comparison train_test_eval.py @ 12:f903c8cf1455 draft

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

11:fc70bf5c3b58

import argparse
import json
import os
import pickle
import warnings
from itertools import chain

import joblib
import numpy as np
import pandas as pd
from galaxy_ml.model_validations import train_test_split
from galaxy_ml.utils import (get_module, get_scoring, load_model,
                             read_columns, SafeEval, try_get_attr)
from scipy.io import mmread
from sklearn import pipeline
from sklearn.metrics.scorer import _check_multimetric_scoring
from sklearn.model_selection import _search, _validation
from sklearn.model_selection._validation import _score
from sklearn.utils import indexable, safe_indexing

_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)

        index_arr = np.arange(n_samples)
        test = index_arr[np.isin(groups, group_names)]
        train = index_arr[~np.isin(groups, group_names)]
        rval = list(
            chain.from_iterable(
                (safe_indexing(a, train), safe_indexing(a, test)) for a in new_arrays
            )
        )
    else:
        rval = train_test_split(*new_arrays, **kwargs)

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

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

    # swap hyperparameter
    swapping = params["experiment_schemes"]["hyperparams_swapping"]
    swap_params = _eval_swap_params(swapping)
    estimator.set_params(**swap_params)

        secondary_scoring = scoring.get("secondary_scoring", None)
        if secondary_scoring is not None:
            # If secondary_scoring is specified, convert the list into comman separated string
            scoring["secondary_scoring"] = ",".join(scoring["secondary_scoring"])
    scorer = get_scoring(scoring)
    scorer, _ = _check_multimetric_scoring(estimator, scoring=scorer)

    # handle test (first) split
    test_split_options = params["experiment_schemes"]["test_split"]["split_algos"]

    if test_split_options["shuffle"] == "group":

    if hasattr(estimator, "evaluate"):
        scores = estimator.evaluate(
            X_test, y_test=y_test, scorer=scorer, is_multimetric=True
        )
    else:
        scores = _score(estimator, X_test, y_test, scorer, is_multimetric=True)
    # handle output
    for name, score in scores.items():
        scores[name] = [score]
    df = pd.DataFrame(scores)
    df = df[sorted(df.columns)]

            if getattr(main_est, "validation_data", None):
                del main_est.validation_data
            if getattr(main_est, "data_generator_", None):
                del main_est.data_generator_

        with open(outfile_object, "wb") as output_handler:
            pickle.dump(estimator, output_handler, pickle.HIGHEST_PROTOCOL)


if __name__ == "__main__":
    aparser = argparse.ArgumentParser()
    aparser.add_argument("-i", "--inputs", dest="inputs", required=True)

12:f903c8cf1455

import argparse
import json
import os
import warnings
from itertools import chain

import joblib
import numpy as np
import pandas as pd
from galaxy_ml.model_persist import dump_model_to_h5, load_model_from_h5
from galaxy_ml.model_validations import train_test_split
from galaxy_ml.utils import (
    clean_params,
    get_module,
    get_scoring,
    read_columns,
    SafeEval,
    try_get_attr
)
from scipy.io import mmread
from sklearn import pipeline
from sklearn.model_selection import _search, _validation
from sklearn.model_selection._validation import _score
from sklearn.utils import _safe_indexing, indexable

_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)

        index_arr = np.arange(n_samples)
        test = index_arr[np.isin(groups, group_names)]
        train = index_arr[~np.isin(groups, group_names)]
        rval = list(
            chain.from_iterable(
                (_safe_indexing(a, train), _safe_indexing(a, test)) for a in new_arrays
            )
        )
    else:
        rval = train_test_split(*new_arrays, **kwargs)

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

    #  load estimator
    estimator = load_model_from_h5(infile_estimator)
    estimator = clean_params(estimator)

    # swap hyperparameter
    swapping = params["experiment_schemes"]["hyperparams_swapping"]
    swap_params = _eval_swap_params(swapping)
    estimator.set_params(**swap_params)

        secondary_scoring = scoring.get("secondary_scoring", None)
        if secondary_scoring is not None:
            # If secondary_scoring is specified, convert the list into comman separated string
            scoring["secondary_scoring"] = ",".join(scoring["secondary_scoring"])
    scorer = get_scoring(scoring)

    # handle test (first) split
    test_split_options = params["experiment_schemes"]["test_split"]["split_algos"]

    if test_split_options["shuffle"] == "group":

    if hasattr(estimator, "evaluate"):
        scores = estimator.evaluate(
            X_test, y_test=y_test, scorer=scorer, is_multimetric=True
        )
    else:
        scores = _score(estimator, X_test, y_test, scorer)
    # handle output
    for name, score in scores.items():
        scores[name] = [score]
    df = pd.DataFrame(scores)
    df = df[sorted(df.columns)]

            if getattr(main_est, "validation_data", None):
                del main_est.validation_data
            if getattr(main_est, "data_generator_", None):
                del main_est.data_generator_

        dump_model_to_h5(estimator, outfile_object)


if __name__ == "__main__":
    aparser = argparse.ArgumentParser()
    aparser.add_argument("-i", "--inputs", dest="inputs", required=True)