"Comparing training and testing accuracy to check over-fitting."
Avichandra
New Altair Community Member
<?xml version="1.0" encoding="UTF-8"?><process version="8.2.000">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="8.2.000" 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="retrieve" compatibility="8.2.000" expanded="true" height="68" name="Retrieve totalfludata20180511" width="90" x="45" y="238">
<parameter key="repository_entry" value="//Local Repository/totalfludata20180511"/>
</operator>
<operator activated="true" class="split_data" compatibility="8.2.000" expanded="true" height="103" name="Split Data" width="90" x="45" y="34">
<enumeration key="partitions">
<parameter key="ratio" value="0.8"/>
<parameter key="ratio" value="0.2"/>
</enumeration>
<parameter key="sampling_type" value="automatic"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
</operator>
<operator activated="true" class="select_attributes" compatibility="8.2.000" expanded="true" height="82" name="Select Attributes" width="90" x="246" y="187">
<parameter key="attribute_filter_type" value="subset"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value="year2017_18|year2016_17|year2015_16|wherereside.factor|weightlb|travel.factor|slaughter.factor|preg0nt.factor|pastmedreproductiveother.factor|pastmedreproductive.factor|pastmedre0ldisother.factor|pastmedre0ldisendstage.factor|pastmedre0ldis.factor|pastmedpcos.factor|pastmedothermed.factor|pastmedorgtransp.factor|pastmedneurodisstroke.factor|pastmedneurodisspi0lcord.factor|pastmedneurodisseizepilep.factor|pastmedneurodispnh.factor|pastmedneurodisother.factor|pastmedneurodisms.factor|pastmedneurodisintelldisab.factor|pastmedneurodiscp.factor|pastmedneurodis.factor|pastmedmetenddisthyroid.factor|pastmedmetenddisother.factor|pastmedmetenddisdiab.factor|pastmedmetenddis.factor|pastmedhivcd4.factor|pastmedhiv.factor|pastmedhepdisother.factor|pastmedhepdishepc.factor|pastmedhepdishepb.factor|pastmedhepdiscirr.factor|pastmedhepdis.factor|pastmedhemdissicklecell.factor|pastmedhemdisother.factor|pastmedhemdislymph.factor|pastmedhemdisleuk.factor|pastmedhemdis.factor|pastmedesld.factor|pastmedendomet.factor|pastmeddialysis.factor|pastmedcvdisvalvdis.factor|pastmedcvdisother.factor|pastmedcvdiscorartdis.factor|pastmedcvdiscongesthrtfail.factor|pastmedcvdiscongenhdis.factor|pastmedcvdiscardiomyop.factor|pastmedcvdis.factor|pastmedchronlundisother.factor|pastmedchronlundiscystfib.factor|pastmedchronlundiscopd.factor|pastmedchronlundisasth.factor|pastmedchronlundis.factor|pastmedcancerrad.factor|pastmedcancerchemo.factor|pastmedcancer.factor|pastmedautoimm.factor|menses.factor|medhistav.factor|largefarm.factor|heightin|gender.factor|foodprep.factor|fluvaccine_date.factor|fluvaccine.factor|flock.factor|farm.factor|exposure_swine.factor|exposure_poultry.factor|exposure_birds.factor|exposure.factor|exposeother.factor|exposehuman.factor|enrolling_site.factor|enrolldate|employed.factor|education.factor|edchrev_ab_ed.factor|cursympt_wheezing.factor|cursympt_stomachpain.factor|cursympt_sorethroat.factor|cursympt_sinuspain.factor|cursympt_shortnessbreath.factor|cursympt_shakingchills.factor|cursympt_rhinorrhea.factor|cursympt_other.factor|cursympt_incrsputum.factor|cursympt_headache.factor|cursympt_getoutofbed.factor|cursympt_fever.factor|cursympt_fatigue.factor|cursympt_diarrhea.factor|cursympt_coughsputum.factor|cursympt_cough.factor|cursympt_conjunctivitis.factor|cursympt_chestpain.factor|cursympt_chesthurt.factor|cursympt_bodyaches.factor|cursympt_appetite.factor|cursympt_0usea.factor|curmedsteroids.factor|curmedimmunosupsp___4.factor|curmedimmunosupsp___3.factor|curmedimmunosupsp___2.factor|curmedimmunosupsp___1.factor|curmedimmunosup.factor|breastfeeding.factor|bcmethod.factor|age|admit.factor|H3|H1|B"/>
<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"/>
</operator>
<operator activated="true" class="set_role" compatibility="8.2.000" expanded="true" height="82" name="Set Role" width="90" x="179" y="34">
<parameter key="attribute_name" value="GeneXpert"/>
<parameter key="target_role" value="label"/>
<list key="set_additional_roles"/>
</operator>
<operator activated="true" class="split_validation" compatibility="8.2.000" expanded="true" height="124" name="Validation" width="90" x="313" y="34">
<parameter key="create_complete_model" value="false"/>
<parameter key="split" value="relative"/>
