comparison train_test_split.py @ 41:d769d83ec796 draft

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

40:4335cec181ba

import argparse
import json
import warnings

import pandas as pd
from galaxy_ml.model_validations import train_test_split
from galaxy_ml.utils import get_cv, read_columns


def _get_single_cv_split(params, array, infile_labels=None, infile_groups=None):

        col_index = target_input["col"][0] - 1
        df = pd.read_csv(infile_labels, sep="\t", header=header, parse_dates=True)
        y = df.iloc[:, col_index].values

    # construct the cv splitter object
    splitter, groups = get_cv(params["mode_selection"]["cv_selector"])

    total_n_splits = splitter.get_n_splits(array.values, y=y, groups=groups)
    if nth_split > total_n_splits:
        raise ValueError(
            "Total number of splits is {}, but got `nth_split` "

41:d769d83ec796

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

import pandas as pd
from galaxy_ml import __version__ as galaxy_ml_version
from galaxy_ml.model_validations import train_test_split
from galaxy_ml.utils import get_cv, read_columns


def _get_single_cv_split(params, array, infile_labels=None, infile_groups=None):

        col_index = target_input["col"][0] - 1
        df = pd.read_csv(infile_labels, sep="\t", header=header, parse_dates=True)
        y = df.iloc[:, col_index].values

    # construct the cv splitter object
    cv_selector = params["mode_selection"]["cv_selector"]
    if Version(galaxy_ml_version) < Version("0.8.3"):
        cv_selector.pop("n_stratification_bins", None)
    splitter, groups = get_cv(cv_selector)

    total_n_splits = splitter.get_n_splits(array.values, y=y, groups=groups)
    if nth_split > total_n_splits:
        raise ValueError(
            "Total number of splits is {}, but got `nth_split` "