Process freezes in the optimization operator

anaRodriguesanaRodrigues Member Posts: 33 Contributor II
edited May 2021 in Help
Hi, 

My process starts logging the same sentence over and over again. Sometimes this happens at 20% optimization, sometimes at 30% and sometimes at 99%, which is extremely annoying after hours of waiting for it to finish. Here are the log entries:

May 7, 2021 12:40:02 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.6931 imp=.1E1 bdf=.0E0
May 7, 2021 12:40:04 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.6928 imp=.1E1 bdf=.56E-1
May 7, 2021 12:40:06 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.693 imp=.1E1 bdf=.28E-1
May 7, 2021 12:40:07 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.6931 imp=.1E1 bdf=.0E0
May 7, 2021 12:40:09 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.6928 imp=.1E1 bdf=.56E-1
May 7, 2021 12:40:11 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.693 imp=.1E1 bdf=.28E-1
May 7, 2021 12:40:12 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.6931 imp=.1E1 bdf=.0E0
May 7, 2021 12:40:14 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.6928 imp=.1E1 bdf=.56E-1
May 7, 2021 12:40:16 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.693 imp=.1E1 bdf=.28E-1
May 7, 2021 12:40:17 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.6931 imp=.1E1 bdf=.0E0
May 7, 2021 12:40:19 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.6928 imp=.1E1 bdf=.56E-1
May 7, 2021 12:40:21 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.693 imp=.1E1 bdf=.28E-1
May 7, 2021 12:40:22 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.6931 imp=.1E1 bdf=.0E0
May 7, 2021 12:40:24 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.6928 imp=.1E1 bdf=.56E-1
May 7, 2021 12:40:26 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.693 imp=.1E1 bdf=.28E-1
May 7, 2021 12:40:27 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.6931 imp=.1E1 bdf=.0E0
May 7, 2021 12:40:29 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.6928 imp=.1E1 bdf=.56E-1
May 7, 2021 12:40:31 PM INFO: H2O: 2% - iter=0 lmb=.0E0 obj=0.693 imp=.1E1 bdf=.28E-1

This only seems to happen when I'm optimizing a logistics regression model. Please help me, I don't know what to do.  Here is my process.

Thank you,
Ana

<?xml version="1.0" encoding="UTF-8"?><process version="9.9.000">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.9.000" 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="false" class="read_csv" compatibility="9.9.000" expanded="true" height="68" name="Read train" width="90" x="45" y="340">
        <parameter key="csv_file" value="C:/Users/ASUS/Documents/Mestrado BBC/tese/4. Feature Extraction/Lesion_data/lesion_trainSet.csv"/>
        <parameter key="column_separators" value=","/>
        <parameter key="trim_lines" value="false"/>
        <parameter key="use_quotes" value="true"/>
        <parameter key="quotes_character" value="&quot;"/>
        <parameter key="escape_character" value="\"/>
        <parameter key="skip_comments" value="false"/>
        <parameter key="comment_characters" value="#"/>
        <parameter key="starting_row" value="1"/>
        <parameter key="parse_numbers" value="true"/>
        <parameter key="decimal_character" value="."/>
        <parameter key="grouped_digits" value="false"/>
        <parameter key="grouping_character" value=","/>
        <parameter key="infinity_representation" value=""/>
        <parameter key="date_format" value=""/>
        <parameter key="first_row_as_names" value="true"/>
        <list key="annotations"/>
        <parameter key="time_zone" value="SYSTEM"/>
        <parameter key="locale" value="English (United States)"/>
        <parameter key="encoding" value="SYSTEM"/>
        <parameter key="read_all_values_as_polynominal" value="false"/>
        <list key="data_set_meta_data_information"/>
        <parameter key="read_not_matching_values_as_missings" value="true"/>
      </operator>
      <operator activated="false" class="read_csv" compatibility="9.9.000" expanded="true" height="68" name="Read rad1" width="90" x="45" y="136">
        <parameter key="csv_file" value="C:/Users/ASUS/Documents/Mestrado BBC/tese/4. Feature Extraction/Lesion_data/lesion_rad1_features.csv"/>
        <parameter key="column_separators" value=","/>
        <parameter key="trim_lines" value="false"/>
        <parameter key="use_quotes" value="true"/>
        <parameter key="quotes_character" value="&quot;"/>
        <parameter key="escape_character" value="\"/>
        <parameter key="skip_comments" value="false"/>
        <parameter key="comment_characters" value="#"/>
        <parameter key="starting_row" value="1"/>
        <parameter key="parse_numbers" value="true"/>
        <parameter key="decimal_character" value="."/>
        <parameter key="grouped_digits" value="false"/>
        <parameter key="grouping_character" value=","/>
        <parameter key="infinity_representation" value=""/>
        <parameter key="date_format" value=""/>
        <parameter key="first_row_as_names" value="true"/>
        <list key="annotations"/>
        <parameter key="time_zone" value="SYSTEM"/>
        <parameter key="locale" value="English (United States)"/>
        <parameter key="encoding" value="SYSTEM"/>
        <parameter key="read_all_values_as_polynominal" value="false"/>
        <list key="data_set_meta_data_information"/>
        <parameter key="read_not_matching_values_as_missings" value="true"/>
      </operator>
      <operator activated="false" class="read_csv" compatibility="9.9.000" expanded="true" height="68" name="Read rad2" width="90" x="45" y="238">
        <parameter key="csv_file" value="C:/Users/ASUS/Documents/Mestrado BBC/tese/4. Feature Extraction/Lesion_data/lesion_rad2_features.csv"/>
        <parameter key="column_separators" value=","/>
        <parameter key="trim_lines" value="false"/>
        <parameter key="use_quotes" value="true"/>
        <parameter key="quotes_character" value="&quot;"/>