<parameter key="split_ratio" value="0.7"/>
<parameter key="training_set_size" value="100"/>
<parameter key="test_set_size" value="-1"/>
<parameter key="sampling_type" value="automatic"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
<process expanded="true">
<operator activated="true" class="concurrency:parallel_random_forest" compatibility="8.2.000" expanded="true" height="103" name="Random Forest" width="90" x="112" y="34">
<parameter key="number_of_trees" value="10"/>
<parameter key="criterion" value="gain_ratio"/>
<parameter key="maximal_depth" value="20"/>
<parameter key="apply_pruning" value="true"/>
<parameter key="confidence" value="0.25"/>
<parameter key="apply_prepruning" value="true"/>
<parameter key="minimal_gain" value="0.1"/>
<parameter key="minimal_leaf_size" value="2"/>
<parameter key="minimal_size_for_split" value="4"/>
<parameter key="number_of_prepruning_alternatives" value="3"/>
<parameter key="random_splits" value="false"/>
<parameter key="guess_subset_ratio" value="true"/>
<parameter key="subset_ratio" value="0.2"/>
<parameter key="voting_strategy" value="confidence vote"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
<parameter key="enable_parallel_execution" value="true"/>
</operator>
<connect from_port="training" to_op="Random Forest" to_port="training set"/>
<connect from_op="Random Forest" from_port="model" to_port="model"/>
<portSpacing port="source_training" 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="8.2.000" expanded="true" height="82" name="Apply Model (2)" width="90" x="45" y="34">
<list key="application_parameters"/>
<parameter key="create_view" value="false"/>
</operator>
<operator activated="true" class="performance" compatibility="8.2.000" expanded="true" height="82" name="Performance" width="90" x="179" y="34">
<parameter key="use_example_weights" value="true"/>
</operator>
<connect from_port="model" to_op="Apply Model (2)" to_port="model"/>
<connect from_port="test set" to_op="Apply Model (2)" to_port="unlabelled data"/>
<connect from_op="Apply Model (2)" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
<connect from_op="Performance" from_port="performance" to_port="averagable 1"/>
<portSpacing port="source_model" spacing="0"/>
<portSpacing port="source_test set" spacing="0"/>
<portSpacing port="source_through 1" spacing="0"/>
<portSpacing port="sink_averagable 1" spacing="0"/>
<portSpacing port="sink_averagable 2" spacing="0"/>
</process>
</operator>
<operator activated="true" class="apply_model" compatibility="8.2.000" expanded="true" height="82" name="Apply Model" width="90" x="447" y="136">
<list key="application_parameters"/>
<parameter key="create_view" value="false"/>
</operator>
<connect from_op="Retrieve totalfludata20180511" from_port="output" to_op="Split Data" to_port="example set"/>
<connect from_op="Split Data" from_port="partition 1" to_op="Set Role" to_port="example set input"/>
<connect from_op="Split Data" from_port="partition 2" to_op="Select Attributes" to_port="example set input"/>
<connect from_op="Select Attributes" from_port="example set output" to_op="Apply Model" to_port="unlabelled data"/>
<connect from_op="Set Role" from_port="example set output" to_op="Validation" to_port="training"/>
<connect from_op="Validation" from_port="model" to_op="Apply Model" to_port="model"/>
<connect from_op="Validation" from_port="averagable 1" to_port="result 1"/>
<connect from_op="Apply Model" from_port="labelled data" 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>
I have designed a random forest classification model with splitting the dataset into training and testing in a ratio of 0.8:0.2. I have validated the model. I got accuracy for the testing dataset. I want to check the over-fitting problem of my model. So, I want to compare accuracy for both training and testing data set. How to retrieve accuracy for both training and testing dataset from my model.
Tagged:
0
Best Answer
-
Hi @Avichandra
In your process, add second PERFORMANCE operator and connect is with lab output of APPLY MODEL, this way you'll also get performance measure for 0.2 test split data.
1
Answers
-
Hi @Avichandra
In your process, add second PERFORMANCE operator and connect is with lab output of APPLY MODEL, this way you'll also get performance measure for 0.2 test split data.
1 -
Thank you very much! I got what I wanted to know.
