comparison stacking_ensembles.py @ 34:1fe00785190d draft

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

33:5d5d9cc554f9

import argparse
import ast
import json
import pickle
import sys
import warnings

import mlxtend.classifier
import mlxtend.regressor
import pandas as pd
from galaxy_ml.utils import (get_cv, get_estimator, get_search_params,
                             load_model)

warnings.filterwarnings("ignore")

N_JOBS = int(__import__("os").environ.get("GALAXY_SLOTS", 1))


def main(inputs_path, output_obj, base_paths=None, meta_path=None, outfile_params=None):
    """
    Parameter
    ---------
    inputs_path : str
        File path for Galaxy parameters

    base_paths : str
        File path or paths concatenated by comma.

    meta_path : str
        File path

    outfile_params : str
        File path for params output
    """
    with open(inputs_path, "r") as param_handler:
        params = json.load(param_handler)

    estimator_type = params["algo_selection"]["estimator_type"]
    # get base estimators
    base_estimators = []
    for idx, base_file in enumerate(base_paths.split(",")):
        if base_file and base_file != "None":
            with open(base_file, "rb") as handler:
                model = load_model(handler)
        else:
            estimator_json = params["base_est_builder"][idx]["estimator_selector"]
            model = get_estimator(estimator_json)

        if estimator_type.startswith("sklearn"):

            base_estimators.append(model)

    # get meta estimator, if applicable
    if estimator_type.startswith("mlxtend"):
        if meta_path:
            with open(meta_path, "rb") as f:
                meta_estimator = load_model(f)
        else:
            estimator_json = params["algo_selection"]["meta_estimator"][
                "estimator_selector"
            ]
            meta_estimator = get_estimator(estimator_json)

    options = params["algo_selection"]["options"]

    cv_selector = options.pop("cv_selector", None)
    if cv_selector:
        splitter, _groups = get_cv(cv_selector)
        options["cv"] = splitter
        # set n_jobs
        options["n_jobs"] = N_JOBS

    weights = options.pop("weights", None)

    print(ensemble_estimator)
    for base_est in base_estimators:
        print(base_est)

    with open(output_obj, "wb") as out_handler:
        pickle.dump(ensemble_estimator, out_handler, pickle.HIGHEST_PROTOCOL)

    if params["get_params"] and outfile_params:
        results = get_search_params(ensemble_estimator)
        df = pd.DataFrame(results, columns=["", "Parameter", "Value"])
        df.to_csv(outfile_params, sep="\t", index=False)


if __name__ == "__main__":
    aparser = argparse.ArgumentParser()
    aparser.add_argument("-b", "--bases", dest="bases")
    aparser.add_argument("-m", "--meta", dest="meta")
    aparser.add_argument("-i", "--inputs", dest="inputs")
    aparser.add_argument("-o", "--outfile", dest="outfile")
    aparser.add_argument("-p", "--outfile_params", dest="outfile_params")
    args = aparser.parse_args()

    main(
        args.inputs,
        args.outfile,
        base_paths=args.bases,
        meta_path=args.meta,
        outfile_params=args.outfile_params,
    )

34:1fe00785190d

import argparse
import ast
import json
import sys
import warnings
from distutils.version import LooseVersion as Version

import mlxtend.classifier
import mlxtend.regressor
from galaxy_ml import __version__ as galaxy_ml_version
from galaxy_ml.model_persist import dump_model_to_h5, load_model_from_h5
from galaxy_ml.utils import get_cv, get_estimator

warnings.filterwarnings("ignore")

N_JOBS = int(__import__("os").environ.get("GALAXY_SLOTS", 1))


def main(inputs_path, output_obj, base_paths=None, meta_path=None):
    """
    Parameter
    ---------
    inputs_path : str
        File path for Galaxy parameters

    base_paths : str
        File path or paths concatenated by comma.

    meta_path : str
        File path
    """
    with open(inputs_path, "r") as param_handler:
        params = json.load(param_handler)

    estimator_type = params["algo_selection"]["estimator_type"]
    # get base estimators
    base_estimators = []
    for idx, base_file in enumerate(base_paths.split(",")):
        if base_file and base_file != "None":
            model = load_model_from_h5(base_file)
        else:
            estimator_json = params["base_est_builder"][idx]["estimator_selector"]
            model = get_estimator(estimator_json)

        if estimator_type.startswith("sklearn"):

            base_estimators.append(model)

    # get meta estimator, if applicable
    if estimator_type.startswith("mlxtend"):
        if meta_path:
            meta_estimator = load_model_from_h5(meta_path)
        else:
            estimator_json = params["algo_selection"]["meta_estimator"][
                "estimator_selector"
            ]
            meta_estimator = get_estimator(estimator_json)

    options = params["algo_selection"]["options"]

    cv_selector = options.pop("cv_selector", None)
    if 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
        # set n_jobs
        options["n_jobs"] = N_JOBS

    weights = options.pop("weights", None)

    print(ensemble_estimator)
    for base_est in base_estimators:
        print(base_est)

    dump_model_to_h5(ensemble_estimator, output_obj)


if __name__ == "__main__":
    aparser = argparse.ArgumentParser()
    aparser.add_argument("-b", "--bases", dest="bases")
    aparser.add_argument("-m", "--meta", dest="meta")
    aparser.add_argument("-i", "--inputs", dest="inputs")
    aparser.add_argument("-o", "--outfile", dest="outfile")
    args = aparser.parse_args()

    main(args.inputs, args.outfile, base_paths=args.bases, meta_path=args.meta)