comparison search_model_validation.py @ 37:e76f6dfea5c9 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit ea12f973df4b97a2691d9e4ce6bf6fae59d57717"

36:420a4bf99244

import imblearn
import joblib
import numpy as np
import pandas as pd
import skrebate
from galaxy_ml.utils import (
    clean_params,
    get_cv,
    get_main_estimator,
    get_module,
    get_scoring,
    load_model,
    read_columns,
    SafeEval,
    try_get_attr
)
from scipy.io import mmread
from sklearn import (
    cluster,
    decomposition,
    feature_selection,
    kernel_approximation,
    model_selection,
    preprocessing,
)
from sklearn.exceptions import FitFailedWarning
from sklearn.model_selection import _search, _validation
from sklearn.model_selection._validation import _score, cross_validate


_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)

        if search_list == "":
            continue

        param_name = p["sp_name"]
        if param_name.lower().endswith(NON_SEARCHABLE):
            print("Warning: `%s` is not eligible for search and was " "omitted!" % param_name)
            continue

        if not search_list.startswith(":"):
            safe_eval = SafeEval(load_scipy=True, load_numpy=True)
            ev = safe_eval(search_list)

                decomposition.FactorAnalysis(random_state=0),
                decomposition.FastICA(random_state=0),
                decomposition.IncrementalPCA(),
                decomposition.KernelPCA(random_state=0, n_jobs=N_JOBS),
                decomposition.LatentDirichletAllocation(random_state=0, n_jobs=N_JOBS),
                decomposition.MiniBatchDictionaryLearning(random_state=0, n_jobs=N_JOBS),
                decomposition.MiniBatchSparsePCA(random_state=0, n_jobs=N_JOBS),
                decomposition.NMF(random_state=0),
                decomposition.PCA(random_state=0),
                decomposition.SparsePCA(random_state=0, n_jobs=N_JOBS),
                decomposition.TruncatedSVD(random_state=0),

                skrebate.SURF(n_jobs=N_JOBS),
                skrebate.SURFstar(n_jobs=N_JOBS),
                skrebate.MultiSURF(n_jobs=N_JOBS),
                skrebate.MultiSURFstar(n_jobs=N_JOBS),
                imblearn.under_sampling.ClusterCentroids(random_state=0, n_jobs=N_JOBS),
                imblearn.under_sampling.CondensedNearestNeighbour(random_state=0, n_jobs=N_JOBS),
                imblearn.under_sampling.EditedNearestNeighbours(random_state=0, n_jobs=N_JOBS),
                imblearn.under_sampling.RepeatedEditedNearestNeighbours(random_state=0, n_jobs=N_JOBS),
                imblearn.under_sampling.AllKNN(random_state=0, n_jobs=N_JOBS),
                imblearn.under_sampling.InstanceHardnessThreshold(random_state=0, n_jobs=N_JOBS),
                imblearn.under_sampling.NearMiss(random_state=0, n_jobs=N_JOBS),
                imblearn.under_sampling.NeighbourhoodCleaningRule(random_state=0, n_jobs=N_JOBS),
                imblearn.under_sampling.OneSidedSelection(random_state=0, n_jobs=N_JOBS),
                imblearn.under_sampling.RandomUnderSampler(random_state=0),
                imblearn.under_sampling.TomekLinks(random_state=0, n_jobs=N_JOBS),
                imblearn.over_sampling.ADASYN(random_state=0, n_jobs=N_JOBS),
                imblearn.over_sampling.RandomOverSampler(random_state=0),
                imblearn.over_sampling.SMOTE(random_state=0, n_jobs=N_JOBS),
                imblearn.over_sampling.SVMSMOTE(random_state=0, n_jobs=N_JOBS),
                imblearn.over_sampling.BorderlineSMOTE(random_state=0, n_jobs=N_JOBS),
                imblearn.over_sampling.SMOTENC(categorical_features=[], random_state=0, n_jobs=N_JOBS),
                imblearn.combine.SMOTEENN(random_state=0),
                imblearn.combine.SMOTETomek(random_state=0),
            )
            newlist = []
            for obj in ev:

    input_type = params["input_options"]["selected_input"]
    # tabular input
    if input_type == "tabular":
        header = "infer" if params["input_options"]["header1"] else None
        column_option = params["input_options"]["column_selector_options_1"]["selected_column_selector_option"]
        if column_option in [
            "by_index_number",
            "all_but_by_index_number",
            "by_header_name",
            "all_but_by_header_name",

        n_intervals = sum(1 for line in open(intervals))
        X = np.arange(n_intervals)[:, np.newaxis]

