Mercurial > repos > bgruening > sklearn_train_test_eval
diff main_macros.xml @ 15:2eb5c017958d draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 9981e25b00de29ed881b2229a173a8c812ded9bb
| author | bgruening |
|---|---|
| date | Wed, 09 Aug 2023 13:15:27 +0000 |
| parents | 4d1637cac794 |
| children | f12383ee3234 |
line wrap: on
line diff
--- a/main_macros.xml Thu Aug 11 09:13:40 2022 +0000 +++ b/main_macros.xml Wed Aug 09 13:15:27 2023 +0000 @@ -1,225 +1,228 @@ <macros> - <token name="@VERSION@">1.0.8.4</token> + <token name="@VERSION@">1.0.10.0</token> + <token name="@PROFILE@">21.05</token> <xml name="python_requirements"> <requirements> - <requirement type="package" version="0.8.3">Galaxy-ML</requirement> + <requirement type="package" version="3.9">python</requirement> + <requirement type="package" version="0.10.0">galaxy-ml</requirement> <yield /> </requirements> </xml> <xml name="macro_stdio"> - <stdio> - <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error" /> - </stdio> - </xml> - - + <stdio> + <exit_code range=":-1" level="fatal" description="Error occurred. Please check Tool Standard Error" /> + <exit_code range="137" level="fatal_oom" description="Out of Memory" /> + <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error" /> + </stdio> + </xml> + <!--Generic interface--> - <xml name="sl_Conditional" token_train="tabular" token_data="tabular" token_model="txt"> - <conditional name="selected_tasks"> - <param name="selected_task" type="select" label="Select a Classification Task"> - <option value="train" selected="true">Train a model</option> - <option value="load">Load a model and predict</option> - </param> - <when value="load"> - <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file." /> - <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify." /> - <param name="header" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" /> - <conditional name="prediction_options"> - <param name="prediction_option" type="select" label="Select the type of prediction"> - <option value="predict">Predict class labels</option> - <option value="advanced">Include advanced options</option> - </param> - <when value="predict"> - </when> - <when value="advanced"> - </when> - </conditional> - </when> - <when value="train"> - <conditional name="selected_algorithms"> - <yield /> - </conditional> - </when> + <xml name="sl_Conditional" token_train="tabular" token_data="tabular" token_model="txt"> + <conditional name="selected_tasks"> + <param name="selected_task" type="select" label="Select a Classification Task"> + <option value="train" selected="true">Train a model</option> + <option value="load">Load a model and predict</option> + </param> + <when value="load"> + <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file." /> + <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify." /> + <param name="header" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" /> + <conditional name="prediction_options"> + <param name="prediction_option" type="select" label="Select the type of prediction"> + <option value="predict">Predict class labels</option> + <option value="advanced">Include advanced options</option> + </param> + <when value="predict"> + </when> + <when value="advanced"> + </when> </conditional> - </xml> + </when> + <when value="train"> + <conditional name="selected_algorithms"> + <yield /> + </conditional> + </when> + </conditional> + </xml> - <xml name="advanced_section"> - <section name="options" title="Advanced Options" expanded="False"> - <yield /> - </section> - </xml> + <xml name="advanced_section"> + <section name="options" title="Advanced Options" expanded="False"> + <yield /> + </section> + </xml> - <!--Generalized Linear Models--> - <xml name="loss" token_help=" " token_select="false"> - <param argument="loss" type="select" label="Loss function" help="@HELP@"> - <option value="squared_loss" selected="@SELECT@">squared loss</option> - <option value="huber">huber</option> - <option value="epsilon_insensitive">epsilon insensitive</option> - <option value="squared_epsilon_insensitive">squared epsilon insensitive</option> - <yield /> - </param> - </xml> + <!--Generalized Linear Models--> + <xml name="loss" token_help=" " token_select="false"> + <param argument="loss" type="select" label="Loss function" help="@HELP@"> + <option value="squared_loss" selected="@SELECT@">squared loss</option> + <option value="huber">huber</option> + <option value="epsilon_insensitive">epsilon insensitive</option> + <option value="squared_epsilon_insensitive">squared epsilon insensitive</option> + <yield /> + </param> + </xml> - <xml name="penalty" token_help=" "> - <param argument="penalty" type="select" label="Penalty (regularization term)" help="@HELP@"> - <option value="l2" selected="true">l2</option> - <option value="l1">l1</option> - <option value="elasticnet">elastic net</option> - <option value="none">none</option> - <yield /> - </param> - </xml> + <xml name="penalty" token_help=" "> + <param argument="penalty" type="select" label="Penalty (regularization term)" help="@HELP@"> + <option value="l2" selected="true">l2</option> + <option value="l1">l1</option> + <option value="elasticnet">elastic net</option> + <option value="none">none</option> + <yield /> + </param> + </xml> - <xml name="l1_ratio" token_default_value="0.15" token_help=" "> - <param argument="l1_ratio" type="float" value="@DEFAULT_VALUE@" label="Elastic Net mixing parameter" help="@HELP@" /> - </xml> + <xml name="l1_ratio" token_default_value="0.15" token_help=" "> + <param argument="l1_ratio" type="float" value="@DEFAULT_VALUE@" label="Elastic Net mixing parameter" help="@HELP@" /> + </xml> - <xml name="epsilon" token_default_value="0.1" token_help="Used if loss is ‘huber’, ‘epsilon_insensitive’, or ‘squared_epsilon_insensitive’. "> - <param argument="epsilon" type="float" value="@DEFAULT_VALUE@" label="Epsilon (epsilon-sensitive loss functions only)" help="@HELP@" /> - </xml> + <xml name="epsilon" token_default_value="0.1" token_help="Used if loss is ‘huber’, ‘epsilon_insensitive’, or ‘squared_epsilon_insensitive’. "> + <param argument="epsilon" type="float" value="@DEFAULT_VALUE@" label="Epsilon (epsilon-sensitive loss functions only)" help="@HELP@" /> + </xml> - <xml name="learning_rate_s" token_help=" " token_selected1="false" token_selected2="false"> - <param argument="learning_rate" type="select" optional="true" label="Learning rate schedule" help="@HELP@"> - <option value="optimal" selected="@SELECTED1@">optimal</option> - <option value="constant">constant</option> - <option value="invscaling" selected="@SELECTED2@">inverse scaling</option> - <yield /> - </param> - </xml> + <xml name="learning_rate_s" token_help=" " token_selected1="false" token_selected2="false"> + <param argument="learning_rate" type="select" optional="true" label="Learning rate schedule" help="@HELP@"> + <option value="optimal" selected="@SELECTED1@">optimal</option> + <option value="constant">constant</option> + <option value="invscaling" selected="@SELECTED2@">inverse scaling</option> + <yield /> + </param> + </xml> - <xml name="eta0" token_default_value="0.0" token_help="Used with ‘constant’ or ‘invscaling’ schedules. "> - <param argument="eta0" type="float" value="@DEFAULT_VALUE@" label="Initial learning rate" help="@HELP@" /> - </xml> + <xml name="eta0" token_default_value="0.0" token_help="Used with ‘constant’ or ‘invscaling’ schedules. "> + <param argument="eta0" type="float" value="@DEFAULT_VALUE@" label="Initial learning rate" help="@HELP@" /> + </xml> - <xml name="power_t" token_default_value="0.5" token_help=" "> - <param argument="power_t" type="float" value="@DEFAULT_VALUE@" label="Exponent for inverse scaling learning rate" help="@HELP@" /> - </xml> + <xml name="power_t" token_default_value="0.5" token_help=" "> + <param argument="power_t" type="float" value="@DEFAULT_VALUE@" label="Exponent for inverse scaling learning rate" help="@HELP@" /> + </xml> - <xml name="normalize" token_checked="false" token_help=" "> - <param argument="normalize" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Normalize samples before training" help=" " /> - </xml> + <xml name="normalize" token_checked="false" token_help=" "> + <param argument="normalize" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Normalize samples before training" help=" " /> + </xml> - <xml name="copy_X" token_checked="true" token_help=" "> - <param argument="copy_X" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Use a copy of samples" help="If false, samples would be overwritten. " /> - </xml> + <xml name="copy_X" token_checked="true" token_help=" "> + <param argument="copy_X" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Use a copy of samples" help="If false, samples would be overwritten. " /> + </xml> - <xml name="ridge_params"> - <expand macro="normalize" /> - <expand macro="alpha" default_value="1.0" /> - <expand macro="fit_intercept" /> - <expand macro="max_iter" default_value="" /> - <expand macro="tol" default_value="0.001" help_text="Precision of the solution. " /> - <!--class_weight--> - <expand macro="copy_X" /> - <param argument="solver" type="select" value="" label="Solver to use in the computational routines" help=" "> - <option value="auto" selected="true">auto</option> - <option value="svd">svd</option> - <option value="cholesky">cholesky</option> - <option value="lsqr">lsqr</option> - <option value="sparse_cg">sparse_cg</option> - <option value="sag">sag</option> - </param> - <expand macro="random_state" /> - </xml> + <xml name="ridge_params"> + <expand macro="normalize" /> + <expand macro="alpha" default_value="1.0" /> + <expand macro="fit_intercept" /> + <expand macro="max_iter" default_value="" /> + <expand macro="tol" default_value="0.001" help_text="Precision of the solution. " /> + <!--class_weight--> + <expand macro="copy_X" /> + <param argument="solver" type="select" value="" label="Solver to use in the computational routines" help=" "> + <option value="auto" selected="true">auto</option> + <option value="svd">svd</option> + <option value="cholesky">cholesky</option> + <option value="lsqr">lsqr</option> + <option value="sparse_cg">sparse_cg</option> + <option value="sag">sag</option> + </param> + <expand macro="random_state" /> + </xml> - <!--Ensemble methods--> - <xml name="n_estimators" token_default_value="10" token_help=" "> - <param argument="n_estimators" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of trees in the forest" help="@HELP@" /> - </xml> + <!--Ensemble methods--> + <xml name="n_estimators" token_default_value="10" token_help=" "> + <param argument="n_estimators" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of trees in the forest" help="@HELP@" /> + </xml> - <xml name="max_depth" token_default_value="" token_help=" "> - <param argument="max_depth" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@" /> - </xml> + <xml name="max_depth" token_default_value="" token_help=" "> + <param argument="max_depth" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@" /> + </xml> - <xml name="min_samples_split" token_type="integer" token_default_value="2" token_help=" "> - <param argument="min_samples_split" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="Minimum number of samples required to split an internal node" help="@HELP@" /> - </xml> + <xml name="min_samples_split" token_type="integer" token_default_value="2" token_help=" "> + <param argument="min_samples_split" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="Minimum number of samples required to split an internal node" help="@HELP@" /> + </xml> - <xml name="min_samples_leaf" token_type="integer" token_default_value="1" token_label="Minimum number of samples in newly created leaves" token_help=" "> - <param argument="min_samples_leaf" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP@" /> - </xml> + <xml name="min_samples_leaf" token_type="integer" token_default_value="1" token_label="Minimum number of samples in newly created leaves" token_help=" "> + <param argument="min_samples_leaf" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP@" /> + </xml> - <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" "> - <param argument="min_weight_fraction_leaf" type="float" optional="true" value="@DEFAULT_VALUE@" label="Minimum weighted fraction of the input samples required to be at a leaf node" help="@HELP@" /> - </xml> + <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" "> + <param argument="min_weight_fraction_leaf" type="float" optional="true" value="@DEFAULT_VALUE@" label="Minimum weighted fraction of the input samples required to be at a leaf node" help="@HELP@" /> + </xml> - <xml name="max_leaf_nodes" token_default_value="" token_help=" "> - <param argument="max_leaf_nodes" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum number of leaf nodes in best-first method" help="@HELP@" /> - </xml> + <xml name="max_leaf_nodes" token_default_value="" token_help=" "> + <param argument="max_leaf_nodes" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum number of leaf nodes in best-first method" help="@HELP@" /> + </xml> - <xml name="min_impurity_decrease" token_default_value="0" token_help=" "> - <param argument="min_impurity_decrease" type="float" value="@DEFAULT_VALUE@" optional="true" label="The threshold value of impurity for stopping node splitting" help="@HELP@" /> - </xml> + <xml name="min_impurity_decrease" token_default_value="0" token_help=" "> + <param argument="min_impurity_decrease" type="float" value="@DEFAULT_VALUE@" optional="true" label="The threshold value of impurity for stopping node splitting" help="@HELP@" /> + </xml> - <xml name="bootstrap" token_checked="true" token_help=" "> - <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@" /> - </xml> + <xml name="bootstrap" token_checked="true" token_help=" "> + <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@" /> + </xml> - <xml name="criterion" token_help=" "> - <param argument="criterion" type="select" label="Function to measure the quality of a split" help=" "> - <option value="gini" selected="true">Gini impurity</option> - <option value="entropy">Information gain</option> - <yield /> - </param> - </xml> + <xml name="criterion" token_help=" "> + <param argument="criterion" type="select" label="Function to measure the quality of a split" help=" "> + <option value="gini" selected="true">Gini impurity</option> + <option value="entropy">Information gain</option> + <yield /> + </param> + </xml> - <xml name="criterion2" token_help=""> - <param argument="criterion" type="select" label="Function to measure the quality of a split"> - <option value="mse">mse - mean squared error</option> - <option value="mae">mae - mean absolute error</option> - <yield /> - </param> - </xml> + <xml name="criterion2" token_help=""> + <param argument="criterion" type="select" label="Function to measure the quality of a split" > + <option value="mse">mse - mean squared error</option> + <option value="mae">mae - mean absolute error</option> + <yield /> + </param> + </xml> - <xml name="oob_score" token_checked="false" token_help=" "> - <param argument="oob_score" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Use out-of-bag samples to estimate the generalization error" help="@HELP@" /> - </xml> + <xml name="oob_score" token_checked="false" token_help=" "> + <param argument="oob_score" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Use out-of-bag samples to estimate the generalization error" help="@HELP@" /> + </xml> - <xml name="max_features"> - <conditional name="select_max_features"> - <param argument="max_features" type="select" label="max_features"> - <option value="auto" selected="true">auto - max_features=n_features</option> - <option value="sqrt">sqrt - max_features=sqrt(n_features)</option> - <option value="log2">log2 - max_features=log2(n_features)</option> - <option value="number_input">I want to type the number in or input None type</option> - </param> - <when value="auto"> - </when> - <when value="sqrt"> - </when> - <when value="log2"> - </when> - <when value="number_input"> - <param name="num_max_features" type="float" value="" optional="true" label="Input max_features number:" help="If int, consider the number of features at each split; If float, then max_features is a percentage and int(max_features * n_features) features are considered at each split." /> - </when> - </conditional> - </xml> + <xml name="max_features"> + <conditional name="select_max_features"> + <param argument="max_features" type="select" label="max_features"> + <option value="auto" selected="true">auto - max_features=n_features</option> + <option value="sqrt">sqrt - max_features=sqrt(n_features)</option> + <option value="log2">log2 - max_features=log2(n_features)</option> + <option value="number_input">I want to type the number in or input None type</option> + </param> + <when value="auto"> + </when> + <when value="sqrt"> + </when> + <when value="log2"> + </when> + <when value="number_input"> + <param name="num_max_features" type="float" value="" optional="true" label="Input max_features number:" help="If int, consider the number of features at each split; If float, then max_features is a percentage and int(max_features * n_features) features are considered at each split." /> + </when> + </conditional> + </xml> - <xml name="verbose" token_default_value="0" token_help="If 1 then it prints progress and performance once in a while. If greater than 1 then it prints progress and performance for every tree."> - <param argument="verbose" type="integer" value="@DEFAULT_VALUE@" optional="true" label="Enable verbose output" help="@HELP@" /> - </xml> + <xml name="verbose" token_default_value="0" token_help="If 1 then it prints progress and performance once in a while. If greater than 1 then it prints progress and performance for every tree."> + <param argument="verbose" type="integer" value="@DEFAULT_VALUE@" optional="true" label="Enable verbose output" help="@HELP@" /> + </xml> - <xml name="learning_rate" token_default_value="1.0" token_help=" "> - <param argument="learning_rate" type="float" optional="true" value="@DEFAULT_VALUE@" label="Learning rate" help="@HELP@" /> - </xml> + <xml name="learning_rate" token_default_value="1.0" token_help=" "> + <param argument="learning_rate" type="float" optional="true" value="@DEFAULT_VALUE@" label="Learning rate" help="@HELP@" /> + </xml> - <xml name="subsample" token_help=" "> - <param argument="subsample" type="float" value="1.0" optional="true" label="The fraction of samples to be used for fitting the individual base learners" help="@HELP@" /> - </xml> + <xml name="subsample" token_help=" "> + <param argument="subsample" type="float" value="1.0" optional="true" label="The fraction of samples to be used for fitting the individual base learners" help="@HELP@" /> + </xml> - <xml name="presort"> - <param argument="presort" type="select" label="Whether to presort the data to speed up the finding of best splits in fitting"> - <option value="auto" selected="true">auto</option> - <option value="true">true</option> - <option value="false">false</option> - </param> - </xml> - - <!-- LightGBM --> + <xml name="presort"> + <param argument="presort" type="select" label="Whether to presort the data to speed up the finding of best splits in fitting" > + <option value="auto" selected="true">auto</option> + <option value="true">true</option> + <option value="false">false</option> + </param> + </xml> + + <!-- LightGBM --> <xml name="feature_fraction" token_help="LightGBM will randomly select part of the features for each iteration (tree) if feature_fraction is smaller than 1.0. For example, if you set it to 0.8, LightGBM will select 80% of features before training each tree."> <param argument="feature_fraction" type="float" value="1.0" label="Proportion of features to train each tree" help="@HELP@" /> </xml> @@ -240,1722 +243,1699 @@ <param argument="min_child_weight" type="float" value="0.0" label="Minimal sum hessian in one leaf" help="@HELP@" /> </xml> - - <!--Parameters--> - <xml name="tol" token_default_value="0.0" token_help_text="Early stopping heuristics based on the relative center changes. Set to default (0.0) to disable this convergence detection."> + <!--Parameters--> + <xml name="tol" token_default_value="0.0" token_help_text="Early stopping heuristics based on the relative center changes. Set to default (0.0) to disable this convergence detection."> <param argument="tol" type="float" optional="true" value="@DEFAULT_VALUE@" label="Tolerance" help="@HELP_TEXT@" /> - </xml> + </xml> - <xml name="n_clusters" token_default_value="8"> - <param argument="n_clusters" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of clusters" help=" " /> - </xml> + <xml name="n_clusters" token_default_value="8"> + <param argument="n_clusters" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of clusters" help=" " /> + </xml> - <xml name="fit_intercept" token_checked="true"> - <param argument="fit_intercept" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Estimate the intercept" help="If false, the data is assumed to be already centered." /> - </xml> + <xml name="fit_intercept" token_checked="true"> + <param argument="fit_intercept" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Estimate the intercept" help="If false, the data is assumed to be already centered." /> + </xml> - <xml name="n_iter_no_change" token_default_value="5" token_help_text="Number of iterations with no improvement to wait before early stopping. "> - <param argument="n_iter_no_change" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of iterations" help="@HELP_TEXT@" /> - </xml> + <xml name="n_iter_no_change" token_default_value="5" token_help_text="Number of iterations with no improvement to wait before early stopping. "> + <param argument="n_iter_no_change" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of iterations" help="@HELP_TEXT@" /> + </xml> - <xml name="shuffle" token_checked="true" token_help_text=" " token_label="Shuffle data after each iteration"> - <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="@LABEL@" help="@HELP_TEXT@" /> - </xml> + <xml name="shuffle" token_checked="true" token_help_text=" " token_label="Shuffle data after each iteration"> + <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="@LABEL@" help="@HELP_TEXT@" /> + </xml> - <xml name="random_state" token_default_value="" token_help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data. A fixed seed allows reproducible results. default=None."> - <param argument="random_state" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Random seed number" help="@HELP_TEXT@" /> - </xml> + <xml name="random_state" token_default_value="" token_help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data. A fixed seed allows reproducible results. default=None."> + <param argument="random_state" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Random seed number" help="@HELP_TEXT@" /> + </xml> - <xml name="warm_start" token_checked="true" token_help_text="When set to True, reuse the solution of the previous call to fit as initialization,otherwise, just erase the previous solution."> - <param argument="warm_start" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Perform warm start" help="@HELP_TEXT@" /> - </xml> + <xml name="warm_start" token_checked="true" token_help_text="When set to True, reuse the solution of the previous call to fit as initialization,otherwise, just erase the previous solution."> + <param argument="warm_start" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Perform warm start" help="@HELP_TEXT@" /> + </xml> - <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term."