sklearn_model_validation: model_validation.xml comparison

comparison model_validation.xml @ 34:1fe00785190d draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 9981e25b00de29ed881b2229a173a8c812ded9bb

author	bgruening
date	Wed, 09 Aug 2023 13:44:18 +0000
parents	4b359039f09f
children

comparison

equal deleted inserted replaced

-:5d5d9cc554f9
+:1fe00785190d
-<tool id="sklearn_model_validation" name="Model Validation" version="@VERSION@" profile="20.05">
+<tool id="sklearn_model_validation" name="Model Validation" version="@VERSION@" profile="@PROFILE@">
 <description>includes cross_validate, cross_val_predict, learning_curve, and more</description>
 <macros>
 <import>main_macros.xml</import>
 </macros>
 <expand macro="python_requirements" />
 import joblib
 import json
 import numpy as np
 import os
 import pandas as pd
-import pickle
 import pprint
 import skrebate
 import sys
 import warnings
 import xgboost
 cluster, compose, decomposition, ensemble, feature_extraction,
 feature_selection, gaussian_process, kernel_approximation, metrics,
 model_selection, naive_bayes, neighbors, pipeline, preprocessing,
 svm, linear_model, tree, discriminant_analysis)
 from sklearn.model_selection import _validation
+from sklearn.preprocessing import LabelEncoder
-from galaxy_ml.utils import (SafeEval, get_cv, get_scoring, load_model,
-read_columns, get_module)
+from distutils.version import LooseVersion as Version
-from galaxy_ml.model_validations import _fit_and_score
+from galaxy_ml import __version__ as galaxy_ml_version
+from galaxy_ml.model_persist import load_model_from_h5
+from galaxy_ml.utils import (SafeEval, get_cv, get_scoring,
-setattr(_validation, '_fit_and_score', _fit_and_score)
+read_columns, get_module,
+clean_params, get_main_estimator)
 N_JOBS = int(os.environ.get('GALAXY_SLOTS', 1))
 CACHE_DIR = os.path.join(os.getcwd(), 'cached')
-del os
-ALLOWED_CALLBACKS = ('EarlyStopping', 'TerminateOnNaN', 'ReduceLROnPlateau',
-'CSVLogger', 'None')
 warnings.filterwarnings('ignore')
 safe_eval = SafeEval()
 input_json_path = sys.argv[1]
 with open(input_json_path, 'r') as param_handler:
 params = json.load(param_handler)
 ## load estimator
-with open('$infile_estimator', 'rb') as estimator_handler:
+estimator = load_model_from_h5('$infile_estimator')
-estimator = load_model(estimator_handler)
+estimator = clean_params(estimator)
+if estimator.__class__.__name__ == 'KerasGBatchClassifier':
+_fit_and_score = try_get_attr('galaxy_ml.model_validations',
+'_fit_and_score')
+setattr(_search, '_fit_and_score', _fit_and_score)
+setattr(_validation, '_fit_and_score', _fit_and_score)
 estimator_params = estimator.get_params()
 ## check estimator hyperparameters
 memory = joblib.Memory(location=CACHE_DIR, verbose=0)
 if estimator.__class__.__name__ == 'IRAPSClassifier':
 estimator.set_params(memory=memory)
 else:
 # For iraps buried in pipeline
 for p, v in estimator_params.items():
-if p.endswith('memory'):
+if p.endswith('__irapsclassifier__memory'):
-# for case of `__irapsclassifier__memory`
+new_params = {p: memory}
-if len(p) > 8 and p[:-8].endswith('irapsclassifier'):
-# cache iraps_core fits could increase search
-# speed significantly
-new_params = {p: memory}
-estimator.set_params(**new_params)
-# security reason, we don't want memory being
-# modified unexpectedly
-elif v:
-new_params = {p, None}
-estimator.set_params(**new_params)
-# For now, 1 CPU is suggested for iprasclassifier
-elif p.endswith('n_jobs'):
-new_params = {p: 1}
 estimator.set_params(**new_params)
-# for security reason, types of callback are limited
-elif p.endswith('callbacks'):
-for cb in v:
-cb_type = cb['callback_selection']['callback_type']
-if cb_type not in ALLOWED_CALLBACKS:
-raise ValueError(
-"Prohibited callback type: %s!" % cb_type)
 ## store read dataframe object
 loaded_df = {}
 #if $input_options.selected_input == 'tabular'
 infile2 = loaded_df[df_key]
 else:
 infile2 = pd.read_csv(infile2, sep='\t', header=header, parse_dates=True)
 loaded_df[df_key] = infile2
 y = read_columns(
 infile2,
 c = c,
 c_option = column_option,
 sep='\t',
 header=header,
 parse_dates=True)
 if len(y.shape) == 2 and y.shape[1] == 1:
 y = y.ravel()
 #if $input_options.selected_input == 'refseq_and_interval'
 estimator.set_params(
 data_batch_generator__features=y.ravel().tolist())
 y = None
+label_encoder = LabelEncoder()
+if get_main_estimator(estimator).__class__.__name__ == "XGBClassifier":
+y = label_encoder.fit_transform(y)
+print(label_encoder.classes_)
 #end if
 ## handle options
 options = params['model_validation_functions']['options']
 #end if
 ## del loaded_df
 del loaded_df
-splitter, groups = get_cv( options.pop('cv_selector') )
+cv_selector = options.pop('cv_selector')
+if Version(galaxy_ml_version) < Version('0.8.3'):
+cv_selector.pop('n_stratification_bins', None)
+splitter, groups = get_cv( cv_selector )
 options['cv'] = splitter
 options['groups'] = groups