        <parameter key="escape_character" value="\"/>
        <parameter key="skip_comments" value="false"/>
        <parameter key="comment_characters" value="#"/>
        <parameter key="starting_row" value="1"/>
        <parameter key="parse_numbers" value="true"/>
        <parameter key="decimal_character" value="."/>
        <parameter key="grouped_digits" value="false"/>
        <parameter key="grouping_character" value=","/>
        <parameter key="infinity_representation" value=""/>
        <parameter key="date_format" value=""/>
        <parameter key="first_row_as_names" value="true"/>
        <list key="annotations"/>
        <parameter key="time_zone" value="SYSTEM"/>
        <parameter key="locale" value="English (United States)"/>
        <parameter key="encoding" value="SYSTEM"/>
        <parameter key="read_all_values_as_polynominal" value="false"/>
        <list key="data_set_meta_data_information"/>
        <parameter key="read_not_matching_values_as_missings" value="true"/>
      </operator>
      <operator activated="false" class="python_scripting:execute_python" compatibility="9.8.000" expanded="true" height="145" name="Stability analysis" width="90" x="179" y="187">
        <parameter key="script" value="import pandas as pd&#10;import re&#10;def icc(ratings, model='twoway', type='agreement', unit='single', confidence_level=0.95):&#10;    import numpy as np&#10;    from scipy.stats import f&#10;    &#10;    ratings = np.asarray(ratings)&#10;&#10;    if (model, type, unit) not in {('oneway', 'agreement', 'single'),&#10;                                   ('twoway', 'agreement', 'single'),&#10;                                   ('twoway', 'consistency', 'single'),&#10;                                   ('oneway', 'agreement', 'average'),&#10;                                   ('twoway', 'agreement', 'average'),&#10;                                   ('twoway', 'consistency', 'average'), }:&#10;        raise ValueError('Using not implemented configuration.')&#10;&#10;    n_subjects, n_raters = ratings.shape&#10;    if n_subjects &lt; 1:&#10;        raise ValueError('Using one subject only. Add more subjects to calculate ICC.')&#10;    #print(&quot;Ratings:&quot;, ratings)&#10;    #print(&quot;n_subjects:&quot;, n_subjects)&#10;    #print(&quot;n_raters:&quot;, n_raters)&#10;    SStotal = np.var(ratings, ddof=1) * (n_subjects * n_raters - 1)&#10;    alpha = 1 - confidence_level&#10;&#10;    MSr = np.var(np.mean(ratings, axis=1), ddof=1) * n_raters&#10;    MSw = np.sum(np.var(ratings, axis=1, ddof=1) / n_subjects)&#10;    MSc = np.var(np.mean(ratings, axis=0), ddof=1) * n_subjects&#10;    MSe = (SStotal - MSr * (n_subjects - 1) - MSc * (n_raters - 1)) / ((n_subjects - 1) * (n_raters - 1))&#10;&#10;    # Single Score ICCs&#10;    if unit == 'single':&#10;        if model == 'oneway':&#10;            # ICC(1,1) One-Way Random, absolute&#10;            coeff = (MSr - MSw) / (MSr + (n_raters - 1) * MSw)&#10;            Fvalue = MSr / MSw&#10;            df1 = n_subjects - 1&#10;            df2 = n_subjects * (n_raters - 1)&#10;            pvalue = 1 - f.cdf(Fvalue, df1, df2)&#10;&#10;            # Confidence interval&#10;            FL = Fvalue / f.ppf(1 - alpha, df1, df2)&#10;            FU = Fvalue * f.ppf(1 - alpha, df2, df1)&#10;            lbound = (FL - 1) / (FL + (n_raters - 1))&#10;            ubound = (FU - 1) / (FU + (n_raters - 1))&#10;&#10;        elif model == 'twoway':&#10;            if type == 'agreement':&#10;                # ICC(2,1) Two-Way Random, absolute&#10;                coeff = (MSr - MSe) / (MSr + (n_raters - 1) * MSe + (n_raters / n_subjects) * (MSc - MSe))&#10;                Fvalue = MSr / MSe&#10;                df1 = n_subjects - 1&#10;                df2 = (n_subjects - 1) * (n_raters - 1)&#10;                pvalue = 1 - f.cdf(Fvalue, df1, df2)&#10;&#10;                # Confidence interval&#10;                Fj = MSc / MSe&#10;                vn = (n_raters - 1) * (n_subjects - 1) * (&#10;                    (n_raters * coeff * Fj + n_subjects * (1 + (n_raters - 1) * coeff) - n_raters * coeff)) ** 2&#10;                vd = (n_subjects - 1) * n_raters ** 2 * coeff ** 2 * Fj ** 2 + (&#10;                        n_subjects * (1 + (n_raters - 1) * coeff) - n_raters * coeff) ** 2&#10;                v = vn / vd&#10;&#10;                FL = f.ppf(1 - alpha, n_subjects - 1, v)&#10;                FU = f.ppf(1 - alpha, v, n_subjects - 1)&#10;                lbound = (n_subjects * (MSr - FL * MSe)) / (FL * (&#10;                        n_raters * MSc + (n_raters * n_subjects - n_raters - n_subjects) * MSe) + n_subjects * MSr)&#10;                ubound = (n_subjects * (FU * MSr - MSe)) / (n_raters * MSc + (&#10;                        n_raters * n_subjects - n_raters - n_subjects) * MSe + n_subjects * FU * MSr)&#10;&#10;            elif type == 'consistency':&#10;                # ICC(3,1) Two-Way Mixed, consistency&#10;                coeff = (MSr - MSe) / (MSr + (n_raters - 1) * MSe)&#10;                Fvalue = MSr / MSe&#10;                df1 = n_subjects - 1&#10;                df2 = (n_subjects - 1) * (n_raters - 1)&#10;                pvalue = 1 - f.cdf(Fvalue, df1, df2)&#10;&#10;                # Confidence interval&#10;                FL = Fvalue / f.ppf(1 - alpha, df1, df2)&#10;                FU = Fvalue * f.ppf(1 - alpha, df2, df1)&#10;                lbound = (FL - 1) / (FL + (n_raters - 1))&#10;                ubound = (FU - 1) / (FU + (n_raters - 1))&#10;&#10;    elif unit == 'average':&#10;        if model == 'oneway':&#10;            # ICC(1,k) One-Way Random, absolute&#10;            coeff = (MSr - MSw) / MSr&#10;            Fvalue = MSr / MSw&#10;            df1 = n_subjects - 1&#10;            df2 = n_subjects * (n_raters - 1)&#10;            pvalue = 1 - f.cdf(Fvalue, df1, df2)&#10;&#10;            # Confidence interval&#10;            FL = (MSr / MSw) / f.ppf(1 - alpha, df1, df2)&#10;            FU = (MSr / MSw) * f.ppf(1 - alpha, df2, df1)&#10;            lbound = 1 - 1 / FL&#10;            ubound = 1 - 1 / FU&#10;&#10;        elif model == 'twoway':&#10;            if type == 'agreement':&#10;                # ICC(2,k) Two-Way Random, absolute&#10;                coeff = (MSr - MSe) / (MSr + (MSc - MSe) / n_subjects)&#10;                Fvalue = MSr / MSe&#10;                df1 = n_subjects - 1&#10;                df2 = (n_subjects - 1) * (n_raters - 1)&#10;                pvalue = 1 - f.cdf(Fvalue, df1, df2)&#10;&#10;                # Confidence interval&#10;                icc2 = (MSr - MSe) / (MSr + (n_raters - 1) * MSe + (n_raters / n_subjects) * (MSc - MSe))&#10;                Fj = MSc / MSe&#10;                vn = (n_raters - 1) * (n_subjects - 1) * (&#10;                    (n_raters * icc2 * Fj + n_subjects * (1 + (n_raters - 1) * icc2) - n_raters * icc2)) ** 2&#10;                vd = (n_subjects - 1) * n_raters ** 2 * icc2 ** 2 * Fj ** 2 + (&#10;                        n_subjects * (1 + (n_raters - 1) * icc2) - n_raters * icc2) ** 2&#10;                v = vn / vd&#10;&#10;                FL = f.ppf(1 - alpha, n_subjects - 1, v)&#10;                FU = f.ppf(1 - alpha, v, n_subjects - 1)&#10;                lb2 = (n_subjects * (MSr - FL * MSe)) / (FL * (&#10;                        n_raters * MSc + (n_raters * n_subjects - n_raters - n_subjects) * MSe) + n_subjects * MSr)&#10;                ub2 = (n_subjects * (FU * MSr - MSe)) / (n_raters * MSc + (&#10;                        n_raters * n_subjects - n_raters - n_subjects) * MSe + n_subjects * FU * MSr)&#10;                lbound = lb2 * n_raters / (1 + lb2 * (n_raters - 1))&#10;                ubound = ub2 * n_raters / (1 + ub2 * (n_raters - 1))&#10;&#10;            elif type == 'consistency':&#10;                # ICC(3,k) Two-Way Mixed, consistency&#10;                coeff = (MSr - MSe) / MSr&#10;                Fvalue = MSr / MSe&#10;                df1 = n_subjects - 1&#10;                df2 = (n_subjects - 1) * (n_raters - 1)&#10;                pvalue = 1 - f.cdf(Fvalue, df1, df2)&#10;&#10;                # Confidence interval&#10;                FL = Fvalue / f.ppf(1 - alpha, df1, df2)&#10;                FU = Fvalue * f.ppf(1 - alpha, df2, df1)&#10;                lbound = 1 - 1 / FL&#10;                ubound = 1 - 1 / FU&#10;&#10;    return coeff, Fvalue, df1, df2, pvalue, lbound, ubound&#10;&#10;def rm_main(rad1, rad2, train):&#10;    patientIDs = list(train['ID'])&#10;    rad1_p = list(rad1['ID'])&#10;    rad2_p = list(rad2['ID'])&#10;    both_rad = [value for value in rad1_p if value in rad2_p]&#10;    both_rad = [value for value in both_rad if value in patientIDs]&#10;    rad1 = rad1.set_index('ID')&#10;    rad2 = rad2.set_index('ID')&#10;    df_rad1 = rad1.loc[both_rad, :]&#10;    df_rad2 = rad2.loc[both_rad, :]&#10;    feature_names = df_rad1.columns[1:-1]&#10;    robustness_analysis = {}&#10;    for i in feature_names:&#10;        a = df_rad1[i]&#10;        b = df_rad2[i]&#10;        features = pd.concat([a, b], axis=1)&#10;        d = {}&#10;        coeff, Fvalue, df1, df2, pvalue, lbound, ubound = icc(features)&#10;        d['coeff'] = coeff&#10;        d['Fvalue'] = Fvalue&#10;        d['df1'] = df1&#10;        d['df2'] = df2&#10;        d['pvalue'] = pvalue&#10;        d['lbound'] = lbound&#10;        d['ubound'] = ubound&#10;        robustness_analysis[i] = d&#10;    robust = pd.DataFrame(robustness_analysis, columns = robustness_analysis.keys(), index = ['coeff', 'Fvalue', 'df1', 'df2', 'pvalue', 'lbound', 'ubound'])&#10;    not_keep = list(robust.loc['lbound'] &lt;= 0.8)&#10;    features_to_eliminate = feature_names[not_keep]&#10;    elm = list(features_to_eliminate)&#10;    for col in train.columns:&#10;        if col in elm:&#10;            del train[col]&#10;    print(&quot;Number of patients used in the stability analysis:&quot;, len(both_rad))&#10;    print(&quot;Number of features eliminated:&quot;, len(elm))&#10;    t = 0&#10;    d = 0&#10;    a = 0&#10;    for i in list(features_to_eliminate):&#10;        if re.search('T2W', i):&#10;            t += 1&#10;        elif re.search('DWI', i):&#10;            d += 1&#10;        elif re.search('ADC', i):&#10;            a +=  1&#10;    print('T2W:', t)&#10;    print('DWI:', d)&#10;    print('ADC:', a)&#10;    return train"/>
        <parameter key="notebook_cell_tag_filter" value=""/>
        <parameter key="use_default_python" value="true"/>
        <parameter key="package_manager" value="conda (anaconda)"/>
        <parameter key="use_macros" value="false"/>
      </operator>
      <operator activated="true" class="read_csv" compatibility="9.9.000" expanded="true" height="68" name="Read train (2)" width="90" x="45" y="34">
        <parameter key="csv_file" value="C:/Users/ASUS/Documents/Mestrado BBC/tese/4. Feature Extraction/Gland_data/gland_trainSet_stable.csv"/>
        <parameter key="column_separators" value=","/>
        <parameter key="trim_lines" value="false"/>
        <parameter key="use_quotes" value="true"/>
        <parameter key="quotes_character" value="&quot;"/>
        <parameter key="escape_character" value="\"/>
        <parameter key="skip_comments" value="false"/>
        <parameter key="comment_characters" value="#"/>
        <parameter key="starting_row" value="1"/>
        <parameter key="parse_numbers" value="true"/>
        <parameter key="decimal_character" value="."/>
        <parameter key="grouped_digits" value="false"/>
        <parameter key="grouping_character" value=","/>
        <parameter key="infinity_representation" value=""/>
        <parameter key="date_format" value=""/>
        <parameter key="first_row_as_names" value="true"/>
        <list key="annotations"/>
        <parameter key="time_zone" value="SYSTEM"/>
        <parameter key="locale" value="English (United States)"/>
        <parameter key="encoding" value="SYSTEM"/>
        <parameter key="read_all_values_as_polynominal" value="false"/>
        <list key="data_set_meta_data_information"/>
        <parameter key="read_not_matching_values_as_missings" value="true"/>
