Mercurial > repos > bgruening > sklearn_ensemble
diff ensemble.xml @ 15:f02eeabab5d1 draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit f54ff2ba2f8e7542d68966ce5a6b17d7f624ac48
author | bgruening |
---|---|
date | Fri, 13 Jul 2018 03:55:19 -0400 |
parents | 84724d805bfa |
children | 4570575d060c |
line wrap: on
line diff
--- a/ensemble.xml Tue Jul 10 03:11:34 2018 -0400 +++ b/ensemble.xml Fri Jul 13 03:55:19 2018 -0400 @@ -27,8 +27,9 @@ # Get inputs, outputs. input_json_path = sys.argv[1] -params = json.load(open(input_json_path, "r")) -print params +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": @@ -63,14 +64,16 @@ 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) + with open(outfile_fit, 'wb') as out_handler: + pickle.dump(estimator, out_handler, pickle.HIGHEST_PROTOCOL) else: - classifier_object = pickle.load(open(infile_model, 'r')) + 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)