    # Get target y
    header = "infer" if params["input_options"]["header2"] else None
    column_option = params["input_options"]["column_selector_options_2"]["selected_column_selector_option2"]
    if column_option in [
        "by_index_number",
        "all_but_by_index_number",
        "by_header_name",
        "all_but_by_header_name",

        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_type == "refseq_and_interval":
        estimator.set_params(data_batch_generator__features=y.ravel().tolist())
        y = None

    if split_options["shuffle"] == "stratified":
        split_options["labels"] = y
        X, X_test, y, y_test = train_test_split(X, y, **split_options)
    elif split_options["shuffle"] == "group":
        if groups is None:
            raise ValueError("No group based CV option was choosen for " "group shuffle!")
        split_options["labels"] = groups
        if y is None:
            X, X_test, groups, _ = train_test_split(X, groups, **split_options)
        else:
            X, X_test, y, y_test, groups, _ = train_test_split(X, y, groups, **split_options)
    else:
        if split_options["shuffle"] == "None":
            split_options["shuffle"] = None
        X, X_test, y, y_test = train_test_split(X, y, **split_options)

    best_estimator_ = getattr(searcher, "best_estimator_")

    # TODO Solve deep learning models in pipeline
    if best_estimator_.__class__.__name__ == "KerasGBatchClassifier":
        test_score = best_estimator_.evaluate(X_test, scorer=scorer_, is_multimetric=is_multimetric)
    else:
        test_score = _score(best_estimator_, X_test, y_test, scorer_, is_multimetric=is_multimetric)

    if not is_multimetric:
        test_score = {primary_scoring: test_score}
    for key, value in test_score.items():
        test_score[key] = [value]

    with open(inputs, "r") as param_handler:
        params = json.load(param_handler)

    # Override the refit parameter
    params["search_schemes"]["options"]["refit"] = True if params["save"] != "nope" else False

    with open(infile_estimator, "rb") as estimator_handler:
        estimator = load_model(estimator_handler)

    optimizer = params["search_schemes"]["selected_search_scheme"]

    # handle gridsearchcv options
    options = params["search_schemes"]["options"]

    if groups:
        header = "infer" if (options["cv_selector"]["groups_selector"]["header_g"]) else None
        column_option = options["cv_selector"]["groups_selector"]["column_selector_options_g"][
            "selected_column_selector_option_g"
        ]
        if column_option in [
            "by_index_number",
            "all_but_by_index_number",
            "by_header_name",
            "all_but_by_header_name",
        ]:
            c = options["cv_selector"]["groups_selector"]["column_selector_options_g"]["col_g"]
        else:
            c = None

        df_key = groups + repr(header)

    # get_scoring() expects secondary_scoring to be a comma separated string (not a list)
    # Check if secondary_scoring is specified
    secondary_scoring = options["scoring"].get("secondary_scoring", None)
    if secondary_scoring is not None:
        # If secondary_scoring is specified, convert the list into comman separated string
        options["scoring"]["secondary_scoring"] = ",".join(options["scoring"]["secondary_scoring"])
    options["scoring"] = get_scoring(options["scoring"])
    if options["error_score"]:
        options["error_score"] = "raise"
    else:
        options["error_score"] = np.NaN
    if options["refit"] and isinstance(options["scoring"], dict):
        options["refit"] = primary_scoring
    if "pre_dispatch" in options and options["pre_dispatch"] == "":
        options["pre_dispatch"] = None

    if split_mode == "nested_cv":
        # make sure refit is choosen
        # this could be True for sklearn models, but not the case for
        # deep learning models
        if not options["refit"] and not all(hasattr(estimator, attr) for attr in ("config", "model_type")):
            warnings.warn("Refit is change to `True` for nested validation!")
            setattr(searcher, "refit", True)

        outer_cv, _ = get_cv(params["outer_split"]["cv_selector"])
        # nested CV, outer cv using cross_validate

                for warning in w:
                    print(repr(warning.message))

        cv_results = pd.DataFrame(searcher.cv_results_)
        cv_results = cv_results[sorted(cv_results.columns)]
        cv_results.to_csv(path_or_buf=outfile_result, sep="\t", header=True, index=False)

    memory.clear(warn=False)