1 -
<?xml version="1.0" encoding="UTF-8"?><process version="8.2.000">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" automodel="EXPORTED" class="process" compatibility="8.2.000" 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" automodel="EXPORTED" class="retrieve" compatibility="8.2.000" expanded="true" height="68" name="Retrieve Data" width="90" x="45" y="238">
<parameter key="repository_entry" value="//Local Repository/totalfludata20180511"/>
<description align="center" color="transparent" colored="false" width="126">Load data.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="subprocess" compatibility="8.2.000" expanded="true" height="82" name="Preprocessing" width="90" x="179" y="238">
<process expanded="true">
<operator activated="true" automodel="EXPORTED" class="select_subprocess" compatibility="8.2.000" expanded="true" height="82" name="Define Target?" width="90" x="45" y="34">
<parameter key="select_which" value="2"/>
<process expanded="true">
<connect from_port="input 1" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" automodel="EXPORTED" class="set_role" compatibility="8.2.000" expanded="true" height="82" name="Define Target" width="90" x="45" y="34">
<parameter key="attribute_name" value="GeneXpert"/>
<parameter key="target_role" value="label"/>
<list key="set_additional_roles"/>
<description align="center" color="transparent" colored="false" width="126">Define the target column for the predictive model.</description>
</operator>
<connect from_port="input 1" to_op="Define Target" to_port="example set input"/>
<connect from_op="Define Target" from_port="example set output" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<description align="center" color="transparent" colored="false" width="126">Should define a target column?</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="select_subprocess" compatibility="8.2.000" expanded="true" height="82" name="Should Discretize?" width="90" x="179" y="34">
<parameter key="select_which" value="1"/>
<process expanded="true">
<connect from_port="input 1" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" automodel="EXPORTED" class="discretize_by_bins" compatibility="8.2.000" expanded="true" height="103" name="Binning" width="90" x="45" y="34">
<parameter key="return_preprocessing_model" value="false"/>
<parameter key="create_view" value="false"/>
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="Age"/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="numeric"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="real"/>
<parameter key="block_type" value="value_series"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_series_end"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="true"/>
<parameter key="number_of_bins" value="2"/>
<parameter key="define_boundaries" value="false"/>
<parameter key="range_name_type" value="short"/>
<parameter key="automatic_number_of_digits" value="true"/>
<parameter key="number_of_digits" value="3"/>
<description align="center" color="transparent" colored="false" width="126">Discretize by binning (same range per bin).</description>
</operator>
<connect from_port="input 1" to_op="Binning" to_port="example set input"/>
<connect from_op="Binning" from_port="example set output" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" automodel="EXPORTED" class="discretize_by_frequency" compatibility="8.2.000" expanded="true" height="103" name="Frequency" width="90" x="45" y="34">
<parameter key="return_preprocessing_model" value="false"/>
<parameter key="create_view" value="false"/>
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="Age"/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="numeric"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="real"/>
<parameter key="block_type" value="value_series"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_series_end"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="true"/>
<parameter key="use_sqrt_of_examples" value="false"/>
<parameter key="number_of_bins" value="2"/>
<parameter key="range_name_type" value="short"/>
<parameter key="automatic_number_of_digits" value="true"/>
<parameter key="number_of_digits" value="-1"/>
<description align="center" color="transparent" colored="false" width="126">Discretize by frequency (same count per bin).</description>
</operator>
<connect from_port="input 1" to_op="Frequency" to_port="example set input"/>
<connect from_op="Frequency" from_port="example set output" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<description align="center" color="transparent" colored="false" width="126">Should discretize numerical target column?</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="select_subprocess" compatibility="8.2.000" expanded="true" height="82" name="Map Values?" width="90" x="313" y="34">
<parameter key="select_which" value="1"/>
<process expanded="true">
<connect from_port="input 1" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" automodel="EXPORTED" class="map" compatibility="8.2.000" expanded="true" height="82" name="Map Values" width="90" x="45" y="34">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="Survived"/>
<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="true"/>
<list key="value_mappings"/>
<parameter key="consider_regular_expressions" value="false"/>
<parameter key="add_default_mapping" value="false"/>
<description align="center" color="transparent" colored="false" width="126">Map some nominal target values to new values.</description>
</operator>
<connect from_port="input 1" to_op="Map Values" to_port="example set input"/>
<connect from_op="Map Values" from_port="example set output" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<description align="center" color="transparent" colored="false" width="126">Should map nominal values?</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="select_subprocess" compatibility="8.2.000" expanded="true" height="82" name="Positive Class?" width="90" x="447" y="34">
<parameter key="select_which" value="2"/>