      </operator>
      <operator activated="true" class="filter_examples" compatibility="9.9.000" expanded="true" height="103" name="Remove missing data" width="90" x="179" y="34">
        <parameter key="parameter_expression" value=""/>
        <parameter key="condition_class" value="no_missing_attributes"/>
        <parameter key="invert_filter" value="false"/>
        <list key="filters_list"/>
        <parameter key="filters_logic_and" value="true"/>
        <parameter key="filters_check_metadata" value="true"/>
      </operator>
      <operator activated="true" class="set_role" compatibility="9.9.000" expanded="true" height="82" name="Set Role (2)" width="90" x="313" y="34">
        <parameter key="attribute_name" value="ID"/>
        <parameter key="target_role" value="id"/>
        <list key="set_additional_roles">
          <parameter key="ID" value="id"/>
          <parameter key="Target" value="label"/>
        </list>
      </operator>
      <operator activated="true" class="multiply" compatibility="9.9.000" expanded="true" height="103" name="Multiply (2)" width="90" x="447" y="34"/>
      <operator activated="true" class="sample" compatibility="9.9.000" expanded="true" height="82" name="Sample (3)" width="90" x="581" y="34">
        <parameter key="sample" value="absolute"/>
        <parameter key="balance_data" value="true"/>
        <parameter key="sample_size" value="100"/>
        <parameter key="sample_ratio" value="0.1"/>
        <parameter key="sample_probability" value="0.1"/>
        <list key="sample_size_per_class">
          <parameter key="False" value="51"/>
          <parameter key="True" value="51"/>
        </list>
        <list key="sample_ratio_per_class"/>
        <list key="sample_probability_per_class"/>
        <parameter key="use_local_random_seed" value="false"/>
        <parameter key="local_random_seed" value="1992"/>
      </operator>
      <operator activated="true" class="concurrency:optimize_parameters_grid" compatibility="9.9.000" expanded="true" height="145" name="with Downsampling" width="90" x="715" y="34">
        <list key="parameters">
          <parameter key="Remove Correlated Attributes.correlation" value="[0.4;1.0;6;linear]"/>
          <parameter key="MRMR-FS.k" value="[10;24;7;linear]"/>
          <parameter key="Logistic Regression.alpha" value="[0.0;1.0;5;linear]"/>
        </list>
        <parameter key="error_handling" value="fail on error"/>
        <parameter key="log_performance" value="true"/>
        <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" class="concurrency:cross_validation" compatibility="9.9.000" expanded="true" height="145" name="Cross Validation (2)" 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="4"/>
            <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="subprocess" compatibility="9.9.000" expanded="true" height="82" name="Remove outliers (2)" width="90" x="45" y="34">
                <process expanded="true">
                  <operator activated="true" class="multiply" compatibility="9.9.000" expanded="true" height="103" name="Multiply (3)" width="90" x="45" y="34"/>
                  <operator activated="true" class="normalize" compatibility="9.9.000" expanded="true" height="103" name="Normalize (2)" width="90" x="112" y="187">
                    <parameter key="return_preprocessing_model" value="false"/>
                    <parameter key="create_view" value="false"/>
                    <parameter key="attribute_filter_type" value="all"/>
                    <parameter key="attribute" value=""/>
                    <parameter key="attributes" value=""/>
                    <parameter key="use_except_expression" value="false"/>
                    <parameter key="value_type" value="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="false"/>
                    <parameter key="method" value="Z-transformation"/>
                    <parameter key="min" value="0.0"/>
                    <parameter key="max" value="1.0"/>
                    <parameter key="allow_negative_values" value="false"/>
                  </operator>
                  <operator activated="true" class="detect_outlier_lof" compatibility="9.9.000" expanded="true" height="82" name="Detect Outlier (LOF)" width="90" x="246" y="187">
                    <parameter key="minimal_points_lower_bound" value="10"/>
                    <parameter key="minimal_points_upper_bound" value="20"/>
                    <parameter key="distance_function" value="euclidian distance"/>
                  </operator>
                  <operator activated="true" class="python_scripting:execute_python" compatibility="9.8.000" expanded="true" height="124" name="Execute Python (3)" width="90" x="380" y="34">
                    <parameter key="script" value="import pandas&#10;&#10;# rm_main is a mandatory function, &#10;# the number of arguments has to be the number of input ports (can be none),&#10;#     or the number of input ports plus one if &quot;use macros&quot; parameter is set&#10;# if you want to use macros, use this instead and check &quot;use macros&quot; parameter:&#10;#def rm_main(data,macros):&#10;def rm_main(ori, norm):&#10;    ids = list(norm.loc[norm['outlier']&lt;2, 'ID'])&#10;    data = ori.set_index('ID', drop = False).loc[ids,:]&#10;    return data"/>
                    <parameter key="notebook_cell_tag_filter" value=""/>
                    <parameter key="use_default_python" value="true"/>
                    <parameter key="package_manager" value="conda (anaconda)"/>
                    <parameter key="use_macros" value="false"/>
                  </operator>
                  <operator activated="true" class="set_role" compatibility="9.9.000" expanded="true" height="82" name="Set Role (4)" width="90" x="581" y="34">
                    <parameter key="attribute_name" value="ID"/>
                    <parameter key="target_role" value="id"/>
                    <list key="set_additional_roles">
