comparison search_model_validation.xml @ 2:907bb0418c9f draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit b1e5fa3170484d2cc3396f2abe99bb8cfcfa9c65

1:f727f5ff7d60

        <configfile name="sklearn_search_model_validation_script">
            <![CDATA[
import sys
import json
import pandas
import pickle
import numpy as np
import xgboost
import scipy
from asteval import Interpreter, make_symbol_table
from sklearn import metrics, preprocessing, model_selection, ensemble
from sklearn.pipeline import Pipeline

@COLUMNS_FUNCTION@
@GET_ESTIMATOR_FUNCTION@
@GET_SEARCH_PARAMS_FUNCTION@

input_json_path = sys.argv[1]
with open(input_json_path, "r") as param_handler:
    params = json.load(param_handler)

infile1 = "$input_options.infile1"
infile2 = "$input_options.infile2"
infile_pipeline = "$search_schemes.infile_pipeline"
outfile_result = "$outfile_result"
outfile_estimator = "$outfile_estimator"
#if $search_schemes.selected_search_scheme == "RandomizedSearchCV":
np.random.seed($search_schemes.random_seed)
#end if

params_builder = params['search_schemes']['search_params_builder']

input_type = params["input_options"]["selected_input"]
if input_type=="tabular":

optimizers = params["search_schemes"]["selected_search_scheme"]
optimizers = getattr(model_selection, optimizers)

options = params["search_schemes"]["options"]
if 'scoring' in options and options['scoring'] == '':
    options['scoring'] = None
if 'pre_dispatch' in options and options['pre_dispatch'] == '':
    options['pre_dispatch'] = None

                <section name="options" title="Advanced Options for SearchCV" expanded="false">
                    <expand macro="search_cv_options"/>
                </section>
            </when>
            <when value="RandomizedSearchCV">
                <param name="random_seed" type="integer" value="65535" min="0" max="65535" label="Set up random seed:"/>
                <expand macro="search_cv_estimator"/>
                <section name="options" title="Advanced Options for SearchCV" expanded="false">
                    <expand macro="search_cv_options"/>
                    <param argument="n_iter" type="integer" value="10" label="Number of parameter settings that are sampled"/>
                    <expand macro="random_state"/>

                <assert_contents>
                    <has_text_matching expression=".+0.08045977011494253[^/w]+10[^/w]" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**
Searches optimized parameter values for an estimator or pipeline through either exhaustive grid cross validation search or Randomized cross validation search.

2:907bb0418c9f

        <configfile name="sklearn_search_model_validation_script">
            <![CDATA[
import sys
import json
import pandas
import re
import pickle
import numpy as np
import xgboost
import scipy
from asteval import Interpreter, make_symbol_table
from sklearn import metrics, preprocessing, model_selection, ensemble
from sklearn.pipeline import Pipeline

@COLUMNS_FUNCTION@
@GET_ESTIMATOR_FUNCTION@
@SAFE_EVAL_FUNCTION@
@GET_SEARCH_PARAMS_FUNCTION@
@GET_CV_FUNCTION@

input_json_path = sys.argv[1]
with open(input_json_path, "r") as param_handler:
    params = json.load(param_handler)

infile1 = "$input_options.infile1"
infile2 = "$input_options.infile2"
infile_pipeline = "$search_schemes.infile_pipeline"
outfile_result = "$outfile_result"
outfile_estimator = "$outfile_estimator"

params_builder = params['search_schemes']['search_params_builder']

input_type = params["input_options"]["selected_input"]
if input_type=="tabular":

optimizers = params["search_schemes"]["selected_search_scheme"]
optimizers = getattr(model_selection, optimizers)

options = params["search_schemes"]["options"]
options['cv'] = get_cv( options['cv'].strip() )
if 'scoring' in options and options['scoring'] == '':
    options['scoring'] = None
if 'pre_dispatch' in options and options['pre_dispatch'] == '':
    options['pre_dispatch'] = None

                <section name="options" title="Advanced Options for SearchCV" expanded="false">
                    <expand macro="search_cv_options"/>
                </section>
            </when>
            <when value="RandomizedSearchCV">
                <expand macro="search_cv_estimator"/>
                <section name="options" title="Advanced Options for SearchCV" expanded="false">
                    <expand macro="search_cv_options"/>
                    <param argument="n_iter" type="integer" value="10" label="Number of parameter settings that are sampled"/>
                    <expand macro="random_state"/>

                <assert_contents>
                    <has_text_matching expression=".+0.08045977011494253[^/w]+10[^/w]" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="selected_search_scheme" value="GridSearchCV"/>
            <param name="infile_pipeline" value="pipeline01"/>
            <conditional name="search_param_selector">
                <param name="search_p" value="C: [1, 10, 100, 1000]"/>
                <param name="selected_param_type" value="final_estimator_p"/>
            </conditional>
            <param name='cv' value="StratifiedKFold(n_splits=3, shuffle=True, random_state=10)"/>
            <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
            <param name="header1" value="true" />
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
            <param name="header2" value="true" />
            <param name="selected_column_selector_option2" value="all_columns"/>
            <output name="outfile_estimator" file="searchCV01" compare="sim_size" delta="1"/>
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**
Searches optimized parameter values for an estimator or pipeline through either exhaustive grid cross validation search or Randomized cross validation search.