Mercurial > repos > bgruening > sklearn_ensemble
diff ensemble.xml @ 13:6352834b1c99 draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 5d71c93a3dd804b1469852240a86021ab9130364
author | bgruening |
---|---|
date | Mon, 09 Jul 2018 14:32:15 -0400 |
parents | a78f96f64939 |
children | 84724d805bfa |
line wrap: on
line diff
--- a/ensemble.xml Sun Jul 01 03:19:54 2018 -0400 +++ b/ensemble.xml Mon Jul 09 14:32:15 2018 -0400 @@ -23,6 +23,7 @@ from scipy.io import mmread @COLUMNS_FUNCTION@ +@GET_X_y_FUNCTION@ input_json_path = sys.argv[1] params = json.load(open(input_json_path, "r")) @@ -46,40 +47,8 @@ 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"]) -input_type = params["selected_tasks"]["selected_algorithms"]["input_options"]["selected_input"] -if input_type=="tabular": - header = 'infer' if params["selected_tasks"]["selected_algorithms"]["input_options"]["header1"] else None - column_option = params["selected_tasks"]["selected_algorithms"]["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"]: - c = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_1"]["col1"] - else: - c = None - X = read_columns( - "$selected_tasks.selected_algorithms.input_options.infile1", - c = c, - c_option = column_option, - sep='\t', - header=header, - parse_dates=True - ) -else: - X = mmread(open("$selected_tasks.selected_algorithms.input_options.infile1", 'r')) -header = 'infer' if params["selected_tasks"]["selected_algorithms"]["input_options"]["header2"] else None -column_option = params["selected_tasks"]["selected_algorithms"]["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"]: - c = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_2"]["col2"] -else: - c = None -y = read_columns( - "$selected_tasks.selected_algorithms.input_options.infile2", - c = c, - c_option = column_option, - sep='\t', - header=header, - parse_dates=True -) -y=y.ravel() +X, y = get_X_y(params, "$selected_tasks.selected_algorithms.input_options.infile1" ,"$selected_tasks.selected_algorithms.input_options.infile2") my_class = getattr(sklearn.ensemble, algorithm) estimator = my_class(**options)