Coverage for biobb_ml/clustering/clustering_predict.py: 74%
89 statements
« prev ^ index » next coverage.py v7.6.1, created at 2024-10-03 14:57 +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.
30 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory.
32 Examples:
33 This is a use example of how to use the building block from Python::
35 from biobb_ml.clustering.clustering_predict import clustering_predict
36 prop = {
37 'predictions': [
38 {
39 'var1': 1.0,
40 'var2': 2.0
41 },
42 {
43 'var1': 4.0,
44 'var2': 2.7
45 }
46 ]
47 }
48 clustering_predict(input_model_path='/path/to/myModel.pkl',
49 output_results_path='/path/to/newPredictedResults.csv',
50 input_dataset_path='/path/to/myDataset.csv',
51 properties=prop)
53 Info:
54 * wrapped_software:
55 * name: scikit-learn
56 * version: >=0.24.2
57 * license: BSD 3-Clause
58 * ontology:
59 * name: EDAM
60 * schema: http://edamontology.org/EDAM.owl
62 """
64 def __init__(self, input_model_path, output_results_path,
65 input_dataset_path=None, properties=None, **kwargs) -> None:
66 properties = properties or {}
68 # Call parent class constructor
69 super().__init__(properties)
70 self.locals_var_dict = locals().copy()
72 # Input/Output files
73 self.io_dict = {
74 "in": {"input_model_path": input_model_path, "input_dataset_path": input_dataset_path},
75 "out": {"output_results_path": output_results_path}
76 }
78 # Properties specific for BB
79 self.predictions = properties.get('predictions', [])
80 self.properties = properties
82 # Check the properties
83 self.check_properties(properties)
84 self.check_arguments()
86 def check_data_params(self, out_log, err_log):
87 """ Checks all the input/output paths and parameters """
88 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__)
89 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__)
90 if self.io_dict["in"]["input_dataset_path"]:
91 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__)
93 @launchlogger
94 def launch(self) -> int:
95 """Execute the :class:`ClusteringPredict <clustering.clustering_predict.ClusteringPredict>` clustering.clustering_predict.ClusteringPredict object."""
97 # check input/output paths and parameters
98 self.check_data_params(self.out_log, self.err_log)
100 # Setup Biobb
101 if self.check_restart():
102 return 0
103 self.stage_files()
105 fu.log('Getting model from %s' % self.io_dict["in"]["input_model_path"], self.out_log, self.global_log)
107 with open(self.io_dict["in"]["input_model_path"], "rb") as f:
108 while True:
109 try:
110 m = joblib.load(f)
111 if (isinstance(m, KMeans)):
112 new_model = m
113 if isinstance(m, StandardScaler):
114 scaler = m
115 if isinstance(m, dict):
116 variables = m
117 except EOFError:
118 break
120 if self.io_dict["in"]["input_dataset_path"]:
121 # load dataset from input_dataset_path file
122 fu.log('Getting dataset from %s' % self.io_dict["in"]["input_dataset_path"], self.out_log, self.global_log)
123 if 'columns' in variables['predictors']:
124 labels = getHeader(self.io_dict["in"]["input_dataset_path"])
125 skiprows = 1
126 else:
127 labels = None
128 skiprows = None
129 new_data_table = pd.read_csv(self.io_dict["in"]["input_dataset_path"], header=None, sep="\\s+|;|:|,|\t", engine="python", skiprows=skiprows, names=labels)
130 else:
131 # load dataset from properties
132 if 'columns' in variables['predictors']:
133 # sorting self.properties in the correct order given by variables['predictors']['columns']
134 index_map = {v: i for i, v in enumerate(variables['predictors']['columns'])}
135 predictions = []
136 for i, pred in enumerate(self.predictions):
137 sorted_pred = sorted(pred.items(), key=lambda pair: index_map[pair[0]])
138 predictions.append(dict(sorted_pred))
139 new_data_table = pd.DataFrame(data=get_list_of_predictors(predictions), columns=get_keys_of_predictors(predictions))
140 else:
141 predictions = self.predictions
142 new_data_table = pd.DataFrame(data=predictions)
144 if variables['scale']:
145 fu.log('Scaling dataset', self.out_log, self.global_log)
146 new_data = scaler.transform(new_data_table)
147 else:
148 new_data = new_data_table
150 p = new_model.predict(new_data)
152 new_data_table['cluster'] = p
153 fu.log('Predicting results\n\nPREDICTION RESULTS\n\n%s\n' % new_data_table, self.out_log, self.global_log)
154 fu.log('Saving results to %s' % self.io_dict["out"]["output_results_path"], self.out_log, self.global_log)
155 new_data_table.to_csv(self.io_dict["out"]["output_results_path"], index=False, header=True, float_format='%.3f')
157 # Copy files to host
158 self.copy_to_host()
160 self.tmp_files.extend([
161 self.stage_io_dict.get("unique_dir")
162 ])
163 self.remove_tmp_files()
165 self.check_arguments(output_files_created=True, raise_exception=False)
167 return 0
170def clustering_predict(input_model_path: str, output_results_path: str, input_dataset_path: str = None, properties: dict = None, **kwargs) -> int:
171 """Execute the :class:`ClusteringPredict <clustering.clustering_predict.ClusteringPredict>` class and
172 execute the :meth:`launch() <clustering.clustering_predict.ClusteringPredict.launch>` method."""
174 return ClusteringPredict(input_model_path=input_model_path,
175 output_results_path=output_results_path,
176 input_dataset_path=input_dataset_path,
177 properties=properties, **kwargs).launch()
180def main():
181 """Command line execution of this building block. Please check the command line documentation."""
182 parser = argparse.ArgumentParser(description="Makes predictions from an input dataset and a given clustering model.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
183 parser.add_argument('--config', required=False, help='Configuration file')
185 # Specific args of each building block
186 required_args = parser.add_argument_group('required arguments')
187 required_args.add_argument('--input_model_path', required=True, help='Path to the input model. Accepted formats: pkl.')
188 required_args.add_argument('--output_results_path', required=True, help='Path to the output results file. Accepted formats: csv.')
189 parser.add_argument('--input_dataset_path', required=False, help='Path to the dataset to predict. Accepted formats: csv.')
191 args = parser.parse_args()
192 args.config = args.config or "{}"
193 properties = settings.ConfReader(config=args.config).get_prop_dic()
195 # Specific call of each building block
196 clustering_predict(input_model_path=args.input_model_path,
197 output_results_path=args.output_results_path,
198 input_dataset_path=args.input_dataset_path,
199 properties=properties)
202if __name__ == '__main__':
203 main()