comparison keras_train_and_eval.py @ 37:e76f6dfea5c9 draft

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

36:420a4bf99244

import numpy as np
import pandas as pd
from galaxy_ml.externals.selene_sdk.utils import compute_score
from galaxy_ml.keras_galaxy_models import _predict_generator
from galaxy_ml.model_validations import train_test_split
from galaxy_ml.utils import (
    clean_params,
    get_main_estimator,
    get_module,
    get_scoring,
    load_model,
    read_columns,
    SafeEval,
    try_get_attr,
)
from scipy.io import mmread
from sklearn.metrics.scorer import _check_multimetric_scoring
from sklearn.model_selection import _search, _validation
from sklearn.model_selection._validation import _score
from sklearn.pipeline import Pipeline
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)

        if swap_value == "":
            continue

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

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

        groups = kwargs["labels"]
        n_samples = new_arrays[0].shape[0]
        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)

    for pos in nones:
        rval[pos * 2: 2] = [None, None]

    if y_true.ndim == 1 or y_true.shape[-1] == 1:
        pred_probas = pred_probas.ravel()
        pred_labels = (pred_probas > 0.5).astype("int32")
        targets = y_true.ravel().astype("int32")
        if not is_multimetric:
            preds = pred_labels if scorer.__class__.__name__ == "_PredictScorer" else pred_probas
            score = scorer._score_func(targets, preds, **scorer._kwargs)

            return score
        else:
            scores = {}
            for name, one_scorer in scorer.items():
                preds = pred_labels if one_scorer.__class__.__name__ == "_PredictScorer" else pred_probas
                score = one_scorer._score_func(targets, preds, **one_scorer._kwargs)
                scores[name] = score

    # TODO: multi-class metrics
    # multi-label
    else:
        pred_labels = (pred_probas > 0.5).astype("int32")
        targets = y_true.astype("int32")
        if not is_multimetric:
            preds = pred_labels if scorer.__class__.__name__ == "_PredictScorer" else pred_probas
            score, _ = compute_score(preds, targets, scorer._score_func)
            return score
        else:
            scores = {}
            for name, one_scorer in scorer.items():
                preds = pred_labels if one_scorer.__class__.__name__ == "_PredictScorer" else pred_probas
                score, _ = compute_score(preds, targets, one_scorer._score_func)
                scores[name] = score

    return scores

    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
    # end y

    # load groups
    if groups:
        groups_selector = (params["experiment_schemes"]["test_split"]["split_algos"]).pop("groups_selector")

        header = "infer" if groups_selector["header_g"] else None
        column_option = 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",

        df_key = groups + repr(header)
        if df_key in loaded_df:
            groups = loaded_df[df_key]

        groups = read_columns(groups,
                              c=c,
                              c_option=column_option,
                              sep='\t',
                              header=header,
                              parse_dates=True)
        groups = groups.ravel()

    # del loaded_df
    del loaded_df

    main_est = get_main_estimator(estimator)
    if main_est.__class__.__name__ == "IRAPSClassifier":
        main_est.set_params(memory=memory)

    # handle scorer, convert to scorer dict
    scoring = params['experiment_schemes']['metrics']['scoring']
    if scoring is not None:
        # get_scoring() expects secondary_scoring to be a comma separated string (not a list)
        # Check if secondary_scoring is specified
        secondary_scoring = scoring.get("secondary_scoring", None)
        if secondary_scoring is not None:

        test_split_options["labels"] = groups
    if test_split_options["shuffle"] == "stratified":
        if y is not None:
            test_split_options["labels"] = y
        else:
            raise ValueError("Stratified shuffle split is not " "applicable on empty target values!")

    (
        X_train,
        X_test,
        y_train,

            val_split_options["labels"] = groups_train
        if val_split_options["shuffle"] == "stratified":
            if y_train is not None:
                val_split_options["labels"] = y_train
            else:
                raise ValueError("Stratified shuffle split is not " "applicable on empty target values!")