    # output best estimator, and weights if applicable
    if outfile_object:

37:e76f6dfea5c9

import imblearn
import joblib
import numpy as np
import pandas as pd
import skrebate
from galaxy_ml.utils import (clean_params, get_cv,
                             get_main_estimator, get_module, get_scoring,
                             load_model, read_columns, SafeEval, try_get_attr)
from scipy.io import mmread
from sklearn import (cluster, decomposition, feature_selection,
                     kernel_approximation, model_selection, preprocessing)
from sklearn.exceptions import FitFailedWarning
from sklearn.model_selection import _search, _validation
from sklearn.model_selection._validation import _score, cross_validate

_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)

        if search_list == "":
            continue

        param_name = p["sp_name"]
        if param_name.lower().endswith(NON_SEARCHABLE):
            print(
                "Warning: `%s` is not eligible for search and was "
                "omitted!" % param_name
            )
            continue

        if not search_list.startswith(":"):
            safe_eval = SafeEval(load_scipy=True, load_numpy=True)
            ev = safe_eval(search_list)

                decomposition.FactorAnalysis(random_state=0),
                decomposition.FastICA(random_state=0),
                decomposition.IncrementalPCA(),
                decomposition.KernelPCA(random_state=0, n_jobs=N_JOBS),
                decomposition.LatentDirichletAllocation(random_state=0, n_jobs=N_JOBS),
                decomposition.MiniBatchDictionaryLearning(
                    random_state=0, n_jobs=N_JOBS
                ),
                decomposition.MiniBatchSparsePCA(random_state=0, n_jobs=N_JOBS),
                decomposition.NMF(random_state=0),
                decomposition.PCA(random_state=0),
                decomposition.SparsePCA(random_state=0, n_jobs=N_JOBS),
                decomposition.TruncatedSVD(random_state=0),

                skrebate.SURF(n_jobs=N_JOBS),
                skrebate.SURFstar(n_jobs=N_JOBS),
                skrebate.MultiSURF(n_jobs=N_JOBS),
                skrebate.MultiSURFstar(n_jobs=N_JOBS),
                imblearn.under_sampling.ClusterCentroids(random_state=0, n_jobs=N_JOBS),
                imblearn.under_sampling.CondensedNearestNeighbour(
                    random_state=0, n_jobs=N_JOBS
                ),
                imblearn.under_sampling.EditedNearestNeighbours(
                    random_state=0, n_jobs=N_JOBS
                ),
                imblearn.under_sampling.RepeatedEditedNearestNeighbours(
                    random_state=0, n_jobs=N_JOBS
                ),
                imblearn.under_sampling.AllKNN(random_state=0, n_jobs=N_JOBS),
                imblearn.under_sampling.InstanceHardnessThreshold(
                    random_state=0, n_jobs=N_JOBS
                ),
                imblearn.under_sampling.NearMiss(random_state=0, n_jobs=N_JOBS),
                imblearn.under_sampling.NeighbourhoodCleaningRule(
                    random_state=0, n_jobs=N_JOBS
                ),
                imblearn.under_sampling.OneSidedSelection(
                    random_state=0, n_jobs=N_JOBS
                ),
                imblearn.under_sampling.RandomUnderSampler(random_state=0),
                imblearn.under_sampling.TomekLinks(random_state=0, n_jobs=N_JOBS),
                imblearn.over_sampling.ADASYN(random_state=0, n_jobs=N_JOBS),
                imblearn.over_sampling.RandomOverSampler(random_state=0),
                imblearn.over_sampling.SMOTE(random_state=0, n_jobs=N_JOBS),
                imblearn.over_sampling.SVMSMOTE(random_state=0, n_jobs=N_JOBS),
                imblearn.over_sampling.BorderlineSMOTE(random_state=0, n_jobs=N_JOBS),
                imblearn.over_sampling.SMOTENC(
                    categorical_features=[], random_state=0, n_jobs=N_JOBS
                ),
                imblearn.combine.SMOTEENN(random_state=0),
                imblearn.combine.SMOTETomek(random_state=0),
            )
            newlist = []
            for obj in ev:

    input_type = params["input_options"]["selected_input"]
    # tabular input
    if input_type == "tabular":
        header = "infer" if params["input_options"]["header1"] else None
        column_option = params["input_options"]["column_selector_options_1"][
            "selected_column_selector_option"
        ]
        if column_option in [
            "by_index_number",
            "all_but_by_index_number",
            "by_header_name",
            "all_but_by_header_name",

        n_intervals = sum(1 for line in open(intervals))
        X = np.arange(n_intervals)[:, np.newaxis]

