RapidMiner 5.3.013 ArrayIdexOutOfBoundsException

Franzi_456
Franzi_456 New Altair Community Member
edited November 2024 in Community Q&A
Hi all,
i have a big problem and need some help. I have a process and get an ArrayindexOutOfBoundsException after the subprocess 'Training'. I can not switch to a newer version.
I already specified the environment variable RAPIDMINER_HOME (Windows 10), but this did not solve my problem.
How can i fix it.

This is my process
<?xml version="1.0" encoding="UTF-8" standalone="no"?><br><process version="5.3.013"><br>  <context><br>    <input/><br>    <output/><br>    <macros/><br>  </context><br>  <operator activated="true" class="process" compatibility="5.3.013" expanded="true" name="Process"><br>    <parameter key="logverbosity" value="init"/><br>    <parameter key="random_seed" value="2001"/><br>    <parameter key="send_mail" value="never"/><br>    <parameter key="notification_email" value=""/><br>    <parameter key="process_duration_for_mail" value="30"/><br>    <parameter key="encoding" value="windows-1252"/><br>    <process expanded="true"><br>      <operator activated="true" class="read_excel" compatibility="5.3.013" expanded="true" height="60" name="Read Excel" width="90" x="45" y="30"><br>        <parameter key="excel_file" value="C:\Users\HEGFRATB\Desktop\Trainingsdaten_Matrix\Trainingsdaten.xls"/><br>        <parameter key="sheet_number" value="1"/><br>        <parameter key="imported_cell_range" value="A1:G7183"/><br>        <parameter key="encoding" value="windows-1252"/><br>        <parameter key="first_row_as_names" value="false"/><br>        <list key="annotations"><br>          <parameter key="0" value="Name"/><br>        </list><br>        <parameter key="date_format" value=""/><br>        <parameter key="time_zone" value="SYSTEM"/><br>        <parameter key="locale" value="German"/><br>        <list key="data_set_meta_data_information"><br>          <parameter key="0" value="ID.true.integer.id"/><br>          <parameter key="1" value="Dokumententitel.true.polynominal.attribute"/><br>          <parameter key="2" value="Kategorie1.true.polynominal.attribute"/><br>          <parameter key="3" value="Kategorie2.true.polynominal.attribute"/><br>          <parameter key="4" value="Kategorie3.true.polynominal.attribute"/><br>          <parameter key="5" value="Dokumentenpfad.true.polynominal.attribute"/><br>          <parameter key="6" value="Text.true.text.attribute"/><br>        </list><br>        <parameter key="read_not_matching_values_as_missings" value="true"/><br>        <parameter key="datamanagement" value="double_array"/><br>      </operator><br>      <operator activated="true" class="text:process_document_from_data" compatibility="5.3.002" expanded="true" height="76" name="Process Documents from Data" width="90" x="179" y="30"><br>        <parameter key="create_word_vector" value="true"/><br>        <parameter key="vector_creation" value="TF-IDF"/><br>        <parameter key="add_meta_information" value="true"/><br>        <parameter key="keep_text" value="false"/><br>        <parameter key="prune_method" value="absolute"/><br>        <parameter key="prune_below_percent" value="3.0"/><br>        <parameter key="prune_above_percent" value="30.0"/><br>        <parameter key="prune_below_absolute" value="2"/><br>        <parameter key="prune_above_absolute" value="999"/><br>        <parameter key="prune_below_rank" value="0.05"/><br>        <parameter key="prune_above_rank" value="0.95"/><br>        <parameter key="datamanagement" value="double_sparse_array"/><br>        <parameter key="select_attributes_and_weights" value="false"/><br>        <list key="specify_weights"/><br>        <process expanded="true"><br>          <operator activated="true" class="web:extract_html_text_content" compatibility="5.3.002" expanded="true" height="60" name="Extract Content" width="90" x="45" y="30"><br>            <parameter key="extract_content" value="true"/><br>            <parameter key="minimum_text_block_length" value="5"/><br>            <parameter key="override_content_type_information" value="true"/><br>            <parameter key="neglegt_span_tags" value="true"/><br>            <parameter key="neglect_p_tags" value="true"/><br>            <parameter key="neglect_b_tags" value="true"/><br>            <parameter key="neglect_i_tags" value="true"/><br>            <parameter key="neglect_br_tags" value="true"/><br>            <parameter key="ignore_non_html_tags" value="true"/><br>          </operator><br>          <operator activated="true" class="text:transform_cases" compatibility="5.3.002" expanded="true" height="60" name="Transform Cases" width="90" x="180" y="30"><br>            <parameter key="transform_to" value="lower case"/><br>          </operator><br>          <operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize" width="90" x="315" y="30"><br>            <parameter key="mode" value="non letters"/><br>            <parameter key="characters" value=".:"/><br>            <parameter key="language" value="English"/><br>            <parameter key="max_token_length" value="3"/><br>          </operator><br>          <operator activated="true" class="text:filter_stopwords_german" compatibility="5.3.002" expanded="true" height="60" name="Filter Stopwords (German)" width="90" x="450" y="30"><br>            <parameter key="stop_word_list" value="Standard"/><br>          </operator><br>          <operator activated="true" class="text:stem_snowball" compatibility="5.3.002" expanded="true" height="60" name="Stem (Snowball)" width="90" x="45" y="120"><br>            <parameter key="language" value="German"/><br>          </operator><br>          <operator activated="true" class="text:filter_by_length" compatibility="5.3.002" expanded="true" height="60" name="Filter Tokens (by Length)" width="90" x="179" y="120"><br>            <parameter key="min_chars" value="4"/><br>            <parameter key="max_chars" value="999"/><br>          </operator><br>          <connect from_port="document" to_op="Extract Content" to_port="document"/><br>          <connect from_op="Extract Content" from_port="document" to_op="Transform Cases" to_port="document"/><br>          <connect from_op="Transform Cases" from_port="document" to_op="Tokenize" to_port="document"/><br>          <connect from_op="Tokenize" from_port="document" to_op="Filter Stopwords (German)" to_port="document"/><br>          <connect from_op="Filter Stopwords (German)" from_port="document" to_op="Stem (Snowball)" to_port="document"/><br>          <connect from_op="Stem (Snowball)" from_port="document" to_op="Filter Tokens (by Length)" to_port="document"/><br>          <connect from_op="Filter Tokens (by Length)" from_port="document" to_port="document 1"/><br>          <portSpacing port="source_document" spacing="0"/><br>          <portSpacing port="sink_document 1" spacing="0"/><br>          <portSpacing port="sink_document 2" spacing="0"/><br>        </process><br>      </operator><br>      <operator activated="true" class="select_attributes" compatibility="5.3.013" expanded="true" height="76" name="Select Attributes" width="90" x="313" y="30"><br>        <parameter key="attribute_filter_type" value="all"/><br>        <parameter key="attribute" value=""/><br>        <parameter key="attributes" value=""/><br>        <parameter key="use_except_expression" value="false"/><br>        <parameter key="value_type" value="attribute_value"/><br>        <parameter key="use_value_type_exception" value="false"/><br>        <parameter key="except_value_type" value="time"/><br>        <parameter key="block_type" value="attribute_block"/><br>        <parameter key="use_block_type_exception" value="false"/><br>        <parameter key="except_block_type" value="value_matrix_row_start"/><br>        <parameter key="invert_selection" value="false"/><br>        <parameter key="include_special_attributes" value="false"/><br>      </operator><br>      <operator activated="true" class="generate_attributes" compatibility="5.3.013" expanded="true" height="76" name="Generate Attributes" width="90" x="447" y="30"><br>        <list key="function_descriptions"><br>          <parameter key="Abnahmestelle" value="if(Kategorie1==&quot;Abnahmestelle&quot;||Kategorie2==&quot;Abnahmestelle&quot;||Kategorie3==&quot;Abnahmestelle&quot;,TRUE,FALSE)"/><br>        </list><br>        <parameter key="use_standard_constants" value="true"/><br>        <parameter key="keep_all" value="true"/><br>      </operator><br>      <operator activated="true" class="set_role" compatibility="5.3.013" expanded="true" height="76" name="Set Role" width="90" x="581" y="30"><br>        <parameter key="attribute_name" value="Abnahmestelle"/><br>        <parameter key="target_role" value="label"/><br>        <list key="set_additional_roles"><br>          <parameter key="ID" value="id"/><br>          <parameter key="Dokumentenpfad" value="regular"/><br>          <parameter key="Dokumententitel" value="regular"/><br>          <parameter key="Kategorie2" value="regular"/><br>          <parameter key="Kategorie3" value="regular"/><br>          <parameter key="Kategorie1" value="regular"/><br>        </list><br>      </operator><br>      <operator activated="true" class="split_validation" compatibility="5.3.013" expanded="true" height="130" name="Validation" width="90" x="380" y="165"><br>        <parameter key="create_complete_model" value="false"/><br>        <parameter key="split" value="relative"/><br>        <parameter key="split_ratio" value="0.7"/><br>        <parameter key="training_set_size" value="100"/><br>        <parameter key="test_set_size" value="-1"/><br>        <parameter key="sampling_type" value="shuffled sampling"/><br>        <parameter key="use_local_random_seed" value="false"/><br>        <parameter key="local_random_seed" value="1992"/><br>        <process expanded="true"><br>          <operator activated="true" class="decision_tree" compatibility="5.3.013" expanded="true" height="76" name="Decision Tree (2)" width="90" x="112" y="30"><br>            <parameter key="criterion" value="gini_index"/><br>            <parameter key="minimal_size_for_split" value="4"/><br>            <parameter key="minimal_leaf_size" value="2"/><br>            <parameter key="minimal_gain" value="0.1"/><br>            <parameter key="maximal_depth" value="20"/><br>            <parameter key="confidence" value="0.25"/><br>            <parameter key="number_of_prepruning_alternatives" value="3"/><br>            <parameter key="no_pre_pruning" value="false"/><br>            <parameter key="no_pruning" value="false"/><br>          </operator><br>          <connect from_port="training" to_op="Decision Tree (2)" to_port="training set"/><br>          <connect from_op="Decision Tree (2)" from_port="model" to_port="model"/><br>          <connect from_op="Decision Tree (2)" from_port="exampleSet" to_port="through 1"/><br>          <portSpacing port="source_training" spacing="0"/><br>          <portSpacing port="sink_model" spacing="0"/><br>          <portSpacing port="sink_through 1" spacing="0"/><br>          <portSpacing port="sink_through 2" spacing="0"/><br>        </process><br>        <process expanded="true"><br>          <operator activated="true" class="apply_model" compatibility="5.3.013" expanded="true" height="76" name="Apply Model (2)" width="90" x="45" y="30"><br>            <list key="application_parameters"/><br>            <parameter key="create_view" value="false"/><br>          </operator><br>          <operator activated="true" class="performance_binominal_classification" compatibility="5.3.013" expanded="true" height="76" name="Performance (2)" width="90" x="179" y="30"><br>            <parameter key="main_criterion" value="first"/><br>            <parameter key="accuracy" value="true"/><br>            <parameter key="classification_error" value="false"/><br>            <parameter key="kappa" value="false"/><br>            <parameter key="AUC (optimistic)" value="false"/><br>            <parameter key="AUC" value="false"/><br>            <parameter key="AUC (pessimistic)" value="false"/><br>            <parameter key="precision" value="false"/><br>            <parameter key="recall" value="false"/><br>            <parameter key="lift" value="false"/><br>            <parameter key="fallout" value="false"/><br>            <parameter key="f_measure" value="true"/><br>            <parameter key="false_positive" value="false"/><br>            <parameter key="false_negative" value="false"/><br>            <parameter key="true_positive" value="false"/><br>            <parameter key="true_negative" value="false"/><br>            <parameter key="sensitivity" value="true"/><br>            <parameter key="specificity" value="false"/><br>            <parameter key="youden" value="false"/><br>            <parameter key="positive_predictive_value" value="false"/><br>            <parameter key="negative_predictive_value" value="false"/><br>            <parameter key="psep" value="false"/><br>            <parameter key="skip_undefined_labels" value="true"/><br>            <parameter key="use_example_weights" value="true"/><br>          </operator><br>          <connect from_port="model" to_op="Apply Model (2)" to_port="model"/><br>          <connect from_port="test set" to_op="Apply Model (2)" to_port="unlabelled data"/><br>          <connect from_op="Apply Model (2)" from_port="labelled data" to_op="Performance (2)" to_port="labelled data"/><br>          <connect from_op="Performance (2)" from_port="performance" to_port="averagable 1"/><br>          <portSpacing port="source_model" spacing="0"/><br>          <portSpacing port="source_test set" spacing="0"/><br>          <portSpacing port="source_through 1" spacing="0"/><br>          <portSpacing port="source_through 2" spacing="0"/><br>          <portSpacing port="sink_averagable 1" spacing="0"/><br>          <portSpacing port="sink_averagable 2" spacing="0"/><br>          <portSpacing port="sink_averagable 3" spacing="0"/><br>        </process><br>      </operator><br>      <connect from_op="Read Excel" from_port="output" to_op="Process Documents from Data" to_port="example set"/><br>      <connect from_op="Process Documents from Data" from_port="example set" to_op="Select Attributes" to_port="example set input"/><br>      <connect from_op="Select Attributes" from_port="example set output" to_op="Generate Attributes" to_port="example set input"/><br>      <connect from_op="Generate Attributes" from_port="example set output" to_op="Set Role" to_port="example set input"/><br>      <connect from_op="Set Role" from_port="example set output" to_op="Validation" to_port="training"/><br>      <connect from_op="Validation" from_port="model" to_port="result 1"/><br>      <connect from_op="Validation" from_port="training" to_port="result 2"/><br>      <connect from_op="Validation" from_port="averagable 1" to_port="result 3"/><br>      <connect from_op="Validation" from_port="averagable 2" to_port="result 4"/><br>      <portSpacing port="source_input 1" spacing="0"/><br>      <portSpacing port="sink_result 1" spacing="0"/><br>      <portSpacing port="sink_result 2" spacing="0"/><br>      <portSpacing port="sink_result 3" spacing="0"/><br>      <portSpacing port="sink_result 4" spacing="0"/><br>      <portSpacing port="sink_result 5" spacing="0"/><br>    </process><br>  </operator><br></process><br>
And the LOG message
 +- Validation[1] (Split Validation)
           subprocess 'Training'
       ==>      |  +- Decision Tree[1] (Decision Tree)
           subprocess 'Testing'
                   +- Apply Model[0] (Apply Model)
                   +- Performance[0] (Performance (Binominal Classification))
Mar 28, 2019 4:16:46 PM SEVERE: java.lang.ArrayIndexOutOfBoundsException: 0

Pleas help me

Thank you
Yours
Franzi


Tagged:

Answers