Mercurial > repos > bgruening > sklearn_ensemble

comparison ensemble.xml @ 21:9ce3e347506c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 2a058459e6daf0486871f93845f00fdb4a4eaca1
author bgruening
date Sat, 29 Sep 2018 07:30:08 -0400
parents 038cecaa9e7c
children 2e69c6ca6e91
comparison
equal deleted inserted replaced
20:038cecaa9e7c 21:9ce3e347506c
20 import numpy as np 20 import numpy as np
21 import sklearn.ensemble 21 import sklearn.ensemble
22 import pandas 22 import pandas
23 from scipy.io import mmread 23 from scipy.io import mmread
24 24
25 execfile("$__tool_directory__/sk_whitelist.py") 25 with open("$__tool_directory__/sk_whitelist.json", "r") as f:
26 execfile("$__tool_directory__/utils.py", globals()) 26 sk_whitelist = json.load(f)
27 exec(open("$__tool_directory__/utils.py").read(), globals())
27 28
28 # Get inputs, outputs. 29 # Get inputs, outputs.
29 input_json_path = sys.argv[1] 30 input_json_path = sys.argv[1]
30 with open(input_json_path, "r") as param_handler: 31 with open(input_json_path, "r") as param_handler:
31 params = json.load(param_handler) 32 params = json.load(param_handler)
73 with open(outfile_fit, 'wb') as out_handler: 74 with open(outfile_fit, 'wb') as out_handler:
74 pickle.dump(estimator, out_handler, pickle.HIGHEST_PROTOCOL) 75 pickle.dump(estimator, out_handler, pickle.HIGHEST_PROTOCOL)
75 76
76 else: 77 else:
77 with open(infile_model, 'rb') as model_handler: 78 with open(infile_model, 'rb') as model_handler:
78 classifier_object = SafePickler.load(model_handler) 79 classifier_object = load_model(model_handler)
79 header = 'infer' if params["selected_tasks"]["header"] else None 80 header = 'infer' if params["selected_tasks"]["header"] else None
80 data = pandas.read_csv(infile_data, sep='\t', header=header, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False) 81 data = pandas.read_csv(infile_data, sep='\t', header=header, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False)
81 prediction = classifier_object.predict(data) 82 prediction = classifier_object.predict(data)
82 prediction_df = pandas.DataFrame(prediction, columns=["predicted"]) 83 prediction_df = pandas.DataFrame(prediction, columns=["predicted"])
83 res = pandas.concat([data, prediction_df], axis=1) 84 res = pandas.concat([data, prediction_df], axis=1)
263 <param name="header2" value="True"/> 264 <param name="header2" value="True"/>
264 <param name="col2" value="1"/> 265 <param name="col2" value="1"/>
265 <param name="selected_task" value="train"/> 266 <param name="selected_task" value="train"/>
266 <param name="selected_algorithm" value="GradientBoostingRegressor"/> 267 <param name="selected_algorithm" value="GradientBoostingRegressor"/>
267 <param name="max_features" value="number_input"/> 268 <param name="max_features" value="number_input"/>
268 <param name="num_max_features" value=""/> 269 <param name="num_max_features" value="0.5"/>
269 <param name="random_state" value="42"/> 270 <param name="random_state" value="42"/>
270 <output name="outfile_fit" file="gbr_model01" compare="sim_size" delta="500"/> 271 <output name="outfile_fit" file="gbr_model01" compare="sim_size" delta="500"/>
271 </test> 272 </test>
272 <test> 273 <test>
273 <param name="infile_model" value="gbr_model01" ftype="zip"/> 274 <param name="infile_model" value="gbr_model01" ftype="zip"/>