Excel (2)" width="90" x="45" y="85">
<parameter key="excel_file" value="/Users/macbook/Desktop/ULS/Change Management in ULS/WASP_Requirements.xlsx"/>
<parameter key="sheet_selection" value="sheet number"/>
<parameter key="sheet_number" value="2"/>
<parameter key="imported_cell_range" value="A1:B1"/>
<parameter key="encoding" value="SYSTEM"/>
<parameter key="first_row_as_names" value="false"/>
<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="A.true.polynominal.id"/>
<parameter key="1" value="B.true.polynominal.attribute"/>
</list>
<parameter key="read_not_matching_values_as_missings" value="true"/>
<parameter key="datamanagement" value="double_array"/>
<parameter key="data_management" value="auto"/>
</operator>
<operator activated="true" class="remove_duplicates" compatibility="8.2.001" expanded="true" height="103" name="Remove Duplicates (2)" width="90" x="45" y="187">
<parameter key="attribute_filter_type" value="all"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="attribute_value"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="time"/>
<parameter key="block_type" value="attribute_block"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_matrix_row_start"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="false"/>
<parameter key="treat_missing_values_as_duplicates" value="false"/>
</operator>
<operator activated="true" class="set_role" compatibility="8.2.001" expanded="true" height="82" name="Set Role (2)" width="90" x="179" y="85">
<parameter key="attribute_name" value="A"/>
<parameter key="target_role" value="id"/>
<list key="set_additional_roles">
<parameter key="B" value="regular"/>
<parameter key="A" value="id"/>
</list>
</operator>
<operator activated="true" class="nominal_to_text" compatibility="8.2.001" expanded="true" height="82" name="Nominal to Text (2)" width="90" x="179" y="187">
<parameter key="attribute_filter_type" value="all"/>
<parameter key="attribute" value=""/>
<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" class="text:process_document_from_data" compatibility="8.1.000" expanded="true" height="82" name="Process Documents from Data (2)" width="90" x="313" y="85">
<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="true"/>
<parameter key="prune_method" value="absolute"/>
<parameter key="prune_below_percent" value="3.0"/>
<parameter key="prune_above_percent" value="30.0"/>
<parameter key="prune_below_absolute" value="2"/>
<parameter key="prune_above_absolute" value="9999"/>
<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="false"/>
<list key="specify_weights">
<parameter key="B" value="1.0"/>
</list>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="8.1.000" expanded="true" height="68" name="Tokenize (2)" width="90" x="112" y="34">
<parameter key="mode" value="linguistic tokens"/>
<parameter key="characters" value=".:"/>
<parameter key="language" value="English"/>
<parameter key="max_token_length" value="3"/>
</operator>
<operator activated="true" class="text:filter_stopwords_english" compatibility="8.1.000" expanded="true" height="68" name="Filter Stopwords (2)" width="90" x="112" y="136"/>
<operator activated="true" class="text:transform_cases" compatibility="8.1.000" expanded="true" height="68" name="Transform Cases (2)" width="90" x="112" y="238">
<parameter key="transform_to" value="lower case"/>
</operator>
<operator activated="true" class="wordnet:open_wordnet_dictionary" compatibility="5.3.000" expanded="true" height="68" name="Open WordNet Dictionary (2)" width="90" x="313" y="391">
<parameter key="resource_type" value="directory"/>
<parameter key="directory" value="/Users/macbook/Downloads/WordNet-3.0/dict"/>
</operator>
<operator activated="true" class="wordnet:stem_wordnet" compatibility="5.3.000" expanded="true" height="82" name="Stem (2)" width="90" x="313" y="238">
<parameter key="allow_ambiguity" value="true"/>