    # Get target y
    header = "infer" if params["input_options"]["header2"] else None
    column_option = params["input_options"]["column_selector_options_2"][
        "selected_column_selector_option2"
    ]
    if column_option in [
        "by_index_number",
        "all_but_by_index_number",
        "by_header_name",
        "all_but_by_header_name",

        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_type == "refseq_and_interval":
        estimator.set_params(data_batch_generator__features=y.ravel().tolist())
        y = None

    if split_options["shuffle"] == "stratified":
        split_options["labels"] = y
        X, X_test, y, y_test = train_test_split(X, y, **split_options)
    elif split_options["shuffle"] == "group":
        if groups is None:
            raise ValueError(
                "No group based CV option was choosen for " "group shuffle!"
            )
        split_options["labels"] = groups
        if y is None:
            X, X_test, groups, _ = train_test_split(X, groups, **split_options)
        else:
            X, X_test, y, y_test, groups, _ = train_test_split(
                X, y, groups, **split_options
            )
    else:
        if split_options["shuffle"] == "None":
            split_options["shuffle"] = None
        X, X_test, y, y_test = train_test_split(X, y, **split_options)

    best_estimator_ = getattr(searcher, "best_estimator_")

    # TODO Solve deep learning models in pipeline
    if best_estimator_.__class__.__name__ == "KerasGBatchClassifier":
        test_score = best_estimator_.evaluate(
            X_test, scorer=scorer_, is_multimetric=is_multimetric
        )
    else:
        test_score = _score(
            best_estimator_, X_test, y_test, scorer_, is_multimetric=is_multimetric
        )

    if not is_multimetric:
        test_score = {primary_scoring: test_score}
    for key, value in test_score.items():
        test_score[key] = [value]

    with open(inputs, "r") as param_handler:
        params = json.load(param_handler)

    # Override the refit parameter
    params["search_schemes"]["options"]["refit"] = (
        True if params["save"] != "nope" else False
    )

    with open(infile_estimator, "rb") as estimator_handler:
        estimator = load_model(estimator_handler)

    optimizer = params["search_schemes"]["selected_search_scheme"]

    # handle gridsearchcv options
    options = params["search_schemes"]["options"]

    if groups:
        header = (
            "infer" if (options["cv_selector"]["groups_selector"]["header_g"]) else None
        )
        column_option = options["cv_selector"]["groups_selector"][
            "column_selector_options_g"
        ]["selected_column_selector_option_g"]
        if column_option in [
            "by_index_number",
            "all_but_by_index_number",
            "by_header_name",
            "all_but_by_header_name",
        ]:
            c = options["cv_selector"]["groups_selector"]["column_selector_options_g"][
                "col_g"
            ]
        else:
            c = None

        df_key = groups + repr(header)

    # get_scoring() expects secondary_scoring to be a comma separated string (not a list)
    # Check if secondary_scoring is specified
    secondary_scoring = options["scoring"].get("secondary_scoring", None)
    if secondary_scoring is not None:
        # If secondary_scoring is specified, convert the list into comman separated string
        options["scoring"]["secondary_scoring"] = ",".join(
            options["scoring"]["secondary_scoring"]
        )
    options["scoring"] = get_scoring(options["scoring"])
    if options["error_score"]:
        options["error_score"] = "raise"
    else:
        options["error_score"] = np.nan
    if options["refit"] and isinstance(options["scoring"], dict):
        options["refit"] = primary_scoring
    if "pre_dispatch" in options and options["pre_dispatch"] == "":
        options["pre_dispatch"] = None

    if split_mode == "nested_cv":
        # make sure refit is choosen
        # this could be True for sklearn models, but not the case for
        # deep learning models
        if not options["refit"] and not all(
            hasattr(estimator, attr) for attr in ("config", "model_type")
        ):
            warnings.warn("Refit is change to `True` for nested validation!")
            setattr(searcher, "refit", True)

        outer_cv, _ = get_cv(params["outer_split"]["cv_selector"])
        # nested CV, outer cv using cross_validate

                for warning in w:
                    print(repr(warning.message))

        cv_results = pd.DataFrame(searcher.cv_results_)
        cv_results = cv_results[sorted(cv_results.columns)]
        cv_results.to_csv(
            path_or_buf=outfile_result, sep="\t", header=True, index=False
        )

    memory.clear(warn=False)

    # output best estimator, and weights if applicable
    if outfile_object: