Coverage for biobb_ml/classification/classification_predict.py: 74%
97 statements
« prev ^ index » next coverage.py v7.5.1, created at 2024-05-07 09:39 +0000
1#!/usr/bin/env python3
3"""Module containing the ClassificationPredict class and the command line interface."""
4import argparse
5import pandas as pd
6import joblib
7from biobb_common.generic.biobb_object import BiobbObject
8from sklearn.preprocessing import StandardScaler
9from sklearn import linear_model
10from sklearn.neighbors import KNeighborsClassifier
11from sklearn.tree import DecisionTreeClassifier
12from sklearn import ensemble
13from sklearn import svm
14from biobb_common.configuration import settings
15from biobb_common.tools import file_utils as fu
16from biobb_common.tools.file_utils import launchlogger
17from biobb_ml.classification.common import check_input_path, check_output_path, getHeader, get_list_of_predictors, get_keys_of_predictors
20class ClassificationPredict(BiobbObject):
21 """
22 | biobb_ml ClassificationPredict
23 | Makes predictions from an input dataset and a given classification model.
24 | Makes predictions from an input dataset (provided either as a file or as a dictionary property) and a given classification model trained with `DecisionTreeClassifier <https://scikit-learn.org/stable/modules/generated/sklearn.tree.DecisionTreeClassifier.html>`_, `KNeighborsClassifier <https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html>`_, `LogisticRegression <https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html>`_, `RandomForestClassifier <https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html>`_, `Support Vector Machine <https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html>`_ methods.
26 Args:
27 input_model_path (str): Path to the input model. File type: input. `Sample file <https://github.com/bioexcel/biobb_ml/raw/master/biobb_ml/test/data/classification/model_classification_predict.pkl>`_. Accepted formats: pkl (edam:format_3653).
28 input_dataset_path (str) (Optional): Path to the dataset to predict. File type: input. `Sample file <https://github.com/bioexcel/biobb_ml/raw/master/biobb_ml/test/data/classification/input_classification_predict.csv>`_. Accepted formats: csv (edam:format_3752).
29 output_results_path (str): Path to the output results file. File type: output. `Sample file <https://github.com/bioexcel/biobb_ml/raw/master/biobb_ml/test/reference/classification/ref_output_classification_predict.csv>`_. Accepted formats: csv (edam:format_3752).
30 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
31 * **predictions** (*list*) - (None) List of dictionaries with all values you want to predict targets. It will be taken into account only in case **input_dataset_path** is not provided. Format: [{ 'var1': 1.0, 'var2': 2.0 }, { 'var1': 4.0, 'var2': 2.7 }] for datasets with headers and [[ 1.0, 2.0 ], [ 4.0, 2.7 ]] for datasets without headers.
32 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
33 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
35 Examples:
36 This is a use example of how to use the building block from Python::
38 from biobb_ml.classification.classification_predict import classification_predict
39 prop = {
40 'predictions': [
41 {
42 'var1': 1.0,
43 'var2': 2.0
44 },
45 {
46 'var1': 4.0,
47 'var2': 2.7
48 }
49 ]
50 }
51 classification_predict(input_model_path='/path/to/myModel.pkl',
52 output_results_path='/path/to/newPredictedResults.csv',
53 input_dataset_path='/path/to/myDataset.csv',
54 properties=prop)
56 Info:
57 * wrapped_software:
58 * name: scikit-learn
59 * version: >=0.24.2
60 * license: BSD 3-Clause
61 * ontology:
62 * name: EDAM
63 * schema: http://edamontology.org/EDAM.owl
65 """
67 def __init__(self, input_model_path, output_results_path,
68 input_dataset_path=None, properties=None, **kwargs) -> None:
69 properties = properties or {}
71 # Call parent class constructor
72 super().__init__(properties)
73 self.locals_var_dict = locals().copy()
75 # Input/Output files
76 self.io_dict = {
77 "in": {"input_model_path": input_model_path, "input_dataset_path": input_dataset_path},
78 "out": {"output_results_path": output_results_path}
79 }
81 # Properties specific for BB
82 self.predictions = properties.get('predictions', [])
83 self.properties = properties
85 # Check the properties
86 self.check_properties(properties)
87 self.check_arguments()
89 def check_data_params(self, out_log, err_log):
90 """ Checks all the input/output paths and parameters """
91 self.io_dict["in"]["input_model_path"] = check_input_path(self.io_dict["in"]["input_model_path"], "input_model_path", out_log, self.__class__.__name__)
92 self.io_dict["out"]["output_results_path"] = check_output_path(self.io_dict["out"]["output_results_path"], "output_results_path", False, out_log, self.__class__.__name__)
93 if self.io_dict["in"]["input_dataset_path"]:
94 self.io_dict["in"]["input_dataset_path"] = check_input_path(self.io_dict["in"]["input_dataset_path"], "input_dataset_path", out_log, self.__class__.__name__)
96 @launchlogger
97 def launch(self) -> int:
98 """Execute the :class:`ClassificationPredict <classification.classification_predict.ClassificationPredict>` classification.classification_predict.ClassificationPredict object."""