> - <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@" /> - </xml> + <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term."> + <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@" /> + </xml> - <!--xml name="class_weight" token_default_value="" token_help_text=""> - <param argument="class_weight" type="" optional="true" value="@DEFAULT_VALUE@" label="" help="@HELP_TEXT@"/> + <!--xml name="class_weight" token_default_value="" token_help_text=""> + <param argument="class_weight" type="" optional="true" value="@DEFAULT_VALUE@" label="" help="@HELP_TEXT@" /> </xml--> - <xml name="alpha" token_default_value="0.0001" token_help_text="Constant that multiplies the regularization term if regularization is used. "> - <param argument="alpha" type="float" optional="true" value="@DEFAULT_VALUE@" label="Regularization coefficient" help="@HELP_TEXT@" /> - </xml> + <xml name="alpha" token_default_value="0.0001" token_help_text="Constant that multiplies the regularization term if regularization is used. "> + <param argument="alpha" type="float" optional="true" value="@DEFAULT_VALUE@" label="Regularization coefficient" help="@HELP_TEXT@" /> + </xml> - <xml name="n_samples" token_default_value="100" token_help_text="The total number of points equally divided among clusters."> - <param argument="n_samples" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of samples" help="@HELP_TEXT@" /> - </xml> + <xml name="n_samples" token_default_value="100" token_help_text="The total number of points equally divided among clusters."> + <param argument="n_samples" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of samples" help="@HELP_TEXT@" /> + </xml> - <xml name="n_features" token_default_value="2" token_help_text="Number of different numerical properties produced for each sample."> - <param argument="n_features" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of features" help="@HELP_TEXT@" /> - </xml> + <xml name="n_features" token_default_value="2" token_help_text="Number of different numerical properties produced for each sample."> + <param argument="n_features" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of features" help="@HELP_TEXT@" /> + </xml> - <xml name="noise" token_default_value="0.0" token_help_text="Floating point number. "> - <param argument="noise" type="float" optional="true" value="@DEFAULT_VALUE@" label="Standard deviation of the Gaussian noise added to the data" help="@HELP_TEXT@" /> - </xml> + <xml name="noise" token_default_value="0.0" token_help_text="Floating point number. "> + <param argument="noise" type="float" optional="true" value="@DEFAULT_VALUE@" label="Standard deviation of the Gaussian noise added to the data" help="@HELP_TEXT@" /> + </xml> - <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term. "> - <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@" /> - </xml> + <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term. "> + <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@" /> + </xml> - <xml name="max_iter" token_default_value="300" token_label="Maximum number of iterations per single run" token_help_text=" "> - <param argument="max_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" /> - </xml> + <xml name="max_iter" token_default_value="300" token_label="Maximum number of iterations per single run" token_help_text=" "> + <param argument="max_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" /> + </xml> - <xml name="n_init" token_default_value="10"> - <param argument="n_init" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of runs with different centroid seeds" help=" " /> - </xml> + <xml name="n_init" token_default_value="10" > + <param argument="n_init" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of runs with different centroid seeds" help=" " /> + </xml> - <xml name="init"> - <param argument="init" type="select" label="Centroid initialization method" help="''k-means++'' selects initial cluster centers that speed up convergence. ''random'' chooses k observations (rows) at random from data as initial centroids."> - <option value="k-means++">k-means++</option> - <option value="random">random</option> - </param> - </xml> + <xml name="init"> + <param argument="init" type="select" label="Centroid initialization method" help="''k-means++'' selects initial cluster centers that speed up convergence. ''random'' chooses k observations (rows) at random from data as initial centroids."> + <option value="k-means++">k-means++</option> + <option value="random">random</option> + </param> + </xml> - <xml name="gamma" token_default_value="1.0" token_label="Scaling parameter" token_help_text=" "> - <param argument="gamma" type="float" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" /> - </xml> + <xml name="gamma" token_default_value="1.0" token_label="Scaling parameter" token_help_text=" "> + <param argument="gamma" type="float" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" /> + </xml> - <xml name="degree" token_default_value="3" token_label="Degree of the polynomial" token_help_text=" "> - <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" /> - </xml> + <xml name="degree" token_default_value="3" token_label="Degree of the polynomial" token_help_text=" "> + <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" /> + </xml> - <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" "> - <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" /> - </xml> + <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" "> + <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" /> + </xml> - <xml name="pos_label" token_default_value=""> - <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" " /> - </xml> + <xml name="pos_label" token_default_value=""> + <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" " /> + </xml> - <xml name="average"> - <param argument="average" type="select" optional="true" label="Averaging type" help=" "> - <option value="micro">Calculate metrics globally by counting the total true positives, false negatives and false positives. (micro)</option> - <option value="samples">Calculate metrics for each instance, and find their average. Only meaningful for multilabel. (samples)</option> - <option value="macro">Calculate metrics for each label, and find their unweighted mean. This does not take label imbalance into account. (macro)</option> - <option value="weighted">Calculate metrics for each label, and find their average, weighted by support (the number of true instances for each label). This alters ‘macro’ to account for label imbalance; it can result in an F-score that is not between precision and recall. (weighted)</option> - <option value="None">None</option> - <yield /> - </param> - </xml> + <xml name="average"> + <param argument="average" type="select" optional="true" label="Averaging type" help=" "> + <option value="micro">Calculate metrics globally by counting the total true positives, false negatives and false positives. (micro)</option> + <option value="samples">Calculate metrics for each instance, and find their average. Only meaningful for multilabel. (samples)</option> + <option value="macro">Calculate metrics for each label, and find their unweighted mean. This does not take label imbalance into account. (macro)</option> + <option value="weighted">Calculate metrics for each label, and find their average, weighted by support (the number of true instances for each label). This alters ‘macro’ to account for label imbalance; it can result in an F-score that is not between precision and recall. (weighted)</option> + <option value="None">None</option> + <yield /> + </param> + </xml> - <xml name="beta"> - <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" " /> - </xml> + <xml name="beta"> + <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" " /> + </xml> - <!--Data interface--> - - <xml name="samples_tabular" token_label1="Training samples dataset:" token_multiple1="false" token_multiple2="false"> - <param name="infile1" type="data" format="tabular" label="@LABEL1@" /> - <param name="header1" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" /> - <conditional name="column_selector_options_1"> - <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@" /> - </conditional> - <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:" /> - <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" /> - <conditional name="column_selector_options_2"> - <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE2@" infile="infile2" /> - </conditional> - <yield /> - </xml> + <!--Data interface--> - <xml name="samples_column_selector_options" token_column_option="selected_column_selector_option" token_col_name="col1" token_multiple="False" token_infile="infile1"> - <param name="@COLUMN_OPTION@" type="select" label="Choose how to select data by column:"> - <option value="by_index_number" selected="true">Select columns by column index number(s)</option> - <option value="all_but_by_index_number">All columns EXCLUDING some by column index number(s)</option> - <option value="by_header_name">Select columns by column header name(s)</option> - <option value="all_but_by_header_name">All columns EXCLUDING some by column header name(s)</option> - <option value="all_columns">All columns</option> - </param> - <when value="by_index_number"> - <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):" /> - </when> - <when value="all_but_by_index_number"> - <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):" /> - </when> - <when value="by_header_name"> - <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2" /> - </when> - <when value="all_but_by_header_name"> - <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2" /> - </when> - <when value="all_columns"> - </when> - </xml> + <xml name="samples_tabular" token_label1="Training samples dataset:" token_multiple1="false" token_multiple2="false"> + <param name="infile1" type="data" format="tabular" label="@LABEL1@" /> + <param name="header1" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" /> + <conditional name="column_selector_options_1"> + <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@" /> + </conditional> + <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:" /> + <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" /> + <conditional name="column_selector_options_2"> + <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE2@" infile="infile2" /> + </conditional> + <yield /> + </xml> - <xml name="clf_inputs_extended" token_label1=" " token_label2=" " token_multiple="False"> - <conditional name="true_columns"> - <param name="selected_input1" type="select" label="Select the input type of true labels dataset:"> - <option value="tabular" selected="true">Tabular</option> - <option value="sparse">Sparse</option> - </param> - <when value="tabular"> - <param name="infile1" type="data" label="@LABEL1@" /> - <param name="col1" type="data_column" data_ref="infile1" label="Select the target column:" /> - </when> - <when value="sparse"> - <param name="infile1" type="data" format="txt" label="@LABEL1@" /> - </when> - </conditional> - <conditional name="predicted_columns"> - <param name="selected_input2" type="select" label="Select the input type of predicted labels dataset:"> - <option value="tabular" selected="true">Tabular</option> - <option value="sparse">Sparse</option> - </param> - <when value="tabular"> - <param name="infile2" type="data" label="@LABEL2@" /> - <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):" /> - </when> - <when value="sparse"> - <param name="infile2" type="data" format="txt" label="@LABEL1@" /> - </when> - </conditional> - </xml> - - <xml name="clf_inputs" token_label1="Dataset containing true labels (tabular):" token_label2="Dataset containing predicted values (tabular):" token_multiple1="False" token_multiple="False"> - <param name="infile1" type="data" format="tabular" label="@LABEL1@" /> - <param name="header1" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" /> - <conditional name="column_selector_options_1"> - <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@" /> - </conditional> - <param name="infile2" type="data" format="tabular" label="@LABEL2@" /> - <param name="header2" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" /> - <conditional name="column_selector_options_2"> - <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE@" infile="infile2" /> - </conditional> - </xml> - - <xml name="multiple_input" token_name="input_files" token_max_num="10" token_format="txt" token_label="Sparse matrix file (.mtx, .txt)" token_help_text="Specify a sparse matrix file in .txt format."> - <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):"> - <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@" /> - </repeat> - </xml> + <xml name="samples_column_selector_options" token_column_option="selected_column_selector_option" token_col_name="col1" token_multiple="False" token_infile="infile1"> + <param name="@COLUMN_OPTION@" type="select" label="Choose how to select data by column:"> + <option value="by_index_number" selected="true">Select columns by column index number(s)</option> + <option value="all_but_by_index_number">All columns EXCLUDING some by column index number(s)</option> + <option value="by_header_name">Select columns by column header name(s)</option> + <option value="all_but_by_header_name">All columns EXCLUDING some by column header name(s)</option> + <option value="all_columns">All columns</option> + </param> + <when value="by_index_number"> + <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):" /> + </when> + <when value="all_but_by_index_number"> + <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):" /> + </when> + <when value="by_header_name"> + <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2" /> + </when> + <when value="all_but_by_header_name"> + <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2" /> + </when> + <when value="all_columns"> + </when> + </xml> - <xml name="sparse_target" token_label1="Select a sparse matrix:" token_label2="Select the tabular containing true labels:" token_multiple="False" token_format1="txt" token_format2="tabular" token_help1="" token_help2=""> - <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@" /> - <expand macro="input_tabular_target" /> - </xml> - - <xml name="sl_mixed_input"> - <conditional name="input_options"> - <expand macro="data_input_options" /> - <expand macro="data_input_whens" /> - </conditional> - </xml> + <xml name="clf_inputs_extended" token_label1=" " token_label2=" " token_multiple="False"> + <conditional name="true_columns"> + <param name="selected_input1" type="select" label="Select the input type of true labels dataset:"> + <option value="tabular" selected="true">Tabular</option> + <option value="sparse">Sparse</option> + </param> + <when value="tabular"> + <param name="infile1" type="data" label="@LABEL1@" /> + <param name="col1" type="data_column" data_ref="infile1" label="Select the target column:" /> + </when> + <when value="sparse"> + <param name="infile1" type="data" format="txt" label="@LABEL1@" /> + </when> + </conditional> + <conditional name="predicted_columns"> + <param name="selected_input2" type="select" label="Select the input type of predicted labels dataset:"> + <option value="tabular" selected="true">Tabular</option> + <option value="sparse">Sparse</option> + </param> + <when value="tabular"> + <param name="infile2" type="data" label="@LABEL2@" /> + <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):" /> + </when> + <when value="sparse"> + <param name="infile2" type="data" format="txt" label="@LABEL1@" /> + </when> + </conditional> + </xml> - <xml name="sl_mixed_input_plus_sequence"> - <conditional name="input_options"> - <expand macro="data_input_options"> - <option value="seq_fasta">sequnences in a fasta file</option> - <option value="refseq_and_interval">reference genome and intervals</option> - </expand> - <expand macro="data_input_whens"> - <when value="seq_fasta"> - <expand macro="inputs_seq_fasta" /> - </when> - <when value="refseq_and_interval"> - <expand macro="inputs_refseq_and_interval" /> - </when> - </expand> - </conditional> - </xml> + <xml name="clf_inputs" token_label1="Dataset containing true labels (tabular):" token_label2="Dataset containing predicted values (tabular):" token_multiple1="False" token_multiple="False"> + <param name="infile1" type="data" format="tabular" label="@LABEL1@" /> + <param name="header1" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" /> + <conditional name="column_selector_options_1"> + <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@" /> + </conditional> + <param name="infile2" type="data" format="tabular" label="@LABEL2@" /> + <param name="header2" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" /> + <conditional name="column_selector_options_2"> + <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE@" infile="infile2" /> + </conditional> + </xml> + + <xml name="multiple_input" token_name="input_files" token_max_num="10" token_format="txt" token_label="Sparse matrix file (.mtx, .txt)" token_help_text="Specify a sparse matrix file in .txt format."> + <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):"> + <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@" /> + </repeat> + </xml> - <xml name="data_input_options"> - <param name="selected_input" type="select" label="Select input type:"> - <option value="tabular" selected="true">tabular data</option> - <option value="sparse">sparse matrix</option> - <yield /> - </param> - </xml> + <xml name="sparse_target" token_label1="Select a sparse matrix:" token_label2="Select the tabular containing true labels:" token_multiple="False" token_format1="txt" token_format2="tabular" token_help1="" token_help2=""> + <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@" /> + <expand macro="input_tabular_target" /> + </xml> - <xml name="data_input_whens"> - <when value="tabular"> - <expand macro="samples_tabular" multiple1="true" multiple2="false" /> - </when> - <when value="sparse"> - <expand macro="sparse_target" /> + <xml name="sl_mixed_input"> + <conditional name="input_options"> + <expand macro="data_input_options" /> + <expand macro="data_input_whens" /> + </conditional> + </xml> + + <xml name="sl_mixed_input_plus_sequence"> + <conditional name="input_options"> + <expand macro="data_input_options"> + <option value="seq_fasta">sequnences in a fasta file</option> + <option value="refseq_and_interval">reference genome and intervals</option> + </expand> + <expand macro="data_input_whens"> + <when value="seq_fasta"> + <expand macro="inputs_seq_fasta" /> </when> - <yield /> - </xml> - - <xml name="input_tabular_target"> - <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:" /> - <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" /> - <conditional name="column_selector_options_2"> - <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="false" infile="infile2" /> - </conditional> - </xml> - - <xml name="inputs_seq_fasta"> - <param name="fasta_path" type="data" format="fasta" label="Dataset containing fasta genomic/protein sequences" help="Sequences will be one-hot encoded to arrays." /> - <expand macro="input_tabular_target" /> - </xml> + <when value="refseq_and_interval"> + <expand macro="inputs_refseq_and_interval" /> + </when> + </expand> + </conditional> + </xml> - <xml name="inputs_refseq_and_interval"> - <param name="ref_genome_file" type="data" format="fasta" label="Dataset containing reference genomic sequence" /> - <param name="interval_file" type="data" format="interval" label="Dataset containing sequence intervals for training" help="interval. Sequences will be retrieved from the reference genome and one-hot encoded to training arrays." /> - <param name="target_file" type="data" format="bed" label="Dataset containing positions and features for target values." help="bed. The file will be compressed with `bgzip` and then indexed using `tabix`." /> - <param name="infile2" type="data" format="tabular" label="Dataset containing the feature list for prediction" /> - <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" /> - <conditional name="column_selector_options_2"> - <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="true" infile="infile2" /> - </conditional> - </xml> - - <!--Advanced options--> - <xml name="nn_advanced_options"> - <section name="options" title="Advanced Options" expanded="False"> - <yield /> - <param argument="weights" type="select" label="Weight function" help="Used in prediction."> - <option value="uniform" selected="true">Uniform weights. All points in each neighborhood are weighted equally. (Uniform)</option> - <option value="distance">Weight points by the inverse of their distance. (Distance)</option> - </param> - <param argument="algorithm" type="select" label="Neighbor selection algorithm" help=" "> - <option value="auto" selected="true">Auto</option> - <option value="ball_tree">BallTree</option> - <option value="kd_tree">KDTree</option> - <option value="brute">Brute-force</option> - </param> - <param argument="leaf_size" type="integer" value="30" label="Leaf size" help="Used with BallTree and KDTree. Affects the time and memory usage of the constructed tree." /> - <!--param name="metric"--> - <!--param name="p"--> - <!--param name="metric_params"--> - </section> - </xml> + <xml name="data_input_options"> + <param name="selected_input" type="select" label="Select input type:"> + <option value="tabular" selected="true">tabular data</option> + <option value="sparse">sparse matrix</option> + <yield /> + </param> + </xml> - <xml name="svc_advanced_options"> - <section name="options" title="Advanced Options" expanded="False"> - <yield /> - <param argument="kernel" type="select" optional="true" label="Kernel type" help="Kernel type to be used in the algorithm. If none is given, ‘rbf’ will be used."> - <option value="rbf" selected="true">rbf</option> - <option value="linear">linear</option> - <option value="poly">poly</option> - <option value="sigmoid">sigmoid</option> - <option value="precomputed">precomputed</option> - </param> - <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 " /> - <!--TODO: param argument="gamma" float, optional (default=’auto’) --> - <param argument="coef0" type="float" optional="true" value="0.0" label="Zero coefficient (polynomial and sigmoid kernels only)" help="Independent term in kernel function. dafault: 0.0 " /> - <param argument="shrinking" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use the shrinking heuristic" help=" " /> - <param argument="probability" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Enable probability estimates. " help="This must be enabled prior to calling fit, and will slow down that method." /> - <!-- param argument="cache_size"--> - <!--expand macro="class_weight"/--> - <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. " /> - <expand macro="max_iter" default_value="-1" label="Solver maximum number of iterations" help_text="Hard limit on iterations within solver, or -1 for no limit." /> - <!--param argument="decision_function_shape"--> - <expand macro="random_state" help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data for probability estimation. A fixed seed allows reproducible results." /> - </section> - </xml> + <xml name="data_input_whens"> + <when value="tabular"> + <expand macro="samples_tabular" multiple1="true" multiple2="false" /> + </when> + <when value="sparse"> + <expand macro="sparse_target" /> + </when> + <yield /> + </xml> + + <xml name="input_tabular_target"> + <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:" /> + <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" /> + <conditional name="column_selector_options_2"> + <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="false" infile="infile2" /> + </conditional> + </xml> + + <xml name="inputs_seq_fasta"> + <param name="fasta_path" type="data" format="fasta" label="Dataset containing fasta genomic/protein sequences" help="Sequences will be one-hot encoded to arrays." /> + <expand macro="input_tabular_target" /> + </xml> - <xml name="spectral_clustering_advanced_options"> - <section name="options" title="Advanced Options" expanded="False"> - <expand macro="n_clusters" /> - <param argument="eigen_solver" type="select" value="" label="Eigen solver" help="The eigenvalue decomposition strategy to use."