<process expanded="true">
<connect from_port="input 1" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" automodel="EXPORTED" class="nominal_to_binominal" compatibility="8.2.000" expanded="true" height="103" name="Nominal to Binominal" width="90" x="45" y="34">
<parameter key="return_preprocessing_model" value="false"/>
<parameter key="create_view" value="false"/>
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="GeneXpert"/>
<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="true"/>
<parameter key="transform_binominal" value="false"/>
<parameter key="use_underscore_in_name" value="false"/>
<description align="center" color="transparent" colored="false" width="126">Make sure that target is binary for positive class mapping.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="remap_binominals" compatibility="8.2.000" expanded="true" height="82" name="Define Positive Class" width="90" x="179" y="34">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="GeneXpert"/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="binominal"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="binominal"/>
<parameter key="block_type" value="value_matrix_start"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_matrix_start"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="true"/>
<parameter key="negative_value" value="Negative"/>
<parameter key="positive_value" value="Positive"/>
<description align="center" color="transparent" colored="false" width="126">Potentially define which one should be the positive class.</description>
</operator>
<connect from_port="input 1" to_op="Nominal to Binominal" to_port="example set input"/>
<connect from_op="Nominal to Binominal" from_port="example set output" to_op="Define Positive Class" to_port="example set input"/>
<connect from_op="Define Positive Class" from_port="example set output" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<description align="center" color="transparent" colored="false" width="126">Should define positive class?</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="select_subprocess" compatibility="8.2.000" expanded="true" height="82" name="Remove Columns?" width="90" x="581" y="34">
<parameter key="select_which" value="1"/>
<process expanded="true">
<connect from_port="input 1" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" automodel="EXPORTED" class="select_attributes" compatibility="8.2.000" expanded="true" height="82" name="Remove Columns" width="90" x="45" y="34">
<parameter key="attribute_filter_type" value="regular_expression"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value=""/>
<parameter key="regular_expression" value="Name|Ticket Number|Cabin|Life Boat"/>
<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="true"/>
<parameter key="include_special_attributes" value="true"/>
<description align="center" color="transparent" colored="false" width="126">Potentially remove columns.</description>
</operator>
<connect from_port="input 1" to_op="Remove Columns" to_port="example set input"/>
<connect from_op="Remove Columns" from_port="example set output" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<description align="center" color="transparent" colored="false" width="126">Should remove columns?</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="subprocess" compatibility="8.2.000" expanded="true" height="82" name="Unify Value Types" width="90" x="715" y="34">
<process expanded="true">
<operator activated="true" automodel="EXPORTED" class="select_attributes" compatibility="8.2.000" expanded="true" height="82" name="Remove Dates" width="90" x="45" y="34">
<parameter key="attribute_filter_type" value="value_type"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="date_time"/>
<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="true"/>
<parameter key="include_special_attributes" value="false"/>
<description align="center" color="transparent" colored="false" width="126">Remove all date columns.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="nominal_to_text" compatibility="8.2.000" expanded="true" height="82" name="Nominal to Text" width="90" x="179" y="34">
<parameter key="attribute_filter_type" value="value_type"/>
<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="true"/>
<description align="center" color="transparent" colored="false" width="126">Transform all nominal columns to text so that we make sure that all will have polynominal type after the next transformation.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="text_to_nominal" compatibility="8.2.000" expanded="true" height="82" name="Text to Nominal" width="90" x="313" y="34">
<parameter key="attribute_filter_type" value="value_type"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="text"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="text"/>
<parameter key="block_type" value="value_matrix"/>
<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="true"/>
<description align="center" color="transparent" colored="false" width="126">Transform all text columns into polynominal columns.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="numerical_to_real" compatibility="8.2.000" expanded="true" height="82" name="Numerical to Real" width="90" x="447" y="34">
<parameter key="attribute_filter_type" value="value_type"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="numeric"/>
<parameter key="use_value_type_exception" value="true"/>
<parameter key="except_value_type" value="integer"/>
<parameter key="block_type" value="value_series"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_series_end"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="true"/>
<description align="center" color="transparent" colored="false" width="126">Turn all numerical columns (not integers though) into real columns.</description>
</operator>
<connect from_port="in 1" to_op="Remove Dates" to_port="example set input"/>
<connect from_op="Remove Dates" 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="Text to Nominal" to_port="example set input"/>