<parameter key="keep_unmatched_stems" value="true"/>
<parameter key="keep_unmatched_tokens" value="true"/>
<parameter key="work_on_type_noun" value="true"/>
<parameter key="work_on_type_verb" value="true"/>
<parameter key="work_on_type_adjective" value="true"/>
<parameter key="work_on_type_adverb" value="true"/>
</operator>
<operator activated="true" class="wordnet:find_synonym_wordnet" compatibility="5.3.000" expanded="true" height="82" name="Find Synonyms (2)" width="90" x="447" y="238">
<parameter key="use_prefix" value="false"/>
<parameter key="synset_word_prefix" value="syn:"/>
<parameter key="maximum_recursion_depth" value="1"/>
<parameter key="multiple_meanings_per_word_policy" value="Take only first meaning"/>
<parameter key="multiple_synsets_policy" value="Take only first synset per meaning"/>
<parameter key="multiple_synset_words_policy" value="Take only first synset word"/>
<parameter key="concatenation" value="Concatenate result per synset"/>
<parameter key="keep_original_tokens" value="true"/>
<parameter key="keep_unmatched_tokens" value="true"/>
<parameter key="take_ID_instead_of_words" value="false"/>
<parameter key="work_on_type_noun" value="true"/>
<parameter key="work_on_type_verb" value="true"/>
<parameter key="work_on_type_adjective" value="true"/>
<parameter key="work_on_type_adverb" value="true"/>
</operator>
<connect from_port="document" to_op="Tokenize (2)" to_port="document"/>
<connect from_op="Tokenize (2)" from_port="document" to_op="Filter Stopwords (2)" to_port="document"/>
<connect from_op="Filter Stopwords (2)" from_port="document" to_op="Transform Cases (2)" to_port="document"/>
<connect from_op="Transform Cases (2)" from_port="document" to_op="Stem (2)" to_port="document"/>
<connect from_op="Open WordNet Dictionary (2)" from_port="dictionary" to_op="Stem (2)" to_port="dictionary"/>
<connect from_op="Stem (2)" from_port="document" to_op="Find Synonyms (2)" to_port="document"/>
<connect from_op="Stem (2)" from_port="dictionary" to_op="Find Synonyms (2)" to_port="dictionary"/>
<connect from_op="Find Synonyms (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="multiply" compatibility="8.2.001" expanded="true" height="103" name="Multiply" width="90" x="447" y="85"/>
<operator activated="true" class="order_attributes" compatibility="8.2.001" expanded="true" height="82" name="Reorder Attributes" width="90" x="447" y="238">
<parameter key="sort_mode" value="reference data"/>
<parameter key="attribute_ordering" value=""/>
<parameter key="use_regular_expressions" value="false"/>
<parameter key="handle_unmatched" value="append"/>
<parameter key="sort_direction" value="ascending"/>
</operator>
<operator activated="true" class="multiply" compatibility="8.2.001" expanded="true" height="103" name="Multiply (2)" width="90" x="581" y="340"/>
<operator activated="true" class="order_attributes" compatibility="8.2.001" expanded="true" height="82" name="Reorder Attributes (2)" width="90" x="581" y="238">
<parameter key="sort_mode" value="reference data"/>
<parameter key="attribute_ordering" value=""/>
<parameter key="use_regular_expressions" value="false"/>
<parameter key="handle_unmatched" value="append"/>
<parameter key="sort_direction" value="ascending"/>
</operator>
<operator activated="true" class="cross_distances" compatibility="8.2.001" expanded="true" height="103" name="Cross Distances" width="90" x="715" y="238">
<parameter key="measure_types" value="NumericalMeasures"/>
<parameter key="mixed_measure" value="MixedEuclideanDistance"/>
<parameter key="nominal_measure" value="SimpleMatchingSimilarity"/>
<parameter key="numerical_measure" value="CosineSimilarity"/>
<parameter key="divergence" value="GeneralizedIDivergence"/>
<parameter key="kernel_type" value="radial"/>
<parameter key="kernel_gamma" value="1.0"/>
<parameter key="kernel_sigma1" value="1.0"/>
<parameter key="kernel_sigma2" value="0.0"/>
