Coverage for biobb_ml/clustering/spectral_clustering.py: 83%
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 SpecClustering class and the command line interface."""
4import argparse
5import pandas as pd
6from biobb_common.generic.biobb_object import BiobbObject
7from sklearn.preprocessing import StandardScaler
8from sklearn.cluster import SpectralClustering
9from biobb_common.configuration import settings
10from biobb_common.tools import file_utils as fu
11from biobb_common.tools.file_utils import launchlogger
12from biobb_ml.clustering.common import check_input_path, check_output_path, getHeader, getIndependentVars, getIndependentVarsList, hopkins, plotCluster
15class SpecClustering(BiobbObject):
16 """
17 | biobb_ml SpecClustering
18 | Wrapper of the scikit-learn SpectralClustering method.
19 | Clusters a given dataset. Visit the `SpectralClustering documentation page <https://scikit-learn.org/stable/modules/generated/sklearn.cluster.SpectralClustering.html>`_ in the sklearn official website for further information.
21 Args:
22 input_dataset_path (str): Path to the input dataset. File type: input. `Sample file <https://github.com/bioexcel/biobb_ml/raw/master/biobb_ml/test/data/clustering/dataset_spectral_clustering.csv>`_. Accepted formats: csv (edam:format_3752).
23 output_results_path (str): Path to the clustered dataset. File type: output. `Sample file <https://github.com/bioexcel/biobb_ml/raw/master/biobb_ml/test/reference/clustering/ref_output_results_spectral_clustering.csv>`_. Accepted formats: csv (edam:format_3752).
24 output_plot_path (str) (Optional): Path to the clustering plot. File type: output. `Sample file <https://github.com/bioexcel/biobb_ml/raw/master/biobb_ml/test/reference/clustering/ref_output_plot_spectral_clustering.png>`_. Accepted formats: png (edam:format_3603).
25 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
26 * **predictors** (*dict*) - ({}) Features or columns from your dataset you want to use for fitting. You can specify either a list of columns names from your input dataset, a list of columns indexes or a range of columns indexes. Formats: { "columns": ["column1", "column2"] } or { "indexes": [0, 2, 3, 10, 11, 17] } or { "range": [[0, 20], [50, 102]] }. In case of mulitple formats, the first one will be picked.
27 * **clusters** (*int*) - (3) [1~100|1] The number of clusters to form as well as the number of centroids to generate.
28 * **affinity** (*string*) - ("rbf") How to construct the affinity matrix. Values: nearest_neighbors (construct the affinity matrix by computing a graph of nearest neighbors), rbf (construct the affinity matrix using a radial basis function -RBF- kernel), precomputed (interpret X as a precomputed affinity matrix), precomputed_nearest_neighbors (interpret X as a sparse graph of precomputed nearest neighbors and constructs the affinity matrix by selecting the n_neighbors nearest neighbors).
29 * **plots** (*list*) - (None) List of dictionaries with all plots you want to generate. Only 2D or 3D plots accepted. Format: [ { 'title': 'Plot 1', 'features': ['feat1', 'feat2'] } ].
30 * **random_state_method** (*int*) - (5) [1~1000|1] A pseudo random number generator used for the initialization of the lobpcg eigen vectors decomposition when *eigen_solver='amg'* and by the K-Means initialization.
31 * **scale** (*bool*) - (False) Whether or not to scale the input dataset.
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.clustering.spectral_clustering import spectral_clustering
39 prop = {
40 'predictors': {
41 'columns': [ 'column1', 'column2', 'column3' ]
42 },
43 'clusters': 3,
44 'affinity': 'rbf',
45 'plots': [
46 {
47 'title': 'Plot 1',
48 'features': ['feat1', 'feat2']
49 }
50 ]
51 }
52 spectral_clustering(input_dataset_path='/path/to/myDataset.csv',
53 output_results_path='/path/to/newTable.csv',
54 output_plot_path='/path/to/newPlot.png',
55 properties=prop)
57 Info:
58 * wrapped_software:
59 * name: scikit-learn SpectralClustering
60 * version: >=0.24.2
61 * license: BSD 3-Clause
62 * ontology:
63 * name: EDAM
64 * schema: http://edamontology.org/EDAM.owl
66 """
68 def __init__(self, input_dataset_path, output_results_path,
69 output_plot_path=None, properties=None, **kwargs) -> None:
70 properties = properties or {}
72 # Call parent class constructor
73 super().__init__(properties)
74 self.locals_var_dict = locals().copy()
76 # Input/Output files
77 self.io_dict = {
78 "in": {"input_dataset_path": input_dataset_path},
79 "out": {"output_results_path": output_results_path, "output_plot_path": output_plot_path}
80 }
82 # Properties specific for BB
83 self.predictors = properties.get('predictors', {})
84 self.clusters = properties.get('clusters', 3)
85 self.affinity = properties.get('affinity', 'rbf')
86 self.plots = properties.get('plots', [])
87 self.random_state_method = properties.get('random_state_method', 5)
88 self.scale = properties.get('scale', False)
89 self.properties = properties
91 # Check the properties
92 self.check_properties(properties)
93 self.check_arguments()
95 def check_data_params(self, out_log, err_log):
96 """ Checks all the input/output paths and parameters """
97 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__)
98 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__)
99 if self.io_dict["out"]["output_plot_path"]:
100 self.io_dict["out"]["output_plot_path"] = check_output_path(self.io_dict["out"]["output_plot_path"], "output_plot_path", True, out_log, self.__class__.__name__)
102 @launchlogger
103 def launch(self) -> int:
104 """Execute the :class:`SpecClustering <clustering.spectral_clustering.SpecClustering>` clustering.spectral_clustering.SpecClustering object."""