<connect from_op="Text to Nominal" from_port="example set output" to_op="Numerical to Real" to_port="example set input"/>
<connect from_op="Numerical to Real" from_port="example set output" to_port="out 1"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="source_in 2" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
</process>
<description align="center" color="transparent" colored="false" width="126">Unify all value types</description>
</operator>
<connect from_port="in 1" to_op="Define Target?" to_port="input 1"/>
<connect from_op="Define Target?" from_port="output 1" to_op="Should Discretize?" to_port="input 1"/>
<connect from_op="Should Discretize?" from_port="output 1" to_op="Map Values?" to_port="input 1"/>
<connect from_op="Map Values?" from_port="output 1" to_op="Positive Class?" to_port="input 1"/>
<connect from_op="Positive Class?" from_port="output 1" to_op="Remove Columns?" to_port="input 1"/>
<connect from_op="Remove Columns?" from_port="output 1" to_op="Unify Value Types" to_port="in 1"/>
<connect from_op="Unify Value Types" from_port="out 1" to_port="out 1"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="source_in 2" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
</process>
<description align="center" color="transparent" colored="false" width="126">All general preprocessing steps happen inside this operator - double click on it to see the details.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="subprocess" compatibility="8.2.000" expanded="true" height="82" name="Replace Missing Values" width="90" x="313" y="238">
<process expanded="true">
<operator activated="true" automodel="EXPORTED" class="generate_attributes" compatibility="8.2.000" expanded="true" height="82" name="Generate Dummy" width="90" x="45" y="34">
<list key="function_descriptions">
<parameter key="DUMMY_NOMINAL_ATTRIBUTE_TO_DELETE" value=""dummy""/>
</list>
<parameter key="keep_all" value="true"/>
<description align="center" color="transparent" colored="false" width="126">Add a dummy nominal attribute to make sure that the loop will always deliver a result.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="concurrency:loop_attributes" compatibility="8.2.000" expanded="true" height="82" name="Loop Nominal Attributes" width="90" x="179" y="34">
<parameter key="attribute_filter_type" value="value_type"/>
<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="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="attribute_name_macro" value="nominal_attribute"/>
<parameter key="reuse_results" value="true"/>
<parameter key="enable_parallel_execution" value="true"/>
<process expanded="true">
<operator activated="true" automodel="EXPORTED" class="extract_macro" compatibility="8.2.000" expanded="true" height="68" name="Calculate No of Missings" width="90" x="45" y="34">
<parameter key="macro" value="no_missings"/>
<parameter key="macro_type" value="statistics"/>
<parameter key="statistics" value="unknown"/>
<parameter key="attribute_name" value="%{nominal_attribute}"/>
<list key="additional_macros"/>
<description align="center" color="transparent" colored="false" width="126">Calculate the number of missing values for this nominal attribute.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="branch" compatibility="8.2.000" expanded="true" height="103" name="Branch" width="90" x="179" y="34">
<parameter key="condition_type" value="expression"/>
<parameter key="expression" value="eval(%{no_missings})==0"/>
<parameter key="io_object" value="ANOVAMatrix"/>
<parameter key="return_inner_output" value="true"/>
<process expanded="true">
<connect from_port="input 1" to_port="input 1"/>
<portSpacing port="source_condition" spacing="0"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_input 1" spacing="0"/>
<portSpacing port="sink_input 2" spacing="0"/>
</process>
<process expanded="true">
<operator activated="true" automodel="EXPORTED" class="replace_missing_values" compatibility="8.2.000" expanded="true" height="103" name="Replace Nominal Missings" width="90" x="112" y="34">
<parameter key="return_preprocessing_model" value="false"/>
<parameter key="create_view" value="false"/>
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="%{nominal_attribute}"/>
<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="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="default" value="value"/>
<list key="columns"/>
<parameter key="replenishment_value" value="MISSING"/>
<description align="center" color="transparent" colored="false" width="126">Replace nominal missings with the word 'missing'.</description>
</operator>
<connect from_port="input 1" to_op="Replace Nominal Missings" to_port="example set input"/>
<connect from_op="Replace Nominal Missings" from_port="example set output" to_port="input 1"/>
<portSpacing port="source_condition" spacing="0"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_input 1" spacing="0"/>
<portSpacing port="sink_input 2" spacing="0"/>
</process>
<description align="center" color="transparent" colored="false" width="126">Only replace missings if there are actually any missings.</description>
</operator>
<connect from_port="input 1" to_op="Calculate No of Missings" to_port="example set"/>
<connect from_op="Calculate No of Missings" from_port="example set" to_op="Branch" to_port="input 1"/>
<connect from_op="Branch" from_port="input 1" to_port="output 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
<description align="center" color="transparent" colored="false" width="126">Loop over all nominal attributes.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="select_attributes" compatibility="8.2.000" expanded="true" height="82" name="Remove Dummy" width="90" x="313" y="34">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="DUMMY_NOMINAL_ATTRIBUTE_TO_DELETE"/>
<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="true"/>
<parameter key="include_special_attributes" value="false"/>
