Error while apply model for unseen data

HeikoeWin786

Hello all,

I am testing the NBC in cross-validation to understand throughly.
I am aware that the train dataset and test dataset needs to follow the same data pre-processing process.
However, when I take the exe of cross-validation and input the exe of pre-processed data (from unseen dataset), I got the error below.
Could you please advise me where I made a mistake here?
I had attached my rmp file and error message for your kind reference. 

Thanks much in advance.
Heikoe 

MartinLiebig

Hi,

you ran into the "WordList Issue" outlined here: https://community.rapidminer.com/discussion/31723/text-mining-and-the-word-list

Attached is a process which passes the word list through and should work.

<?xml version="1.0" encoding="UTF-8"?><process version="9.7.002">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.7.002" 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="9.7.002" expanded="true" height="68" name="Read Excel" width="90" x="581" y="187">
        <parameter key="excel_file" value="C:\Users\MYAT\Documents\1.0 Master Study\Learning\Data Science\subjectivity_Dataset_Validated.xlsx"/>
        <parameter key="sheet_selection" value="sheet number"/>
        <parameter key="sheet_number" value="1"/>
        <parameter key="imported_cell_range" value="A1:F10485776"/>
        <parameter key="encoding" value="SYSTEM"/>
        <parameter key="first_row_as_names" value="true"/>
        <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="customer_review.true.polynominal.attribute"/>
          <parameter key="1" value="confident_score.true.binominal.label"/>
          <parameter key="2" value="Airlines.true.polynominal.attribute"/>
          <parameter key="3" value="TB_label.false.polynominal.attribute"/>
          <parameter key="4" value="TB_Opinion.false.polynominal.attribute"/>
          <parameter key="5" value="Vader_Score.false.polynominal.attribute"/>
        </list>
        <parameter key="read_not_matching_values_as_missings" value="false"/>
        <parameter key="datamanagement" value="double_array"/>
        <parameter key="data_management" value="auto"/>
      </operator>
      <operator activated="true" class="split_data" compatibility="9.7.002" expanded="true" height="103" name="Split Data" width="90" x="715" y="187">
        <enumeration key="partitions">
          <parameter key="ratio" value="0.75"/>
          <parameter key="ratio" value="0.25"/>
        </enumeration>
        <parameter key="sampling_type" value="stratified sampling"/>
        <parameter key="use_local_random_seed" value="false"/>
        <parameter key="local_random_seed" value="1992"/>
      </operator>
      <operator activated="true" class="store" compatibility="9.7.002" expanded="true" height="68" name="Store (3)" width="90" x="916" y="187">
        <parameter key="repository_entry" value="../Data/unseen_data"/>
      </operator>
      <operator activated="true" class="nominal_to_text" compatibility="9.7.002" expanded="true" height="82" name="Nominal to Text (2)" width="90" x="1117" y="85">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="customer_review"/>
        <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="nominal_to_text" compatibility="9.7.002" expanded="true" height="82" name="Nominal to Text" width="90" x="246" y="493">
        <parameter key="attribute_filter_type" value="single"/>
        <parameter key="attribute" value="customer_review"/>
        <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="9.3.001" expanded="true" height="82" name="Process Documents from Data" width="90" x="849" y="442">
        <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="false"/>
        <parameter key="prune_method" value="none"/>
        <parameter key="prune_below_percent" value="3.0"/>
        <parameter key="prune_above_percent" value="30.0"/>
        <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"/>
        <process expanded="true">
          <operator activated="true" class="text:tokenize" compatibility="9.3.001" expanded="true" height="68" name="Tokenize" width="90" x="45" y="34">
            <parameter key="mode" value="non letters"/>
            <parameter key="characters" value=".:"/>
            <parameter key="language" value="English"/>
            <parameter key="max_token_length" value="3"/>
          </operator>
          <operator activated="true" class="text:transform_cases" compatibility="9.3.001" expanded="true" height="68" name="Transform Cases" width="90" x="179" y="34">
            <parameter key="transform_to" value="lower case"/>
          </operator>
          <operator activated="true" class="text:filter_stopwords_english" compatibility="9.3.001" expanded="true" height="68" name="Filter Stopwords (English)" width="90" x="313" y="34"/>
          <operator activated="true" class="text:stem_porter" compatibility="9.3.001" expanded="true" height="68" name="Stem (Porter)" width="90" x="447" y="34"/>
          <operator activated="true" class="text:filter_by_length" compatibility="9.3.001" expanded="true" height="68" name="Filter Tokens (by Length)" width="90" x="581" y="34">
            <parameter key="min_chars" value="3"/>
