Mercurial > repos > bgruening > sklearn_nn_classifier

comparison nn_classifier.xml @ 6:e972a913e61a 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 8cf3d813ec755166ee0bd517b4ecbbd4f84d4df1
author bgruening
date Thu, 23 Aug 2018 16:15:30 -0400
parents 753ebd417b17
children 5072ac474cd5
comparison
equal deleted inserted replaced
5:753ebd417b17 6:e972a913e61a
17 import sys 17 import sys
18 import json 18 import json
19 import numpy as np 19 import numpy as np
20 import sklearn.neighbors 20 import sklearn.neighbors
21 import pandas 21 import pandas
22 import pickle
23 22
24 execfile("$__tool_directory__/utils.py") 23 execfile("$__tool_directory__/sk_whitelist.py")
24 execfile("$__tool_directory__/utils.py", globals())
25 25
26 input_json_path = sys.argv[1] 26 input_json_path = sys.argv[1]
27 with open(input_json_path, "r") as param_handler: 27 with open(input_json_path, "r") as param_handler:
28 params = json.load(param_handler) 28 params = json.load(param_handler)
29 29
30 #if $selected_tasks.selected_task == "load": 30 #if $selected_tasks.selected_task == "load":
31 31
32 with open("$infile_model", 'rb') as model_handler: 32 with open("$infile_model", 'rb') as model_handler:
33 classifier_object = pickle.load(model_handler) 33 classifier_object = SafePickler.load(model_handler)
34 34
35 header = 'infer' if params["selected_tasks"]["header"] else None 35 header = 'infer' if params["selected_tasks"]["header"] else None
36 data = pandas.read_csv("$selected_tasks.infile_data", sep='\t', header=header, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False) 36 data = pandas.read_csv("$selected_tasks.infile_data", sep='\t', header=header, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False)
37 prediction = classifier_object.predict(data) 37 prediction = classifier_object.predict(data)
38 prediction_df = pandas.DataFrame(prediction) 38 prediction_df = pandas.DataFrame(prediction)