> - <option value="arpack" selected="true">arpack</option> - <option value="lobpcg">lobpcg</option> - <option value="amg">amg</option> - <!--None--> - </param> - <expand macro="random_state" /> - <expand macro="n_init" /> - <param argument="gamma" type="float" optional="true" value="1.0" label="Kernel scaling factor" help="Scaling factor of RBF, polynomial, exponential chi^2 and sigmoid affinity kernel. Ignored for affinity=''nearest_neighbors''." /> - <param argument="affinity" type="select" label="Affinity" help="Affinity kernel to use. "> - <option value="rbf" selected="true">RBF</option> - <option value="precomputed">precomputed</option> - <option value="nearest_neighbors">Nearset neighbors</option> - </param> - <param argument="n_neighbors" type="integer" optional="true" value="10" label="Number of neighbors" help="Number of neighbors to use when constructing the affinity matrix using the nearest neighbors method. Ignored for affinity=''rbf''" /> - <!--param argument="eigen_tol"--> - <param argument="assign_labels" type="select" label="Assign labels" help="The strategy to use to assign labels in the embedding space."> - <option value="kmeans" selected="true">kmeans</option> - <option value="discretize">discretize</option> - </param> - <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 " /> - <param argument="coef0" type="integer" optional="true" value="1" label="Zero coefficient (polynomial and sigmoid kernels only)" help="Ignored by other kernels. dafault : 1 " /> - <!--param argument="kernel_params"--> - </section> - </xml> + <xml name="inputs_refseq_and_interval"> + <param name="ref_genome_file" type="data" format="fasta" label="Dataset containing reference genomic sequence" /> + <param name="interval_file" type="data" format="interval" label="Dataset containing sequence intervals for training" help="interval. Sequences will be retrieved from the reference genome and one-hot encoded to training arrays." /> + <param name="target_file" type="data" format="bed" label="Dataset containing positions and features for target values." help="bed. The file will be compressed with `bgzip` and then indexed using `tabix`." /> + <param name="infile2" type="data" format="tabular" label="Dataset containing the feature list for prediction" /> + <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" /> + <conditional name="column_selector_options_2"> + <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="true" infile="infile2" /> + </conditional> + </xml> - <xml name="minibatch_kmeans_advanced_options"> - <section name="options" title="Advanced Options" expanded="False"> - <expand macro="n_clusters" /> - <expand macro="init" /> - <expand macro="n_init" default_value="3" /> - <expand macro="max_iter" default_value="100" /> - <expand macro="tol" help_text="Early stopping heuristics based on normalized center change. To disable set to 0.0 ." /> - <expand macro="random_state" /> - <param argument="batch_size" type="integer" optional="true" value="100" label="Batch size" help="Size of the mini batches." /> - <!--param argument="compute_labels"--> - <param argument="max_no_improvement" type="integer" optional="true" value="10" label="Maximum number of improvement attempts" help=" - Convergence detection based on inertia (the consecutive number of mini batches that doe not yield an improvement on the smoothed inertia). - To disable, set max_no_improvement to None. " /> - <param argument="init_size" type="integer" optional="true" value="" label="Number of random initialization samples" help="Number of samples to randomly sample for speeding up the initialization . ( default: 3 * batch_size )" /> - <param argument="reassignment_ratio" type="float" optional="true" value="0.01" label="Re-assignment ratio" help="Controls the fraction of the maximum number of counts for a center to be reassigned. Higher values yield better clustering results." /> - </section> - </xml> - - <xml name="kmeans_advanced_options"> - <section name="options" title="Advanced Options" expanded="False"> - <expand macro="n_clusters" /> - <expand macro="init" /> - <expand macro="n_init" /> - <expand macro="max_iter" /> - <expand macro="tol" default_value="0.0001" help_text="Relative tolerance with regards to inertia to declare convergence." /> - <!--param argument="precompute_distances"/--> - <expand macro="random_state" /> - <param argument="copy_x" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing distances" help="Mofifying the original data introduces small numerical differences caused by subtracting and then adding the data mean." /> - <expand macro="kmeans_algorithm" /> - </section> - </xml> - - <xml name="kmeans_algorithm"> - <param argument="algorithm" type="select" label="K-means algorithm to use:"> - <option value="auto" selected="true">auto</option> - <option value="full">full</option> - <option value="elkan">elkan</option> - </param> - </xml> - - <xml name="birch_advanced_options"> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="threshold" type="float" optional="true" value="0.5" label="Subcluster radius threshold" help="The radius of the subcluster obtained by merging a new sample; the closest subcluster should be less than the threshold to avoid a new subcluster." /> - <param argument="branching_factor" type="integer" optional="true" value="50" label="Maximum number of subclusters per branch" help="Maximum number of CF subclusters in each node." /> - <expand macro="n_clusters" default_value="3" /> - <!--param argument="compute_labels"/--> - </section> - </xml> + <!--Advanced options--> + <xml name="nn_advanced_options"> + <section name="options" title="Advanced Options" expanded="False"> + <yield /> + <param argument="weights" type="select" label="Weight function" help="Used in prediction."> + <option value="uniform" selected="true">Uniform weights. All points in each neighborhood are weighted equally. (Uniform)</option> + <option value="distance">Weight points by the inverse of their distance. (Distance)</option> + </param> + <param argument="algorithm" type="select" label="Neighbor selection algorithm" help=" "> + <option value="auto" selected="true">Auto</option> + <option value="ball_tree">BallTree</option> + <option value="kd_tree">KDTree</option> + <option value="brute">Brute-force</option> + </param> + <param argument="leaf_size" type="integer" value="30" label="Leaf size" help="Used with BallTree and KDTree. Affects the time and memory usage of the constructed tree." /> + <!--param name="metric"--> + <!--param name="p"--> + <!--param name="metric_params"--> + </section> + </xml> - <xml name="dbscan_advanced_options"> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="eps" type="float" optional="true" value="0.5" label="Maximum neighborhood distance" help="The maximum distance between two samples for them to be considered as in the same neighborhood." /> - <param argument="min_samples" type="integer" optional="true" value="5" label="Minimal core point density" help="The number of samples (or total weight) in a neighborhood for a point (including the point itself) to be considered as a core point." /> - <param argument="metric" type="text" optional="true" value="euclidean" label="Metric" help="The metric to use when calculating distance between instances in a feature array." /> - <param argument="algorithm" type="select" label="Pointwise distance computation algorithm" help="The algorithm to be used by the NearestNeighbors module to compute pointwise distances and find nearest neighbors."> - <option value="auto" selected="true">auto</option> - <option value="ball_tree">ball_tree</option> - <option value="kd_tree">kd_tree</option> - <option value="brute">brute</option> - </param> - <param argument="leaf_size" type="integer" optional="true" value="30" label="Leaf size" help="Leaf size passed to BallTree or cKDTree. Memory and time efficieny factor in tree constrution and querying." /> - </section> - </xml> - - <xml name="clustering_algorithms_options"> - <conditional name="algorithm_options"> - <param name="selected_algorithm" type="select" label="Clustering Algorithm"> - <option value="KMeans" selected="true">KMeans</option> - <option value="SpectralClustering">Spectral Clustering</option> - <option value="MiniBatchKMeans">Mini Batch KMeans</option> - <option value="DBSCAN">DBSCAN</option> - <option value="Birch">Birch</option> - </param> - <when value="KMeans"> - <expand macro="kmeans_advanced_options" /> - </when> - <when value="DBSCAN"> - <expand macro="dbscan_advanced_options" /> - </when> - <when value="Birch"> - <expand macro="birch_advanced_options" /> - </when> - <when value="SpectralClustering"> - <expand macro="spectral_clustering_advanced_options" /> - </when> - <when value="MiniBatchKMeans"> - <expand macro="minibatch_kmeans_advanced_options" /> - </when> - </conditional> - </xml> - - <xml name="distance_metrics"> - <param argument="metric" type="select" label="Distance metric" help=" "> - <option value="euclidean" selected="true">euclidean</option> - <option value="cityblock">cityblock</option> - <option value="cosine">cosine</option> - <option value="l1">l1</option> - <option value="l2">l2</option> - <option value="manhattan">manhattan</option> - <yield /> - </param> - </xml> + <xml name="svc_advanced_options"> + <section name="options" title="Advanced Options" expanded="False"> + <yield /> + <param argument="kernel" type="select" optional="true" label="Kernel type" help="Kernel type to be used in the algorithm. If none is given, ‘rbf’ will be used."> + <option value="rbf" selected="true">rbf</option> + <option value="linear">linear</option> + <option value="poly">poly</option> + <option value="sigmoid">sigmoid</option> + <option value="precomputed">precomputed</option> + </param> + <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 " /> + <!--TODO: param argument="gamma" float, optional (default=’auto’) --> + <param argument="coef0" type="float" optional="true" value="0.0" label="Zero coefficient (polynomial and sigmoid kernels only)" + help="Independent term in kernel function. dafault: 0.0 " /> + <param argument="shrinking" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" + label="Use the shrinking heuristic" help=" " /> + <param argument="probability" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" + label="Enable probability estimates. " help="This must be enabled prior to calling fit, and will slow down that method." /> + <!-- param argument="cache_size"--> + <!--expand macro="class_weight"/--> + <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. " /> + <expand macro="max_iter" default_value="-1" label="Solver maximum number of iterations" help_text="Hard limit on iterations within solver, or -1 for no limit." /> + <!--param argument="decision_function_shape"--> + <expand macro="random_state" help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data for probability estimation. A fixed seed allows reproducible results." /> + </section> + </xml> - <xml name="distance_nonsparse_metrics"> - <option value="braycurtis">braycurtis</option> - <option value="canberra">canberra</option> - <option value="chebyshev">chebyshev</option> - <option value="correlation">correlation</option> - <option value="dice">dice</option> - <option value="hamming">hamming</option> - <option value="jaccard">jaccard</option> - <option value="kulsinski">kulsinski</option> - <option value="mahalanobis">mahalanobis</option> - <option value="matching">matching</option> - <option value="minkowski">minkowski</option> - <option value="rogerstanimoto">rogerstanimoto</option> - <option value="russellrao">russellrao</option> - <option value="seuclidean">seuclidean</option> - <option value="sokalmichener">sokalmichener</option> - <option value="sokalsneath">sokalsneath</option> - <option value="sqeuclidean">sqeuclidean</option> - <option value="yule">yule</option> - </xml> - - <xml name="pairwise_kernel_metrics"> - <param argument="metric" type="select" label="Pirwise Kernel metric" help=" "> - <option value="rbf" selected="true">rbf</option> - <option value="sigmoid">sigmoid</option> - <option value="polynomial">polynomial</option> - <option value="linear" selected="true">linear</option> - <option value="chi2">chi2</option> - <option value="additive_chi2">additive_chi2</option> - </param> - </xml> + <xml name="spectral_clustering_advanced_options"> + <section name="options" title="Advanced Options" expanded="False"> + <expand macro="n_clusters" /> + <param argument="eigen_solver" type="select" value="" label="Eigen solver" help="The eigenvalue decomposition strategy to use."> + <option value="arpack" selected="true">arpack</option> + <option value="lobpcg">lobpcg</option> + <option value="amg">amg</option> + <!--None--> + </param> + <expand macro="random_state" /> + <expand macro="n_init" /> + <param argument="gamma" type="float" optional="true" value="1.0" label="Kernel scaling factor" help="Scaling factor of RBF, polynomial, exponential chi^2 and sigmoid affinity kernel. Ignored for affinity=''nearest_neighbors''." /> + <param argument="affinity" type="select" label="Affinity" help="Affinity kernel to use. "> + <option value="rbf" selected="true">RBF</option> + <option value="precomputed">precomputed</option> + <option value="nearest_neighbors">Nearset neighbors</option> + </param> + <param argument="n_neighbors" type="integer" optional="true" value="10" label="Number of neighbors" help="Number of neighbors to use when constructing the affinity matrix using the nearest neighbors method. Ignored for affinity=''rbf''" /> + <!--param argument="eigen_tol"--> + <param argument="assign_labels" type="select" label="Assign labels" help="The strategy to use to assign labels in the embedding space."> + <option value="kmeans" selected="true">kmeans</option> + <option value="discretize">discretize</option> + </param> + <param argument="degree" type="integer" optional="true" value="3" + label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 " /> + <param argument="coef0" type="integer" optional="true" value="1" + label="Zero coefficient (polynomial and sigmoid kernels only)" help="Ignored by other kernels. dafault : 1 " /> + <!--param argument="kernel_params"--> + </section> + </xml> - <xml name="sparse_pairwise_metric_functions"> - <param name="selected_metric_function" type="select" label="Select the pairwise metric you want to compute:"> - <option value="euclidean_distances" selected="true">Euclidean distance matrix</option> - <option value="pairwise_distances">Distance matrix</option> - <option value="pairwise_distances_argmin">Minimum distances between one point and a set of points</option> - <yield /> - </param> - </xml> - - <xml name="pairwise_metric_functions"> - <option value="additive_chi2_kernel">Additive chi-squared kernel</option> - <option value="chi2_kernel">Exponential chi-squared kernel</option> - <option value="linear_kernel">Linear kernel</option> - <option value="manhattan_distances">L1 distances</option> - <option value="pairwise_kernels">Kernel</option> - <option value="polynomial_kernel">Polynomial kernel</option> - <option value="rbf_kernel">Gaussian (rbf) kernel</option> - <option value="laplacian_kernel">Laplacian kernel</option> - </xml> - - <xml name="sparse_pairwise_condition"> - <when value="pairwise_distances"> - <section name="options" title="Advanced Options" expanded="False"> - <expand macro="distance_metrics"> - <yield /> - </expand> - </section> - </when> - <when value="euclidean_distances"> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="squared" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Return squared Euclidean distances" help=" " /> - </section> - </when> - </xml> + <xml name="minibatch_kmeans_advanced_options"> + <section name="options" title="Advanced Options" expanded="False"> + <expand macro="n_clusters" /> + <expand macro="init" /> + <expand macro="n_init" default_value="3" /> + <expand macro="max_iter" default_value="100" /> + <expand macro="tol" help_text="Early stopping heuristics based on normalized center change. To disable set to 0.0 ." /> + <expand macro="random_state" /> + <param argument="batch_size" type="integer" optional="true" value="100" label="Batch size" help="Size of the mini batches." /> + <!--param argument="compute_labels"--> + <param argument="max_no_improvement" type="integer" optional="true" value="10" label="Maximum number of improvement attempts" help=" + Convergence detection based on inertia (the consecutive number of mini batches that doe not yield an improvement on the smoothed inertia). + To disable, set max_no_improvement to None. " /> + <param argument="init_size" type="integer" optional="true" value="" label="Number of random initialization samples" help="Number of samples to randomly sample for speeding up the initialization . ( default: 3 * batch_size )" /> + <param argument="reassignment_ratio" type="float" optional="true" value="0.01" label="Re-assignment ratio" help="Controls the fraction of the maximum number of counts for a center to be reassigned. Higher values yield better clustering results." /> + </section> + </xml> - <xml name="argmin_distance_condition"> - <when value="pairwise_distances_argmin"> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="axis" type="integer" optional="true" value="1" label="Axis" help="Axis along which the argmin and distances are to be computed." /> - <expand macro="distance_metrics"> - <yield /> - </expand> - <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run." /> - </section> - </when> - </xml> + <xml name="kmeans_advanced_options"> + <section name="options" title="Advanced Options" expanded="False"> + <expand macro="n_clusters" /> + <expand macro="init" /> + <expand macro="n_init" /> + <expand macro="max_iter" /> + <expand macro="tol" default_value="0.0001" help_text="Relative tolerance with regards to inertia to declare convergence." /> + <!--param argument="precompute_distances"/--> + <expand macro="random_state" /> + <param argument="copy_x" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing distances" help="Mofifying the original data introduces small numerical differences caused by subtracting and then adding the data mean." /> + <expand macro="kmeans_algorithm" /> + </section> + </xml> - <xml name="sparse_preprocessors"> - <param name="selected_pre_processor" type="select" label="Select a preprocessor:"> - <option value="StandardScaler" selected="true">Standard Scaler (Standardizes features by removing the mean and scaling to unit variance)</option> - <option value="Binarizer">Binarizer (Binarizes data)</option> - <option value="MaxAbsScaler">Max Abs Scaler (Scales features by their maximum absolute value)</option> - <option value="Normalizer">Normalizer (Normalizes samples individually to unit norm)</option> - <yield /> - </param> - </xml> + <xml name="kmeans_algorithm"> + <param argument="algorithm" type="select" label="K-means algorithm to use:"> + <option value="auto" selected="true">auto</option> + <option value="full">full</option> + <option value="elkan">elkan</option> + </param> + </xml> - <xml name="sparse_preprocessors_ext"> - <expand macro="sparse_preprocessors"> - <option value="KernelCenterer">Kernel Centerer (Centers a kernel matrix)</option> - <option value="MinMaxScaler">Minmax Scaler (Scales features to a range)</option> - <option value="PolynomialFeatures">Polynomial Features (Generates polynomial and interaction features)</option> - <option value="RobustScaler">Robust Scaler (Scales features using outlier-invariance statistics)</option> - <option value="QuantileTransformer">QuantileTransformer (Transform features using quantiles information)</option> - <option value="PowerTransformer">PowerTransformer (Apply a power transform featurewise to make data more Gaussian-like)</option> - <option value="KBinsDiscretizer">KBinsDiscretizer (Bin continuous data into intervals.)</option> - </expand> - </xml> + <xml name="birch_advanced_options"> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="threshold" type="float" optional="true" value="0.5" label="Subcluster radius threshold" help="The radius of the subcluster obtained by merging a new sample; the closest subcluster should be less than the threshold to avoid a new subcluster." /> + <param argument="branching_factor" type="integer" optional="true" value="50" label="Maximum number of subclusters per branch" help="Maximum number of CF subclusters in each node." /> + <expand macro="n_clusters" default_value="3" /> + <!--param argument="compute_labels"/--> + </section> + </xml> - <xml name="sparse_preprocessor_options"> - <when value="Binarizer"> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing binarization" help=" " /> - <param argument="threshold" type="float" optional="true" value="0.0" label="Threshold" help="Feature values below or equal to this are replaced by 0, above it by 1. Threshold may not be less than 0 for operations on sparse matrices. " /> - </section> - </when> - <when value="StandardScaler"> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for performing inplace scaling" help=" " /> - <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Center the data before scaling" help=" " /> - <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Scale the data to unit variance (or unit standard deviation)" help=" " /> - </section> - </when> - <when value="MaxAbsScaler"> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing scaling" help=" " /> - </section> - </when> - <when value="Normalizer"> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" "> - <option value="l1" selected="true">l1</option> - <option value="l2">l2</option> - <option value="max">max</option> - </param> - <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing row normalization" help=" " /> - </section> - </when> - <yield /> - </xml> + <xml name="dbscan_advanced_options"> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="eps" type="float" optional="true" value="0.5" label="Maximum neighborhood distance" help="The maximum distance between two samples for them to be considered as in the same neighborhood." /> + <param argument="min_samples" type="integer" optional="true" value="5" label="Minimal core point density" help="The number of samples (or total weight) in a neighborhood for a point (including the point itself) to be considered as a core point." /> + <param argument="metric" type="text" optional="true" value="euclidean" label="Metric" help="The metric to use when calculating distance between instances in a feature array." /> + <param argument="algorithm" type="select" label="Pointwise distance computation algorithm" help="The algorithm to be used by the NearestNeighbors module to compute pointwise distances and find nearest neighbors."> + <option value="auto" selected="true">auto</option> + <option value="ball_tree">ball_tree</option> + <option value="kd_tree">kd_tree</option> + <option value="brute">brute</option> + </param> + <param argument="leaf_size" type="integer" optional="true" value="30" label="Leaf size" help="Leaf size passed to BallTree or cKDTree. Memory and time efficieny factor in tree constrution and querying." /> + </section> + </xml> - <xml name="sparse_preprocessor_options_ext"> - <expand macro="sparse_preprocessor_options"> - <when value="KernelCenterer"> - <section name="options" title="Advanced Options" expanded="False"> - </section> - </when> - <when value="MinMaxScaler"> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="feature_range" type="text" value="(0, 1)" optional="true" help="Desired range of transformed data. None or tuple (min, max). None equals to (0, 1)" /> - <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing normalization" help=" " /> - </section> - </when> - <when value="PolynomialFeatures"> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="degree" type="integer" optional="true" value="2" label="The degree of the polynomial features " help="" /> - <param argument="interaction_only" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false" label="Produce interaction features only" help="(Features that are products of at most degree distinct input features) " /> - <param argument="include_bias" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Include a bias column" help="Feature in which all polynomial powers are zero " /> - </section> - </when> - <when value="RobustScaler"> - <section name="options" title="Advanced Options" expanded="False"> - <!--=True, =True, copy=True--> - <param argument="with_centering" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Center the data before scaling" help=" " /> - <param argument="with_scaling" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Scale the data to interquartile range" help=" " /> - <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for inplace scaling" help=" " /> - </section> - </when> - <when value="QuantileTransformer"> - <section name="options" title="Advanced Options" expanded="False"> - <param name="n_quantiles" type="integer" value="1000" min="0" label="Number of quantiles to be computed" /> - <param name="output_distribution" type="select" label="Marginal distribution for the transformed data"> - <option value="uniform" selected="true">uniform</option> - <option value="normal">normal</option> - </param> - <param name="ignore_implicit_zeros" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Whether to discard sparse entries" help="Only applies to sparse matrices. If False, sparse entries are treated as zeros" /> - <param name="subsample" type="integer" value="100000" label="Maximum number of samples used to estimate the quantiles for computational efficiency" help="Note that the subsampling procedure may differ for value-identical sparse and dense matrices." /> - <expand macro="random_state" help_text="This is used by subsampling and smoothing noise" /> - </section> - </when> - <when value="PowerTransformer"> - <section name="options" title="Advanced Options" expanded="False"> - <param name="method" type="select" label="The power transform method"> - <option value="yeo-johnson" selected="true">yeo-johnson (works with positive and negative values)</option> - <option value="box-cox">box-cox (might perform better, but only works with strictly positive values)</option> - </param> - <param name="standardize" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Whether to apply zero-mean, unit-variance normalization to the transformed output." /> - </section> - </when> - <when value="KBinsDiscretizer"> - <section name="options" title="Advanced Options" expanded="False"> - <param name="n_bins" type="integer" value="5" min="2" label="The number of bins to produce" /> - <param name="encode" type="select" label="Method used to encode the transformed result"> - <option value="onehot" selected="true">onehot (encode the transformed result with one-hot encoding and return a sparse matrix)</option> - <option value="onehot-dense">onehot-dense (encode the transformed result with one-hot encoding and return a dense array)</option> - <option value="ordinal">ordinal (return the bin identifier encoded as an integer value)</option> - </param> - <param name="strategy" type="select" label="Strategy used to define the widths of the bins"> - <option value="uniform">uniform (all bins in each feature have identical widths)</option> - <option value="quantile" selected="true">quantile (all bins in each feature have the same number of points)</option> - <option value="kmeans">kmeans (values in each bin have the same nearest center of a 1D k-means cluster)</option> - </param> - </section> - </when> - </expand> - </xml> + <xml name="clustering_algorithms_options"> + <conditional name="algorithm_options"> + <param name="selected_algorithm" type="select" label="Clustering Algorithm"> + <option value="KMeans" selected="true">KMeans</option> + <option value="SpectralClustering">Spectral Clustering</option> + <option value="MiniBatchKMeans">Mini Batch KMeans</option> + <option value="DBSCAN">DBSCAN</option> + <option value="Birch">Birch</option> + </param> + <when value="KMeans"> + <expand macro="kmeans_advanced_options" /> + </when> + <when value="DBSCAN"> + <expand macro="dbscan_advanced_options" /> + </when> + <when value="Birch"> + <expand macro="birch_advanced_options" /> + </when> + <when value="SpectralClustering"> + <expand macro="spectral_clustering_advanced_options" /> + </when> + <when value="MiniBatchKMeans"> + <expand macro="minibatch_kmeans_advanced_options" /> + </when> + </conditional> + </xml> + + <xml name="distance_metrics"> + <param argument="metric" type="select" label="Distance metric" help=" "> + <option value="euclidean" selected="true">euclidean</option> + <option value="cityblock">cityblock</option> + <option value="cosine">cosine</option> + <option value="l1">l1</option> + <option value="l2">l2</option> + <option value="manhattan">manhattan</option> + <yield /> + </param> + </xml> - <xml name="cv_splitter"> - <option value="default" selected="true">default splitter</option> - <option value="KFold">KFold</option> - <option value="StratifiedKFold">StratifiedKFold</option> - <option value="LeaveOneOut">LeaveOneOut</option> - <option value="LeavePOut">LeavePOut</option> - <option value="RepeatedKFold">RepeatedKFold</option> - <option value="RepeatedStratifiedKFold">RepeatedStratifiedKFold</option> - <option value="ShuffleSplit">ShuffleSplit</option> - <option value="StratifiedShuffleSplit">StratifiedShuffleSplit</option> - <option value="TimeSeriesSplit">TimeSeriesSplit</option> - <option value="PredefinedSplit">PredefinedSplit</option> - <option value="OrderedKFold">OrderedKFold</option> - <option value="RepeatedOrderedKFold">RepeatedOrderedKFold</option> - <yield /> - </xml> + <xml name="distance_nonsparse_metrics"> + <option value="braycurtis">braycurtis</option> + <option value="canberra">canberra</option> + <option value="chebyshev">chebyshev</option> + <option value="correlation">correlation</option> + <option value="dice">dice</option> + <option value="hamming">hamming</option> + <option value="jaccard">jaccard</option> + <option value="kulsinski">kulsinski</option> + <option value="mahalanobis">mahalanobis</option> + <option value="matching">matching</option> + <option value="minkowski">minkowski</option> + <option value="rogerstanimoto">rogerstanimoto</option> + <option value="russellrao">russellrao</option> + <option value="seuclidean">seuclidean</option> + <option value="sokalmichener">sokalmichener</option> + <option value="sokalsneath">sokalsneath</option> + <option value="sqeuclidean">sqeuclidean</option> + <option value="yule">yule</option> + </xml> + + <xml name="pairwise_kernel_metrics"> + <param argument="metric" type="select" label="Pirwise Kernel metric" help=" "> + <option value="rbf" selected="true">rbf</option> + <option value="sigmoid">sigmoid</option> + <option value="polynomial">polynomial</option> + <option value="linear" selected="true">linear</option> + <option value="chi2">chi2</option> + <option value="additive_chi2">additive_chi2</option> + </param> + </xml> + + <xml name="sparse_pairwise_metric_functions"> + <param name="selected_metric_function" type="select" label="Select the pairwise metric you want to compute:"> + <option value="euclidean_distances" selected="true">Euclidean distance matrix</option> + <option value="pairwise_distances">Distance matrix</option> + <option value="pairwise_distances_argmin">Minimum distances between one point and a set of points</option> + <yield /> + </param> + </xml> + + <xml name="pairwise_metric_functions"> + <option value="additive_chi2_kernel" >Additive chi-squared kernel</option> + <option value="chi2_kernel">Exponential chi-squared kernel</option> + <option value="linear_kernel">Linear kernel</option> + <option value="manhattan_distances">L1 distances</option> + <option value="pairwise_kernels">Kernel</option> + <option value="polynomial_kernel">Polynomial kernel</option> + <option value="rbf_kernel">Gaussian (rbf) kernel</option> + <option value="laplacian_kernel">Laplacian kernel</option> + </xml> - <xml name="cv_splitter_options"> - <when value="default"> - <expand macro="cv_n_splits" /> - </when> - <when value="KFold"> - <expand macro="cv_n_splits" /> - <expand macro="cv_shuffle" /> - <expand macro="random_state" /> - </when> - <when value="StratifiedKFold"> - <expand macro="cv_n_splits" /> - <expand macro="cv_shuffle" /> - <expand macro="random_state" /> - </when> - <when value="LeaveOneOut"> - </when> - <when value="LeavePOut"> - <param argument="p" type="integer" value="" label="p" help="Integer. Size of the test sets." /> - </when> - <when value="RepeatedKFold"> - <expand macro="cv_n_splits" value="5" /> - <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." /> - <expand macro="random_state" /> - </when> - <when value="RepeatedStratifiedKFold"> - <expand macro="cv_n_splits" value="5" /> - <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." /> - <expand macro="random_state" /> - </when> - <when value="ShuffleSplit"> - <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations." /> - <expand macro="cv_test_size" value="0.1" /> - <expand macro="random_state" /> - </when> - <when value="StratifiedShuffleSplit"> - <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations." /> - <expand macro="cv_test_size" value="0.1" /> - <expand macro="random_state" /> - </when> - <when value="TimeSeriesSplit"> - <expand macro="cv_n_splits" /> - <param argument="max_train_size" type="integer" value="" optional="true" label="Maximum size of the training set" help="Maximum size for a single training set." /> - </when> - <when value="PredefinedSplit"> - <param argument="test_fold" type="text" value="" area="true" label="test_fold" help="List, e.g., [0, 1, -1, 1], represents two test sets, [X[0]] and [X[1], X[3]], X[2] is excluded from any test set due to '-1'." /> - </when> - <when value="OrderedKFold"> - <expand macro="cv_n_splits" /> - <expand macro="cv_shuffle" /> - <expand macro="random_state" /> - </when> - <when value="RepeatedOrderedKFold"> - <expand macro="cv_n_splits" /> - <param argument="n_repeats" type="integer" value="5" /> - <expand macro="random_state" /> - </when> - <yield /> - </xml> + <xml name="sparse_pairwise_condition"> + <when value="pairwise_distances"> + <section name="options" title="Advanced Options" expanded="False"> + <expand macro="distance_metrics"> + <yield /> + </expand> + </section> + </when> + <when value="euclidean_distances"> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="squared" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" + label="Return squared Euclidean distances" help=" " /> + </section> + </when> + </xml> - <xml name="cv"> - <conditional name="cv_selector"> - <param name="selected_cv" type="select" label="Select the cv splitter:"> - <expand macro="cv_splitter"> - <option value="GroupKFold">GroupKFold</option> - <option value="GroupShuffleSplit">GroupShuffleSplit</option> - <option value="LeaveOneGroupOut">LeaveOneGroupOut</option> - <option value="LeavePGroupsOut">LeavePGroupsOut</option> - </expand> - </param> - <expand macro="cv_splitter_options"> - <when value="GroupKFold"> - <expand macro="cv_n_splits" /> - <expand macro="cv_groups" /> - </when> - <when value="GroupShuffleSplit"> - <expand macro="cv_n_splits" value="5" /> - <expand macro="cv_test_size" /> - <expand macro="random_state" /> - <expand macro="cv_groups" /> - </when> - <when value="LeaveOneGroupOut"> - <expand macro="cv_groups" /> - </when> - <when value="LeavePGroupsOut"> - <param argument="n_groups" type="integer" value="" label="n_groups" help="Number of groups (p) to leave out in the test split." /> - <expand macro="cv_groups" /> - </when> - </expand> - </conditional> - </xml> + <xml name="argmin_distance_condition"> + <when value="pairwise_distances_argmin"> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="axis" type="integer" optional="true" value="1" label="Axis" help="Axis along which the argmin and distances are to be computed." /> + <expand macro="distance_metrics"> + <yield /> + </expand> + <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run." /> + </section> + </when> + </xml> - <xml name="cv_reduced" token_label="Select the cv splitter"> - <conditional name="cv_selector"> - <param name="selected_cv" type="select" label="@LABEL@"> - <expand macro="cv_splitter" /> - </param> - <expand macro="cv_splitter_options" /> - </conditional> - </xml> - - <xml name="cv_n_splits" token_value="3" token_help="Number of folds. Must be at least 2."> - <param argument="n_splits" type="integer" value="@VALUE@" min="1" label="n_splits" help="@HELP@" /> - </xml> + <xml name="sparse_preprocessors"> + <param name="selected_pre_processor" type="select" label="Select a preprocessor:"> + <option value="StandardScaler" selected="true">Standard Scaler (Standardizes features by removing the mean and scaling to unit variance)</option> + <option value="Binarizer">Binarizer (Binarizes data)</option> + <option value="MaxAbsScaler">Max Abs Scaler (Scales features by their maximum absolute value)</option> + <option value="Normalizer">Normalizer (Normalizes samples individually to unit norm)</option> + <yield /> + </param> + </xml> - <xml name="cv_shuffle"> - <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Whether to shuffle data before splitting" /> - </xml> - - <xml name="cv_test_size" token_value="0.2"> - <param argument="test_size" type="float" value="@VALUE@" min="0.0" label="Portion or number of the test set" help="0.0-1.0, proportion of the dataset to include in the test split; >1, integer only, the absolute number of test samples " /> - </xml> - - <xml name="cv_groups"> - <section name="groups_selector" title="Groups column selector" expanded="true"> - <param name="infile_g" type="data" format="tabular" label="Choose dataset containing groups info:" /> - <param name="header_g" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" /> - <conditional name="column_selector_options_g"> - <expand macro="samples_column_selector_options" column_option="selected_column_selector_option_g" col_name="col_g" multiple="False" infile="infile_g" /> - </conditional> - </section> - </xml> + <xml name="sparse_preprocessors_ext"> + <expand macro="sparse_preprocessors"> + <option value="KernelCenterer">Kernel Centerer (Centers a kernel matrix)</option> + <option value="MinMaxScaler">Minmax Scaler (Scales features to a range)</option> + <option value="PolynomialFeatures">Polynomial Features (Generates polynomial and interaction features)</option> + <option value="RobustScaler">Robust Scaler (Scales features using outlier-invariance statistics)</option> + <option value="QuantileTransformer">QuantileTransformer (Transform features using quantiles information)</option> + <option value="PowerTransformer">PowerTransformer (Apply a power transform featurewise to make data more Gaussian-like)</option> + <option value="KBinsDiscretizer">KBinsDiscretizer (Bin continuous data into intervals.)</option> + </expand> + </xml> - <xml name="train_test_split_params"> - <conditional name="split_algos"> - <param name="shuffle" type="select" label="Select the splitting method"> - <option value="None">No shuffle</option> - <option value="simple" selected="true">ShuffleSplit</option> - <option value="stratified">StratifiedShuffleSplit -- target values serve as class labels</option> - <option value="group">GroupShuffleSplit or split by group names</option> - </param> - <when value="None"> - <expand macro="train_test_split_test_size" /> - </when> - <when value="simple"> - <expand macro="train_test_split_test_size" /> - <expand macro="random_state" /> - </when> - <when value="stratified"> - <expand macro="train_test_split_test_size" /> - <expand macro="random_state" /> - </when> - <when value="group"> - <expand macro="train_test_split_test_size" optional="true" /> - <expand macro="random_state" /> - <param argument="group_names" type="text" value="" optional="true" label="Type in group names instead" help="For example: chr6, chr7. This parameter is optional. If used, it will override the holdout size and random seed." /> - <yield /> - </when> - </conditional> - <!--param argument="train_size" type="float" optional="True" value="" label="Train size:"/>--> - </xml> - - <xml name="train_test_split_test_size" token_optional="false"> - <param name="test_size" type="float" value="0.2" optional="@OPTIONAL@" label="Holdout size" help="Leass than 1, for preportion; greater than 1 (integer), for number of samples." /> - </xml> - - <xml name="feature_selection_algorithms"> - <option value="SelectKBest" selected="true">SelectKBest - Select features according to the k highest scores</option> - <option value="GenericUnivariateSelect">GenericUnivariateSelect - Univariate feature selector with configurable strategy</option> - <option value="SelectPercentile">SelectPercentile - Select features according to a percentile of the highest scores</option> - <option value="SelectFpr">SelectFpr - Filter: Select the p-values below alpha based on a FPR test</option> - <option value="SelectFdr">SelectFdr - Filter: Select the p-values for an estimated false discovery rate</option> - <option value="SelectFwe">SelectFwe - Filter: Select the p-values corresponding to Family-wise error rate</option> - <option value="VarianceThreshold">VarianceThreshold - Feature selector that removes all low-variance features</option> - <option value="SelectFromModel">SelectFromModel - Meta-transformer for selecting features based on importance weights</option> - <option value="RFE">RFE - Feature ranking with recursive feature elimination</option> - <option value="RFECV">RFECV - Feature ranking with recursive feature elimination and cross-validated selection of the best number of features</option> - <yield /> - </xml> + <xml name="sparse_preprocessor_options"> + <when value="Binarizer"> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" + label="Use a copy of data for precomputing binarization" help=" " /> + <param argument="threshold" type="float" optional="true" value="0.0" + label="Threshold" + help="Feature values below or equal to this are replaced by 0, above it by 1. Threshold may not be less than 0 for operations on sparse matrices. " /> + </section> + </when> + <when value="StandardScaler"> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" + label="Use a copy of data for performing inplace scaling" help=" " /> + <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" + label="Center the data before scaling" help=" " /> + <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" + label="Scale the data to unit variance (or unit standard deviation)" help=" " /> + </section> + </when> + <when value="MaxAbsScaler"> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" + label="Use a copy of data for precomputing scaling" help=" " /> + </section> + </when> + <when value="Normalizer"> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" "> + <option value="l1" selected="true">l1</option> + <option value="l2">l2</option> + <option value="max">max</option> + </param> + <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" + label="Use a copy of data for precomputing row normalization" help=" " /> + </section> + </when> + <yield /> + </xml> - <xml name="feature_selection_algorithm_details"> - <when value="GenericUnivariateSelect"> - <expand macro="feature_selection_score_function" /> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="mode" type="select" label="Feature selection mode"> - <option value="percentile">percentile</option> - <option value="k_best">k_best</option> - <option value="fpr">fpr</option> - <option value="fdr">fdr</option> - <option value="fwe">fwe</option> - </param> - <param argument="param" type="float" value="" optional="true" label="Parameter of the corresponding mode" help="float or int depending on the feature selection mode" /> - </section> - </when> - <when value="SelectPercentile"> - <expand macro="feature_selection_score_function" /> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="percentile" type="integer" value="10" optional="True" label="Percent of features to keep" /> - </section> - </when> - <when value="SelectKBest"> - <expand macro="feature_selection_score_function" /> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="k" type="integer" value="10" optional="True" label="Number of top features to select" help="No 'all' option is supported." /> - </section> - </when> - <when value="SelectFpr"> - <expand macro="feature_selection_score_function" /> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest p-value for features to be kept." /> - </section> - </when> - <when value="SelectFdr"> - <expand macro="feature_selection_score_function" /> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep." /> - </section> - </when> - <when value="SelectFwe"> - <expand macro="feature_selection_score_function" /> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep." /> - </section> - </when> - <when value="VarianceThreshold"> - <section name="options" title="Options" expanded="False"> - <param argument="threshold" type="float" value="0.0" optional="True" label="Threshold" help="Features with a training-set variance lower than this threshold will be removed." /> - </section> - </when> - </xml> - - <xml name="feature_selection_SelectFromModel"> - <when value="SelectFromModel"> - <conditional name="model_inputter"> - <param name="input_mode" type="select" label="Construct a new estimator from a selection list?"> - <option value="new" selected="true">Yes</option> - <option value="prefitted">No. Load a prefitted estimator</option> - </param> - <when value="new"> - <expand macro="estimator_selector_fs" /> - </when> - <when value="prefitted"> - <param name="fitted_estimator" type="data" format='zip' label="Load a prefitted estimator" /> - </when> - </conditional> - <expand macro="feature_selection_SelectFromModel_options" /> - </when> - </xml> - - <xml name="feature_selection_SelectFromModel_no_prefitted"> - <when value="SelectFromModel"> - <conditional name="model_inputter"> - <param name="input_mode" type="select" label="Construct a new estimator from a selection list?"