<description align="center" color="transparent" colored="false" width="126">Remove dummy attribute again.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="replace_infinite_values" compatibility="8.2.000" expanded="true" height="103" name="Replace Pos Infinite Values" width="90" x="447" y="34">
<parameter key="return_preprocessing_model" value="false"/>
<parameter key="create_view" value="false"/>
<parameter key="attribute_filter_type" value="value_type"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="numeric"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="real"/>
<parameter key="block_type" value="value_series"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_series_end"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="true"/>
<parameter key="default" value="missing"/>
<list key="columns"/>
<parameter key="replenish_what" value="positive_infinity"/>
<description align="center" color="transparent" colored="false" width="126">Replace positive infinity values by missing.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="replace_infinite_values" compatibility="8.2.000" expanded="true" height="103" name="Replace Neg Infinite Values" width="90" x="581" y="34">
<parameter key="return_preprocessing_model" value="false"/>
<parameter key="create_view" value="false"/>
<parameter key="attribute_filter_type" value="value_type"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="numeric"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="real"/>
<parameter key="block_type" value="value_series"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="value_series_end"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="true"/>
<parameter key="default" value="missing"/>
<list key="columns"/>
<parameter key="replenish_what" value="negative_infinity"/>
<description align="center" color="transparent" colored="false" width="126">Replace negative infinity values by missing.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="replace_missing_values" compatibility="8.2.000" expanded="true" height="103" name="Replace Numerical Missings" width="90" x="715" y="34">
<parameter key="return_preprocessing_model" value="false"/>
<parameter key="create_view" value="false"/>
<parameter key="attribute_filter_type" value="value_type"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="numeric"/>
<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="default" value="average"/>
<list key="columns"/>
<description align="center" color="transparent" colored="false" width="126">Replace numerical missings with the average of the column.</description>
</operator>
<connect from_port="in 1" to_op="Generate Dummy" to_port="example set input"/>
<connect from_op="Generate Dummy" from_port="example set output" to_op="Loop Nominal Attributes" to_port="input 1"/>
<connect from_op="Loop Nominal Attributes" from_port="output 1" to_op="Remove Dummy" to_port="example set input"/>
<connect from_op="Remove Dummy" from_port="example set output" to_op="Replace Pos Infinite Values" to_port="example set input"/>
<connect from_op="Replace Pos Infinite Values" from_port="example set output" to_op="Replace Neg Infinite Values" to_port="example set input"/>
<connect from_op="Replace Neg Infinite Values" from_port="example set output" to_op="Replace Numerical Missings" to_port="example set input"/>
<connect from_op="Replace Numerical Missings" from_port="example set output" to_port="out 1"/>
<portSpacing port="source_in 1" spacing="0"/>
<portSpacing port="source_in 2" spacing="0"/>
<portSpacing port="sink_out 1" spacing="0"/>
<portSpacing port="sink_out 2" spacing="0"/>
</process>
<description align="center" color="transparent" colored="false" width="126">Replace missing values.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="order_attributes" compatibility="8.2.000" expanded="true" height="82" name="Reorder Attributes" width="90" x="447" y="238">
<parameter key="sort_mode" value="alphabetically"/>
<parameter key="attribute_ordering" value=""/>
<parameter key="use_regular_expressions" value="false"/>
<parameter key="handle_unmatched" value="append"/>
<parameter key="sort_direction" value="ascending"/>
<description align="center" color="transparent" colored="false" width="126">Order columns alphabetically.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="filter_examples" compatibility="8.2.000" expanded="true" height="103" name="Filter Examples" width="90" x="581" y="238">
<parameter key="parameter_expression" value=""/>
<parameter key="condition_class" value="no_missing_labels"/>
<parameter key="invert_filter" value="false"/>
<list key="filters_list"/>
<parameter key="filters_logic_and" value="true"/>
<parameter key="filters_check_metadata" value="true"/>
<description align="center" color="transparent" colored="false" width="126">Model on cases with label value, apply the model on cases with a missing for the target column.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="sample_stratified" compatibility="8.2.000" expanded="true" height="82" name="Sample (Stratified)" width="90" x="715" y="136">
<parameter key="sample" value="absolute"/>
<parameter key="sample_size" value="60000"/>
<parameter key="sample_ratio" value="0.1"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
<description align="center" color="transparent" colored="false" width="126">Sample down to 60,000 examples in case there are more.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="split_data" compatibility="8.2.000" expanded="true" height="103" name="Split Data" width="90" x="849" y="136">
<enumeration key="partitions">
<parameter key="ratio" value="0.8"/>
<parameter key="ratio" value="0.2"/>
</enumeration>
<parameter key="sampling_type" value="automatic"/>
<parameter key="use_local_random_seed" value="true"/>
<parameter key="local_random_seed" value="1992"/>
<description align="center" color="transparent" colored="false" width="126">Split of a validation set.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="multiply" compatibility="8.2.000" expanded="true" height="124" name="Multiply Training" width="90" x="983" y="136">
