Coverage for biobb_ml/dimensionality_reduction/principal_component.py: 81%
102 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 PrincipalComponentAnalysis class and the command line interface."""
4import argparse
5import pandas as pd
6import numpy as np
7import matplotlib.pyplot as plt
8from biobb_common.generic.biobb_object import BiobbObject
9from sklearn.preprocessing import StandardScaler
10from sklearn.decomposition import PCA
11from biobb_common.configuration import settings
12from biobb_common.tools import file_utils as fu
13from biobb_common.tools.file_utils import launchlogger
14from biobb_ml.dimensionality_reduction.common import check_input_path, check_output_path, getHeader, getIndependentVars, getIndependentVarsList, getTargetValue, generate_columns_labels, PCA2CPlot, PCA3CPlot
17class PrincipalComponentAnalysis(BiobbObject):
18 """
19 | biobb_ml PrincipalComponentAnalysis
20 | Wrapper of the scikit-learn PCA method.
21 | Analyses a given dataset through Principal Component Analysis (PCA). Visit the `PCA documentation page <https://scikit-learn.org/stable/modules/generated/sklearn.decomposition.PCA.html>`_ in the sklearn official website for further information.
23 Args:
24 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/dimensionality_reduction/dataset_principal_component.csv>`_. Accepted formats: csv (edam:format_3752).
25 output_results_path (str): Path to the analysed dataset. File type: output. `Sample file <https://github.com/bioexcel/biobb_ml/raw/master/biobb_ml/test/reference/dimensionality_reduction/ref_output_results_principal_component.csv>`_. Accepted formats: csv (edam:format_3752).
26 output_plot_path (str) (Optional): Path to the Principal Component plot, only if number of components is 2 or 3. File type: output. `Sample file <https://github.com/bioexcel/biobb_ml/raw/master/biobb_ml/test/reference/dimensionality_reduction/ref_output_plot_principal_component.png>`_. Accepted formats: png (edam:format_3603).
27 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
28 * **features** (*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.
29 * **target** (*dict*) - ({}) Dependent variable you want to predict from your dataset. You can specify either a column name or a column index. Formats: { "column": "column3" } or { "index": 21 }. In case of mulitple formats, the first one will be picked.
30 * **n_components** (*dict*) - ({}) Dictionary containing the number of components to keep (int) or the minimum number of principal components such the 0 to 1 range of the variance (float) is retained. If not set ({}) all components are kept. Formats for integer values: { "value": 2 } or for float values: { "value": 0.3 }
31 * **random_state_method** (*int*) - (5) [1~1000|1] Controls the randomness of the estimator.
32 * **scale** (*bool*) - (False) Whether or not to scale the input dataset.
33 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
34 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
36 Examples:
37 This is a use example of how to use the building block from Python::
39 from biobb_ml.dimensionality_reduction.principal_component import principal_component
40 prop = {
41 'features': {
42 'columns': [ 'column1', 'column2', 'column3' ]
43 },
44 'target': {
45 'column': 'target'
46 },
47 'n_components': {
48 'int': 2
49 }
50 }
51 principal_component(input_dataset_path='/path/to/myDataset.csv',
52 output_results_path='/path/to/newTable.csv',
53 output_plot_path='/path/to/newPlot.png',
54 properties=prop)
56 Info:
57 * wrapped_software:
58 * name: scikit-learn PCA
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_dataset_path, output_results_path,
68 output_plot_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_dataset_path": input_dataset_path},
78 "out": {"output_results_path": output_results_path, "output_plot_path": output_plot_path}
79 }
81 # Properties specific for BB
82 self.features = properties.get('features', {})
83 self.target = properties.get('target', {})
84 self.n_components = properties.get('n_components', {})
85 self.random_state_method = properties.get('random_state_method', 5)
86 self.scale = properties.get('scale', False)
87 self.properties = properties
89 # Check the properties
90 self.check_properties(properties)
91 self.check_arguments()
93 def check_data_params(self, out_log, err_log):
94 """ Checks all the input/output paths and parameters """
95 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 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__)
97 if self.io_dict["out"]["output_plot_path"]:
98 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__)
100 @launchlogger
101 def launch(self) -> int:
102 """Execute the :class:`PrincipalComponentAnalysis <dimensionality_reduction.principal_component.PrincipalComponentAnalysis>` dimensionality_reduction.pincipal_component.PrincipalComponentAnalysis object."""