            <parameter key="max_chars" value="25"/>
          </operator>
          <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_op="Filter Stopwords (English)" to_port="document"/>
          <connect from_op="Filter Stopwords (English)" from_port="document" to_op="Stem (Porter)" to_port="document"/>
          <connect from_op="Stem (Porter)" from_port="document" to_op="Filter Tokens (by Length)" to_port="document"/>
          <connect from_op="Filter Tokens (by Length)" 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="text:process_document_from_data" compatibility="9.3.001" expanded="true" height="82" name="Process Documents from Data (2)" width="90" x="1318" y="187">
        <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="false"/>
        <parameter key="prune_method" value="none"/>
        <parameter key="prune_below_percent" value="3.0"/>
        <parameter key="prune_above_percent" value="30.0"/>
        <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"/>
        <process expanded="true">
          <operator activated="true" class="text:tokenize" compatibility="9.3.001" expanded="true" height="68" name="Tokenize (2)" width="90" x="45" y="34">
            <parameter key="mode" value="non letters"/>
            <parameter key="characters" value=".:"/>
            <parameter key="language" value="English"/>
            <parameter key="max_token_length" value="3"/>
          </operator>
          <operator activated="true" class="text:transform_cases" compatibility="9.3.001" expanded="true" height="68" name="Transform Cases (2)" width="90" x="179" y="34">
            <parameter key="transform_to" value="lower case"/>
          </operator>
          <operator activated="true" class="text:filter_stopwords_english" compatibility="9.3.001" expanded="true" height="68" name="Filter Stopwords (English) (2)" width="90" x="313" y="34"/>
          <operator activated="true" class="text:stem_porter" compatibility="9.3.001" expanded="true" height="68" name="Stem (Porter) (2)" width="90" x="447" y="34"/>
          <operator activated="true" class="text:filter_by_length" compatibility="9.3.001" expanded="true" height="68" name="Filter Tokens (by Length) (2)" width="90" x="581" y="34">
            <parameter key="min_chars" value="3"/>
            <parameter key="max_chars" value="25"/>
          </operator>
          <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="Filter Stopwords (English) (2)" to_port="document"/>
          <connect from_op="Filter Stopwords (English) (2)" from_port="document" to_op="Stem (Porter) (2)" to_port="document"/>
          <connect from_op="Stem (Porter) (2)" from_port="document" to_op="Filter Tokens (by Length) (2)" to_port="document"/>
          <connect from_op="Filter Tokens (by Length) (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="concurrency:cross_validation" compatibility="9.7.002" expanded="true" height="145" name="Cross Validation" width="90" x="1050" y="442">
        <parameter key="split_on_batch_attribute" value="false"/>
        <parameter key="leave_one_out" value="false"/>
        <parameter key="number_of_folds" value="10"/>
        <parameter key="sampling_type" value="automatic"/>
        <parameter key="use_local_random_seed" value="false"/>
        <parameter key="local_random_seed" value="1992"/>
        <parameter key="enable_parallel_execution" value="true"/>
        <process expanded="true">
          <operator activated="true" class="naive_bayes" compatibility="9.7.002" expanded="true" height="82" name="Naive Bayes" width="90" x="45" y="34">
            <parameter key="laplace_correction" value="true"/>
          </operator>
          <connect from_port="training set" to_op="Naive Bayes" to_port="training set"/>
          <connect from_op="Naive Bayes" from_port="model" to_port="model"/>
          <portSpacing port="source_training set" 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="9.7.002" expanded="true" height="82" name="Apply Model" width="90" x="45" y="34">
            <list key="application_parameters"/>
            <parameter key="create_view" value="false"/>
          </operator>
          <operator activated="true" class="performance_binominal_classification" compatibility="9.7.002" expanded="true" height="82" name="Performance" width="90" x="179" y="34">
            <parameter key="manually_set_positive_class" value="false"/>
            <parameter key="main_criterion" value="first"/>
            <parameter key="accuracy" value="true"/>
            <parameter key="classification_error" value="false"/>
            <parameter key="kappa" value="true"/>
            <parameter key="AUC (optimistic)" value="false"/>
            <parameter key="AUC" value="false"/>
            <parameter key="AUC (pessimistic)" value="false"/>
            <parameter key="precision" value="true"/>
            <parameter key="recall" value="true"/>
            <parameter key="lift" value="false"/>
            <parameter key="fallout" value="false"/>
            <parameter key="f_measure" value="true"/>
            <parameter key="false_positive" value="false"/>
            <parameter key="false_negative" value="false"/>