<parameter key="kernel_sigma3" value="2.0"/>
<parameter key="kernel_degree" value="3.0"/>
<parameter key="kernel_shift" value="1.0"/>
<parameter key="kernel_a" value="1.0"/>
<parameter key="kernel_b" value="0.0"/>
<parameter key="only_top_k" value="false"/>
<parameter key="k" value="10"/>
<parameter key="search_for" value="nearest"/>
<parameter key="compute_similarities" value="true"/>
</operator>
<operator activated="false" class="data_to_similarity" compatibility="8.2.001" expanded="true" height="82" name="Data to Similarity" width="90" x="648" y="34">
<parameter key="measure_types" value="NumericalMeasures"/>
<parameter key="mixed_measure" value="MixedEuclideanDistance"/>
<parameter key="nominal_measure" value="NominalDistance"/>
<parameter key="numerical_measure" value="CosineSimilarity"/>
<parameter key="divergence" value="GeneralizedIDivergence"/>
<parameter key="kernel_type" value="radial"/>
<parameter key="kernel_gamma" value="1.0"/>
<parameter key="kernel_sigma1" value="1.0"/>
<parameter key="kernel_sigma2" value="0.0"/>
<parameter key="kernel_sigma3" value="2.0"/>
<parameter key="kernel_degree" value="3.0"/>
<parameter key="kernel_shift" value="1.0"/>
<parameter key="kernel_a" value="1.0"/>
<parameter key="kernel_b" value="0.0"/>
</operator>
<connect from_op="Read Excel" from_port="output" to_op="Remove Duplicates" to_port="example set input"/>
<connect from_op="Remove Duplicates" 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_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="Reorder Attributes" to_port="example set input"/>
<connect from_op="Read Excel (2)" from_port="output" to_op="Remove Duplicates (2)" to_port="example set input"/>
<connect from_op="Remove Duplicates (2)" 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="Nominal to Text (2)" to_port="example set input"/>
<connect from_op="Nominal to Text (2)" from_port="example set 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_op="Multiply" to_port="input"/>
<connect from_op="Multiply" from_port="output 1" to_op="Reorder Attributes (2)" to_port="example set input"/>
<connect from_op="Multiply" from_port="output 2" to_op="Reorder Attributes" to_port="reference_data"/>
<connect from_op="Reorder Attributes" from_port="example set output" to_op="Multiply (2)" to_port="input"/>
<connect from_op="Multiply (2)" from_port="output 1" to_op="Reorder Attributes (2)" to_port="reference_data"/>
<connect from_op="Multiply (2)" from_port="output 2" to_op="Cross Distances" to_port="reference set"/>
<connect from_op="Reorder Attributes (2)" from_port="example set output" to_op="Cross Distances" to_port="request set"/>
<connect from_op="Cross Distances" from_port="result 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"/>
<description align="center" color="gray" colored="true" height="163" resized="true" width="142" x="28" y="320">Read Requirements Document</description>
<description align="center" color="gray" colored="true" height="147" resized="true" width="126" x="30" y="14">Read Requirements Change Requests</description>
</process>
</operator>
</process>
Tagged:
0
Best Answers
-
lionelderkrikor
RapidMiner Certified Analyst, Member Posts: 1,195 
Unicorn
Hi @asafwat,
I think I found elements of answers (now calculated distances/similarities have numerical values) :
In the documentation of the Cross-Distances operator it is said that :
"Please note that both input ExampleSets should have the same attributes and in the same order".
So you have to use a Superset (cf documentation of this operator) operator to feed the req and ref ports of the Cross-Distances operator with 2 datasets which have strictly the same attributes.
Moreover, I made some modifications in your process :
- in the Process Documents from Data operators : vector creation -> Term Occurences.
- in the Tokenize operators : mode -> non letters.