                      <parameter key="Target" value="label"/>
                      <parameter key="ID" value="id"/>
                    </list>
                  </operator>
                  <connect from_port="in 1" to_op="Multiply (3)" to_port="input"/>
                  <connect from_op="Multiply (3)" from_port="output 1" to_op="Execute Python (3)" to_port="input 1"/>
                  <connect from_op="Multiply (3)" from_port="output 2" to_op="Normalize (2)" to_port="example set input"/>
                  <connect from_op="Normalize (2)" from_port="example set output" to_op="Detect Outlier (LOF)" to_port="example set input"/>
                  <connect from_op="Detect Outlier (LOF)" from_port="example set output" to_op="Execute Python (3)" to_port="input 2"/>
                  <connect from_op="Execute Python (3)" from_port="output 1" to_op="Set Role (4)" to_port="example set input"/>
                  <connect from_op="Set Role (4)" 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>
              </operator>
              <operator activated="true" class="remove_correlated_attributes" compatibility="9.9.000" expanded="true" height="82" name="Remove Correlated Attributes" width="90" x="179" y="34">
                <parameter key="correlation" value="1.0"/>
                <parameter key="filter_relation" value="greater"/>
                <parameter key="attribute_order" value="random"/>
                <parameter key="use_absolute_correlation" value="true"/>
                <parameter key="use_local_random_seed" value="false"/>
                <parameter key="local_random_seed" value="1992"/>
              </operator>
              <operator activated="true" class="featselext:mrmr_feature_selection" compatibility="1.1.004" expanded="true" height="82" name="MRMR-FS" width="90" x="313" y="34">
                <parameter key="normalize_weights" value="false"/>
                <parameter key="sort_weights" value="false"/>
                <parameter key="sort_direction" value="ascending"/>
                <parameter key="sets_or_ranks" value="sets"/>
                <parameter key="calculate full ranking" value="true"/>
                <parameter key="k" value="24"/>
                <parameter key="relevance_redundancy_relation" value="quotient"/>
                <parameter key="use_ensemble_method" value="none"/>
                <parameter key="ensemble_size" value="10"/>
                <parameter key="logging" value="false"/>
              </operator>
              <operator activated="true" class="h2o:logistic_regression" compatibility="9.9.000" expanded="true" height="124" name="Logistic Regression" width="90" x="447" y="34">
                <parameter key="solver" value="AUTO"/>
                <parameter key="reproducible" value="false"/>
                <parameter key="maximum_number_of_threads" value="4"/>
                <parameter key="use_regularization" value="true"/>
                <parameter key="lambda_search" value="false"/>
                <parameter key="number_of_lambdas" value="0"/>
                <parameter key="lambda_min_ratio" value="0.0"/>
                <parameter key="early_stopping" value="true"/>
                <parameter key="stopping_rounds" value="3"/>
                <parameter key="stopping_tolerance" value="0.001"/>
                <parameter key="standardize" value="true"/>
                <parameter key="non-negative_coefficients" value="false"/>
                <parameter key="add_intercept" value="true"/>
                <parameter key="compute_p-values" value="true"/>
                <parameter key="remove_collinear_columns" value="true"/>
                <parameter key="missing_values_handling" value="MeanImputation"/>
                <parameter key="max_iterations" value="0"/>
                <parameter key="max_runtime_seconds" value="0"/>
              </operator>
              <connect from_port="training set" to_op="Remove outliers (2)" to_port="in 1"/>
              <connect from_op="Remove outliers (2)" from_port="out 1" to_op="Remove Correlated Attributes" to_port="example set input"/>
              <connect from_op="Remove Correlated Attributes" from_port="example set output" to_op="MRMR-FS" to_port="example set"/>
              <connect from_op="MRMR-FS" from_port="example set" to_op="Logistic Regression" to_port="training set"/>
              <connect from_op="Logistic Regression" 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="9.9.000" 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_binominal_classification" compatibility="9.9.000" expanded="true" height="82" name="CV-D" width="90" x="179" y="34">
                <parameter key="manually_set_positive_class" value="true"/>
                <parameter key="positive_class" value="True"/>
                <parameter key="main_criterion" value="recall"/>
                <parameter key="accuracy" value="false"/>
                <parameter key="classification_error" value="false"/>
                <parameter key="kappa" value="true"/>
                <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="false"/>
                <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="operator_toolbox:performance_auprc" compatibility="2.9.000" expanded="true" height="82" name="Performance (AUPRC)" width="90" x="313" y="34">
                <parameter key="main_criterion" value="first"/>
                <parameter key="accuracy" value="false"/>
                <parameter key="AUC" value="false"/>
                <parameter key="AUPRC" value="true"/>
                <parameter key="skip_undefined_labels" value="true"/>
                <parameter key="use_example_weights" value="true"/>
              </operator>
              <operator activated="true" class="radiomics_test:my_own_operator" compatibility="1.0.000" expanded="true" height="82" name="Performance (Fbeta-score)" width="90" x="447" y="34">
                <parameter key="Manually set positive class" value="true"/>
                <parameter key="Positive class" value="True"/>
