Coverage for biobb_ml/clustering/dbscan.py: 85%
97 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 DBSCANClustering 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 DBSCAN
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 DBSCANClustering(BiobbObject):
16 """
17 | biobb_ml DBSCANClustering
18 | Wrapper of the scikit-learn DBSCAN method.
19 | Clusters a given dataset. Visit the `DBSCAN documentation page <https://scikit-learn.org/stable/modules/generated/sklearn.cluster.DBSCAN.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_dbscan.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_dbscan.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_dbscan.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 * **eps** (*float*) - (0.5) [0~10|0.1] The maximum distance between two samples for one to be considered as in the neighborhood of the other.
28 * **min_samples** (*int*) - (5) [1~100|1] The number of samples (or total weight) in a neighborhood for a point to be considered as a core point. This includes the point itself.
29 * **metric** (*str*) - ("euclidean") The metric to use when calculating distance between instances in a feature array. Values: cityblock (Compute the City Block -Manhattan- distance), cosine (Compute the Cosine distance between 1-D arrays), euclidean (Computes the Euclidean distance between two 1-D arrays), l1, l2, manhattan (Compute the Manhattan distance), braycurtis (Compute the Bray-Curtis distance between two 1-D arrays), canberra (Compute the Canberra distance between two 1-D arrays), chebyshev (Compute the Chebyshev distance), correlation (Compute the correlation distance between two 1-D arrays), dice (Compute the Dice dissimilarity between two boolean 1-D arrays), hamming (Compute the Hamming distance between two 1-D arrays), jaccard (Compute the Jaccard-Needham dissimilarity between two boolean 1-D arrays), kulsinski (Compute the Kulsinski dissimilarity between two boolean 1-D arrays), mahalanobis (Compute the Mahalanobis distance between two 1-D arrays), minkowski (Compute the Minkowski distance between two 1-D arrays), rogerstanimoto (Compute the Rogers-Tanimoto dissimilarity between two boolean 1-D arrays), russellrao (Compute the Russell-Rao dissimilarity between two boolean 1-D arrays), seuclidean (Return the standardized Euclidean distance between two 1-D arrays), sokalmichener (Compute the Sokal-Michener dissimilarity between two boolean 1-D arrays), sokalsneath (Compute the Sokal-Sneath dissimilarity between two boolean 1-D arrays), sqeuclidean (Compute the squared Euclidean distance between two 1-D arrays), yule (Compute the Yule dissimilarity between two boolean 1-D arrays).
30 * **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'] } ].
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.dbscan import dbscan
39 prop = {
40 'predictors': {
41 'columns': [ 'column1', 'column2', 'column3' ]
42 },
43 'eps': 1.4,
44 'min_samples': 3,
45 'metric': 'euclidean',
46 'plots': [
47 {
48 'title': 'Plot 1',
49 'features': ['feat1', 'feat2']
50 }
51 ]
52 }
53 dbscan(input_dataset_path='/path/to/myDataset.csv',
54 output_results_path='/path/to/newTable.csv',
55 output_plot_path='/path/to/newPlot.png',
56 properties=prop)
58 Info:
59 * wrapped_software:
60 * name: scikit-learn DBSCAN
61 * version: >=0.24.2
62 * license: BSD 3-Clause
63 * ontology:
64 * name: EDAM
65 * schema: http://edamontology.org/EDAM.owl
67 """
69 def __init__(self, input_dataset_path, output_results_path,
70 output_plot_path=None, properties=None, **kwargs) -> None:
71 properties = properties or {}
73 # Call parent class constructor
74 super().__init__(properties)
75 self.locals_var_dict = locals().copy()
77 # Input/Output files
78 self.io_dict = {
79 "in": {"input_dataset_path": input_dataset_path},
80 "out": {"output_results_path": output_results_path, "output_plot_path": output_plot_path}
81 }
83 # Properties specific for BB
84 self.predictors = properties.get('predictors', {})
85 self.eps = properties.get('eps', .5)
86 self.min_samples = properties.get('min_samples', 5)
87 self.metric = properties.get('metric', 'euclidean')
88 self.plots = properties.get('plots', [])
89 self.scale = properties.get('scale', False)
90 self.properties = properties
92 # Check the properties
93 self.check_properties(properties)
94 self.check_arguments()
96 def check_data_params(self, out_log, err_log):
97 """ Checks all the input/output paths and parameters """
98 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__)
99 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__)
100 if self.io_dict["out"]["output_plot_path"]:
101 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__)
103 @launchlogger
104 def launch(self) -> int:
105 """Execute the :class:`DBSCANClustering <clustering.dbscan.DBSCANClustering>` clustering.dbscan.DBSCANClustering object."""