            <parameter key="true_positive" value="false"/>
            <parameter key="true_negative" value="false"/>
            <parameter key="sensitivity" value="false"/>
            <parameter key="specificity" value="false"/>
            <parameter key="youden" value="false"/>
            <parameter key="positive_predictive_value" value="false"/>
            <parameter key="negative_predictive_value" value="false"/>
            <parameter key="psep" value="false"/>
            <parameter key="skip_undefined_labels" value="true"/>
            <parameter key="use_example_weights" value="true"/>
          </operator>
          <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="performance 1"/>
          <portSpacing port="source_model" spacing="0"/>
          <portSpacing port="source_test set" spacing="0"/>
          <portSpacing port="source_through 1" spacing="0"/>
          <portSpacing port="sink_test set results" spacing="0"/>
          <portSpacing port="sink_performance 1" spacing="0"/>
          <portSpacing port="sink_performance 2" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="store" compatibility="9.7.002" expanded="true" height="68" name="Store (5)" width="90" x="1452" y="493">
        <parameter key="repository_entry" value="../Model/NBC_Performance"/>
      </operator>
      <operator activated="true" class="store" compatibility="9.7.002" expanded="true" height="68" name="Store (4)" width="90" x="1385" y="340">
        <parameter key="repository_entry" value="../Model/NBC"/>
      </operator>
      <operator activated="true" class="apply_model" compatibility="9.7.002" expanded="true" height="82" name="Apply Model (2)" width="90" x="1653" y="442">
        <list key="application_parameters"/>
        <parameter key="create_view" value="false"/>
      </operator>
      <operator activated="true" class="performance_binominal_classification" compatibility="9.7.002" expanded="true" height="82" name="Performance (2)" width="90" x="1854" y="442">
        <parameter key="manually_set_positive_class" value="false"/>
        <parameter key="main_criterion" value="first"/>
        <parameter key="accuracy" value="true"/>
        <parameter key="classification_error" value="false"/>
        <parameter key="kappa" value="true"/>
        <parameter key="AUC (optimistic)" value="false"/>
        <parameter key="AUC" value="false"/>
        <parameter key="AUC (pessimistic)" value="false"/>
        <parameter key="precision" value="true"/>
        <parameter key="recall" value="true"/>
        <parameter key="lift" value="false"/>
        <parameter key="fallout" value="false"/>
        <parameter key="f_measure" value="true"/>
        <parameter key="false_positive" value="false"/>
        <parameter key="false_negative" value="false"/>
        <parameter key="true_positive" value="false"/>
        <parameter key="true_negative" value="false"/>
        <parameter key="sensitivity" value="false"/>
        <parameter key="specificity" value="false"/>
        <parameter key="youden" value="false"/>
        <parameter key="positive_predictive_value" value="false"/>
        <parameter key="negative_predictive_value" value="false"/>
        <parameter key="psep" value="false"/>
        <parameter key="skip_undefined_labels" value="true"/>
        <parameter key="use_example_weights" value="true"/>
      </operator>
      <operator activated="true" class="store" compatibility="9.7.002" expanded="true" height="68" name="Store (6)" width="90" x="2055" y="442">
        <parameter key="repository_entry" value="../Model/NBC_Unseen_Performance"/>
      </operator>
      <connect from_op="Read Excel" from_port="output" to_op="Split Data" to_port="example set"/>
      <connect from_op="Split Data" from_port="partition 1" to_op="Nominal to Text" to_port="example set input"/>
      <connect from_op="Split Data" from_port="partition 2" to_op="Store (3)" to_port="input"/>
      <connect from_op="Store (3)" from_port="through" 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="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="Cross Validation" to_port="example set"/>
      <connect from_op="Process Documents from Data" from_port="word list" to_op="Process Documents from Data (2)" to_port="word list"/>
      <connect from_op="Process Documents from Data (2)" from_port="example set" to_op="Apply Model (2)" to_port="unlabelled data"/>
      <connect from_op="Cross Validation" from_port="model" to_op="Store (4)" to_port="input"/>
      <connect from_op="Cross Validation" from_port="performance 1" to_op="Store (5)" to_port="input"/>
      <connect from_op="Store (4)" from_port="through" to_op="Apply Model (2)" to_port="model"/>
      <connect from_op="Apply Model (2)" from_port="labelled data" to_op="Performance (2)" to_port="labelled data"/>
      <connect from_op="Performance (2)" from_port="performance" to_op="Store (6)" to_port="input"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
    </process>
  </operator>
</process>

HeikoeWin786

Hello @mschmitz

Much appreciated for your kind clarification here.
Indeed, this is what I was missing.
Well noted!

Much thanks.
Heikoe