The process :
<?xml version="1.0" encoding="UTF-8"?><process version="9.0.000-BETA">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="9.0.000-BETA" expanded="true" name="Process">
<process expanded="true">
<operator activated="true" class="read_excel" compatibility="9.0.000-BETA" expanded="true" height="68" name="Read Excel" width="90" x="45" y="391">
<parameter key="excel_file" value="C:\Users\Lionel\Documents\Formations_DataScience\Rapidminer\Tests_Rapidminer\Cross_Distances\Cross_Distances.xlsx"/>
<list key="annotations"/>
<parameter key="date_format" value="MMM d, yyyy h:mm:ss a z"/>
<list key="data_set_meta_data_information">
<parameter key="0" value="Id.true.integer.attribute"/>
<parameter key="1" value="Text.true.polynominal.attribute"/>
</list>
<parameter key="read_not_matching_values_as_missings" value="false"/>
</operator>
<operator activated="true" class="remove_duplicates" compatibility="9.0.000-BETA" expanded="true" height="103" name="Remove Duplicates" width="90" x="45" y="493"/>
<operator activated="true" class="set_role" compatibility="9.0.000-BETA" expanded="true" height="82" name="Set Role" width="90" x="179" y="391">
<parameter key="attribute_name" value="Id"/>
<parameter key="target_role" value="id"/>
<list key="set_additional_roles"/>
</operator>
<operator activated="true" class="nominal_to_text" compatibility="9.0.000-BETA" expanded="true" height="82" name="Nominal to Text" width="90" x="179" y="493"/>
<operator activated="true" class="text:process_document_from_data" compatibility="8.1.000" expanded="true" height="82" name="Process Documents from Data" width="90" x="313" y="391">
<parameter key="vector_creation" value="Term Occurrences"/>
<parameter key="keep_text" value="true"/>
<parameter key="prune_below_absolute" value="2"/>
<parameter key="prune_above_absolute" value="9999"/>
<list key="specify_weights">
<parameter key="B" value="1.0"/>
</list>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="8.1.000" expanded="true" height="68" name="Tokenize" width="90" x="112" y="34"/>
<operator activated="true" class="text:filter_stopwords_english" compatibility="8.1.000" expanded="true" height="68" name="Filter Stopwords (English)" width="90" x="112" y="136"/>
<operator activated="true" class="text:transform_cases" compatibility="8.1.000" expanded="true" height="68" name="Transform Cases" width="90" x="112" y="238"/>
<operator activated="false" class="wordnet:open_wordnet_dictionary" compatibility="5.3.000" expanded="true" height="68" name="Open WordNet Dictionary" width="90" x="313" y="493">
<parameter key="directory" value="/Users/macbook/Downloads/WordNet-3.0/dict"/>
</operator>
<operator activated="false" class="wordnet:stem_wordnet" compatibility="5.3.000" expanded="true" height="82" name="Stem (WordNet)" width="90" x="313" y="340">
<parameter key="allow_ambiguity" value="true"/>
<parameter key="keep_unmatched_stems" value="true"/>
<parameter key="keep_unmatched_tokens" value="true"/>
</operator>
<operator activated="false" class="wordnet:find_synonym_wordnet" compatibility="5.3.000" expanded="true" height="82" name="Find Synonyms (WordNet)" width="90" x="447" y="340">
<parameter key="use_prefix" value="false"/>
<parameter key="multiple_meanings_per_word_policy" value="Take only first meaning"/>
<parameter key="keep_original_tokens" value="true"/>
<parameter key="keep_unmatched_tokens" value="true"/>
</operator>
<connect from_port="document" to_op="Tokenize" to_port="document"/>
<connect from_op="Tokenize" from_port="document" to_op="Filter Stopwords (English)" to_port="document"/>
<connect from_op="Filter Stopwords (English)" from_port="document" to_op="Transform Cases" to_port="document"/>
<connect from_op="Transform Cases" from_port="document" to_port="document 1"/>
<connect from_op="Open WordNet Dictionary" from_port="dictionary" to_op="Stem (WordNet)" to_port="dictionary"/>
<connect from_op="Stem (WordNet)" from_port="document" to_op="Find Synonyms (WordNet)" to_port="document"/>
<connect from_op="Stem (WordNet)" from_port="dictionary" to_op="Find Synonyms (WordNet)" to_port="dictionary"/>
<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="concurrency:k_means" compatibility="9.0.000-BETA" expanded="true" height="82" name="Clustering" width="90" x="782" y="34">