107 # check input/output paths and parameters
108 self.check_data_params(self.out_log, self.err_log)
110 # Setup Biobb
111 if self.check_restart():
112 return 0
113 self.stage_files()
115 # load dataset
116 fu.log('Getting dataset from %s' % self.io_dict["in"]["input_dataset_path"], self.out_log, self.global_log)
117 if 'columns' in self.predictors:
118 labels = getHeader(self.io_dict["in"]["input_dataset_path"])
119 skiprows = 1
120 else:
121 labels = None
122 skiprows = None
123 data = pd.read_csv(self.io_dict["in"]["input_dataset_path"], header=None, sep="\\s+|;|:|,|\t", engine="python", skiprows=skiprows, names=labels)
125 # the features are the predictors
126 predictors = getIndependentVars(self.predictors, data, self.out_log, self.__class__.__name__)
127 fu.log('Predictors: [%s]' % (getIndependentVarsList(self.predictors)), self.out_log, self.global_log)
129 # Hopkins test
130 H = hopkins(predictors)
131 fu.log('Performing Hopkins test over dataset. H = %f' % H, self.out_log, self.global_log)
133 # scale dataset
134 if self.scale:
135 fu.log('Scaling dataset', self.out_log, self.global_log)
136 scaler = StandardScaler()
137 predictors = scaler.fit_transform(predictors)
139 # create a DBSCAN object with self.clusters clusters
140 model = DBSCAN(eps=self.eps, min_samples=self.min_samples, metric=self.metric)
141 # fit the data
142 model.fit(predictors)
144 # create a copy of data, so we can see the clusters next to the original data
145 clusters = data.copy()
146 # predict the cluster for each observation
147 clusters['cluster'] = model.fit_predict(predictors)
149 fu.log('Calculating results\n\nCLUSTERING TABLE\n\n%s\n' % clusters, self.out_log, self.global_log)
151 # get number of clusters discarding outliers
152 clstrs = set(clusters['cluster'])
153 if -1 in clstrs:
154 clstrs.remove(-1)
155 fu.log('Total of clusters computed by DBSCAN = %d' % len(clstrs), self.out_log, self.global_log)
157 outliers = clusters['cluster'].tolist().count(-1)
158 op = (outliers / len(clusters['cluster'].tolist())) * 100
159 fu.log('Total of outliers = %d (%.2f%%)' % (outliers, op), self.out_log, self.global_log)
161 # save results
162 fu.log('Saving results to %s' % self.io_dict["out"]["output_results_path"], self.out_log, self.global_log)
163 clusters.to_csv(self.io_dict["out"]["output_results_path"], index=False, header=True, float_format='%.3f')
165 if self.io_dict["out"]["output_plot_path"] and self.plots:
166 new_plots = []
167 i = 0
168 for plot in self.plots:
169 if len(plot['features']) == 2 or len(plot['features']) == 3:
170 new_plots.append(plot)
171 i += 1
172 if i == 6:
173 break
175 plot = plotCluster(new_plots, clusters)
176 fu.log('Saving output plot to %s' % self.io_dict["out"]["output_plot_path"], self.out_log, self.global_log)
177 plot.savefig(self.io_dict["out"]["output_plot_path"], dpi=150)
179 # Copy files to host
180 self.copy_to_host()
182 self.tmp_files.extend([
183 self.stage_io_dict.get("unique_dir")
184 ])
185 self.remove_tmp_files()
187 self.check_arguments(output_files_created=True, raise_exception=False)
189 return 0
192def dbscan(input_dataset_path: str, output_results_path: str, output_plot_path: str = None, properties: dict = None, **kwargs) -> int:
193 """Execute the :class:`DBSCANClustering <clustering.dbscan.DBSCANClustering>` class and
194 execute the :meth:`launch() <clustering.dbscan.DBSCANClustering.launch>` method."""
196 return DBSCANClustering(input_dataset_path=input_dataset_path,
197 output_results_path=output_results_path,
198 output_plot_path=output_plot_path,
199 properties=properties, **kwargs).launch()
202def main():
203 """Command line execution of this building block. Please check the command line documentation."""
204 parser = argparse.ArgumentParser(description="Wrapper of the scikit-learn DBSCAN method.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
205 parser.add_argument('--config', required=False, help='Configuration file')
207 # Specific args of each building block
208 required_args = parser.add_argument_group('required arguments')
209 required_args.add_argument('--input_dataset_path', required=True, help='Path to the input dataset. Accepted formats: csv.')
210 required_args.add_argument('--output_results_path', required=True, help='Path to the clustered dataset. Accepted formats: csv.')
211 parser.add_argument('--output_plot_path', required=False, help='Path to the clustering plot. Accepted formats: png.')
213 args = parser.parse_args()
214 args.config = args.config or "{}"
215 properties = settings.ConfReader(config=args.config).get_prop_dic()
217 # Specific call of each building block
218 dbscan(input_dataset_path=args.input_dataset_path,
219 output_results_path=args.output_results_path,
220 output_plot_path=args.output_plot_path,
221 properties=properties)
224if __name__ == '__main__':
225 main()