<description align="center" color="transparent" colored="false" width="126">Copy data for simulator.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="concurrency:optimize_parameters_grid" compatibility="8.2.000" expanded="true" height="124" name="Optimize Parameters (Grid)" width="90" x="1117" y="34">
<list key="parameters">
<parameter key="Gradient Boosted Trees.number_of_trees" value="[20;140;3;linear]"/>
<parameter key="Gradient Boosted Trees.maximal_depth" value="2,4,7"/>
</list>
<parameter key="error_handling" value="fail on error"/>
<parameter key="log_performance" value="false"/>
<parameter key="log_all_criteria" value="false"/>
<parameter key="synchronize" value="false"/>
<parameter key="enable_parallel_execution" value="true"/>
<process expanded="true">
<operator activated="true" automodel="EXPORTED" class="concurrency:cross_validation" compatibility="8.2.000" expanded="true" height="145" name="Cross Validation" width="90" x="45" y="34">
<parameter key="split_on_batch_attribute" value="false"/>
<parameter key="leave_one_out" value="false"/>
<parameter key="number_of_folds" value="3"/>
<parameter key="sampling_type" value="automatic"/>
<parameter key="use_local_random_seed" value="true"/>
<parameter key="local_random_seed" value="1992"/>
<parameter key="enable_parallel_execution" value="true"/>
<process expanded="true">
<operator activated="true" automodel="EXPORTED" class="h2o:gradient_boosted_trees" compatibility="8.2.000" expanded="true" height="103" name="Gradient Boosted Trees" width="90" x="45" y="34">
<parameter key="number_of_trees" value="20"/>
<parameter key="reproducible" value="true"/>
<parameter key="maximum_number_of_threads" value="1"/>
<parameter key="use_local_random_seed" value="true"/>
<parameter key="local_random_seed" value="1992"/>
<parameter key="maximal_depth" value="5"/>
<parameter key="min_rows" value="10.0"/>
<parameter key="min_split_improvement" value="0.0"/>
<parameter key="number_of_bins" value="20"/>
<parameter key="learning_rate" value="0.1"/>
<parameter key="sample_rate" value="1.0"/>
<parameter key="distribution" value="AUTO"/>
<parameter key="early_stopping" value="false"/>
<parameter key="stopping_rounds" value="1"/>
<parameter key="stopping_metric" value="AUTO"/>
<parameter key="stopping_tolerance" value="0.001"/>
<parameter key="max_runtime_seconds" value="0"/>
<list key="expert_parameters"/>
</operator>
<connect from_port="training set" to_op="Gradient Boosted Trees" to_port="training set"/>
<connect from_op="Gradient Boosted Trees" 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" automodel="EXPORTED" class="apply_model" compatibility="8.2.000" 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" automodel="EXPORTED" class="performance_binominal_classification" compatibility="8.2.000" expanded="true" height="82" name="Inner Performance" width="90" x="179" y="34">
<parameter key="main_criterion" value="accuracy"/>
<parameter key="accuracy" value="true"/>
<parameter key="classification_error" value="true"/>
<parameter key="kappa" value="false"/>
<parameter key="AUC (optimistic)" value="false"/>
<parameter key="AUC" value="true"/>
<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="true"/>
<parameter key="specificity" value="true"/>
<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="Inner Performance" to_port="labelled data"/>
<connect from_op="Inner 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>
<description align="center" color="transparent" colored="false" width="126">Cross-validate the model and build final model on complete data.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="log" compatibility="8.2.000" expanded="true" height="82" name="Log Performances" width="90" x="179" y="85">
<list key="log">
<parameter key="Number of Trees" value="operator.Gradient Boosted Trees.parameter.number_of_trees"/>
<parameter key="Maximal Depth" value="operator.Gradient Boosted Trees.parameter.maximal_depth"/>
<parameter key="Performance" value="operator.Cross Validation.value.performance main criterion"/>
</list>
<parameter key="sorting_type" value="none"/>
<parameter key="sorting_k" value="100"/>
<parameter key="persistent" value="false"/>
<description align="center" color="transparent" colored="false" width="126">Log the performance for all parameter combinations.</description>
</operator>
<connect from_port="input 1" to_op="Cross Validation" to_port="example set"/>
<connect from_op="Cross Validation" from_port="model" to_port="model"/>
<connect from_op="Cross Validation" from_port="performance 1" to_op="Log Performances" to_port="through 1"/>
<connect from_op="Log Performances" from_port="through 1" to_port="performance"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="source_input 2" spacing="0"/>
<portSpacing port="sink_performance" spacing="0"/>
<portSpacing port="sink_model" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
</process>
<description align="center" color="transparent" colored="false" width="126">Find optimal parameters.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="multiply" compatibility="8.2.000" expanded="true" height="124" name="Multiply Validation" width="90" x="983" y="340">
<description align="center" color="transparent" colored="false" width="126">Copy validation data.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="model_simulator:model_simulator" compatibility="8.2.000" expanded="true" height="103" name="Model Simulator" width="90" x="1318" y="34">
<description align="center" color="transparent" colored="false" width="126">Create model simulator.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="multiply" compatibility="8.2.000" expanded="true" height="124" name="Multiply Model" width="90" x="1452" y="187">
<description align="center" color="transparent" colored="false" width="126">Copy model.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="apply_model" compatibility="8.2.000" expanded="true" height="82" name="Apply Optimized Model" width="90" x="1586" y="85">
<list key="application_parameters"/>