                <parameter key="Make Fbeta-score the main criterion" value="true"/>
                <parameter key="Beta" value="2.0"/>
              </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="CV-D" to_port="labelled data"/>
              <connect from_op="CV-D" from_port="performance" to_op="Performance (AUPRC)" to_port="performance"/>
              <connect from_op="CV-D" from_port="example set" to_op="Performance (AUPRC)" to_port="labelled data"/>
              <connect from_op="Performance (AUPRC)" from_port="performance" to_op="Performance (Fbeta-score)" to_port="performance vector"/>
              <connect from_op="Performance (AUPRC)" from_port="example set" to_op="Performance (Fbeta-score)" to_port="labelled example set"/>
              <connect from_op="Performance (Fbeta-score)" from_port="performance vector" to_port="performance 1"/>
              <connect from_op="Performance (Fbeta-score)" from_port="labelled example set" to_port="test set results"/>
              <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>
          <connect from_port="input 1" to_op="Cross Validation (2)" to_port="example set"/>
          <connect from_op="Cross Validation (2)" from_port="model" to_port="model"/>
          <connect from_op="Cross Validation (2)" from_port="test result set" to_port="output 1"/>
          <connect from_op="Cross Validation (2)" from_port="performance 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"/>
          <portSpacing port="sink_output 2" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="store" compatibility="9.9.000" expanded="true" height="68" name="Store" width="90" x="916" y="85">
        <parameter key="repository_entry" value="../Models_mRMR/G_D_mRMR_LR-EN"/>
      </operator>
      <operator activated="true" class="concurrency:optimize_parameters_grid" compatibility="9.9.000" expanded="true" height="145" name="without downsampling" width="90" x="715" y="187">
        <list key="parameters">
          <parameter key="Remove Correlated Attributes (2).correlation" value="[0.4;1.0;6;linear]"/>
          <parameter key="MRMR-FS (2).k" value="[10;24;7;linear]"/>
          <parameter key="Logistic Regression (2).alpha" value="[0.0;1.0;5;linear]"/>
        </list>
        <parameter key="error_handling" value="fail on error"/>
        <parameter key="log_performance" value="true"/>
        <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" class="concurrency:cross_validation" compatibility="9.9.000" 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="4"/>
            <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="subprocess" compatibility="9.9.000" expanded="true" height="82" name="Remove outliers" width="90" x="45" y="34">
                <process expanded="true">
                  <operator activated="true" class="multiply" compatibility="9.9.000" expanded="true" height="103" name="Multiply (4)" width="90" x="45" y="34"/>
                  <operator activated="true" class="normalize" compatibility="9.9.000" expanded="true" height="103" name="Normalize" width="90" x="112" y="187">
                    <parameter key="return_preprocessing_model" value="false"/>
                    <parameter key="create_view" value="false"/>
                    <parameter key="attribute_filter_type" value="all"/>
                    <parameter key="attribute" value=""/>
                    <parameter key="attributes" value=""/>
                    <parameter key="use_except_expression" value="false"/>
                    <parameter key="value_type" value="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="false"/>
                    <parameter key="method" value="Z-transformation"/>
                    <parameter key="min" value="0.0"/>
                    <parameter key="max" value="1.0"/>
                    <parameter key="allow_negative_values" value="false"/>
                  </operator>
                  <operator activated="true" class="detect_outlier_lof" compatibility="9.9.000" expanded="true" height="82" name="Detect Outlier (LOF) (2)" width="90" x="246" y="187">
                    <parameter key="minimal_points_lower_bound" value="10"/>
                    <parameter key="minimal_points_upper_bound" value="20"/>
                    <parameter key="distance_function" value="euclidian distance"/>
                  </operator>
                  <operator activated="true" class="python_scripting:execute_python" compatibility="9.8.000" expanded="true" height="124" name="Execute Python (4)" width="90" x="380" y="34">
                    <parameter key="script" value="import pandas&#10;&#10;# rm_main is a mandatory function, &#10;# the number of arguments has to be the number of input ports (can be none),&#10;#     or the number of input ports plus one if &quot;use macros&quot; parameter is set&#10;# if you want to use macros, use this instead and check &quot;use macros&quot; parameter:&#10;#def rm_main(data,macros):&#10;def rm_main(ori, norm):&#10;    ids = list(norm.loc[norm['outlier']&lt;2, 'ID'])&#10;    data = ori.set_index('ID', drop = False).loc[ids,:]&#10;    return data"/>
                    <parameter key="notebook_cell_tag_filter" value=""/>
                    <parameter key="use_default_python" value="true"/>
                    <parameter key="package_manager" value="conda (anaconda)"/>
                    <parameter key="use_macros" value="false"/>
                  </operator>
                  <operator activated="true" class="set_role" compatibility="9.9.000" expanded="true" height="82" name="Set Role (5)" width="90" x="581" y="34">
                    <parameter key="attribute_name" value="ID"/>
                    <parameter key="target_role" value="id"/>
                    <list key="set_additional_roles">
                      <parameter key="Target" value="label"/>
                      <parameter key="ID" value="id"/>
                    </list>
                  </operator>
                  <connect from_port="in 1" to_op="Multiply (4)" to_port="input"/>