> - <option value="new" selected="true">Yes</option> - </param> - <when value="new"> - <expand macro="estimator_selector_all" /> - </when> - </conditional> - <expand macro="feature_selection_SelectFromModel_options" /> - </when> - </xml> - - <xml name="feature_selection_SelectFromModel_options"> + <xml name="sparse_preprocessor_options_ext"> + <expand macro="sparse_preprocessor_options"> + <when value="KernelCenterer"> + <section name="options" title="Advanced Options" expanded="False"> + </section> + </when> + <when value="MinMaxScaler"> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="feature_range" type="text" value="(0, 1)" optional="true" help="Desired range of transformed data. None or tuple (min, max). None equals to (0, 1)" /> + <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" + label="Use a copy of data for precomputing normalization" help=" " /> + </section> + </when> + <when value="PolynomialFeatures"> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="degree" type="integer" optional="true" value="2" label="The degree of the polynomial features " help="" /> + <param argument="interaction_only" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false" label="Produce interaction features only" help="(Features that are products of at most degree distinct input features) " /> + <param argument="include_bias" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Include a bias column" help="Feature in which all polynomial powers are zero " /> + </section> + </when> + <when value="RobustScaler"> + <section name="options" title="Advanced Options" expanded="False"> + <!--=True, =True, copy=True--> + <param argument="with_centering" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" + label="Center the data before scaling" help=" " /> + <param argument="with_scaling" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" + label="Scale the data to interquartile range" help=" " /> + <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" + label="Use a copy of data for inplace scaling" help=" " /> + </section> + </when> + <when value="QuantileTransformer"> + <section name="options" title="Advanced Options" expanded="False"> + <param name="n_quantiles" type="integer" value="1000" min="0" label="Number of quantiles to be computed" /> + <param name="output_distribution" type="select" label="Marginal distribution for the transformed data"> + <option value="uniform" selected="true">uniform</option> + <option value="normal">normal</option> + </param> + <param name="ignore_implicit_zeros" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Whether to discard sparse entries" help="Only applies to sparse matrices. If False, sparse entries are treated as zeros" /> + <param name="subsample" type="integer" value="100000" label="Maximum number of samples used to estimate the quantiles for computational efficiency" help="Note that the subsampling procedure may differ for value-identical sparse and dense matrices." /> + <expand macro="random_state" help_text="This is used by subsampling and smoothing noise" /> + </section> + </when> + <when value="PowerTransformer"> + <section name="options" title="Advanced Options" expanded="False"> + <param name="method" type="select" label="The power transform method"> + <option value="yeo-johnson" selected="true">yeo-johnson (works with positive and negative values)</option> + <option value="box-cox">box-cox (might perform better, but only works with strictly positive values)</option> + </param> + <param name="standardize" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Whether to apply zero-mean, unit-variance normalization to the transformed output." /> + </section> + </when> + <when value="KBinsDiscretizer"> <section name="options" title="Advanced Options" expanded="False"> - <param argument="threshold" type="text" value="" optional="true" label="threshold" help="The threshold value to use for feature selection. e.g. 'mean', 'median', '1.25*mean'." /> - <param argument="norm_order" type="integer" value="1" label="norm_order" help="Order of the norm used to filter the vectors of coefficients below threshold in the case where the coef_ attribute of the estimator is of dimension 2. " /> - <param argument="max_features" type="integer" value="" optional="true" label="The maximum number of features selected scoring above threshold" help="To disable threshold and only select based on max_features, set threshold=-np.inf." /> + <param name="n_bins" type="integer" value="5" min="2" label="The number of bins to produce" /> + <param name="encode" type="select" label="Method used to encode the transformed result"> + <option value="onehot" selected="true">onehot (encode the transformed result with one-hot encoding and return a sparse matrix)</option> + <option value="onehot-dense">onehot-dense (encode the transformed result with one-hot encoding and return a dense array)</option> + <option value="ordinal">ordinal (return the bin identifier encoded as an integer value)</option> + </param> + <param name="strategy" type="select" label="Strategy used to define the widths of the bins"> + <option value="uniform">uniform (all bins in each feature have identical widths)</option> + <option value="quantile" selected="true">quantile (all bins in each feature have the same number of points)</option> + <option value="kmeans">kmeans (values in each bin have the same nearest center of a 1D k-means cluster)</option> + </param> </section> - </xml> - - <xml name="feature_selection_RFE"> - <when value="RFE"> - <yield /> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="n_features_to_select" type="integer" value="" optional="true" label="n_features_to_select" help="The number of features to select. If None, half of the features are selected." /> - <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " /> - <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." /> - </section> - </when> - </xml> + </when> + </expand> + </xml> - <xml name="feature_selection_RFECV_fs"> - <when value="RFECV"> - <yield /> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " /> - <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected" /> - <expand macro="cv" /> - <expand macro="scoring_selection" /> - <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." /> - </section> - </when> - </xml> - - <xml name="feature_selection_RFECV_pipeline"> - <when value="RFECV"> - <yield /> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " /> - <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected" /> - <expand macro="cv_reduced" /> - <!-- TODO: group splitter support--> - <expand macro="scoring_selection" /> - <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." /> - </section> - </when> - </xml> + <xml name="cv_splitter"> + <option value="default" selected="true">default splitter</option> + <option value="KFold">KFold</option> + <option value="StratifiedKFold">StratifiedKFold</option> + <option value="LeaveOneOut">LeaveOneOut</option> + <option value="LeavePOut">LeavePOut</option> + <option value="RepeatedKFold">RepeatedKFold</option> + <option value="RepeatedStratifiedKFold">RepeatedStratifiedKFold</option> + <option value="ShuffleSplit">ShuffleSplit</option> + <option value="StratifiedShuffleSplit">StratifiedShuffleSplit</option> + <option value="TimeSeriesSplit">TimeSeriesSplit</option> + <option value="PredefinedSplit">PredefinedSplit</option> + <option value="OrderedKFold">OrderedKFold</option> + <option value="RepeatedOrderedKFold">RepeatedOrderedKFold</option> + <yield /> + </xml> - <xml name="feature_selection_DyRFECV_fs"> - <when value="DyRFECV"> - <yield /> - <section name="options" title="Advanced Options" expanded="False"> - <param argument="step" type="text" size="30" value="1" label="step" optional="true" help="Default = 1. Support float, int and list."> - <sanitizer> - <valid initial="default"> - <add value="[" /> - <add value="]" /> - </valid> - </sanitizer> - </param> - <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected" /> - <expand macro="cv" /> - <expand macro="scoring_selection" /> - <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." /> - </section> - </when> - </xml> + <xml name="cv_splitter_options"> + <when value="default"> + <expand macro="cv_n_splits" /> + </when> + <when value="KFold"> + <expand macro="cv_n_splits" /> + <expand macro="cv_shuffle" /> + <expand macro="random_state" /> + </when> + <when value="StratifiedKFold"> + <expand macro="cv_n_splits" /> + <expand macro="cv_shuffle" /> + <expand macro="random_state" /> + </when> + <when value="LeaveOneOut"> + </when> + <when value="LeavePOut"> + <param argument="p" type="integer" value="" label="p" help="Integer. Size of the test sets." /> + </when> + <when value="RepeatedKFold"> + <expand macro="cv_n_splits" value="5" /> + <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." /> + <expand macro="random_state" /> + </when> + <when value="RepeatedStratifiedKFold"> + <expand macro="cv_n_splits" value="5" /> + <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." /> + <expand macro="random_state" /> + </when> + <when value="ShuffleSplit"> + <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations." /> + <expand macro="cv_test_size" value="0.1" /> + <expand macro="random_state" /> + </when> + <when value="StratifiedShuffleSplit"> + <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations." /> + <expand macro="cv_test_size" value="0.1" /> + <expand macro="random_state" /> + </when> + <when value="TimeSeriesSplit"> + <expand macro="cv_n_splits" /> + <param argument="max_train_size" type="integer" value="" optional="true" label="Maximum size of the training set" help="Maximum size for a single training set." /> + </when> + <when value="PredefinedSplit"> + <param argument="test_fold" type="text" value="" area="true" label="test_fold" help="List, e.g., [0, 1, -1, 1], represents two test sets, [X[0]] and [X[1], X[3]], X[2] is excluded from any test set due to '-1'." /> + </when> + <when value="OrderedKFold"> + <expand macro="cv_n_splits" /> + <expand macro="cv_shuffle" /> + <expand macro="random_state" /> + <expand macro="cv_n_stratification_bins" /> + </when> + <when value="RepeatedOrderedKFold"> + <expand macro="cv_n_splits" /> + <param argument="n_repeats" type="integer" value="5" /> + <expand macro="random_state" /> + <expand macro="cv_n_stratification_bins" /> + </when> + <yield /> + </xml> - <xml name="feature_selection_pipeline"> - <!--compare to `feature_selection_fs`, no fitted estimator for SelectFromModel and no custom estimator for RFE and RFECV--> - <conditional name="fs_algorithm_selector"> - <param name="selected_algorithm" type="select" label="Select a feature selection algorithm"> - <expand macro="feature_selection_algorithms" /> - </param> - <expand macro="feature_selection_algorithm_details" /> - <expand macro="feature_selection_SelectFromModel_no_prefitted" /> - <expand macro="feature_selection_RFE"> - <expand macro="estimator_selector_all" /> - </expand> - <expand macro="feature_selection_RFECV_pipeline"> - <expand macro="estimator_selector_all" /> - </expand> - <!-- TODO: add DyRFECV to pipeline--> - </conditional> - </xml> + <xml name="cv"> + <conditional name="cv_selector"> + <param name="selected_cv" type="select" label="Select the cv splitter:"> + <expand macro="cv_splitter"> + <option value="GroupKFold">GroupKFold</option> + <option value="GroupShuffleSplit">GroupShuffleSplit</option> + <option value="LeaveOneGroupOut">LeaveOneGroupOut</option> + <option value="LeavePGroupsOut">LeavePGroupsOut</option> + </expand> + </param> + <expand macro="cv_splitter_options"> + <when value="GroupKFold"> + <expand macro="cv_n_splits" /> + <expand macro="cv_groups" /> + </when> + <when value="GroupShuffleSplit"> + <expand macro="cv_n_splits" value="5" /> + <expand macro="cv_test_size" /> + <expand macro="random_state" /> + <expand macro="cv_groups" /> + </when> + <when value="LeaveOneGroupOut"> + <expand macro="cv_groups" /> + </when> + <when value="LeavePGroupsOut"> + <param argument="n_groups" type="integer" value="" label="n_groups" help="Number of groups (p) to leave out in the test split." /> + <expand macro="cv_groups" /> + </when> + </expand> + </conditional> + </xml> - <xml name="feature_selection_fs"> - <conditional name="fs_algorithm_selector"> - <param name="selected_algorithm" type="select" label="Select a feature selection algorithm"> - <expand macro="feature_selection_algorithms"> - <option value="DyRFECV">DyRFECV - Extended RFECV with changeable steps</option> - </expand> - </param> - <expand macro="feature_selection_algorithm_details" /> - <expand macro="feature_selection_SelectFromModel" /> - <expand macro="feature_selection_RFE"> - <expand macro="estimator_selector_fs" /> - </expand> - <expand macro="feature_selection_RFECV_fs"> - <expand macro="estimator_selector_fs" /> - </expand> - <expand macro="feature_selection_DyRFECV_fs"> - <expand macro="estimator_selector_fs" /> - </expand> - </conditional> - </xml> + <xml name="cv_reduced" token_label="Select the cv splitter"> + <conditional name="cv_selector"> + <param name="selected_cv" type="select" label="@LABEL@"> + <expand macro="cv_splitter" /> + </param> + <expand macro="cv_splitter_options" /> + </conditional> + </xml> - <xml name="feature_selection_score_function"> - <param argument="score_func" type="select" label="Select a score function"> - <option value="chi2">chi2 - Compute chi-squared stats between each non-negative feature and class</option> - <option value="f_classif">f_classif - Compute the ANOVA F-value for the provided sample</option> - <option value="f_regression">f_regression - Univariate linear regression tests</option> - <option value="mutual_info_classif">mutual_info_classif - Estimate mutual information for a discrete target variable</option> - <option value="mutual_info_regression">mutual_info_regression - Estimate mutual information for a continuous target variable</option> - </param> - </xml> + <xml name="cv_n_splits" token_value="5" token_help="Number of folds. Must be at least 2."> + <!--why set min to 1?--> + <param argument="n_splits" type="integer" value="@VALUE@" min="1" label="n_splits" help="@HELP@" /> + </xml> - <xml name="model_validation_common_options"> - <expand macro="cv" /> - <expand macro="verbose" /> - <yield /> - </xml> + <xml name="cv_shuffle"> + <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Whether to shuffle data before splitting" /> + </xml> - <xml name="scoring_selection"> - <conditional name="scoring"> - <param name="primary_scoring" type="select" multiple="false" label="Select the primary metric (scoring):" help="Metric to refit the best estimator."> - <option value="default" selected="true">default with estimator</option> - <option value="accuracy">Classification -- 'accuracy'</option> - <option value="balanced_accuracy">Classification -- 'balanced_accuracy'</option> - <option value="average_precision">Classification -- 'average_precision'</option> - <option value="f1">Classification -- 'f1'</option> - <option value="f1_micro">Classification -- 'f1_micro'</option> - <option value="f1_macro">Classification -- 'f1_macro'</option> - <option value="f1_weighted">Classification -- 'f1_weighted'</option> - <option value="f1_samples">Classification -- 'f1_samples'</option> - <option value="neg_log_loss">Classification -- 'neg_log_loss'</option> - <option value="precision">Classification -- 'precision'</option> - <option value="precision_micro">Classification -- 'precision_micro'</option> - <option value="precision_macro">Classification -- 'precision_macro'</option> - <option value="precision_wighted">Classification -- 'precision_wighted'</option> - <option value="precision_samples">Classification -- 'precision_samples'</option> - <option value="recall">Classification -- 'recall'</option> - <option value="recall_micro">Classification -- 'recall_micro'</option> - <option value="recall_macro">Classification -- 'recall_macro'</option> - <option value="recall_wighted">Classification -- 'recall_wighted'</option> - <option value="recall_samples">Classification -- 'recall_samples'</option> - <option value="roc_auc">Classification -- 'roc_auc'</option> - <option value="explained_variance">Regression -- 'explained_variance'</option> - <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option> - <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option> - <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option> - <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option> - <option value="r2">Regression -- 'r2'</option> - <option value="max_error">Regression -- 'max_error'</option> - <option value="binarize_auc_scorer">anomaly detection -- binarize_auc_scorer</option> - <option value="binarize_average_precision_scorer">anomaly detection -- binarize_average_precision_scorer</option> - </param> - <when value="default" /> - <when value="accuracy"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="balanced_accuracy"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="average_precision"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="f1"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="f1_micro"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="f1_macro"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="f1_weighted"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="f1_samples"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="neg_log_loss"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="precision"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="precision_micro"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="precision_macro"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="precision_wighted"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="precision_samples"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="recall"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="recall_micro"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="recall_macro"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="recall_wighted"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="recall_samples"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="roc_auc"> - <expand macro="secondary_scoring_selection_classification" /> - </when> - <when value="explained_variance"> - <expand macro="secondary_scoring_selection_regression" /> - </when> - <when value="neg_mean_absolute_error"> - <expand macro="secondary_scoring_selection_regression" /> - </when> - <when value="neg_mean_squared_error"> - <expand macro="secondary_scoring_selection_regression" /> - </when> - <when value="neg_mean_squared_log_error"> - <expand macro="secondary_scoring_selection_regression" /> - </when> - <when value="neg_median_absolute_error"> - <expand macro="secondary_scoring_selection_regression" /> - </when> - <when value="r2"> - <expand macro="secondary_scoring_selection_regression" /> - </when> - <when value="max_error"> - <expand macro="secondary_scoring_selection_regression" /> - </when> - <when value="binarize_auc_scorer"> - <expand macro="secondary_scoring_selection_anormaly" /> - </when> - <when value="binarize_average_precision_scorer"> - <expand macro="secondary_scoring_selection_anormaly" /> - </when> - </conditional> - </xml> + <xml name="cv_n_stratification_bins"> + <param argument="n_stratification_bins" type="integer" value="" optional="true" help="Integer. The number of stratification bins. Only relevent when shuffle is True. Valid in [2, `n_samples // n_splits`]. Default value is None, which is same as `n_samples // n_splits`. The higher the value is, the distribution of target values is more approximately the ame across all split folds." /> + </xml> + + <xml name="cv_test_size" token_value="0.2"> + <param argument="test_size" type="float" value="@VALUE@" min="0.0" label="Portion or number of the test set" help="0.0-1.0, proportion of the dataset to include in the test split; >1, integer only, the absolute number of test samples " /> + </xml> + + <xml name="cv_groups" > + <section name="groups_selector" title="Groups column selector" expanded="true"> + <param name="infile_g" type="data" format="tabular" label="Choose dataset containing groups info:" /> + <param name="header_g" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" /> + <conditional name="column_selector_options_g"> + <expand macro="samples_column_selector_options" column_option="selected_column_selector_option_g" col_name="col_g" multiple="False" infile="infile_g" /> + </conditional> + </section> + </xml> + + <xml name="train_test_split_params"> + <conditional name="split_algos"> + <param name="shuffle" type="select" label="Select the splitting method"> + <option value="None">No shuffle</option> + <option value="simple" selected="true">ShuffleSplit</option> + <option value="stratified">StratifiedShuffleSplit -- target values serve as class labels</option> + <option value="group">GroupShuffleSplit or split by group names</option> + </param> + <when value="None"> + <expand macro="train_test_split_test_size" /> + </when> + <when value="simple"> + <expand macro="train_test_split_test_size" /> + <expand macro="random_state" /> + </when> + <when value="stratified"> + <expand macro="train_test_split_test_size" /> + <expand macro="random_state" /> + </when> + <when value="group"> + <expand macro="train_test_split_test_size" optional="true" /> + <expand macro="random_state" /> + <param argument="group_names" type="text" value="" optional="true" label="Type in group names instead" + help="For example: chr6, chr7. This parameter is optional. If used, it will override the holdout size and random seed." /> + <yield /> + </when> + </conditional> + <!--param argument="train_size" type="float" optional="True" value="" label="Train size:" />--> + </xml> + + <xml name="train_test_split_test_size" token_optional="false"> + <param name="test_size" type="float" value="0.2" optional="@OPTIONAL@" label="Holdout size" help="Leass than 1, for preportion; greater than 1 (integer), for number of samples." /> + </xml> + + <xml name="feature_selection_algorithms"> + <option value="SelectKBest" selected="true">SelectKBest - Select features according to the k highest scores</option> + <option value="GenericUnivariateSelect">GenericUnivariateSelect - Univariate feature selector with configurable strategy</option> + <option value="SelectPercentile">SelectPercentile - Select features according to a percentile of the highest scores</option> + <option value="SelectFpr">SelectFpr - Filter: Select the p-values below alpha based on a FPR test</option> + <option value="SelectFdr">SelectFdr - Filter: Select the p-values for an estimated false discovery rate</option> + <option value="SelectFwe">SelectFwe - Filter: Select the p-values corresponding to Family-wise error rate</option> + <option value="VarianceThreshold">VarianceThreshold - Feature selector that removes all low-variance features</option> + <option value="SelectFromModel">SelectFromModel - Meta-transformer for selecting features based on importance weights</option> + <option value="RFE">RFE - Feature ranking with recursive feature elimination</option> + <option value="RFECV">RFECV - Feature ranking with recursive feature elimination and cross-validated selection of the best number of features</option> + <yield /> + </xml> - <xml name="secondary_scoring_selection_classification"> - <param name="secondary_scoring" type="select" multiple="true" label="Additional scoring used in multi-metric mode:" help="If the same metric with the primary is chosen, the metric will be ignored."