<parameter key="create_view" value="false"/>
<description align="center" color="transparent" colored="false" width="126">Apply optimized model on validation set.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="performance_binominal_classification" compatibility="8.2.000" expanded="true" height="82" name="Performance" width="90" x="1720" y="34">
<parameter key="main_criterion" value="accuracy"/>
<parameter key="accuracy" value="true"/>
<parameter key="classification_error" value="true"/>
<parameter key="kappa" value="false"/>
<parameter key="AUC (optimistic)" value="false"/>
<parameter key="AUC" value="true"/>
<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="true"/>
<parameter key="specificity" value="true"/>
<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"/>
<description align="center" color="transparent" colored="false" width="126">Performance on validation set.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="model_simulator:explain_predictions" compatibility="8.2.000" expanded="true" height="103" name="Explain Predictions" width="90" x="1586" y="289">
<parameter key="maximal explaining attributes" value="3"/>
<parameter key="local sample size" value="500"/>
<description align="center" color="transparent" colored="false" width="126">Create predictions for cases without value and add explanations for predictions.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="log_to_data" compatibility="8.2.000" expanded="true" height="82" name="Log to Data" width="90" x="1586" y="697">
<parameter key="log_name" value="Log Performances"/>
<description align="center" color="transparent" colored="false" width="126">Deliver all performances.</description>
</operator>
<operator activated="true" automodel="EXPORTED" class="model_simulator:lift_chart" compatibility="8.2.000" expanded="true" height="82" name="Create Lift Chart" width="90" x="1586" y="544">
<parameter key="target class" value="Positive"/>
<description align="center" color="transparent" colored="false" width="126">Create lift chart.</description>
</operator>
<connect from_op="Retrieve Data" from_port="output" to_op="Preprocessing" to_port="in 1"/>
<connect from_op="Preprocessing" from_port="out 1" to_op="Replace Missing Values" to_port="in 1"/>
<connect from_op="Replace Missing Values" from_port="out 1" to_op="Reorder Attributes" to_port="example set input"/>
<connect from_op="Reorder Attributes" from_port="example set output" to_op="Filter Examples" to_port="example set input"/>
<connect from_op="Filter Examples" from_port="example set output" to_op="Sample (Stratified)" to_port="example set input"/>
<connect from_op="Filter Examples" from_port="unmatched example set" to_op="Explain Predictions" to_port="test data"/>
<connect from_op="Sample (Stratified)" from_port="example set output" to_op="Split Data" to_port="example set"/>
<connect from_op="Split Data" from_port="partition 1" to_op="Multiply Training" to_port="input"/>
<connect from_op="Split Data" from_port="partition 2" to_op="Multiply Validation" to_port="input"/>
<connect from_op="Multiply Training" from_port="output 1" to_op="Optimize Parameters (Grid)" to_port="input 1"/>
<connect from_op="Multiply Training" from_port="output 2" to_op="Model Simulator" to_port="training data"/>
<connect from_op="Multiply Training" from_port="output 3" to_op="Explain Predictions" to_port="training data"/>
<connect from_op="Optimize Parameters (Grid)" from_port="model" to_op="Model Simulator" to_port="model"/>
<connect from_op="Optimize Parameters (Grid)" from_port="parameter set" to_port="result 2"/>
<connect from_op="Multiply Validation" from_port="output 1" to_op="Model Simulator" to_port="test data"/>
<connect from_op="Multiply Validation" from_port="output 2" to_op="Create Lift Chart" to_port="test data"/>
<connect from_op="Multiply Validation" from_port="output 3" to_op="Apply Optimized Model" to_port="unlabelled data"/>
<connect from_op="Model Simulator" from_port="simulator output" to_port="result 3"/>
<connect from_op="Model Simulator" from_port="model output" to_op="Multiply Model" to_port="input"/>
<connect from_op="Multiply Model" from_port="output 1" to_op="Apply Optimized Model" to_port="model"/>
<connect from_op="Multiply Model" from_port="output 2" to_op="Explain Predictions" to_port="model"/>
<connect from_op="Multiply Model" from_port="output 3" to_op="Create Lift Chart" to_port="model"/>
<connect from_op="Apply Optimized Model" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
<connect from_op="Apply Optimized Model" from_port="model" to_port="result 4"/>
<connect from_op="Performance" from_port="performance" to_port="result 1"/>
<connect from_op="Explain Predictions" from_port="visualization output" to_port="result 5"/>
<connect from_op="Explain Predictions" from_port="example set output" to_port="result 6"/>
<connect from_op="Log to Data" from_port="exampleSet" to_port="result 8"/>
<connect from_op="Create Lift Chart" from_port="lift chart" to_port="result 7"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="42"/>
<portSpacing port="sink_result 3" spacing="0"/>
<portSpacing port="sink_result 4" spacing="0"/>
<portSpacing port="sink_result 5" spacing="84"/>
<portSpacing port="sink_result 6" spacing="0"/>
<portSpacing port="sink_result 7" spacing="252"/>
<portSpacing port="sink_result 8" spacing="84"/>
<portSpacing port="sink_result 9" spacing="0"/>
<description align="left" color="yellow" colored="false" height="175" resized="true" width="481" x="372" y="477">Results:<br>1. Performance from validation set (split off before parameter optimization)<br>2. Optimal parameters<br>3. Model simulator<br>4. Model<br>5. Predicted data with explanations viz (only if the data had missing labels)<br>6. Predicted data with explanations table (only if the data had missing labels)<br>7. Lift chart<br>8. All performances from 3-fold cross-validation in parameter optimization</description>
</process>
</operator>
</process>How can I check performance for testing dataset from Auto Model process?
0