comparison ensemble.xml @ 15:f02eeabab5d1 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit f54ff2ba2f8e7542d68966ce5a6b17d7f624ac48

14:84724d805bfa

@COLUMNS_FUNCTION@
@GET_X_y_FUNCTION@

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

# Put all cheetah up here to avoid confusion.
#if $selected_tasks.selected_task == "train":
infile1 = "$selected_tasks.selected_algorithms.input_options.infile1"
infile2 = "$selected_tasks.selected_algorithms.input_options.infile2"

        options["min_samples_leaf"] = 1
    if "min_samples_split" in options and options["min_samples_split"] > 1.0:
        options["min_samples_split"] = int(options["min_samples_split"])

    X, y = get_X_y(params, infile1, infile2)
                   
    my_class = getattr(sklearn.ensemble, algorithm)
    estimator = my_class(**options)
    estimator.fit(X,y)
    pickle.dump(estimator,open(outfile_fit, 'w+'), pickle.HIGHEST_PROTOCOL)

else:
    classifier_object = pickle.load(open(infile_model, 'r'))
    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)

15:f02eeabab5d1

@COLUMNS_FUNCTION@
@GET_X_y_FUNCTION@

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

# Put all cheetah up here to avoid confusion.
#if $selected_tasks.selected_task == "train":
infile1 = "$selected_tasks.selected_algorithms.input_options.infile1"
infile2 = "$selected_tasks.selected_algorithms.input_options.infile2"

        options["min_samples_leaf"] = 1
    if "min_samples_split" in options and options["min_samples_split"] > 1.0:
        options["min_samples_split"] = int(options["min_samples_split"])

    X, y = get_X_y(params, infile1, infile2)

    my_class = getattr(sklearn.ensemble, algorithm)
    estimator = my_class(**options)
    estimator.fit(X,y)
    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 = pickle.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)