106 # check input/output paths and parameters
107 self.check_data_params(self.out_log, self.err_log)
109 # Setup Biobb
110 if self.check_restart():
111 return 0
112 self.stage_files()
114 # load dataset
115 fu.log('Getting dataset from %s' % self.io_dict["in"]["input_dataset_path"], self.out_log, self.global_log)
116 if 'columns' in self.predictors:
117 labels = getHeader(self.io_dict["in"]["input_dataset_path"])
118 skiprows = 1
119 else:
120 labels = None
121 skiprows = None
122 data = pd.read_csv(self.io_dict["in"]["input_dataset_path"], header=None, sep="\\s+|;|:|,|\t", engine="python", skiprows=skiprows, names=labels)
124 # the features are the predictors
125 predictors = getIndependentVars(self.predictors, data, self.out_log, self.__class__.__name__)
126 fu.log('Predictors: [%s]' % (getIndependentVarsList(self.predictors)), self.out_log, self.global_log)
128 # Hopkins test
129 H = hopkins(predictors)
130 fu.log('Performing Hopkins test over dataset. H = %f' % H, self.out_log, self.global_log)
132 # scale dataset
133 if self.scale:
134 fu.log('Scaling dataset', self.out_log, self.global_log)
135 scaler = StandardScaler()
136 predictors = scaler.fit_transform(predictors)
138 # create a spectral clustering object with self.clusters clusters
139 model = SpectralClustering(n_clusters=self.clusters, affinity=self.affinity, random_state=self.random_state_method)
140 # fit the data
141 model.fit(predictors)
143 # create a copy of data, so we can see the clusters next to the original data
144 clusters = data.copy()
145 # predict the cluster for each observation
146 clusters['cluster'] = model.fit_predict(predictors)
148 fu.log('Calculating results\n\nCLUSTERING TABLE\n\n%s\n' % clusters, self.out_log, self.global_log)
150 # save results
151 fu.log('Saving results to %s' % self.io_dict["out"]["output_results_path"], self.out_log, self.global_log)
152 clusters.to_csv(self.io_dict["out"]["output_results_path"], index=False, header=True, float_format='%.3f')
154 if self.io_dict["out"]["output_plot_path"] and self.plots:
155 new_plots = []
156 i = 0
157 for plot in self.plots:
158 if len(plot['features']) == 2 or len(plot['features']) == 3:
159 new_plots.append(plot)
160 i += 1
161 if i == 6:
162 break
164 plot = plotCluster(new_plots, clusters)
165 fu.log('Saving output plot to %s' % self.io_dict["out"]["output_plot_path"], self.out_log, self.global_log)
166 plot.savefig(self.io_dict["out"]["output_plot_path"], dpi=150)
168 # Copy files to host
169 self.copy_to_host()
171 self.tmp_files.extend([
172 self.stage_io_dict.get("unique_dir")
173 ])
174 self.remove_tmp_files()
176 self.check_arguments(output_files_created=True, raise_exception=False)
178 return 0
181def spectral_clustering(input_dataset_path: str, output_results_path: str, output_plot_path: str = None, properties: dict = None, **kwargs) -> int:
182 """Execute the :class:`SpecClustering <clustering.spectral_clustering.SpecClustering>` class and
183 execute the :meth:`launch() <clustering.spectral_clustering.SpecClustering.launch>` method."""
185 return SpecClustering(input_dataset_path=input_dataset_path,
186 output_results_path=output_results_path,
187 output_plot_path=output_plot_path,
188 properties=properties, **kwargs).launch()
191def main():
192 """Command line execution of this building block. Please check the command line documentation."""
193 parser = argparse.ArgumentParser(description="Wrapper of the scikit-learn SpectralClustering method.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
194 parser.add_argument('--config', required=False, help='Configuration file')
196 # Specific args of each building block
197 required_args = parser.add_argument_group('required arguments')
198 required_args.add_argument('--input_dataset_path', required=True, help='Path to the input dataset. Accepted formats: csv.')
199 required_args.add_argument('--output_results_path', required=True, help='Path to the clustered dataset. Accepted formats: csv.')
200 parser.add_argument('--output_plot_path', required=False, help='Path to the clustering plot. Accepted formats: png.')
202 args = parser.parse_args()
203 args.config = args.config or "{}"
204 properties = settings.ConfReader(config=args.config).get_prop_dic()
206 # Specific call of each building block
207 spectral_clustering(input_dataset_path=args.input_dataset_path,
208 output_results_path=args.output_results_path,
209 output_plot_path=args.output_plot_path,
210 properties=properties)
213if __name__ == '__main__':
214 main()