OpenML
9198979

Run 9198979

Task 49 (Supervised Classification) tic-tac-toe Uploaded 27-04-2018 by Hilde Weerts
0 likes downloaded by 0 people 0 issues 0 downvotes , 0 total downloads
  • openml-python Sklearn_0.19.1. study_98
Issue #Downvotes for this reason By


Flow

sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeli ne.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hote ncoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn. feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble .forest.RandomForestClassifier))(1)Automatically created scikit-learn flow.
sklearn.preprocessing.data.OneHotEncoder(17)_categorical_features[0, 1, 2, 3, 4, 5, 6, 7, 8]
sklearn.preprocessing.data.OneHotEncoder(17)_dtype{"oml-python:serialized_object": "type", "value": "np.float64"}
sklearn.preprocessing.data.OneHotEncoder(17)_handle_unknown"ignore"
sklearn.preprocessing.data.OneHotEncoder(17)_n_values"auto"
sklearn.preprocessing.data.OneHotEncoder(17)_sparsetrue
sklearn.feature_selection.variance_threshold.VarianceThreshold(11)_threshold0.0
sklearn.ensemble.forest.RandomForestClassifier(32)_bootstraptrue
sklearn.ensemble.forest.RandomForestClassifier(32)_class_weightnull
sklearn.ensemble.forest.RandomForestClassifier(32)_criterion"gini"
sklearn.ensemble.forest.RandomForestClassifier(32)_max_depthnull
sklearn.ensemble.forest.RandomForestClassifier(32)_max_features"auto"
sklearn.ensemble.forest.RandomForestClassifier(32)_max_leaf_nodesnull
sklearn.ensemble.forest.RandomForestClassifier(32)_min_impurity_decrease0.0
sklearn.ensemble.forest.RandomForestClassifier(32)_min_impurity_splitnull
sklearn.ensemble.forest.RandomForestClassifier(32)_min_samples_leaf1
sklearn.ensemble.forest.RandomForestClassifier(32)_min_samples_split2
sklearn.ensemble.forest.RandomForestClassifier(32)_min_weight_fraction_leaf0.0
sklearn.ensemble.forest.RandomForestClassifier(32)_n_estimators10
sklearn.ensemble.forest.RandomForestClassifier(32)_n_jobs1
sklearn.ensemble.forest.RandomForestClassifier(32)_oob_scorefalse
sklearn.ensemble.forest.RandomForestClassifier(32)_random_state40510
sklearn.ensemble.forest.RandomForestClassifier(32)_verbose0
sklearn.ensemble.forest.RandomForestClassifier(32)_warm_startfalse
sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier)(1)_memorynull
hyperimp.utils.preprocessing.ConditionalImputer(1)_axis0
hyperimp.utils.preprocessing.ConditionalImputer(1)_categorical_features[0, 1, 2, 3, 4, 5, 6, 7, 8]
hyperimp.utils.preprocessing.ConditionalImputer(1)_copytrue
hyperimp.utils.preprocessing.ConditionalImputer(1)_fill_empty0
hyperimp.utils.preprocessing.ConditionalImputer(1)_missing_values"NaN"
hyperimp.utils.preprocessing.ConditionalImputer(1)_strategy"mean"
hyperimp.utils.preprocessing.ConditionalImputer(1)_strategy_nominal"most_frequent"
hyperimp.utils.preprocessing.ConditionalImputer(1)_verbose0
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier))(1)_cv5
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier))(1)_error_score"raise"
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier))(1)_fit_paramsnull
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier))(1)_iidtrue
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier))(1)_n_iter100
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier))(1)_n_jobs-1
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier))(1)_param_distributions{"clf__bootstrap": [true, false], "clf__criterion": ["gini", "entropy"], "clf__max_features": {"oml-python:serialized_object": "rv_frozen", "value": {"dist": "scipy.stats._continuous_distns.uniform_gen", "a": 0.0, "b": 1.0, "args": [], "kwds": {"loc": 0, "scale": 1}}}, "clf__min_samples_leaf": {"oml-python:serialized_object": "rv_frozen", "value": {"dist": "scipy.stats._discrete_distns.randint_gen", "a": 1, "b": 20, "args": [], "kwds": {"low": 1, "high": 21}}}, "clf__min_samples_split": {"oml-python:serialized_object": "rv_frozen", "value": {"dist": "scipy.stats._discrete_distns.randint_gen", "a": 2, "b": 20, "args": [], "kwds": {"low": 2, "high": 21}}}, "clf__n_estimators": [300], "clf__random_state": {"oml-python:serialized_object": "rv_frozen", "value": {"dist": "scipy.stats._discrete_distns.randint_gen", "a": 1, "b": 100000, "args": [], "kwds": {"low": 1, "high": 100001}}}}
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier))(1)_pre_dispatch"2*n_jobs"
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier))(1)_random_state581283
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier))(1)_refittrue
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier))(1)_return_train_score"warn"
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier))(1)_scoringnull
sklearn.model_selection._search.RandomizedSearchCV(estimator=sklearn.pipeline.Pipeline(imputation=hyperimp.utils.preprocessing.ConditionalImputer,hotencoding=sklearn.preprocessing.data.OneHotEncoder,variencethreshold=sklearn.feature_selection.variance_threshold.VarianceThreshold,clf=sklearn.ensemble.forest.RandomForestClassifier))(1)_verbose1

Result files

xml
Description

XML file describing the run, including user-defined evaluation measures.

arff
Predictions

ARFF file with instance-level predictions generated by the model.

arff
Trace

ARFF file with the trace of all hyperparameter settings tried during optimization, and their performance.

17 Evaluation measures

Area under ROC curve
0.9981 ± 0.0029
Per class
Cross-validation details (10-fold Crossvalidation)
F measure
0.9906 ± 0.0092
Per class
Cross-validation details (10-fold Crossvalidation)
Kappa
0.9791 ± 0.0204
Cross-validation details (10-fold Crossvalidation)
KB relative information score
735.1875 ± 4.4988
Cross-validation details (10-fold Crossvalidation)
Mean absolute error
0.1294 ± 0.0247
Cross-validation details (10-fold Crossvalidation)
Mean prior absolute error
0.453 ± 0.0013
Cross-validation details (10-fold Crossvalidation)
Number of instances
958
Per class
Cross-validation details (10-fold Crossvalidation)
Precision
0.9907 ± 0.0088
Per class
Cross-validation details (10-fold Crossvalidation)
Predictive accuracy
0.9906 ± 0.0091
Cross-validation details (10-fold Crossvalidation)
Prior entropy
0.9312
Cross-validation details (10-fold Crossvalidation)
Recall
0.9906 ± 0.0091
Per class
Cross-validation details (10-fold Crossvalidation)
Relative absolute error
0.2856 ± 0.0549
Cross-validation details (10-fold Crossvalidation)
Root mean prior squared error
0.4759 ± 0.0014
Cross-validation details (10-fold Crossvalidation)
Root mean squared error
0.1765 ± 0.0201
Cross-validation details (10-fold Crossvalidation)
Root relative squared error
0.371 ± 0.0427
Cross-validation details (10-fold Crossvalidation)