100 # check input/output paths and parameters
101 self.check_data_params(self.out_log, self.err_log)
103 # Setup Biobb
104 if self.check_restart():
105 return 0
106 self.stage_files()
108 fu.log('Getting model from %s' % self.io_dict["in"]["input_model_path"], self.out_log, self.global_log)
110 with open(self.io_dict["in"]["input_model_path"], "rb") as f:
111 while True:
112 try:
113 m = joblib.load(f)
114 if (isinstance(m, linear_model.LogisticRegression) or isinstance(m, KNeighborsClassifier) or isinstance(m, DecisionTreeClassifier) or isinstance(m, ensemble.RandomForestClassifier) or isinstance(m, svm.SVC)):
115 new_model = m
116 if isinstance(m, StandardScaler):
117 scaler = m
118 if isinstance(m, dict):
119 variables = m
120 except EOFError:
121 break
123 if self.io_dict["in"]["input_dataset_path"]:
124 # load dataset from input_dataset_path file
125 fu.log('Getting dataset from %s' % self.io_dict["in"]["input_dataset_path"], self.out_log, self.global_log)
126 if 'columns' in variables['independent_vars']:
127 labels = getHeader(self.io_dict["in"]["input_dataset_path"])
128 skiprows = 1
129 else:
130 labels = None
131 skiprows = None
132 new_data_table = pd.read_csv(self.io_dict["in"]["input_dataset_path"], header=None, sep="\\s+|;|:|,|\t", engine="python", skiprows=skiprows, names=labels)
133 else:
134 # load dataset from properties
135 if 'columns' in variables['independent_vars']:
136 # sorting self.properties in the correct order given by variables['independent_vars']['columns']
137 index_map = {v: i for i, v in enumerate(variables['independent_vars']['columns'])}
138 predictions = []
139 for i, pred in enumerate(self.predictions):
140 sorted_pred = sorted(pred.items(), key=lambda pair: index_map[pair[0]])
141 predictions.append(dict(sorted_pred))
142 new_data_table = pd.DataFrame(data=get_list_of_predictors(predictions), columns=get_keys_of_predictors(predictions))
143 else:
144 predictions = self.predictions
145 new_data_table = pd.DataFrame(data=predictions)
147 if variables['scale']:
148 fu.log('Scaling dataset', self.out_log, self.global_log)
149 new_data = scaler.transform(new_data_table)
150 else:
151 new_data = new_data_table
153 p = new_model.predict_proba(new_data)
155 # if headers, create target column with proper label
156 if self.io_dict["in"]["input_dataset_path"] or 'columns' in variables['independent_vars']:
157 clss = ' (' + ', '.join(str(x) for x in variables['target_values']) + ')'
158 new_data_table[variables['target']['column'] + ' ' + clss] = tuple(map(tuple, p))
159 else:
160 new_data_table[len(new_data_table.columns)] = tuple(map(tuple, p))
161 fu.log('Predicting results\n\nPREDICTION RESULTS\n\n%s\n' % new_data_table, self.out_log, self.global_log)
162 fu.log('Saving results to %s' % self.io_dict["out"]["output_results_path"], self.out_log, self.global_log)
163 new_data_table.to_csv(self.io_dict["out"]["output_results_path"], index=False, header=True, float_format='%.3f')
165 # Copy files to host
166 self.copy_to_host()
168 self.tmp_files.extend([
169 self.stage_io_dict.get("unique_dir")
170 ])
171 self.remove_tmp_files()
173 self.check_arguments(output_files_created=True, raise_exception=False)
175 return 0
178def classification_predict(input_model_path: str, output_results_path: str, input_dataset_path: str = None, properties: dict = None, **kwargs) -> int:
179 """Execute the :class:`ClassificationPredict <classification.classification_predict.ClassificationPredict>` class and
180 execute the :meth:`launch() <classification.classification_predict.ClassificationPredict.launch>` method."""
182 return ClassificationPredict(input_model_path=input_model_path,
183 output_results_path=output_results_path,
184 input_dataset_path=input_dataset_path,
185 properties=properties, **kwargs).launch()
188def main():
189 """Command line execution of this building block. Please check the command line documentation."""
190 parser = argparse.ArgumentParser(description="Makes predictions from an input dataset and a given classification model.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
191 parser.add_argument('--config', required=False, help='Configuration file')
193 # Specific args of each building block
194 required_args = parser.add_argument_group('required arguments')
195 required_args.add_argument('--input_model_path', required=True, help='Path to the input model. Accepted formats: pkl.')
196 required_args.add_argument('--output_results_path', required=True, help='Path to the output results file. Accepted formats: csv.')
197 parser.add_argument('--input_dataset_path', required=False, help='Path to the dataset to predict. Accepted formats: csv.')
199 args = parser.parse_args()
200 args.config = args.config or "{}"
201 properties = settings.ConfReader(config=args.config).get_prop_dic()
203 # Specific call of each building block
204 classification_predict(input_model_path=args.input_model_path,
205 output_results_path=args.output_results_path,
206 input_dataset_path=args.input_dataset_path,
207 properties=properties)
210if __name__ == '__main__':
211 main()