                  <connect from_op="Multiply (4)" from_port="output 1" to_op="Execute Python (4)" to_port="input 1"/>
                  <connect from_op="Multiply (4)" from_port="output 2" to_op="Normalize" to_port="example set input"/>
                  <connect from_op="Normalize" from_port="example set output" to_op="Detect Outlier (LOF) (2)" to_port="example set input"/>
                  <connect from_op="Detect Outlier (LOF) (2)" from_port="example set output" to_op="Execute Python (4)" to_port="input 2"/>
                  <connect from_op="Execute Python (4)" from_port="output 1" to_op="Set Role (5)" to_port="example set input"/>
                  <connect from_op="Set Role (5)" 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>
              </operator>
              <operator activated="true" class="remove_correlated_attributes" compatibility="9.9.000" expanded="true" height="82" name="Remove Correlated Attributes (2)" width="90" x="179" y="34">
                <parameter key="correlation" value="0.2"/>
                <parameter key="filter_relation" value="greater"/>
                <parameter key="attribute_order" value="random"/>
                <parameter key="use_absolute_correlation" value="true"/>
                <parameter key="use_local_random_seed" value="false"/>
                <parameter key="local_random_seed" value="1992"/>
              </operator>
              <operator activated="true" class="featselext:mrmr_feature_selection" compatibility="1.1.004" expanded="true" height="82" name="MRMR-FS (2)" width="90" x="313" y="34">
                <parameter key="normalize_weights" value="false"/>
                <parameter key="sort_weights" value="false"/>
                <parameter key="sort_direction" value="ascending"/>
                <parameter key="sets_or_ranks" value="sets"/>
                <parameter key="calculate full ranking" value="true"/>
                <parameter key="k" value="100"/>
                <parameter key="relevance_redundancy_relation" value="quotient"/>
                <parameter key="use_ensemble_method" value="none"/>
                <parameter key="ensemble_size" value="10"/>
                <parameter key="logging" value="false"/>
              </operator>
              <operator activated="true" class="h2o:logistic_regression" compatibility="9.9.000" expanded="true" height="124" name="Logistic Regression (2)" width="90" x="581" y="34">
                <parameter key="solver" value="AUTO"/>
                <parameter key="reproducible" value="false"/>
                <parameter key="maximum_number_of_threads" value="4"/>
                <parameter key="use_regularization" value="true"/>
                <parameter key="lambda_search" value="false"/>
                <parameter key="number_of_lambdas" value="0"/>
                <parameter key="lambda_min_ratio" value="0.0"/>
                <parameter key="early_stopping" value="true"/>
                <parameter key="stopping_rounds" value="3"/>
                <parameter key="stopping_tolerance" value="0.001"/>
                <parameter key="standardize" value="true"/>
                <parameter key="non-negative_coefficients" value="false"/>
                <parameter key="add_intercept" value="true"/>
                <parameter key="compute_p-values" value="true"/>
                <parameter key="remove_collinear_columns" value="true"/>
                <parameter key="missing_values_handling" value="MeanImputation"/>
                <parameter key="max_iterations" value="0"/>
                <parameter key="max_runtime_seconds" value="0"/>
              </operator>
              <connect from_port="training set" to_op="Remove outliers" to_port="in 1"/>
              <connect from_op="Remove outliers" from_port="out 1" to_op="Remove Correlated Attributes (2)" to_port="example set input"/>
              <connect from_op="Remove Correlated Attributes (2)" from_port="example set output" to_op="MRMR-FS (2)" to_port="example set"/>
              <connect from_op="MRMR-FS (2)" from_port="example set" to_op="Logistic Regression (2)" to_port="training set"/>
              <connect from_op="Logistic Regression (2)" 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="9.9.000" 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" class="performance_binominal_classification" compatibility="9.9.000" expanded="true" height="82" name="CV-nD" width="90" x="179" y="34">
                <parameter key="manually_set_positive_class" value="true"/>
                <parameter key="positive_class" value="True"/>
                <parameter key="main_criterion" value="recall"/>
                <parameter key="accuracy" value="false"/>
                <parameter key="classification_error" value="false"/>
                <parameter key="kappa" value="true"/>
                <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="false"/>
                <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="operator_toolbox:performance_auprc" compatibility="2.9.000" expanded="true" height="82" name="Performance (AUPRC) (2)" width="90" x="313" y="34">
                <parameter key="main_criterion" value="first"/>
                <parameter key="accuracy" value="false"/>
                <parameter key="AUC" value="false"/>
                <parameter key="AUPRC" value="true"/>
                <parameter key="skip_undefined_labels" value="true"/>
                <parameter key="use_example_weights" value="true"/>
              </operator>
              <operator activated="true" class="radiomics_test:my_own_operator" compatibility="1.0.000" expanded="true" height="82" name="Performance (Fbeta-score) (3)" width="90" x="447" y="34">
                <parameter key="Manually set positive class" value="true"/>
                <parameter key="Positive class" value="True"/>
                <parameter key="Make Fbeta-score the main criterion" value="true"/>
                <parameter key="Beta" value="2.0"/>
