Coverage for biobb_ml/clustering/clustering_predict.py: 74%
90 statements
« prev ^ index » next coverage.py v7.5.1, created at 2024-05-07 09:39 +0000
« 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 ClusteringPredict 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.cluster import KMeans
10from biobb_common.configuration import settings
11from biobb_common.tools import file_utils as fu
12from biobb_common.tools.file_utils import launchlogger
13from biobb_ml.clustering.common import check_input_path, check_output_path, getHeader, get_list_of_predictors, get_keys_of_predictors
16class ClusteringPredict(BiobbObject):
17 """
18 | biobb_ml ClusteringPredict
19 | Makes predictions from an input dataset and a given clustering model.
20 | Makes predictions from an input dataset (provided either as a file or as a dictionary property) and a given clustering model fitted with `KMeans <https://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html>`_ method.
22 Args:
23 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/clustering/model_clustering_predict.pkl>`_. Accepted formats: pkl (edam:format_3653).
24 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/clustering/input_clustering_predict.csv>`_. Accepted formats: csv (edam:format_3752).
25 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/clustering/ref_output_results_clustering_predict.csv>`_. Accepted formats: csv (edam:format_3752).
26 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
27 * **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.
28 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
29 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
31 Examples:
32 This is a use example of how to use the building block from Python::
34 from biobb_ml.clustering.clustering_predict import clustering_predict
35 prop = {
36 'predictions': [
37 {
38 'var1': 1.0,
39 'var2': 2.0
40 },
41 {
42 'var1': 4.0,
43 'var2': 2.7
44 }
45 ]
46 }
47 clustering_predict(input_model_path='/path/to/myModel.pkl',
48 output_results_path='/path/to/newPredictedResults.csv',
49 input_dataset_path='/path/to/myDataset.csv',
50 properties=prop)
52 Info:
53 * wrapped_software:
54 * name: scikit-learn
55 * version: >=0.24.2
56 * license: BSD 3-Clause
57 * ontology:
58 * name: EDAM
59 * schema: http://edamontology.org/EDAM.owl
61 """
63 def __init__(self, input_model_path, output_results_path,
64 input_dataset_path=None, properties=None, **kwargs) -> None:
65 properties = properties or {}
67 # Call parent class constructor
68 super().__init__(properties)
69 self.locals_var_dict = locals().copy()
71 # Input/Output files
72 self.io_dict = {
73 "in": {"input_model_path": input_model_path, "input_dataset_path": input_dataset_path},
74 "out": {"output_results_path": output_results_path}
75 }
77 # Properties specific for BB
78 self.predictions = properties.get('predictions', [])
79 self.properties = properties
81 # Check the properties
82 self.check_properties(properties)
83 self.check_arguments()
85 def check_data_params(self, out_log, err_log):
86 """ Checks all the input/output paths and parameters """
87 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__)
88 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__)
89 if self.io_dict["in"]["input_dataset_path"]:
90 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__)
92 @launchlogger
93 def launch(self) -> int:
94 """Execute the :class:`ClusteringPredict <clustering.clustering_predict.ClusteringPredict>` clustering.clustering_predict.ClusteringPredict object."""
96 # check input/output paths and parameters
97 self.check_data_params(self.out_log, self.err_log)
99 # Setup Biobb
100 if self.check_restart():
101 return 0
102 self.stage_files()
104 fu.log('Getting model from %s' % self.io_dict["in"]["input_model_path"], self.out_log, self.global_log)
106 with open(self.io_dict["in"]["input_model_path"], "rb") as f:
107 while True:
108 try:
109 m = joblib.load(f)
110 if (isinstance(m, KMeans)):
111 new_model = m
112 if isinstance(m, StandardScaler):
113 scaler = m
114 if isinstance(m, dict):
115 variables = m
116 except EOFError:
117 break
119 if self.io_dict["in"]["input_dataset_path"]:
120 # load dataset from input_dataset_path file
121 fu.log('Getting dataset from %s' % self.io_dict["in"]["input_dataset_path"], self.out_log, self.global_log)
122 if 'columns' in variables['predictors']:
123 labels = getHeader(self.io_dict["in"]["input_dataset_path"])
124 skiprows = 1
125 else:
126 labels = None
127 skiprows = None
128 new_data_table = pd.read_csv(self.io_dict["in"]["input_dataset_path"], header=None, sep="\\s+|;|:|,|\t", engine="python", skiprows=skiprows, names=labels)
129 else:
130 # load dataset from properties
131 if 'columns' in variables['predictors']:
132 # sorting self.properties in the correct order given by variables['predictors']['columns']
133 index_map = {v: i for i, v in enumerate(variables['predictors']['columns'])}
134 predictions = []
135 for i, pred in enumerate(self.predictions):
136 sorted_pred = sorted(pred.items(), key=lambda pair: index_map[pair[0]])
137 predictions.append(dict(sorted_pred))
138 new_data_table = pd.DataFrame(data=get_list_of_predictors(predictions), columns=get_keys_of_predictors(predictions))
139 else:
140 predictions = self.predictions
141 new_data_table = pd.DataFrame(data=predictions)
143 if variables['scale']:
144 fu.log('Scaling dataset', self.out_log, self.global_log)
145 new_data = scaler.transform(new_data_table)
146 else:
147 new_data = new_data_table
149 p = new_model.predict(new_data)
151 new_data_table['cluster'] = p
152 fu.log('Predicting results\n\nPREDICTION RESULTS\n\n%s\n' % new_data_table, self.out_log, self.global_log)
153 fu.log('Saving results to %s' % self.io_dict["out"]["output_results_path"], self.out_log, self.global_log)
154 new_data_table.to_csv(self.io_dict["out"]["output_results_path"], index=False, header=True, float_format='%.3f')
156 # Copy files to host
157 self.copy_to_host()
159 self.tmp_files.extend([
160 self.stage_io_dict.get("unique_dir")
161 ])
162 self.remove_tmp_files()
164 self.check_arguments(output_files_created=True, raise_exception=False)
166 return 0
169def clustering_predict(input_model_path: str, output_results_path: str, input_dataset_path: str = None, properties: dict = None, **kwargs) -> int:
170 """Execute the :class:`ClusteringPredict <clustering.clustering_predict.ClusteringPredict>` class and
171 execute the :meth:`launch() <clustering.clustering_predict.ClusteringPredict.launch>` method."""
173 return ClusteringPredict(input_model_path=input_model_path,
174 output_results_path=output_results_path,
175 input_dataset_path=input_dataset_path,
176 properties=properties, **kwargs).launch()
179def main():
180 """Command line execution of this building block. Please check the command line documentation."""
181 parser = argparse.ArgumentParser(description="Makes predictions from an input dataset and a given clustering model.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
182 parser.add_argument('--config', required=False, help='Configuration file')
184 # Specific args of each building block
185 required_args = parser.add_argument_group('required arguments')
186 required_args.add_argument('--input_model_path', required=True, help='Path to the input model. Accepted formats: pkl.')
187 required_args.add_argument('--output_results_path', required=True, help='Path to the output results file. Accepted formats: csv.')
188 parser.add_argument('--input_dataset_path', required=False, help='Path to the dataset to predict. Accepted formats: csv.')
190 args = parser.parse_args()
191 args.config = args.config or "{}"
192 properties = settings.ConfReader(config=args.config).get_prop_dic()
194 # Specific call of each building block
195 clustering_predict(input_model_path=args.input_model_path,
196 output_results_path=args.output_results_path,
197 input_dataset_path=args.input_dataset_path,
198 properties=properties)
201if __name__ == '__main__':
202 main()