        (
            X_train,
            X_val,
            y_train,

        estimator.fit(X_train, y_train)

    if hasattr(estimator, "evaluate"):
        steps = estimator.prediction_steps
        batch_size = estimator.batch_size
        generator = estimator.data_generator_.flow(X_test, y=y_test, batch_size=batch_size)
        predictions, y_true = _predict_generator(estimator.model_, generator, steps=steps)
        scores = _evaluate(y_true, predictions, scorer, is_multimetric=True)

    else:
        if hasattr(estimator, "predict_proba"):
            predictions = estimator.predict_proba(X_test)

37:e76f6dfea5c9

import numpy as np
import pandas as pd
from galaxy_ml.externals.selene_sdk.utils import compute_score
from galaxy_ml.keras_galaxy_models import _predict_generator
from galaxy_ml.model_validations import train_test_split
from galaxy_ml.utils import (clean_params, get_main_estimator,
                             get_module, get_scoring, load_model, read_columns,
                             SafeEval, try_get_attr)
from scipy.io import mmread
from sklearn.metrics.scorer import _check_multimetric_scoring
from sklearn.model_selection import _search, _validation
from sklearn.model_selection._validation import _score
from sklearn.pipeline import Pipeline
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)

        if swap_value == "":
            continue

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

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

        groups = kwargs["labels"]
        n_samples = new_arrays[0].shape[0]
        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)

    for pos in nones:
        rval[pos * 2: 2] = [None, None]

    if y_true.ndim == 1 or y_true.shape[-1] == 1:
        pred_probas = pred_probas.ravel()
        pred_labels = (pred_probas > 0.5).astype("int32")
        targets = y_true.ravel().astype("int32")
        if not is_multimetric:
            preds = (
                pred_labels
                if scorer.__class__.__name__ == "_PredictScorer"
                else pred_probas
            )
            score = scorer._score_func(targets, preds, **scorer._kwargs)

            return score
        else:
            scores = {}
            for name, one_scorer in scorer.items():
                preds = (
                    pred_labels
                    if one_scorer.__class__.__name__ == "_PredictScorer"
                    else pred_probas
                )
                score = one_scorer._score_func(targets, preds, **one_scorer._kwargs)
                scores[name] = score

    # TODO: multi-class metrics
    # multi-label
    else:
        pred_labels = (pred_probas > 0.5).astype("int32")
        targets = y_true.astype("int32")
        if not is_multimetric:
            preds = (
                pred_labels
                if scorer.__class__.__name__ == "_PredictScorer"
                else pred_probas
            )
            score, _ = compute_score(preds, targets, scorer._score_func)
            return score
        else:
            scores = {}
            for name, one_scorer in scorer.items():
                preds = (
                    pred_labels
                    if one_scorer.__class__.__name__ == "_PredictScorer"
                    else pred_probas
                )
                score, _ = compute_score(preds, targets, one_scorer._score_func)
                scores[name] = score

    return scores

    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
    # end y

    # load groups
    if groups:
        groups_selector = (
            params["experiment_schemes"]["test_split"]["split_algos"]
        ).pop("groups_selector")

        header = "infer" if groups_selector["header_g"] else None
        column_option = 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",

        df_key = groups + repr(header)
        if df_key in loaded_df:
            groups = loaded_df[df_key]

        groups = read_columns(
            groups,
            c=c,
            c_option=column_option,
            sep="\t",
            header=header,
            parse_dates=True,
        )
        groups = groups.ravel()

    # del loaded_df
    del loaded_df

    main_est = get_main_estimator(estimator)
    if main_est.__class__.__name__ == "IRAPSClassifier":
        main_est.set_params(memory=memory)

    # handle scorer, convert to scorer dict
    scoring = params["experiment_schemes"]["metrics"]["scoring"]
    if scoring is not None:
        # get_scoring() expects secondary_scoring to be a comma separated string (not a list)
        # Check if secondary_scoring is specified
        secondary_scoring = scoring.get("secondary_scoring", None)
        if secondary_scoring is not None:

        test_split_options["labels"] = groups
    if test_split_options["shuffle"] == "stratified":
        if y is not None:
            test_split_options["labels"] = y
        else:
            raise ValueError(
                "Stratified shuffle split is not " "applicable on empty target values!"
            )

    (
        X_train,
        X_test,
        y_train,

            val_split_options["labels"] = groups_train
        if val_split_options["shuffle"] == "stratified":
            if y_train is not None:
                val_split_options["labels"] = y_train
            else:
                raise ValueError(
                    "Stratified shuffle split is not "
                    "applicable on empty target values!"
                )

        (
            X_train,
            X_val,
            y_train,

        estimator.fit(X_train, y_train)

    if hasattr(estimator, "evaluate"):
        steps = estimator.prediction_steps
        batch_size = estimator.batch_size
        generator = estimator.data_generator_.flow(
            X_test, y=y_test, batch_size=batch_size
        )
        predictions, y_true = _predict_generator(
            estimator.model_, generator, steps=steps
        )
        scores = _evaluate(y_true, predictions, scorer, is_multimetric=True)

    else:
        if hasattr(estimator, "predict_proba"):
            predictions = estimator.predict_proba(X_test)