comparison simple_model_fit.py @ 21:14fa42b095c4 draft

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

20:a5665e1b06b0

import pandas as pd
from galaxy_ml.utils import load_model, read_columns
from scipy.io import mmread
from sklearn.pipeline import Pipeline


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


# TODO import from galaxy_ml.utils in future versions

    for name, p in estimator_params.items():
        # all potential unauthorized file write
        if name == "memory" or name.endswith("__memory") or name.endswith("_path"):
            new_p = {name: None}
            estimator.set_params(**new_p)
        elif n_jobs is not None and (name == 'n_jobs' or name.endswith('__n_jobs')):
            new_p = {name: n_jobs}
            estimator.set_params(**new_p)
        elif name.endswith("callbacks"):
            for cb in p:
                cb_type = cb["callback_selection"]["callback_type"]

    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",

    elif input_type == "sparse":
        X = mmread(open(infile1, "r"))

    # 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()

    return X, y

21:14fa42b095c4

import pandas as pd
from galaxy_ml.utils import load_model, read_columns
from scipy.io import mmread
from sklearn.pipeline import Pipeline

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


# TODO import from galaxy_ml.utils in future versions

    for name, p in estimator_params.items():
        # all potential unauthorized file write
        if name == "memory" or name.endswith("__memory") or name.endswith("_path"):
            new_p = {name: None}
            estimator.set_params(**new_p)
        elif n_jobs is not None and (name == "n_jobs" or name.endswith("__n_jobs")):
            new_p = {name: n_jobs}
            estimator.set_params(**new_p)
        elif name.endswith("callbacks"):
            for cb in p:
                cb_type = cb["callback_selection"]["callback_type"]

    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",

    elif input_type == "sparse":
        X = mmread(open(infile1, "r"))

    # 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()

    return X, y