<parameter key="k" value="40"/>
<parameter key="determine_good_start_values" value="true"/>
</operator>
<operator activated="true" class="read_excel" compatibility="9.0.000-BETA" expanded="true" height="68" name="Read Excel (2)" width="90" x="45" y="85">
<parameter key="excel_file" value="C:\Users\Lionel\Documents\Formations_DataScience\Rapidminer\Tests_Rapidminer\Cross_Distances\Cross_Distances.xlsx"/>
<parameter key="sheet_number" value="2"/>
<list key="annotations"/>
<parameter key="date_format" value="MMM d, yyyy h:mm:ss a z"/>
<list key="data_set_meta_data_information">
<parameter key="0" value="Id.true.integer.attribute"/>
<parameter key="1" value="text.true.polynominal.attribute"/>
</list>
<parameter key="read_not_matching_values_as_missings" value="false"/>
</operator>
<operator activated="true" class="remove_duplicates" compatibility="9.0.000-BETA" expanded="true" height="103" name="Remove Duplicates (2)" width="90" x="45" y="187"/>
<operator activated="true" class="set_role" compatibility="9.0.000-BETA" expanded="true" height="82" name="Set Role (2)" width="90" x="179" y="85">
<parameter key="attribute_name" value="Id"/>
<parameter key="target_role" value="id"/>
<list key="set_additional_roles"/>
</operator>
<operator activated="true" class="nominal_to_text" compatibility="9.0.000-BETA" expanded="true" height="82" name="Nominal to Text (2)" width="90" x="179" y="187">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="text"/>
</operator>
<operator activated="true" class="text:process_document_from_data" compatibility="8.1.000" expanded="true" height="82" name="Process Documents from Data (2)" width="90" x="313" y="85">
<parameter key="vector_creation" value="Term Occurrences"/>
<parameter key="keep_text" value="true"/>
<parameter key="prune_below_absolute" value="2"/>
<parameter key="prune_above_absolute" value="9999"/>
<list key="specify_weights">
<parameter key="B" value="1.0"/>
</list>
<process expanded="true">
<operator activated="true" class="text:tokenize" compatibility="8.1.000" expanded="true" height="68" name="Tokenize (2)" width="90" x="112" y="34"/>
<operator activated="true" class="text:filter_stopwords_english" compatibility="8.1.000" expanded="true" height="68" name="Filter Stopwords (2)" width="90" x="112" y="136"/>
<operator activated="true" class="text:transform_cases" compatibility="8.1.000" expanded="true" height="68" name="Transform Cases (2)" width="90" x="112" y="238"/>
<operator activated="false" class="wordnet:open_wordnet_dictionary" compatibility="5.3.000" expanded="true" height="68" name="Open WordNet Dictionary (2)" width="90" x="313" y="544">
<parameter key="directory" value="/Users/macbook/Downloads/WordNet-3.0/dict"/>
</operator>
<operator activated="false" class="wordnet:stem_wordnet" compatibility="5.3.000" expanded="true" height="82" name="Stem (2)" width="90" x="313" y="391">
<parameter key="allow_ambiguity" value="true"/>
<parameter key="keep_unmatched_stems" value="true"/>
<parameter key="keep_unmatched_tokens" value="true"/>
</operator>
<operator activated="false" class="wordnet:find_synonym_wordnet" compatibility="5.3.000" expanded="true" height="82" name="Find Synonyms (2)" width="90" x="447" y="391">
<parameter key="use_prefix" value="false"/>
<parameter key="multiple_meanings_per_word_policy" value="Take only first meaning"/>
<parameter key="keep_original_tokens" value="true"/>
<parameter key="keep_unmatched_tokens" value="true"/>
</operator>
<connect from_port="document" to_op="Tokenize (2)" to_port="document"/>
<connect from_op="Tokenize (2)" from_port="document" to_op="Filter Stopwords (2)" to_port="document"/>
<connect from_op="Filter Stopwords (2)" from_port="document" to_op="Transform Cases (2)" to_port="document"/>
<connect from_op="Transform Cases (2)" from_port="document" to_port="document 1"/>
<connect from_op="Open WordNet Dictionary (2)" from_port="dictionary" to_op="Stem (2)" to_port="dictionary"/>
<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="multiply" compatibility="9.0.000-BETA" expanded="true" height="103" name="Multiply" width="90" x="447" y="85"/>
<operator activated="true" class="order_attributes" compatibility="9.0.000-BETA" expanded="true" height="82" name="Reorder Attributes" width="90" x="447" y="238">
