comparison ensemble.xml @ 21:9ce3e347506c draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 2a058459e6daf0486871f93845f00fdb4a4eaca1

20:038cecaa9e7c

import numpy as np
import sklearn.ensemble
import pandas
from scipy.io import mmread

execfile("$__tool_directory__/sk_whitelist.py")
execfile("$__tool_directory__/utils.py", globals())

# Get inputs, outputs.
input_json_path = sys.argv[1]
with open(input_json_path, "r") as param_handler:
    params = json.load(param_handler)

    with open(outfile_fit, 'wb') as out_handler:
        pickle.dump(estimator, out_handler, pickle.HIGHEST_PROTOCOL)

else:
    with open(infile_model, 'rb') as model_handler:
        classifier_object = SafePickler.load(model_handler)
    header = 'infer' if params["selected_tasks"]["header"] else None
    data = pandas.read_csv(infile_data, sep='\t', header=header, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False)
    prediction = classifier_object.predict(data)
    prediction_df = pandas.DataFrame(prediction, columns=["predicted"])
    res = pandas.concat([data, prediction_df], axis=1)

            <param name="header2" value="True"/>
            <param name="col2" value="1"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="GradientBoostingRegressor"/>
            <param name="max_features" value="number_input"/>
            <param name="num_max_features" value=""/>
            <param name="random_state" value="42"/>
            <output name="outfile_fit" file="gbr_model01" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile_model" value="gbr_model01" ftype="zip"/>

21:9ce3e347506c

import numpy as np
import sklearn.ensemble
import pandas
from scipy.io import mmread

with open("$__tool_directory__/sk_whitelist.json", "r") as f:
    sk_whitelist = json.load(f)
exec(open("$__tool_directory__/utils.py").read(), globals())

# Get inputs, outputs.
input_json_path = sys.argv[1]
with open(input_json_path, "r") as param_handler:
    params = json.load(param_handler)

    with open(outfile_fit, 'wb') as out_handler:
        pickle.dump(estimator, out_handler, pickle.HIGHEST_PROTOCOL)

else:
    with open(infile_model, 'rb') as model_handler:
        classifier_object = load_model(model_handler)
    header = 'infer' if params["selected_tasks"]["header"] else None
    data = pandas.read_csv(infile_data, sep='\t', header=header, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False)
    prediction = classifier_object.predict(data)
    prediction_df = pandas.DataFrame(prediction, columns=["predicted"])
    res = pandas.concat([data, prediction_df], axis=1)

            <param name="header2" value="True"/>
            <param name="col2" value="1"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="GradientBoostingRegressor"/>
            <param name="max_features" value="number_input"/>
            <param name="num_max_features" value="0.5"/>
            <param name="random_state" value="42"/>
            <output name="outfile_fit" file="gbr_model01" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile_model" value="gbr_model01" ftype="zip"/>