> - <option value="accuracy">Classification -- 'accuracy'</option> - <option value="balanced_accuracy">Classification -- 'balanced_accuracy'</option> - <option value="average_precision">Classification -- 'average_precision'</option> - <option value="f1">Classification -- 'f1'</option> - <option value="f1_micro">Classification -- 'f1_micro'</option> - <option value="f1_macro">Classification -- 'f1_macro'</option> - <option value="f1_weighted">Classification -- 'f1_weighted'</option> - <option value="f1_samples">Classification -- 'f1_samples'</option> - <option value="neg_log_loss">Classification -- 'neg_log_loss'</option> - <option value="precision">Classification -- 'precision'</option> - <option value="precision_micro">Classification -- 'precision_micro'</option> - <option value="precision_macro">Classification -- 'precision_macro'</option> - <option value="precision_wighted">Classification -- 'precision_wighted'</option> - <option value="precision_samples">Classification -- 'precision_samples'</option> - <option value="recall">Classification -- 'recall'</option> - <option value="recall_micro">Classification -- 'recall_micro'</option> - <option value="recall_macro">Classification -- 'recall_macro'</option> - <option value="recall_wighted">Classification -- 'recall_wighted'</option> - <option value="recall_samples">Classification -- 'recall_samples'</option> - <option value="roc_auc">Classification -- 'roc_auc'</option> + <xml name="feature_selection_algorithm_details"> + <when value="GenericUnivariateSelect"> + <expand macro="feature_selection_score_function" /> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="mode" type="select" label="Feature selection mode"> + <option value="percentile">percentile</option> + <option value="k_best">k_best</option> + <option value="fpr">fpr</option> + <option value="fdr">fdr</option> + <option value="fwe">fwe</option> </param> - </xml> - - <xml name="secondary_scoring_selection_regression"> - <param name="secondary_scoring" type="select" multiple="true" label="Additional scoring used in multi-metric mode:" help="If the same metric with the primary is chosen, the metric will be ignored."> - <option value="explained_variance">Regression -- 'explained_variance'</option> - <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option> - <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option> - <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option> - <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option> - <option value="r2">Regression -- 'r2'</option> - <option value="max_error">Regression -- 'max_error'</option> - </param> - </xml> - - <xml name="secondary_scoring_selection_anormaly"> - <param name="secondary_scoring" type="select" multiple="true" label="Additional scoring used in multi-metric mode:" help="If the same metric with the primary is chosen, the metric will be ignored."> - <option value="binarize_auc_scorer">anomaly detection -- binarize_auc_scorer</option> - <option value="binarize_average_precision_scorer">anomaly detection -- binarize_average_precision_scorer</option> - </param> - </xml> - - <xml name="pre_dispatch" token_type="hidden" token_default_value="all" token_help="Number of predispatched jobs for parallel execution"> - <param argument="pre_dispatch" type="@TYPE@" value="@DEFAULT_VALUE@" optional="true" label="pre_dispatch" help="@HELP@" /> - </xml> + <param argument="param" type="float" value="" optional="true" label="Parameter of the corresponding mode" help="float or int depending on the feature selection mode" /> + </section> + </when> + <when value="SelectPercentile"> + <expand macro="feature_selection_score_function" /> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="percentile" type="integer" value="10" optional="True" label="Percent of features to keep" /> + </section> + </when> + <when value="SelectKBest"> + <expand macro="feature_selection_score_function" /> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="k" type="integer" value="10" optional="True" label="Number of top features to select" help="No 'all' option is supported." /> + </section> + </when> + <when value="SelectFpr"> + <expand macro="feature_selection_score_function" /> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest p-value for features to be kept." /> + </section> + </when> + <when value="SelectFdr"> + <expand macro="feature_selection_score_function" /> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep." /> + </section> + </when> + <when value="SelectFwe"> + <expand macro="feature_selection_score_function" /> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep." /> + </section> + </when> + <when value="VarianceThreshold"> + <section name="options" title="Options" expanded="False"> + <param argument="threshold" type="float" value="0.0" optional="True" label="Threshold" help="Features with a training-set variance lower than this threshold will be removed." /> + </section> + </when> + </xml> - <xml name="estimator_and_hyperparameter"> - <param name="infile_estimator" type="data" format="zip" label="Choose the dataset containing pipeline/estimator object" /> - <section name="hyperparams_swapping" title="Hyperparameter Swapping" expanded="false"> - <param name="infile_params" type="data" format="tabular" optional="true" label="Choose the dataset containing hyperparameters for the pipeline/estimator above" help="This dataset could be the output of `get_params` in the `Estimator Attributes` tool." /> - <repeat name="param_set" min="1" max="30" title="New hyperparameter setting"> - <param name="sp_name" type="select" optional="true" label="Choose a parameter name (with current value)"> - <options from_dataset="infile_params" startswith="@"> - <column name="name" index="2" /> - <column name="value" index="1" /> - <filter type="unique_value" name="unique_param" column="1" /> - </options> - </param> - <param name="sp_value" type="text" value="" optional="true" label="New value" help="Supports int, float, boolean, single quoted string, and selected object constructor. Similar to the `Parameter settings for search` section in `searchcv` tool except that only single value is expected here."> - <sanitizer> - <valid initial="default"> - <add value="'" /> - <add value=""" /> - </valid> - </sanitizer> - </param> - </repeat> - </section> - </xml> - - <xml name="search_cv_options"> - <expand macro="scoring_selection" /> - <expand macro="model_validation_common_options" /> - <!--expand macro="pre_dispatch" default_value="2*n_jobs" help="Controls the number of jobs that get dispatched during parallel execution"/--> - <param argument="iid" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="iid" help="If True, data is identically distributed across the folds" /> - <!--param argument="refit" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="refit" help="Refit an estimator using the best found parameters on the whole dataset. Be aware that `refit=True` invokes extra computation, but it's REQUIRED for outputting the best estimator!"/> --> - <param argument="error_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Raise fit error:" help="If false, the metric score is assigned to NaN if an error occurs in estimator fitting and FitFailedWarning is raised." /> - <param argument="return_train_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="return_train_score" help="" /> - </xml> - - <xml name="estimator_module_options"> - <option value="svm" selected="true">sklearn.svm</option> - <option value="linear_model">sklearn.linear_model</option> - <option value="ensemble">sklearn.ensemble</option> - <option value="naive_bayes">sklearn.naive_bayes</option> - <option value="tree">sklearn.tree</option> - <option value="neighbors">sklearn.neighbors</option> - <option value="xgboost">xgboost</option> - <yield /> - </xml> + <xml name="feature_selection_SelectFromModel"> + <when value="SelectFromModel"> + <conditional name="model_inputter"> + <param name="input_mode" type="select" label="Construct a new estimator from a selection list?" > + <option value="new" selected="true">Yes</option> + <option value="prefitted">No. Load a prefitted estimator</option> + </param> + <when value="new"> + <expand macro="estimator_selector_fs" /> + </when> + <when value="prefitted"> + <param name="fitted_estimator" type="data" format='h5mlm' label="Load a prefitted estimator" /> + </when> + </conditional> + <expand macro="feature_selection_SelectFromModel_options" /> + </when> + </xml> - <xml name="estimator_suboptions"> - <when value="svm"> - <param name="selected_estimator" type="select" label="Choose estimator class:"> - <option value="LinearSVC" selected="true">LinearSVC</option> - <option value="LinearSVR">LinearSVR</option> - <option value="NuSVC">NuSVC</option> - <option value="NuSVR">NuSVR</option> - <option value="OneClassSVM">OneClassSVM</option> - <option value="SVC">SVC</option> - <option value="SVR">SVR</option> - </param> - <expand macro="estimator_params_text" /> - </when> - <when value="linear_model"> - <param name="selected_estimator" type="select" label="Choose estimator class:"> - <option value="ARDRegression" selected="true">ARDRegression</option> - <option value="BayesianRidge">BayesianRidge</option> - <option value="ElasticNet">ElasticNet</option> - <option value="ElasticNetCV">ElasticNetCV</option> - <option value="HuberRegressor">HuberRegressor</option> - <option value="Lars">Lars</option> - <option value="LarsCV">LarsCV</option> - <option value="Lasso">Lasso</option> - <option value="LassoCV">LassoCV</option> - <option value="LassoLars">LassoLars</option> - <option value="LassoLarsCV">LassoLarsCV</option> - <option value="LassoLarsIC">LassoLarsIC</option> - <option value="LinearRegression">LinearRegression</option> - <option value="LogisticRegression">LogisticRegression</option> - <option value="LogisticRegressionCV">LogisticRegressionCV</option> - <option value="MultiTaskLasso">MultiTaskLasso</option> - <option value="MultiTaskElasticNet">MultiTaskElasticNet</option> - <option value="MultiTaskLassoCV">MultiTaskLassoCV</option> - <option value="MultiTaskElasticNetCV">MultiTaskElasticNetCV</option> - <option value="OrthogonalMatchingPursuit">OrthogonalMatchingPursuit</option> - <option value="OrthogonalMatchingPursuitCV">OrthogonalMatchingPursuitCV</option> - <option value="PassiveAggressiveClassifier">PassiveAggressiveClassifier</option> - <option value="PassiveAggressiveRegressor">PassiveAggressiveRegressor</option> - <option value="Perceptron">Perceptron</option> - <option value="RANSACRegressor">RANSACRegressor</option> - <option value="Ridge">Ridge</option> - <option value="RidgeClassifier">RidgeClassifier</option> - <option value="RidgeClassifierCV">RidgeClassifierCV</option> - <option value="RidgeCV">RidgeCV</option> - <option value="SGDClassifier">SGDClassifier</option> - <option value="SGDRegressor">SGDRegressor</option> - <option value="TheilSenRegressor">TheilSenRegressor</option> - </param> - <expand macro="estimator_params_text" /> + <xml name="feature_selection_SelectFromModel_no_prefitted"> + <when value="SelectFromModel"> + <conditional name="model_inputter"> + <param name="input_mode" type="select" label="Construct a new estimator from a selection list?" > + <option value="new" selected="true">Yes</option> + </param> + <when value="new"> + <expand macro="estimator_selector_all" /> </when> - <when value="ensemble"> - <param name="selected_estimator" type="select" label="Choose estimator class:"> - <option value="AdaBoostClassifier" selected="true">AdaBoostClassifier</option> - <option value="AdaBoostRegressor">AdaBoostRegressor</option> - <option value="BaggingClassifier">BaggingClassifier</option> - <option value="BaggingRegressor">BaggingRegressor</option> - <option value="ExtraTreesClassifier">ExtraTreesClassifier</option> - <option value="ExtraTreesRegressor">ExtraTreesRegressor</option> - <option value="GradientBoostingClassifier">GradientBoostingClassifier</option> - <option value="GradientBoostingRegressor">GradientBoostingRegressor</option> - <option value="IsolationForest">IsolationForest</option> - <option value="HistGradientBoostingClassifier">HistGradientBoostingClassifier</option> - <option value="HistGradientBoostingRegressor">HistGradientBoostingRegressor</option> - <option value="RandomForestClassifier">RandomForestClassifier</option> - <option value="RandomForestRegressor">RandomForestRegressor</option> - <option value="RandomTreesEmbedding">RandomTreesEmbedding</option> - <!--option value="VotingClassifier">VotingClassifier</option--> - </param> - <expand macro="estimator_params_text" /> - </when> - <when value="naive_bayes"> - <param name="selected_estimator" type="select" label="Choose estimator class:"> - <option value="BernoulliNB" selected="true">BernoulliNB</option> - <option value="GaussianNB">GaussianNB</option> - <option value="MultinomialNB">MultinomialNB</option> - </param> - <expand macro="estimator_params_text" /> - </when> - <when value="tree"> - <param name="selected_estimator" type="select" label="Choose estimator class:"> - <option value="DecisionTreeClassifier" selected="true">DecisionTreeClassifier</option> - <option value="DecisionTreeRegressor">DecisionTreeRegressor</option> - <option value="ExtraTreeClassifier">ExtraTreeClassifier</option> - <option value="ExtraTreeRegressor">ExtraTreeRegressor</option> - </param> - <expand macro="estimator_params_text" /> - </when> - <when value="neighbors"> - <param name="selected_estimator" type="select" label="Choose estimator class:"> - <option value="KNeighborsClassifier" selected="true">KNeighborsClassifier</option> - <option value="KNeighborsRegressor">KNeighborsRegressor</option> - <!--option value="BallTree">BallTree</option--> - <!--option value="KDTree">KDTree</option--> - <option value="KernelDensity">KernelDensity</option> - <option value="LocalOutlierFactor">LocalOutlierFactor</option> - <option value="RadiusNeighborsClassifier">RadiusNeighborsClassifier</option> - <option value="RadiusNeighborsRegressor">RadiusNeighborsRegressor</option> - <option value="NearestCentroid">NearestCentroid</option> - <option value="NearestNeighbors">NearestNeighbors</option> - </param> - <expand macro="estimator_params_text" /> - </when> - <when value="xgboost"> - <param name="selected_estimator" type="select" label="Choose estimator class:"> - <option value="XGBRegressor" selected="true">XGBRegressor</option> - <option value="XGBClassifier">XGBClassifier</option> - </param> - <expand macro="estimator_params_text" /> - </when> - <yield /> - </xml> + </conditional> + <expand macro="feature_selection_SelectFromModel_options" /> + </when> + </xml> + + <xml name="feature_selection_SelectFromModel_options"> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="threshold" type="text" value="" optional="true" label="threshold" help="The threshold value to use for feature selection. e.g. 'mean', 'median', '1.25*mean'." /> + <param argument="norm_order" type="integer" value="1" label="norm_order" help="Order of the norm used to filter the vectors of coefficients below threshold in the case where the coef_ attribute of the estimator is of dimension 2. " /> + <param argument="max_features" type="integer" value="" optional="true" label="The maximum number of features selected scoring above threshold" help="To disable threshold and only select based on max_features, set threshold=-np.inf." /> + </section> + </xml> + + <xml name="feature_selection_RFE"> + <when value="RFE"> + <yield /> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="n_features_to_select" type="integer" value="" optional="true" label="n_features_to_select" help="The number of features to select. If None, half of the features are selected." /> + <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " /> + <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." /> + </section> + </when> + </xml> + + <xml name="feature_selection_RFECV_fs"> + <when value="RFECV"> + <yield /> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " /> + <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected" /> + <expand macro="cv" /> + <expand macro="scoring_selection" /> + <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." /> + </section> + </when> + </xml> + + <xml name="feature_selection_RFECV_pipeline"> + <when value="RFECV"> + <yield /> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " /> + <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected" /> + <expand macro="cv_reduced" /> + <!-- TODO: group splitter support--> + <expand macro="scoring_selection" /> + <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." /> + </section> + </when> + </xml> + + <xml name="feature_selection_DyRFECV_fs"> + <when value="DyRFECV"> + <yield /> + <section name="options" title="Advanced Options" expanded="False"> + <param argument="step" type="text" size="30" value="1" label="step" optional="true" help="Default = 1. Support float, int and list." > + <sanitizer> + <valid initial="default"> + <add value="[" /> + <add value="]" /> + </valid> + </sanitizer> + </param> + <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected" /> + <expand macro="cv" /> + <expand macro="scoring_selection" /> + <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." /> + </section> + </when> + </xml> + + <xml name="feature_selection_pipeline"> + <!--compare to `feature_selection_fs`, no fitted estimator for SelectFromModel and no custom estimator for RFE and RFECV--> + <conditional name="fs_algorithm_selector"> + <param name="selected_algorithm" type="select" label="Select a feature selection algorithm"> + <expand macro="feature_selection_algorithms" /> + </param> + <expand macro="feature_selection_algorithm_details" /> + <expand macro="feature_selection_SelectFromModel_no_prefitted" /> + <expand macro="feature_selection_RFE"> + <expand macro="estimator_selector_all" /> + </expand> + <expand macro="feature_selection_RFECV_pipeline"> + <expand macro="estimator_selector_all" /> + </expand> + <!-- TODO: add DyRFECV to pipeline--> + </conditional> + </xml> + + <xml name="feature_selection_fs"> + <conditional name="fs_algorithm_selector"> + <param name="selected_algorithm" type="select" label="Select a feature selection algorithm"> + <expand macro="feature_selection_algorithms"> + <option value="DyRFECV">DyRFECV - Extended RFECV with changeable steps</option> + </expand> + </param> + <expand macro="feature_selection_algorithm_details" /> + <expand macro="feature_selection_SelectFromModel" /> + <expand macro="feature_selection_RFE"> + <expand macro="estimator_selector_fs" /> + </expand> + <expand macro="feature_selection_RFECV_fs"> + <expand macro="estimator_selector_fs" /> + </expand> + <expand macro="feature_selection_DyRFECV_fs"> + <expand macro="estimator_selector_fs" /> + </expand> + </conditional> + </xml> + + <xml name="feature_selection_score_function"> + <param argument="score_func" type="select" label="Select a score function"> + <option value="chi2">chi2 - Compute chi-squared stats between each non-negative feature and class</option> + <option value="f_classif">f_classif - Compute the ANOVA F-value for the provided sample</option> + <option value="f_regression">f_regression - Univariate linear regression tests</option> + <option value="mutual_info_classif">mutual_info_classif - Estimate mutual information for a discrete target variable</option> + <option value="mutual_info_regression">mutual_info_regression - Estimate mutual information for a continuous target variable</option> + </param> + </xml> + + <xml name="model_validation_common_options"> + <expand macro="cv" /> + <expand macro="verbose" /> + <yield /> + </xml> - <xml name="estimator_selector_all"> - <conditional name="estimator_selector"> - <param name="selected_module" type="select" label="Choose the module that contains target estimator:"> - <expand macro="estimator_module_options" /> - </param> - <expand macro="estimator_suboptions" /> - </conditional> - </xml> + <xml name="scoring_selection" token_help="Metric to refit the best estimator."> + <conditional name="scoring"> + <param name="primary_scoring" type="select" multiple="false" label="Select the primary metric (scoring):" help="@HELP@"> + <option value="default" selected="true">default with estimator</option> + <expand macro="scoring_selection_options" /> + </param> + <when value="default" /> + <when value="accuracy"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="balanced_accuracy"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="average_precision"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="f1"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="f1_micro"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="f1_macro"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="f1_weighted"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="f1_samples"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="neg_log_loss"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="precision"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="precision_micro"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="precision_macro"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="precision_wighted"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="precision_samples"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="recall"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="recall_micro"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="recall_macro"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="recall_wighted"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="recall_samples"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="roc_auc"><expand macro="secondary_scoring_selection_classification" /></when> + <when value="explained_variance"><expand macro="secondary_scoring_selection_regression" /></when> + <when value="neg_mean_absolute_error"><expand macro="secondary_scoring_selection_regression" /></when> + <when value="neg_mean_squared_error"><expand macro="secondary_scoring_selection_regression" /></when> + <when value="neg_mean_squared_log_error"><expand macro="secondary_scoring_selection_regression" /></when> + <when value="neg_median_absolute_error"><expand macro="secondary_scoring_selection_regression" /></when> + <when value="r2"><expand macro="secondary_scoring_selection_regression" /></when> + <when value="max_error"><expand macro="secondary_scoring_selection_regression" /></when> + <when value="spearman_correlation"><expand macro="secondary_scoring_selection_regression" /></when> + <when value="binarize_auc_scorer"><expand macro="secondary_scoring_selection_anormaly" /></when> + <when value="binarize_average_precision_scorer"><expand macro="secondary_scoring_selection_anormaly" /></when> + </conditional> + </xml> - <xml name="estimator_selector_fs"> - <conditional name="estimator_selector"> - <param name="selected_module" type="select" label="Choose the module that contains target estimator:"> - <expand macro="estimator_module_options"> - <option value="custom_estimator">Load a custom estimator</option> - </expand> - </param> - <expand macro="estimator_suboptions"> - <when value="custom_estimator"> - <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the custom estimator or pipeline:" /> - </when> - </expand> - </conditional> - </xml> + <xml name="scoring_selection_options"> + <option value="accuracy">Classification -- 'accuracy'</option> + <option value="balanced_accuracy">Classification -- 'balanced_accuracy'</option> + <option value="average_precision">Classification -- 'average_precision'</option> + <option value="f1">Classification -- 'f1'</option> + <option value="f1_micro">Classification -- 'f1_micro'</option> + <option value="f1_macro">Classification -- 'f1_macro'</option> + <option value="f1_weighted">Classification -- 'f1_weighted'</option> + <option value="f1_samples">Classification -- 'f1_samples'</option> + <option value="neg_log_loss">Classification -- 'neg_log_loss'</option> + <option value="precision">Classification -- 'precision'</option> + <option value="precision_micro">Classification -- 'precision_micro'</option> + <option value="precision_macro">Classification -- 'precision_macro'</option> + <option value="precision_wighted">Classification -- 'precision_wighted'</option> + <option value="precision_samples">Classification -- 'precision_samples'</option> + <option value="recall">Classification -- 'recall'</option> + <option value="recall_micro">Classification -- 'recall_micro'</option> + <option value="recall_macro">Classification -- 'recall_macro'</option> + <option value="recall_wighted">Classification -- 'recall_wighted'</option> + <option value="recall_samples">Classification -- 'recall_samples'</option> + <option value="roc_auc">Classification -- 'roc_auc'</option> + <option value="explained_variance">Regression -- 'explained_variance'</option> + <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option> + <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option> + <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option> + <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option> + <option value="r2">Regression -- 'r2'</option> + <option value="max_error">Regression -- 'max_error'</option> + <option value="spearman_correlation">Regression -- Spearman's rank correlation coefficient</option> + <option value="binarize_auc_scorer">anomaly detection -- binarize_auc_scorer</option> + <option value="binarize_average_precision_scorer">anomaly detection -- binarize_average_precision_scorer</option> + </xml> - <xml name="estimator_params_text" token_label="Type in parameter settings if different from default:" token_default_value='' token_help="Dictionary-capable, e.g., C=1, kernel='linear'. No double quotes. Leave this box blank for default estimator."