 options['n_jobs'] = N_JOBS
 if 'scoring' in options:
 primary_scoring = options['scoring']['primary_scoring']
 else:
 rval = pd.DataFrame(predicted)
 elif selected_function == 'learning_curve':
 try:
 train_sizes = safe_eval(options['train_sizes'])
-except Exception:
+except:
 sys.exit("Unsupported train_sizes input! Supports int/float in tuple and array-like structure.")
 if type(train_sizes) is tuple:
 train_sizes = np.linspace(*train_sizes)
 options['train_sizes'] = train_sizes
 train_sizes_abs, train_scores, test_scores = validator(estimator, X, y, **options)
 ]]>
 </configfile>
 </configfiles>
 <inputs>
-<param name="infile_estimator" type="data" format="zip" label="Choose the dataset containing model/pipeline object" />
+<param name="infile_estimator" type="data" format="h5mlm" label="Choose the dataset containing model/pipeline object" />
 <conditional name="model_validation_functions">
 <param name="selected_function" type="select" label="Select a model validation function">
 <option value="cross_validate">cross_validate - Evaluate metric(s) by cross-validation and also record fit/score times</option>
 <option value="cross_val_predict">cross_val_predict - Generate cross-validated estimates for each input data point</option>
 <option value="learning_curve">learning_curve - Learning curve</option>
 <when value="cross_validate">
 <section name="options" title="Other Options" expanded="false">
 <expand macro="scoring_selection" />
 <expand macro="model_validation_common_options" />
 <param argument="return_train_score" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" help="Whether to include train scores." />
-<!--param argument="return_estimator" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" help="Whether to return the estimators fitted on each split."/> -->
+<!--param argument="return_estimator" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" help="Whether to return the estimators fitted on each split." /> -->
-<!--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="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." /> -->
 <!--fit_params-->
 <expand macro="pre_dispatch" />
 </section>
 </when>
 <when value="cross_val_predict">
 </when>
 <when value="learning_curve">
 <section name="options" title="Other Options" expanded="false">
 <expand macro="scoring_selection" />
 <expand macro="model_validation_common_options" />
-<param argument="train_sizes" type="text" value="(0.1, 1.0, 5)" label="train_sizes" help="Relative or absolute numbers of training examples that will be used to generate the learning curve. Supports 1) tuple, to be evaled by np.linspace, e.g. (0.1, 1.0, 5); 2) array-like, e.g. [0.1  , 0.325, 0.55 , 0.775, 1.]">
+<param argument="train_sizes" type="text" value="(0.1, 1.0, 5)" label="train_sizes"
+help="Relative or absolute numbers of training examples that will be used to generate the learning curve. Supports 1) tuple, to be evaled by np.linspace, e.g. (0.1, 1.0, 5); 2) array-like, e.g. [0.1  , 0.325, 0.55 , 0.775, 1.]">
 <sanitizer>
 <valid initial="default">
 <add value="[" />
 <add value="]" />
 </valid>
 <param name="infile2" value="regression_train.tabular" ftype="tabular" />
 <param name="col2" value="6" />
 <output name="outfile">
 <assert_contents>
 <has_n_columns n="6" />
-<has_text text="0.9999961390418067" />
+<has_text text="0.9998136508657879" />
-<has_text text="0.9944541531269271" />
+<has_text text="0.9999980090366614" />
-<has_text text="0.9999193322454393" />
+<has_text text="0.9999977541353663" />
 </assert_contents>
 </output>
 </test>
 <test>
 <param name="infile_estimator" value="pipeline02" />
 <param name="selected_function" value="cross_val_predict" />
 <param name="infile1" value="regression_train.tabular" ftype="tabular" />
 <param name="col1" value="1,2,3,4,5" />
 <param name="infile2" value="regression_train.tabular" ftype="tabular" />
 <param name="col2" value="6" />
-<output name="outfile" file="mv_result02.tabular" lines_diff="14" />
+<output name="outfile">
+<assert_contents>
+<has_n_columns n="1" />
+<has_text text="1.5781414" />
+<has_text text="-1.19994559787" />
+<has_text text="-0.7187446" />
+<has_text text="0.324693926" />
+<has_text text="1.25823227" />
+</assert_contents>
+</output>
 </test>
 <test>
 <param name="infile_estimator" value="pipeline05" />
 <param name="selected_function" value="learning_curve" />
 <param name="infile1" value="regression_X.tabular" ftype="tabular" />
 <param name="infile2" value="regression_train.tabular" ftype="tabular" />
 <param name="col2" value="6" />
 <output name="outfile">
 <assert_contents>
 <has_n_columns n="3" />
-<has_text text="0.25697059258228816" />
+<has_text text="-2.7453395018288753" />
 </assert_contents>
 </output>
 </test>
 <test>
 <param name="infile_estimator" value="pipeline05" />

Mercurial > repos > bgruening > sklearn_model_validation

comparison model_validation.xml @ 34:1fe00785190d draft