              </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="CV-nD" to_port="labelled data"/>
              <connect from_op="CV-nD" from_port="performance" to_op="Performance (AUPRC) (2)" to_port="performance"/>
              <connect from_op="CV-nD" from_port="example set" to_op="Performance (AUPRC) (2)" to_port="labelled data"/>
              <connect from_op="Performance (AUPRC) (2)" from_port="performance" to_op="Performance (Fbeta-score) (3)" to_port="performance vector"/>
              <connect from_op="Performance (AUPRC) (2)" from_port="example set" to_op="Performance (Fbeta-score) (3)" to_port="labelled example set"/>
              <connect from_op="Performance (Fbeta-score) (3)" from_port="performance vector" to_port="performance 1"/>
              <connect from_op="Performance (Fbeta-score) (3)" from_port="labelled example set" to_port="test set results"/>
              <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>
          <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="test result set" to_port="output 1"/>
          <connect from_op="Cross Validation" from_port="performance 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"/>
          <portSpacing port="sink_output 2" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="store" compatibility="9.9.000" expanded="true" height="68" name="Store (2)" width="90" x="916" y="238">
        <parameter key="repository_entry" value="../Models_mRMR/G_nD_mRMR_LR-EN"/>
      </operator>
      <operator activated="false" class="python_scripting:execute_python" compatibility="9.8.000" expanded="true" height="82" name="DeLong Test (AUPRC) (3)" width="90" x="916" y="340">
        <parameter key="script" value="import pandas&#10;import scipy.stats as st&#10;from sklearn import metrics&#10;from sklearn.metrics import precision_recall_curve&#10;from sklearn.metrics import auc&#10;&#10;def kernel(X, Y):&#10;    return .5 if Y==X else int(Y &lt; X)&#10;def structural_components(X, Y):&#10;    V10 = [1/len(Y) * sum([kernel(x, y) for y in Y]) for x in X]&#10;    V01 = [1/len(X) * sum([kernel(x, y) for x in X]) for y in Y]&#10;    return V10, V01&#10;def get_S_entry(V_A, V_B, auc_A, auc_B):&#10;    return 1/(len(V_A)-1) * sum([(a-auc_A)*(b-auc_B) for a,b in zip(V_A, V_B)])&#10;def z_score(var_A, var_B, covar_AB, auc_A, auc_B):&#10;    return (auc_A - auc_B)/((var_A + var_B - 2*covar_AB)**(.5))&#10;def group_preds_by_label(preds, actual):&#10;    X = [p for (p, a) in zip(preds, actual) if a=='True']&#10;    Y = [p for (p, a) in zip(preds, actual) if not a=='True']&#10;    return X, Y&#10;&#10;def rm_main(dataA, dataB):&#10;    preds_A = dataA.loc[:, 'prediction(Target)']&#10;    preds_B = dataB.loc[:, 'prediction(Target)']&#10;    actual_A = dataA.loc[:, 'Target']&#10;    actual_B = dataB.loc[:, 'Target']&#10;    &#10;    X_A, Y_A = group_preds_by_label(preds_A, actual_A)&#10;    X_B, Y_B = group_preds_by_label(preds_B, actual_B)&#10;    V_A10, V_A01 = structural_components(X_A, Y_A)&#10;    V_B10, V_B01 = structural_components(X_B, Y_B)&#10;    &#10;    a_A = [1 if elem == 'True' else 0 for elem in actual_A]&#10;    a_B = [1 if elem == 'True' else 0 for elem in actual_B]&#10;    p_A = [1 if elem == 'True' else 0 for elem in preds_A]&#10;    p_B = [1 if elem == 'True' else 0 for elem in preds_B]&#10;    precision_A, recall_A, thresholds_A = precision_recall_curve(a_A, p_A)&#10;    auc_A = auc(recall_A, precision_A)&#10;    precision_B, recall_B, thresholds_B = precision_recall_curve(a_B, p_B)&#10;    auc_B = auc(recall_B, precision_B)&#10;    &#10;    # Compute entries of covariance matrix S (covar_AB = covar_BA)&#10;    var_A = (get_S_entry(V_A10, V_A10, auc_A, auc_A) * 1/len(V_A10)&#10;             + get_S_entry(V_A01, V_A01, auc_A, auc_A) * 1/len(V_A01))&#10;    var_B = (get_S_entry(V_B10, V_B10, auc_B, auc_B) * 1/len(V_B10)&#10;             + get_S_entry(V_B01, V_B01, auc_B, auc_B) * 1/len(V_B01))&#10;    covar_AB = (get_S_entry(V_A10, V_B10, auc_A, auc_B) * 1/len(V_A10)&#10;                + get_S_entry(V_A01, V_B01, auc_A, auc_B) * 1/len(V_A01))&#10;    # Two tailed test&#10;    z = z_score(var_A, var_B, covar_AB, auc_A, auc_B)&#10;    p = st.norm.sf(abs(z))*2&#10;    print('Is AUPRC_A significantly different from AUPRC_B?')&#10;    print('CV p-value:', p)&#10;    return p"/>
        <parameter key="notebook_cell_tag_filter" value=""/>
        <parameter key="use_default_python" value="true"/>
        <parameter key="package_manager" value="conda (anaconda)"/>
        <parameter key="use_macros" value="false"/>
      </operator>
      <connect from_op="Read train" from_port="output" to_op="Stability analysis" to_port="input 3"/>
      <connect from_op="Read rad1" from_port="output" to_op="Stability analysis" to_port="input 1"/>
      <connect from_op="Read rad2" from_port="output" to_op="Stability analysis" to_port="input 2"/>
      <connect from_op="Read train (2)" from_port="output" to_op="Remove missing data" to_port="example set input"/>
      <connect from_op="Remove missing data" from_port="example set output" to_op="Set Role (2)" to_port="example set input"/>
      <connect from_op="Set Role (2)" from_port="example set output" to_op="Multiply (2)" to_port="input"/>
      <connect from_op="Multiply (2)" from_port="output 1" to_op="Sample (3)" to_port="example set input"/>
      <connect from_op="Multiply (2)" from_port="output 2" to_op="without downsampling" to_port="input 1"/>
      <connect from_op="Sample (3)" from_port="example set output" to_op="with Downsampling" to_port="input 1"/>
      <connect from_op="with Downsampling" from_port="performance" to_port="result 1"/>
      <connect from_op="with Downsampling" from_port="model" to_op="Store" to_port="input"/>
      <connect from_op="without downsampling" from_port="performance" to_port="result 2"/>
      <connect from_op="without downsampling" from_port="model" to_op="Store (2)" to_port="input"/>
      <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>


Sign In or Register to comment.