> - <param name="text_params" type="text" value="@DEFAULT_VALUE@" optional="true" label="@LABEL@" help="@HELP@"> + <xml name="secondary_scoring_selection_classification"> + <param name="secondary_scoring" type="select" multiple="true" label="Additional scoring used in multi-metric mode:" help="If the same metric with the primary is chosen, the metric will be ignored."> + <option value="accuracy">Classification -- 'accuracy'</option> + <option value="balanced_accuracy">Classification -- 'balanced_accuracy'</option> + <option value="average_precision">Classification -- 'average_precision'</option> + <option value="f1">Classification -- 'f1'</option> + <option value="f1_micro">Classification -- 'f1_micro'</option> + <option value="f1_macro">Classification -- 'f1_macro'</option> + <option value="f1_weighted">Classification -- 'f1_weighted'</option> + <option value="f1_samples">Classification -- 'f1_samples'</option> + <option value="neg_log_loss">Classification -- 'neg_log_loss'</option> + <option value="precision">Classification -- 'precision'</option> + <option value="precision_micro">Classification -- 'precision_micro'</option> + <option value="precision_macro">Classification -- 'precision_macro'</option> + <option value="precision_wighted">Classification -- 'precision_wighted'</option> + <option value="precision_samples">Classification -- 'precision_samples'</option> + <option value="recall">Classification -- 'recall'</option> + <option value="recall_micro">Classification -- 'recall_micro'</option> + <option value="recall_macro">Classification -- 'recall_macro'</option> + <option value="recall_wighted">Classification -- 'recall_wighted'</option> + <option value="recall_samples">Classification -- 'recall_samples'</option> + <option value="roc_auc">Classification -- 'roc_auc'</option> + </param> + </xml> + + <xml name="secondary_scoring_selection_regression"> + <param name="secondary_scoring" type="select" multiple="true" label="Additional scoring used in multi-metric mode:" help="If the same metric with the primary is chosen, the metric will be ignored."> + <option value="explained_variance">Regression -- 'explained_variance'</option> + <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option> + <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option> + <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option> + <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option> + <option value="r2">Regression -- 'r2'</option> + <option value="max_error">Regression -- 'max_error'</option> + <option value="spearman_correlation">Regression -- Spearman's rank correlation coefficient</option> + </param> + </xml> + + <xml name="secondary_scoring_selection_anormaly"> + <param name="secondary_scoring" type="select" multiple="true" label="Additional scoring used in multi-metric mode:" help="If the same metric with the primary is chosen, the metric will be ignored."> + <expand macro="scoring_selection_options" /> + </param> + </xml> + + <xml name="pre_dispatch" token_type="hidden" token_default_value="all" token_help="Number of predispatched jobs for parallel execution"> + <param argument="pre_dispatch" type="@TYPE@" value="@DEFAULT_VALUE@" optional="true" label="pre_dispatch" help="@HELP@" /> + </xml> + + <xml name="estimator_and_hyperparameter"> + <param name="infile_estimator" type="data" format="h5mlm" label="Choose the dataset containing pipeline/estimator object" /> + <section name="hyperparams_swapping" title="Hyperparameter Swapping" expanded="false"> + <repeat name="param_set" min="1" max="30" title="New hyperparameter setting"> + <param name="sp_name" type="select" optional="true" label="Choose a parameter name (with current value)"> + <options from_dataset="infile_estimator" meta_file_key="hyper_params" startswith="@"> + <column name="name" index="2" /> + <column name="value" index="1" /> + <filter type="unique_value" name="unique_param" column="1" /> + </options> + </param> + <param name="sp_value" type="text" value="" optional="true" label="New value" help="Supports int, float, boolean, single quoted string, and selected object constructor. Similar to the `Parameter settings for search` section in `searchcv` tool except that only single value is expected here."> <sanitizer> - <valid initial="default"> - <add value="'" /> - </valid> + <valid initial="default"> + <add value="'" /> + <add value=""" /> + </valid> </sanitizer> - </param> - </xml> - - <xml name="kernel_approximation_all"> - <conditional name="kernel_approximation_selector"> - <param name="select_algorithm" type="select" label="Choose a kernel approximation algorithm:"> - <option value="Nystroem" selected="true">Nystroem</option> - <option value="RBFSampler">RBFSampler</option> - <option value="AdditiveChi2Sampler">AdditiveChi2Sampler</option> - <option value="SkewedChi2Sampler">SkewedChi2Sampler</option> - </param> - <when value="Nystroem"> - <expand macro="estimator_params_text" help="Default(=blank): coef0=None, degree=None, gamma=None, kernel='rbf', kernel_params=None, n_components=100, random_state=None. No double quotes" /> - </when> - <when value="RBFSampler"> - <expand macro="estimator_params_text" help="Default(=blank): gamma=1.0, n_components=100, random_state=None." /> - </when> - <when value="AdditiveChi2Sampler"> - <expand macro="estimator_params_text" help="Default(=blank): sample_interval=None, sample_steps=2." /> - </when> - <when value="SkewedChi2Sampler"> - <expand macro="estimator_params_text" help="Default(=blank): n_components=100, random_state=None, skewedness=1.0." /> - </when> - </conditional> - </xml> + </param> + </repeat> + </section> + </xml> - <xml name="matrix_decomposition_all"> - <conditional name="matrix_decomposition_selector"> - <param name="select_algorithm" type="select" label="Choose a matrix decomposition algorithm:"> - <option value="DictionaryLearning" selected="true">DictionaryLearning</option> - <option value="FactorAnalysis">FactorAnalysis</option> - <option value="FastICA">FastICA</option> - <option value="IncrementalPCA">IncrementalPCA</option> - <option value="KernelPCA">KernelPCA</option> - <option value="LatentDirichletAllocation">LatentDirichletAllocation</option> - <option value="MiniBatchDictionaryLearning">MiniBatchDictionaryLearning</option> - <option value="MiniBatchSparsePCA">MiniBatchSparsePCA</option> - <option value="NMF">NMF</option> - <option value="PCA">PCA</option> - <option value="SparsePCA">SparsePCA</option> - <!--option value="SparseCoder">SparseCoder</option--> - <option value="TruncatedSVD">TruncatedSVD</option> - </param> - <when value="DictionaryLearning"> - <expand macro="estimator_params_text" help="Default(=blank): alpha=1, code_init=None, dict_init=None, fit_algorithm='lars', max_iter=1000, n_components=None, random_state=None, split_sign=False, tol=1e-08, transform_algorithm='omp', transform_alpha=None, transform_n_nonzero_coefs=None, verbose=False." /> - </when> - <when value="FactorAnalysis"> - <expand macro="estimator_params_text" help="Default(=blank): copy=True, iterated_power=3, max_iter=1000, n_components=None, noise_variance_init=None, random_state=0, svd_method='randomized', tol=0.01." /> - </when> - <when value="FastICA"> - <expand macro="estimator_params_text" help="Default(=blank): algorithm='parallel', fun='logcosh', fun_args=None, max_iter=200, n_components=None, random_state=None, tol=0.0001, w_init=None, whiten=True. No double quotes." /> - </when> - <when value="IncrementalPCA"> - <expand macro="estimator_params_text" help="Default(=blank): batch_size=None, copy=True, n_components=None, whiten=False." /> - </when> - <when value="KernelPCA"> - <expand macro="estimator_params_text" help="Default(=blank): alpha=1.0, coef0=1, copy_X=True, degree=3, eigen_solver='auto', fit_inverse_transform=False, gamma=None, kernel='linear', kernel_params=None, max_iter=None, n_components=None, random_state=None, remove_zero_eig=False, tol=0. No double quotes." /> - </when> - <when value="LatentDirichletAllocation"> - <expand macro="estimator_params_text" help="Default(=blank): batch_size=128, doc_topic_prior=None, evaluate_every=-1, learning_decay=0.7, learning_method=None, learning_offset=10.0, max_doc_update_iter=100, max_iter=10, mean_change_tol=0.001, n_components=10, n_topics=None, perp_tol=0.1, random_state=None, topic_word_prior=None, total_samples=1000000.0, verbose=0." /> - </when> - <when value="MiniBatchDictionaryLearning"> - <expand macro="estimator_params_text" help="Default(=blank): alpha=1, batch_size=3, dict_init=None, fit_algorithm='lars', n_components=None, n_iter=1000, random_state=None, shuffle=True, split_sign=False, transform_algorithm='omp', transform_alpha=None, transform_n_nonzero_coefs=None, verbose=False." /> - </when> - <when value="MiniBatchSparsePCA"> - <expand macro="estimator_params_text" help="Default(=blank): alpha=1, batch_size=3, callback=None, method='lars', n_components=None, n_iter=100, random_state=None, ridge_alpha=0.01, shuffle=True, verbose=False." /> - </when> - <when value="NMF"> - <expand macro="estimator_params_text" help="Default(=blank): alpha=0.0, beta_loss='frobenius', init=None, l1_ratio=0.0, max_iter=200, n_components=None, random_state=None, shuffle=False, solver='cd', tol=0.0001, verbose=0." /> - </when> - <when value="PCA"> - <expand macro="estimator_params_text" help="Default(=blank): copy=True, iterated_power='auto', n_components=None, random_state=None, svd_solver='auto', tol=0.0, whiten=False." /> - </when> - <when value="SparsePCA"> - <expand macro="estimator_params_text" help="Default(=blank): U_init=None, V_init=None, alpha=1, max_iter=1000, method='lars', n_components=None, random_state=None, ridge_alpha=0.01, tol=1e-08, verbose=False." /> - </when> - <when value="TruncatedSVD"> - <expand macro="estimator_params_text" help="Default(=blank): algorithm='randomized', n_components=2, n_iter=5, random_state=None, tol=0.0." /> - </when> - </conditional> - </xml> + <xml name="search_cv_options"> + <expand macro="scoring_selection" /> + <expand macro="model_validation_common_options" /> + <!--expand macro="pre_dispatch" default_value="2*n_jobs" help="Controls the number of jobs that get dispatched during parallel execution"/--> + <!--param argument="iid" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="iid" help="If True, data is identically distributed across the folds" />--> + <!--param argument="refit" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="refit" help="Refit an estimator using the best found parameters on the whole dataset. Be aware that `refit=True` invokes extra computation, but it's REQUIRED for outputting the best estimator!" /> --> + <param argument="error_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Raise fit error:" help="If false, the metric score is assigned to NaN if an error occurs in estimator fitting and FitFailedWarning is raised." /> + <param argument="return_train_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="return_train_score" help="" /> + </xml> - <xml name="FeatureAgglomeration"> - <conditional name="FeatureAgglomeration_selector"> - <param name="select_algorithm" type="select" label="Choose the algorithm:"> - <option value="FeatureAgglomeration" selected="true">FeatureAgglomeration</option> - </param> - <when value="FeatureAgglomeration"> - <expand macro="estimator_params_text" help="Default(=blank): affinity='euclidean', compute_full_tree='auto', connectivity=None, linkage='ward', memory=None, n_clusters=2, pooling_func=np.mean." /> - </when> - </conditional> - </xml> + <xml name="estimator_module_options"> + <option value="svm" selected="true">sklearn.svm</option> + <option value="linear_model">sklearn.linear_model</option> + <option value="ensemble">sklearn.ensemble</option> + <option value="naive_bayes">sklearn.naive_bayes</option> + <option value="tree">sklearn.tree</option> + <option value="neighbors">sklearn.neighbors</option> + <option value="xgboost">xgboost</option> + <yield /> + </xml> - <xml name="skrebate"> - <conditional name="skrebate_selector"> - <param name="select_algorithm" type="select" label="Choose the algorithm:"> - <option value="ReliefF">ReliefF</option> - <option value="SURF">SURF</option> - <option value="SURFstar">SURFstar</option> - <option value="MultiSURF">MultiSURF</option> - <option value="MultiSURFstar">MultiSURFstar</option> - <!--option value="TuRF">TuRF</option> --> - </param> - <when value="ReliefF"> - <expand macro="estimator_params_text" help="Default(=blank): discrete_threshold=10, n_features_to_select=10, n_neighbors=100, verbose=False." /> - </when> - <when value="SURF"> - <expand macro="estimator_params_text" help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False." /> - </when> - <when value="SURFstar"> - <expand macro="estimator_params_text" help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False." /> - </when> - <when value="MultiSURF"> - <expand macro="estimator_params_text" help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False." /> - </when> - <when value="MultiSURFstar"> - <expand macro="estimator_params_text" help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False." /> - </when> - <!--when value="TuRF"> - <expand macro="estimator_params_text" help="Default(=blank): core_algorithm='ReliefF', discrete_threshold=10, n_features_to_select=10, n_neighbors=100, pct=0.5, verbose=False."/> - </when> --> - </conditional> - </xml> + <xml name="estimator_suboptions"> + <when value="svm"> + <param name="selected_estimator" type="select" label="Choose estimator class:"> + <option value="LinearSVC" selected="true">LinearSVC</option> + <option value="LinearSVR">LinearSVR</option> + <option value="NuSVC">NuSVC</option> + <option value="NuSVR">NuSVR</option> + <option value="OneClassSVM">OneClassSVM</option> + <option value="SVC">SVC</option> + <option value="SVR">SVR</option> + </param> + <expand macro="estimator_params_text" /> + </when> + <when value="linear_model"> + <param name="selected_estimator" type="select" label="Choose estimator class:"> + <option value="ARDRegression" selected="true">ARDRegression</option> + <option value="BayesianRidge">BayesianRidge</option> + <option value="ElasticNet">ElasticNet</option> + <option value="ElasticNetCV">ElasticNetCV</option> + <option value="HuberRegressor">HuberRegressor</option> + <option value="Lars">Lars</option> + <option value="LarsCV">LarsCV</option> + <option value="Lasso">Lasso</option> + <option value="LassoCV">LassoCV</option> + <option value="LassoLars">LassoLars</option> + <option value="LassoLarsCV">LassoLarsCV</option> + <option value="LassoLarsIC">LassoLarsIC</option> + <option value="LinearRegression">LinearRegression</option> + <option value="LogisticRegression">LogisticRegression</option> + <option value="LogisticRegressionCV">LogisticRegressionCV</option> + <option value="MultiTaskLasso">MultiTaskLasso</option> + <option value="MultiTaskElasticNet">MultiTaskElasticNet</option> + <option value="MultiTaskLassoCV">MultiTaskLassoCV</option> + <option value="MultiTaskElasticNetCV">MultiTaskElasticNetCV</option> + <option value="OrthogonalMatchingPursuit">OrthogonalMatchingPursuit</option> + <option value="OrthogonalMatchingPursuitCV">OrthogonalMatchingPursuitCV</option> + <option value="PassiveAggressiveClassifier">PassiveAggressiveClassifier</option> + <option value="PassiveAggressiveRegressor">PassiveAggressiveRegressor</option> + <option value="Perceptron">Perceptron</option> + <option value="RANSACRegressor">RANSACRegressor</option> + <option value="Ridge">Ridge</option> + <option value="RidgeClassifier">RidgeClassifier</option> + <option value="RidgeClassifierCV">RidgeClassifierCV</option> + <option value="RidgeCV">RidgeCV</option> + <option value="SGDClassifier">SGDClassifier</option> + <option value="SGDRegressor">SGDRegressor</option> + <option value="TheilSenRegressor">TheilSenRegressor</option> + </param> + <expand macro="estimator_params_text" /> + </when> + <when value="ensemble"> + <param name="selected_estimator" type="select" label="Choose estimator class:"> + <option value="AdaBoostClassifier" selected="true">AdaBoostClassifier</option> + <option value="AdaBoostRegressor">AdaBoostRegressor</option> + <option value="BaggingClassifier">BaggingClassifier</option> + <option value="BaggingRegressor">BaggingRegressor</option> + <option value="ExtraTreesClassifier">ExtraTreesClassifier</option> + <option value="ExtraTreesRegressor">ExtraTreesRegressor</option> + <option value="GradientBoostingClassifier">GradientBoostingClassifier</option> + <option value="GradientBoostingRegressor">GradientBoostingRegressor</option> + <option value="IsolationForest">IsolationForest</option> + <option value="HistGradientBoostingClassifier">HistGradientBoostingClassifier</option> + <option value="HistGradientBoostingRegressor">HistGradientBoostingRegressor</option> + <option value="RandomForestClassifier">RandomForestClassifier</option> + <option value="RandomForestRegressor">RandomForestRegressor</option> + <option value="RandomTreesEmbedding">RandomTreesEmbedding</option> + <!--option value="VotingClassifier">VotingClassifier</option--> + </param> + <expand macro="estimator_params_text" /> + </when> + <when value="naive_bayes"> + <param name="selected_estimator" type="select" label="Choose estimator class:"> + <option value="BernoulliNB" selected="true">BernoulliNB</option> + <option value="GaussianNB">GaussianNB</option> + <option value="MultinomialNB">MultinomialNB</option> + </param> + <expand macro="estimator_params_text" /> + </when> + <when value="tree"> + <param name="selected_estimator" type="select" label="Choose estimator class:"> + <option value="DecisionTreeClassifier" selected="true">DecisionTreeClassifier</option> + <option value="DecisionTreeRegressor">DecisionTreeRegressor</option> + <option value="ExtraTreeClassifier">ExtraTreeClassifier</option> + <option value="ExtraTreeRegressor">ExtraTreeRegressor</option> + </param> + <expand macro="estimator_params_text" /> + </when> + <when value="neighbors"> + <param name="selected_estimator" type="select" label="Choose estimator class:"> + <option value="KNeighborsClassifier" selected="true">KNeighborsClassifier</option> + <option value="KNeighborsRegressor">KNeighborsRegressor</option> + <!--option value="BallTree">BallTree</option--> + <!--option value="KDTree">KDTree</option--> + <option value="KernelDensity">KernelDensity</option> + <option value="LocalOutlierFactor">LocalOutlierFactor</option> + <option value="RadiusNeighborsClassifier">RadiusNeighborsClassifier</option> + <option value="RadiusNeighborsRegressor">RadiusNeighborsRegressor</option> + <option value="NearestCentroid">NearestCentroid</option> + <option value="NearestNeighbors">NearestNeighbors</option> + </param> + <expand macro="estimator_params_text" /> + </when> + <when value="xgboost"> + <param name="selected_estimator" type="select" label="Choose estimator class:"> + <option value="XGBRegressor" selected="true">XGBRegressor</option> + <option value="XGBClassifier">XGBClassifier</option> + </param> + <expand macro="estimator_params_text" /> + </when> + <yield /> + </xml> + + <xml name="estimator_selector_all"> + <conditional name="estimator_selector"> + <param name="selected_module" type="select" label="Choose the module that contains target estimator:" > + <expand macro="estimator_module_options" /> + </param> + <expand macro="estimator_suboptions" /> + </conditional> + </xml> + + <xml name="estimator_selector_fs"> + <conditional name="estimator_selector"> + <param name="selected_module" type="select" label="Choose the module that contains target estimator:" > + <expand macro="estimator_module_options"> + <option value="custom_estimator">Load a custom estimator</option> + </expand> + </param> + <expand macro="estimator_suboptions"> + <when value="custom_estimator"> + <param name="c_estimator" type="data" format="h5mlm" label="Choose the dataset containing the custom estimator or pipeline:" /> + </when> + </expand> + </conditional> + </xml> + + <xml name="estimator_params_text" token_label="Type in parameter settings if different from default:" token_default_value='' + token_help="Dictionary-capable, e.g., C=1, kernel='linear'. No double quotes. Leave this box blank for default estimator."