Mercurial > repos > bgruening > sklearn_label_encoder
comparison fitted_model_eval.py @ 0:3b6ee54eb7e2 draft
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit ea12f973df4b97a2691d9e4ce6bf6fae59d57717"
author | bgruening |
---|---|
date | Sat, 01 May 2021 00:57:35 +0000 |
parents | |
children | 108141350edb |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:3b6ee54eb7e2 |
---|---|
1 import argparse | |
2 import json | |
3 import warnings | |
4 | |
5 import pandas as pd | |
6 from galaxy_ml.utils import get_scoring, load_model, read_columns | |
7 from scipy.io import mmread | |
8 from sklearn.metrics.scorer import _check_multimetric_scoring | |
9 from sklearn.model_selection._validation import _score | |
10 from sklearn.pipeline import Pipeline | |
11 | |
12 | |
13 def _get_X_y(params, infile1, infile2): | |
14 """read from inputs and output X and y | |
15 | |
16 Parameters | |
17 ---------- | |
18 params : dict | |
19 Tool inputs parameter | |
20 infile1 : str | |
21 File path to dataset containing features | |
22 infile2 : str | |
23 File path to dataset containing target values | |
24 | |
25 """ | |
26 # store read dataframe object | |
27 loaded_df = {} | |
28 | |
29 input_type = params["input_options"]["selected_input"] | |
30 # tabular input | |
31 if input_type == "tabular": | |
32 header = "infer" if params["input_options"]["header1"] else None | |
33 column_option = params["input_options"]["column_selector_options_1"][ | |
34 "selected_column_selector_option" | |
35 ] | |
36 if column_option in [ | |
37 "by_index_number", | |
38 "all_but_by_index_number", | |
39 "by_header_name", | |
40 "all_but_by_header_name", | |
41 ]: | |
42 c = params["input_options"]["column_selector_options_1"]["col1"] | |
43 else: | |
44 c = None | |
45 | |
46 df_key = infile1 + repr(header) | |
47 df = pd.read_csv(infile1, sep="\t", header=header, parse_dates=True) | |
48 loaded_df[df_key] = df | |
49 | |
50 X = read_columns(df, c=c, c_option=column_option).astype(float) | |
51 # sparse input | |
52 elif input_type == "sparse": | |
53 X = mmread(open(infile1, "r")) | |
54 | |
55 # Get target y | |
56 header = "infer" if params["input_options"]["header2"] else None | |
57 column_option = params["input_options"]["column_selector_options_2"][ | |
58 "selected_column_selector_option2" | |
59 ] | |
60 if column_option in [ | |
61 "by_index_number", | |
62 "all_but_by_index_number", | |
63 "by_header_name", | |
64 "all_but_by_header_name", | |
65 ]: | |
66 c = params["input_options"]["column_selector_options_2"]["col2"] | |
67 else: | |
68 c = None | |
69 | |
70 df_key = infile2 + repr(header) | |
71 if df_key in loaded_df: | |
72 infile2 = loaded_df[df_key] | |
73 else: | |
74 infile2 = pd.read_csv(infile2, sep="\t", header=header, parse_dates=True) | |
75 loaded_df[df_key] = infile2 | |
76 | |
77 y = read_columns( | |
78 infile2, c=c, c_option=column_option, sep="\t", header=header, parse_dates=True | |
79 ) | |
80 if len(y.shape) == 2 and y.shape[1] == 1: | |
81 y = y.ravel() | |
82 | |
83 return X, y | |
84 | |
85 | |
86 def main( | |
87 inputs, | |
88 infile_estimator, | |
89 outfile_eval, | |
90 infile_weights=None, | |
91 infile1=None, | |
92 infile2=None, | |
93 ): | |
94 """ | |
95 Parameter | |
96 --------- | |
97 inputs : str | |
98 File path to galaxy tool parameter | |
99 | |
100 infile_estimator : strgit | |
101 File path to trained estimator input | |
102 | |
103 outfile_eval : str | |
104 File path to save the evalulation results, tabular | |
105 | |
106 infile_weights : str | |
107 File path to weights input | |
108 | |
109 infile1 : str | |
110 File path to dataset containing features | |
111 | |
112 infile2 : str | |
113 File path to dataset containing target values | |
114 """ | |
115 warnings.filterwarnings("ignore") | |
116 | |
117 with open(inputs, "r") as param_handler: | |
118 params = json.load(param_handler) | |
119 | |
120 X_test, y_test = _get_X_y(params, infile1, infile2) | |
121 | |
122 # load model | |
123 with open(infile_estimator, "rb") as est_handler: | |
124 estimator = load_model(est_handler) | |
125 | |
126 main_est = estimator | |
127 if isinstance(estimator, Pipeline): | |
128 main_est = estimator.steps[-1][-1] | |
129 if hasattr(main_est, "config") and hasattr(main_est, "load_weights"): | |
130 if not infile_weights or infile_weights == "None": | |
131 raise ValueError( | |
132 "The selected model skeleton asks for weights, " | |
133 "but no dataset for weights was provided!" | |
134 ) | |
135 main_est.load_weights(infile_weights) | |
136 | |
137 # handle scorer, convert to scorer dict | |
138 # Check if scoring is specified | |
139 scoring = params["scoring"] | |
140 if scoring is not None: | |
141 # get_scoring() expects secondary_scoring to be a comma separated string (not a list) | |
142 # Check if secondary_scoring is specified | |
143 secondary_scoring = scoring.get("secondary_scoring", None) | |
144 if secondary_scoring is not None: | |
145 # If secondary_scoring is specified, convert the list into comman separated string | |
146 scoring["secondary_scoring"] = ",".join(scoring["secondary_scoring"]) | |
147 | |
148 scorer = get_scoring(scoring) | |
149 scorer, _ = _check_multimetric_scoring(estimator, scoring=scorer) | |
150 | |
151 if hasattr(estimator, "evaluate"): | |
152 scores = estimator.evaluate( | |
153 X_test, y_test=y_test, scorer=scorer, is_multimetric=True | |
154 ) | |
155 else: | |
156 scores = _score(estimator, X_test, y_test, scorer, is_multimetric=True) | |
157 | |
158 # handle output | |
159 for name, score in scores.items(): | |
160 scores[name] = [score] | |
161 df = pd.DataFrame(scores) | |
162 df = df[sorted(df.columns)] | |
163 df.to_csv(path_or_buf=outfile_eval, sep="\t", header=True, index=False) | |
164 | |
165 | |
166 if __name__ == "__main__": | |
167 aparser = argparse.ArgumentParser() | |
168 aparser.add_argument("-i", "--inputs", dest="inputs", required=True) | |
169 aparser.add_argument("-e", "--infile_estimator", dest="infile_estimator") | |
170 aparser.add_argument("-w", "--infile_weights", dest="infile_weights") | |
171 aparser.add_argument("-X", "--infile1", dest="infile1") | |
172 aparser.add_argument("-y", "--infile2", dest="infile2") | |
173 aparser.add_argument("-O", "--outfile_eval", dest="outfile_eval") | |
174 args = aparser.parse_args() | |
175 | |
176 main( | |
177 args.inputs, | |
178 args.infile_estimator, | |
179 args.outfile_eval, | |
180 infile_weights=args.infile_weights, | |
181 infile1=args.infile1, | |
182 infile2=args.infile2, | |
183 ) |