<parameter key="sort_mode" value="reference data"/>
</operator>
<operator activated="true" class="multiply" compatibility="9.0.000-BETA" expanded="true" height="103" name="Multiply (2)" width="90" x="581" y="340"/>
<operator activated="true" class="order_attributes" compatibility="9.0.000-BETA" expanded="true" height="82" name="Reorder Attributes (2)" width="90" x="581" y="187">
<parameter key="sort_mode" value="reference data"/>
</operator>
<operator activated="false" class="data_to_similarity" compatibility="9.0.000-BETA" expanded="true" height="82" name="Data to Similarity" width="90" x="648" y="34">
<parameter key="measure_types" value="NumericalMeasures"/>
<parameter key="numerical_measure" value="CosineSimilarity"/>
</operator>
<operator activated="true" class="superset" compatibility="9.0.000-BETA" expanded="true" height="82" name="Superset" width="90" x="782" y="238"/>
<operator activated="true" class="cross_distances" compatibility="9.0.000-BETA" expanded="true" height="103" name="Cross Distances" width="90" x="916" y="238">
<parameter key="measure_types" value="NumericalMeasures"/>
<parameter key="nominal_measure" value="SimpleMatchingSimilarity"/>
<parameter key="numerical_measure" value="CosineSimilarity"/>
</operator>
<connect from_op="Read Excel" from_port="output" to_op="Remove Duplicates" to_port="example set input"/>
<connect from_op="Remove Duplicates" 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_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="Reorder Attributes" to_port="example set input"/>
<connect from_op="Read Excel (2)" from_port="output" to_op="Remove Duplicates (2)" to_port="example set input"/>
<connect from_op="Remove Duplicates (2)" 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="Nominal to Text (2)" to_port="example set input"/>
<connect from_op="Nominal to Text (2)" from_port="example set 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_op="Multiply" to_port="input"/>
<connect from_op="Multiply" from_port="output 1" to_op="Reorder Attributes (2)" to_port="example set input"/>
<connect from_op="Multiply" from_port="output 2" to_op="Reorder Attributes" to_port="reference_data"/>
<connect from_op="Reorder Attributes" from_port="example set output" to_op="Multiply (2)" to_port="input"/>
<connect from_op="Multiply (2)" from_port="output 1" to_op="Reorder Attributes (2)" to_port="reference_data"/>
<connect from_op="Multiply (2)" from_port="output 2" to_op="Superset" to_port="example set 2"/>
<connect from_op="Reorder Attributes (2)" from_port="example set output" to_op="Superset" to_port="example set 1"/>
<connect from_op="Superset" from_port="superset 1" to_op="Cross Distances" to_port="request set"/>
<connect from_op="Superset" from_port="superset 2" to_op="Cross Distances" to_port="reference set"/>
<connect from_op="Cross Distances" from_port="result 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"/>
<description align="center" color="gray" colored="true" height="163" resized="true" width="142" x="28" y="320">Read Requirements Document</description>
<description align="center" color="gray" colored="true" height="147" resized="true" width="126" x="30" y="14">Read Requirements Change Requests</description>
</process>
</operator>
</process>I hope it helps,
Regards,
Lionel
0 -
lionelderkrikor
RapidMiner Certified Analyst, Member Posts: 1,195 Unicorn
Hi (one more time ...) @asafwat,
Just a (last ?) little advice, you don't need to specify that an attribute is "regular" in the Set Role operator :
By default, RapidMiner set automatically an attribute as "regular"...
Regards,
Lionel
1
Answers
Hi @asafwat,
Are your attributes "numerical" ?
Can you share your dataset(s) in order we can reproduce what you observe ?
Regards,
Lionel
Sure, here is it, i have changed it to csv in order to attach it
Hi again @asafwat,
I have difficulties with your CSV file, can you send me your original Excel file by :
- zipping it, then, attaching it to this post
- sending your Excel file on Google Drive and then copy and share the link here in the forum
Regards,
Lionel
Hi again (and again) @asafwat,
Can you send me your Wordnet dictionnary too (by zipping it for example).
Regards,
Lionel
@lionelderkrikor wooow it works, great efforts, really you made my day. much apperciated
Thanks a lot