> + <param name="text_params" type="text" value="@DEFAULT_VALUE@" optional="true" label="@LABEL@" help="@HELP@"> + <sanitizer> + <valid initial="default"> + <add value="'" /> + </valid> + </sanitizer> + </param> + </xml> + + <xml name="kernel_approximation_all"> + <conditional name="kernel_approximation_selector"> + <param name="select_algorithm" type="select" label="Choose a kernel approximation algorithm:"> + <option value="Nystroem" selected="true">Nystroem</option> + <option value="RBFSampler">RBFSampler</option> + <option value="AdditiveChi2Sampler">AdditiveChi2Sampler</option> + <option value="SkewedChi2Sampler">SkewedChi2Sampler</option> + </param> + <when value="Nystroem"> + <expand macro="estimator_params_text" + help="Default(=blank): coef0=None, degree=None, gamma=None, kernel='rbf', kernel_params=None, n_components=100, random_state=None. No double quotes" /> + </when> + <when value="RBFSampler"> + <expand macro="estimator_params_text" + help="Default(=blank): gamma=1.0, n_components=100, random_state=None." /> + </when> + <when value="AdditiveChi2Sampler"> + <expand macro="estimator_params_text" + help="Default(=blank): sample_interval=None, sample_steps=2." /> + </when> + <when value="SkewedChi2Sampler"> + <expand macro="estimator_params_text" + help="Default(=blank): n_components=100, random_state=None, skewedness=1.0." /> + </when> + </conditional> + </xml> - <xml name="imbalanced_learn_sampling"> - <conditional name="imblearn_selector"> - <param name="select_algorithm" type="select" label="Choose the algorithm:"> - <option value="under_sampling.ClusterCentroids" selected="true">under_sampling.ClusterCentroids</option> - <option value="under_sampling.CondensedNearestNeighbour">under_sampling.CondensedNearestNeighbour</option> - <option value="under_sampling.EditedNearestNeighbours">under_sampling.EditedNearestNeighbours</option> - <option value="under_sampling.RepeatedEditedNearestNeighbours">under_sampling.RepeatedEditedNearestNeighbours</option> - <option value="under_sampling.AllKNN">under_sampling.AllKNN</option> - <option value="under_sampling.InstanceHardnessThreshold">under_sampling.InstanceHardnessThreshold</option> - <option value="under_sampling.NearMiss">under_sampling.NearMiss</option> - <option value="under_sampling.NeighbourhoodCleaningRule">under_sampling.NeighbourhoodCleaningRule</option> - <option value="under_sampling.OneSidedSelection">under_sampling.OneSidedSelection</option> - <option value="under_sampling.RandomUnderSampler">under_sampling.RandomUnderSampler</option> - <option value="under_sampling.TomekLinks">under_sampling.TomekLinks</option> - <option value="over_sampling.ADASYN">over_sampling.ADASYN</option> - <option value="over_sampling.RandomOverSampler">over_sampling.RandomOverSampler</option> - <option value="over_sampling.SMOTE">over_sampling.SMOTE</option> - <option value="over_sampling.SVMSMOTE">over_sampling.SVMSMOTE</option> - <option value="over_sampling.BorderlineSMOTE">over_sampling.BorderlineSMOTE</option> - <option value="over_sampling.SMOTENC">over_sampling.SMOTENC</option> - <option value="combine.SMOTEENN">combine.SMOTEENN</option> - <option value="combine.SMOTETomek">combine.SMOTETomek</option> - <option value="Z_RandomOverSampler">Z_RandomOverSampler - for regression</option> - </param> - <when value="under_sampling.ClusterCentroids"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, estimator=None, voting='auto'." /> - </when> - <when value="under_sampling.CondensedNearestNeighbour"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=None, n_seeds_S=1." /> - </when> - <when value="under_sampling.EditedNearestNeighbours"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, max_iter=100, kind_sel='all'." /> - </when> - <when value="under_sampling.RepeatedEditedNearestNeighbours"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, max_iter=100, kind_sel='all'." /> - </when> - <when value="under_sampling.AllKNN"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, kind_sel='all', allow_minority=False." /> - </when> - <when value="under_sampling.InstanceHardnessThreshold"> - <expand macro="estimator_params_text" help="Default(=blank): estimator=None, sampling_strategy='auto', random_state=None, cv=5." /> - </when> - <when value="under_sampling.NearMiss"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, version=1, n_neighbors=3, n_neighbors_ver3=3." /> - </when> - <when value="under_sampling.NeighbourhoodCleaningRule"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, kind_sel='all', threshold_cleaning=0.5." /> - </when> - <when value="under_sampling.OneSidedSelection"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=None, n_seeds_S=1." /> - </when> - <when value="under_sampling.RandomUnderSampler"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, replacement=False." /> - </when> - <when value="under_sampling.TomekLinks"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None." /> - </when> - <when value="over_sampling.ADASYN"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=5." /> - </when> - <when value="over_sampling.RandomOverSampler"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None." /> - </when> - <when value="over_sampling.SMOTE"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, k_neighbors=5." /> - </when> - <when value="over_sampling.SVMSMOTE"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', k_neighbors=5, m_neighbors=10, out_step=0.5, random_state=None, svm_estimator=None." /> - </when> - <when value="over_sampling.BorderlineSMOTE"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', k_neighbors=5, kind='borderline-1', m_neighbors=10, random_state=None." /> - </when> - <when value="over_sampling.SMOTENC"> - <expand macro="estimator_params_text" help="Default: categorical_features=[], sampling_strategy='auto', random_state=None, k_neighbors=5." /> - </when> - <when value="combine.SMOTEENN"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, enn=None." /> - </when> - <when value="combine.SMOTETomek"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, tomek=None." /> - </when> - <when value="Z_RandomOverSampler"> - <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, negative_thres=0, positive_thres=-1." /> - </when> - </conditional> - </xml> + <xml name="matrix_decomposition_all"> + <conditional name="matrix_decomposition_selector"> + <param name="select_algorithm" type="select" label="Choose a matrix decomposition algorithm:"> + <option value="DictionaryLearning" selected="true">DictionaryLearning</option> + <option value="FactorAnalysis">FactorAnalysis</option> + <option value="FastICA">FastICA</option> + <option value="IncrementalPCA">IncrementalPCA</option> + <option value="KernelPCA">KernelPCA</option> + <option value="LatentDirichletAllocation">LatentDirichletAllocation</option> + <option value="MiniBatchDictionaryLearning">MiniBatchDictionaryLearning</option> + <option value="MiniBatchSparsePCA">MiniBatchSparsePCA</option> + <option value="NMF">NMF</option> + <option value="PCA">PCA</option> + <option value="SparsePCA">SparsePCA</option> + <!--option value="SparseCoder">SparseCoder</option--> + <option value="TruncatedSVD">TruncatedSVD</option> + </param> + <when value="DictionaryLearning"> + <expand macro="estimator_params_text" + help="Default(=blank): alpha=1, code_init=None, dict_init=None, fit_algorithm='lars', max_iter=1000, n_components=None, random_state=None, split_sign=False, tol=1e-08, transform_algorithm='omp', transform_alpha=None, transform_n_nonzero_coefs=None, verbose=False." /> + </when> + <when value="FactorAnalysis"> + <expand macro="estimator_params_text" + help="Default(=blank): copy=True, iterated_power=3, max_iter=1000, n_components=None, noise_variance_init=None, random_state=0, svd_method='randomized', tol=0.01." /> + </when> + <when value="FastICA"> + <expand macro="estimator_params_text" + help="Default(=blank): algorithm='parallel', fun='logcosh', fun_args=None, max_iter=200, n_components=None, random_state=None, tol=0.0001, w_init=None, whiten=True. No double quotes." /> + </when> + <when value="IncrementalPCA"> + <expand macro="estimator_params_text" + help="Default(=blank): batch_size=None, copy=True, n_components=None, whiten=False." /> + </when> + <when value="KernelPCA"> + <expand macro="estimator_params_text" + help="Default(=blank): alpha=1.0, coef0=1, copy_X=True, degree=3, eigen_solver='auto', fit_inverse_transform=False, gamma=None, kernel='linear', kernel_params=None, max_iter=None, n_components=None, random_state=None, remove_zero_eig=False, tol=0. No double quotes." /> + </when> + <when value="LatentDirichletAllocation"> + <expand macro="estimator_params_text" + help="Default(=blank): batch_size=128, doc_topic_prior=None, evaluate_every=-1, learning_decay=0.7, learning_method=None, learning_offset=10.0, max_doc_update_iter=100, max_iter=10, mean_change_tol=0.001, n_components=10, n_topics=None, perp_tol=0.1, random_state=None, topic_word_prior=None, total_samples=1000000.0, verbose=0." /> + </when> + <when value="MiniBatchDictionaryLearning"> + <expand macro="estimator_params_text" + help="Default(=blank): alpha=1, batch_size=3, dict_init=None, fit_algorithm='lars', n_components=None, n_iter=1000, random_state=None, shuffle=True, split_sign=False, transform_algorithm='omp', transform_alpha=None, transform_n_nonzero_coefs=None, verbose=False." /> + </when> + <when value="MiniBatchSparsePCA"> + <expand macro="estimator_params_text" + help="Default(=blank): alpha=1, batch_size=3, callback=None, method='lars', n_components=None, n_iter=100, random_state=None, ridge_alpha=0.01, shuffle=True, verbose=False." /> + </when> + <when value="NMF"> + <expand macro="estimator_params_text" + help="Default(=blank): alpha=0.0, beta_loss='frobenius', init=None, l1_ratio=0.0, max_iter=200, n_components=None, random_state=None, shuffle=False, solver='cd', tol=0.0001, verbose=0." /> + </when> + <when value="PCA"> + <expand macro="estimator_params_text" + help="Default(=blank): copy=True, iterated_power='auto', n_components=None, random_state=None, svd_solver='auto', tol=0.0, whiten=False." /> + </when> + <when value="SparsePCA"> + <expand macro="estimator_params_text" + help="Default(=blank): U_init=None, V_init=None, alpha=1, max_iter=1000, method='lars', n_components=None, random_state=None, ridge_alpha=0.01, tol=1e-08, verbose=False." /> + </when> + <when value="TruncatedSVD"> + <expand macro="estimator_params_text" + help="Default(=blank): algorithm='randomized', n_components=2, n_iter=5, random_state=None, tol=0.0." /> + </when> + </conditional> + </xml> - <xml name="stacking_ensemble_inputs"> - <section name="options" title="Advanced Options" expanded="false"> - <yield /> - <param argument="use_features_in_secondary" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" /> - <param argument="store_train_meta_features" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" /> - </section> - </xml> + <xml name="FeatureAgglomeration"> + <conditional name="FeatureAgglomeration_selector"> + <param name="select_algorithm" type="select" label="Choose the algorithm:"> + <option value="FeatureAgglomeration" selected="true">FeatureAgglomeration</option> + </param> + <when value="FeatureAgglomeration"> + <expand macro="estimator_params_text" + help="Default(=blank): affinity='euclidean', compute_full_tree='auto', connectivity=None, linkage='ward', memory=None, n_clusters=2, pooling_func=np.mean." /> + </when> + </conditional> + </xml> + + <xml name="skrebate"> + <conditional name="skrebate_selector"> + <param name="select_algorithm" type="select" label="Choose the algorithm:"> + <option value="ReliefF">ReliefF</option> + <option value="SURF">SURF</option> + <option value="SURFstar">SURFstar</option> + <option value="MultiSURF">MultiSURF</option> + <option value="MultiSURFstar">MultiSURFstar</option> + <!--option value="TuRF">TuRF</option> --> + </param> + <when value="ReliefF"> + <expand macro="estimator_params_text" + help="Default(=blank): discrete_threshold=10, n_features_to_select=10, n_neighbors=100, verbose=False." /> + </when> + <when value="SURF"> + <expand macro="estimator_params_text" + help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False." /> + </when> + <when value="SURFstar"> + <expand macro="estimator_params_text" + help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False." /> + </when> + <when value="MultiSURF"> + <expand macro="estimator_params_text" + help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False." /> + </when> + <when value="MultiSURFstar"> + <expand macro="estimator_params_text" + help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False." /> + </when> + <!--when value="TuRF"> + <expand macro="estimator_params_text" + help="Default(=blank): core_algorithm='ReliefF', discrete_threshold=10, n_features_to_select=10, n_neighbors=100, pct=0.5, verbose=False." /> + </when> --> + </conditional> + </xml> - <xml name="stacking_base_estimator"> - <conditional name="estimator_selector"> - <param name="selected_module" type="select" label="Choose the module that contains target estimator:"> - <expand macro="estimator_module_options"> - <option value="custom_estimator">Load a custom estimator</option> - </expand> - </param> - <expand macro="estimator_suboptions"> - <when value="custom_estimator"> - <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the custom estimator or pipeline" /> - </when> - </expand> - </conditional> - </xml> - - <xml name="stacking_voting_weights"> - <section name="options" title="Advanced Options" expanded="false"> - <param argument="weights" type="text" value="[]" optional="true" help="Sequence of weights (float or int). Uses uniform weights if None (`[]`)."> - <sanitizer> - <valid initial="default"> - <add value="[" /> - <add value="]" /> - </valid> - </sanitizer> - </param> - <yield /> - </section> - </xml> - - <xml name="preprocessors_sequence_encoders"> - <conditional name="encoder_selection"> - <param name="encoder_type" type="select" label="Choose the sequence encoder class"> - <option value="GenomeOneHotEncoder">GenomeOneHotEncoder</option> - <option value="ProteinOneHotEncoder">ProteinOneHotEncoder</option> - </param> - <when value="GenomeOneHotEncoder"> - <expand macro="preprocessors_sequence_encoder_arguments" /> - </when> - <when value="ProteinOneHotEncoder"> - <expand macro="preprocessors_sequence_encoder_arguments" /> - </when> - </conditional> - </xml> - - <xml name="preprocessors_sequence_encoder_arguments"> - <param argument="seq_length" type="integer" value="" min="0" optional="true" help="Integer. Sequence length" /> - <param argument="padding" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" help="Whether to pad or truncate sequence to meet the sequence length." /> - </xml> - - <!-- Outputs --> + <xml name="imbalanced_learn_sampling"> + <conditional name="imblearn_selector"> + <param name="select_algorithm" type="select" label="Choose the algorithm:"> + <option value="under_sampling.ClusterCentroids" selected="true">under_sampling.ClusterCentroids</option> + <option value="under_sampling.CondensedNearestNeighbour">under_sampling.CondensedNearestNeighbour</option> + <option value="under_sampling.EditedNearestNeighbours">under_sampling.EditedNearestNeighbours</option> + <option value="under_sampling.RepeatedEditedNearestNeighbours">under_sampling.RepeatedEditedNearestNeighbours</option> + <option value="under_sampling.AllKNN">under_sampling.AllKNN</option> + <option value="under_sampling.InstanceHardnessThreshold">under_sampling.InstanceHardnessThreshold</option> + <option value="under_sampling.NearMiss">under_sampling.NearMiss</option> + <option value="under_sampling.NeighbourhoodCleaningRule">under_sampling.NeighbourhoodCleaningRule</option> + <option value="under_sampling.OneSidedSelection">under_sampling.OneSidedSelection</option> + <option value="under_sampling.RandomUnderSampler">under_sampling.RandomUnderSampler</option> + <option value="under_sampling.TomekLinks">under_sampling.TomekLinks</option> + <option value="over_sampling.ADASYN">over_sampling.ADASYN</option> + <option value="over_sampling.RandomOverSampler">over_sampling.RandomOverSampler</option> + <option value="over_sampling.SMOTE">over_sampling.SMOTE</option> + <option value="over_sampling.SVMSMOTE">over_sampling.SVMSMOTE</option> + <option value="over_sampling.BorderlineSMOTE">over_sampling.BorderlineSMOTE</option> + <option value="over_sampling.SMOTENC">over_sampling.SMOTENC</option> + <option value="combine.SMOTEENN">combine.SMOTEENN</option> + <option value="combine.SMOTETomek">combine.SMOTETomek</option> + <option value="Z_RandomOverSampler">Z_RandomOverSampler - for regression</option> + </param> + <when value="under_sampling.ClusterCentroids"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, estimator=None, voting='auto'." /> + </when> + <when value="under_sampling.CondensedNearestNeighbour"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=None, n_seeds_S=1." /> + </when> + <when value="under_sampling.EditedNearestNeighbours"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, max_iter=100, kind_sel='all'." /> + </when> + <when value="under_sampling.RepeatedEditedNearestNeighbours"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, max_iter=100, kind_sel='all'." /> + </when> + <when value="under_sampling.AllKNN"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, kind_sel='all', allow_minority=False." /> + </when> + <when value="under_sampling.InstanceHardnessThreshold"> + <expand macro="estimator_params_text" + help="Default(=blank): estimator=None, sampling_strategy='auto', random_state=None, cv=5." /> + </when> + <when value="under_sampling.NearMiss"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, version=1, n_neighbors=3, n_neighbors_ver3=3." /> + </when> + <when value="under_sampling.NeighbourhoodCleaningRule"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, kind_sel='all', threshold_cleaning=0.5." /> + </when> + <when value="under_sampling.OneSidedSelection"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=None, n_seeds_S=1." /> + </when> + <when value="under_sampling.RandomUnderSampler"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, replacement=False." /> + </when> + <when value="under_sampling.TomekLinks"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None." /> + </when> + <when value="over_sampling.ADASYN"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=5." /> + </when> + <when value="over_sampling.RandomOverSampler"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None." /> + </when> + <when value="over_sampling.SMOTE"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, k_neighbors=5." /> + </when> + <when value="over_sampling.SVMSMOTE"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', k_neighbors=5, m_neighbors=10, out_step=0.5, random_state=None, svm_estimator=None." /> + </when> + <when value="over_sampling.BorderlineSMOTE"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', k_neighbors=5, kind='borderline-1', m_neighbors=10, random_state=None." /> + </when> + <when value="over_sampling.SMOTENC"> + <expand macro="estimator_params_text" + help="Default: categorical_features=[], sampling_strategy='auto', random_state=None, k_neighbors=5." /> + </when> + <when value="combine.SMOTEENN"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, enn=None." /> + </when> + <when value="combine.SMOTETomek"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, tomek=None." /> + </when> + <when value="Z_RandomOverSampler"> + <expand macro="estimator_params_text" + help="Default(=blank): sampling_strategy='auto', random_state=None, negative_thres=0, positive_thres=-1." /> + </when> + </conditional> + </xml> - <xml name="output"> - <outputs> - <data format="tabular" name="outfile_predict"> - <filter>selected_tasks['selected_task'] == 'load'</filter> - </data> - <data format="zip" name="outfile_fit" label="${tool.name}.${selected_tasks.selected_algorithms.selected_algorithm}"> - <filter>selected_tasks['selected_task'] == 'train'</filter> - </data> - </outputs> - </xml> + <xml name="preprocessors_sequence_encoders"> + <conditional name="encoder_selection"> + <param name="encoder_type" type="select" label="Choose the sequence encoder class"> + <option value="GenomeOneHotEncoder">GenomeOneHotEncoder</option> + <option value="ProteinOneHotEncoder">ProteinOneHotEncoder</option> + </param> + <when value="GenomeOneHotEncoder"> + <expand macro="preprocessors_sequence_encoder_arguments" /> + </when> + <when value="ProteinOneHotEncoder"> + <expand macro="preprocessors_sequence_encoder_arguments" /> + </when> + </conditional> + </xml> - <!--Citations--> - <xml name="eden_citation"> - <citations> - <citation type="doi">10.5281/zenodo.15094</citation> - </citations> - </xml> + <xml name="preprocessors_sequence_encoder_arguments"> + <param argument="seq_length" type="integer" value="" min="0" optional="true" help="Integer. Sequence length" /> + <param argument="padding" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" help="Whether to pad or truncate sequence to meet the sequence length." /> + </xml> + + <!-- Outputs --> + + <xml name="output"> + <outputs> + <data format="tabular" name="outfile_predict"> + <filter>selected_tasks['selected_task'] == 'load'</filter> + </data> + <data format="h5mlm" name="outfile_fit" label="${tool.name}.${selected_tasks.selected_algorithms.selected_algorithm}"> + <filter>selected_tasks['selected_task'] == 'train'</filter> + </data> + </outputs> + </xml> - <xml name="sklearn_citation"> - <citations> - <citation type="doi">10.1371/journal.pcbi.1009014</citation> - <citation type="bibtex"> - @article{JMLR:v12:pedregosa11a, - title = {Scikit-learn: Machine Learning in {P}ython}, - author = {Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V. - and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P. - and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and - Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.}, - journal = {Journal of Machine Learning Research}, - volume = {12}, - pages = {2825--2830}, - year = {2011} - url = {http://jmlr.org/papers/v12/pedregosa11a.html} - } - </citation> - <yield /> - </citations> - </xml> + <!--Citations--> + <xml name="eden_citation"> + <citations> + <citation type="doi">10.5281/zenodo.15094</citation> + </citations> + </xml> - <xml name="scipy_citation"> - <citations> - <citation type="bibtex"> - @Misc{, - author = {Eric Jones and Travis Oliphant and Pearu Peterson and others}, - title = {{SciPy}: Open source scientific tools for {Python}}, - year = {2001--}, - url = {http://www.scipy.org/}, - note = {[Online; accessed 2016-04-09]} + <xml name="sklearn_citation"> + <citations> + <citation type="bibtex"> + @article{scikit-learn, + title={Scikit-learn: Machine Learning in {P}ython}, + author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V. + and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P. + and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and + Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.}, + journal={Journal of Machine Learning Research}, + volume={12}, + pages={2825--2830}, + year={2011} } - </citation> - </citations> - </xml> + </citation> + <yield /> + </citations> + </xml> - <xml name="skrebate_citation"> - <citation type="bibtex"> + <xml name="scipy_citation"> + <citations> + <citation type="bibtex"> + @Misc{, + author = {Eric Jones and Travis Oliphant and Pearu Peterson and others}, + title = {{SciPy}: Open source scientific tools for {Python}}, + year = {2001--}, + url = "http://www.scipy.org/", + note = {[Online; accessed 2016-04-09]} + } + </citation> + </citations> + </xml> + + <xml name="skrebate_citation"> + <citation type="bibtex"> @article{DBLP:journals/corr/abs-1711-08477, author = {Ryan J. Urbanowicz and Randal S. Olson and @@ -1973,33 +1953,33 @@ biburl = {https://dblp.org/rec/bib/journals/corr/abs-1711-08477}, bibsource = {dblp computer science bibliography, https://dblp.org} } - </citation> - </xml> + </citation> + </xml> - <xml name="xgboost_citation"> - <citation type="bibtex"> + <xml name="xgboost_citation"> + <citation type="bibtex"> @inproceedings{Chen:2016:XST:2939672.2939785, - author = {Chen, Tianqi and Guestrin, Carlos}, - title = {{XGBoost}: A Scalable Tree Boosting System}, + author = {Chen, Tianqi and Guestrin, Carlos}, + title = {{XGBoost}: A Scalable Tree Boosting System}, booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining}, - series = {KDD '16}, - year = {2016}, - isbn = {978-1-4503-4232-2}, - location = {San Francisco, California, USA}, - pages = {785--794}, - numpages = {10}, - url = {http://doi.acm.org/10.1145/2939672.2939785}, - doi = {10.1145/2939672.2939785}, - acmid = {2939785}, + series = {KDD '16}, + year = {2016}, + isbn = {978-1-4503-4232-2}, + location = {San Francisco, California, USA}, + pages = {785--794}, + numpages = {10}, + url = {http://doi.acm.org/10.1145/2939672.2939785}, + doi = {10.1145/2939672.2939785}, + acmid = {2939785}, publisher = {ACM}, - address = {New York, NY, USA}, - keywords = {large-scale machine learning}, + address = {New York, NY, USA}, + keywords = {large-scale machine learning}, } - </citation> - </xml> + </citation> + </xml> - <xml name="imblearn_citation"> - <citation type="bibtex"> + <xml name="imblearn_citation"> + <citation type="bibtex"> @article{JMLR:v18:16-365, author = {Guillaume Lema{{\^i}}tre and Fernando Nogueira and Christos K. Aridas}, title = {Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning}, @@ -2010,11 +1990,22 @@ pages = {1-5}, url = {http://jmlr.org/papers/v18/16-365.html} } - </citation> - </xml> + </citation> + </xml> - <xml name="selene_citation"> - <citation type="doi">10.1038/s41592-019-0360-8</citation> - </xml> + <xml name="selene_citation"> + <citation type="bibtex"> + @article{chen2019selene, + title={Selene: a PyTorch-based deep learning library for sequence data}, + author={Chen, Kathleen M and Cofer, Evan M and Zhou, Jian and Troyanskaya, Olga G}, + journal={Nature methods}, + volume={16}, + number={4}, + pages={315}, + year={2019}, + publisher={Nature Publishing Group} + } + </citation> + </xml> </macros>