104 # check input/output paths and parameters
105 self.check_data_params(self.out_log, self.err_log)
107 # Setup Biobb
108 if self.check_restart():
109 return 0
110 self.stage_files()
112 # load dataset
113 fu.log('Getting dataset from %s' % self.io_dict["in"]["input_dataset_path"], self.out_log, self.global_log)
114 if 'columns' in self.features:
115 labels = getHeader(self.io_dict["in"]["input_dataset_path"])
116 skiprows = 1
117 else:
118 labels = None
119 skiprows = None
120 data = pd.read_csv(self.io_dict["in"]["input_dataset_path"], header=None, sep="\\s+|;|:|,|\t", engine="python", skiprows=skiprows, names=labels)
122 # declare inputs, targets and weights
123 # the inputs are all the features
124 features = getIndependentVars(self.features, data, self.out_log, self.__class__.__name__)
125 fu.log('Features: [%s]' % (getIndependentVarsList(self.features)), self.out_log, self.global_log)
126 # target
127 y_value = getTargetValue(self.target)
128 fu.log('Target: %s' % (y_value), self.out_log, self.global_log)
130 if self.scale:
131 fu.log('Scaling dataset', self.out_log, self.global_log)
132 scaler = StandardScaler()
133 features = scaler.fit_transform(features)
135 # create a PCA object with self.n_components['value'] n_components
136 if 'value' not in self.n_components:
137 n_c = None
138 else:
139 n_c = self.n_components['value']
140 fu.log('Fitting dataset', self.out_log, self.global_log)
141 model = PCA(n_components=n_c, random_state=self.random_state_method)
142 # fit the data
143 model.fit(features)
145 # calculate variance ratio
146 v_ratio = model.explained_variance_ratio_
147 fu.log('Variance ratio for %d Principal Components: %s' % (v_ratio.shape[0], np.array2string(v_ratio, precision=3, separator=', ')), self.out_log, self.global_log)
149 # transform
150 fu.log('Transforming dataset', self.out_log, self.global_log)
151 pca = model.transform(features)
152 pca = pd.DataFrame(data=pca, columns=generate_columns_labels('PC', v_ratio.shape[0]))
154 if 'columns' in self.features:
155 d = data[[y_value]]
156 target_plot = y_value
157 else:
158 d = data.loc[:, int(y_value)]
159 target_plot = int(y_value)
161 # output results
162 pca_table = pd.concat([pca, d], axis=1)
163 fu.log('Calculating PCA for dataset\n\n%d COMPONENT PCA TABLE\n\n%s\n' % (v_ratio.shape[0], pca_table), self.out_log, self.global_log)
165 # save results
166 fu.log('Saving data to %s' % self.io_dict["out"]["output_results_path"], self.out_log, self.global_log)
167 pca_table.to_csv(self.io_dict["out"]["output_results_path"], index=False, header=True)
169 # create output plot
170 if (self.io_dict["out"]["output_plot_path"]):
171 if v_ratio.shape[0] > 3:
172 fu.log('%d PC\'s found. Displaying only 1st, 2nd and 3rd PC' % v_ratio.shape[0], self.out_log, self.global_log)
173 fu.log('Saving PC plot to %s' % self.io_dict["out"]["output_plot_path"], self.out_log, self.global_log)
174 targets = np.unique(d)
175 if v_ratio.shape[0] == 2:
176 PCA2CPlot(pca_table, targets, target_plot)
178 if v_ratio.shape[0] >= 3:
179 PCA3CPlot(pca_table, targets, target_plot)
181 plt.savefig(self.io_dict["out"]["output_plot_path"], dpi=150)
183 # Copy files to host
184 self.copy_to_host()
186 self.tmp_files.extend([
187 self.stage_io_dict.get("unique_dir")
188 ])
189 self.remove_tmp_files()
191 self.check_arguments(output_files_created=True, raise_exception=False)
193 return 0
196def principal_component(input_dataset_path: str, output_results_path: str, output_plot_path: str = None, properties: dict = None, **kwargs) -> int:
197 """Execute the :class:`PrincipalComponentAnalysis <dimensionality_reduction.principal_component.PrincipalComponentAnalysis>` class and
198 execute the :meth:`launch() <dimensionality_reduction.principal_component.PrincipalComponentAnalysis.launch>` method."""
200 return PrincipalComponentAnalysis(input_dataset_path=input_dataset_path,
201 output_results_path=output_results_path,
202 output_plot_path=output_plot_path,
203 properties=properties, **kwargs).launch()
206def main():
207 """Command line execution of this building block. Please check the command line documentation."""
208 parser = argparse.ArgumentParser(description="Wrapper of the scikit-learn PCA method.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
209 parser.add_argument('--config', required=False, help='Configuration file')
211 # Specific args of each building block
212 required_args = parser.add_argument_group('required arguments')
213 required_args.add_argument('--input_dataset_path', required=True, help='Path to the input dataset. Accepted formats: csv.')
214 required_args.add_argument('--output_results_path', required=True, help='Path to the analysed dataset. Accepted formats: csv.')
215 parser.add_argument('--output_plot_path', required=False, help='Path to the Principal Component plot, only if number of components is 2 or 3. Accepted formats: png.')
217 args = parser.parse_args()
218 args.config = args.config or "{}"
219 properties = settings.ConfReader(config=args.config).get_prop_dic()
221 # Specific call of each building block
222 principal_component(input_dataset_path=args.input_dataset_path,
223 output_results_path=args.output_results_path,
224 output_plot_path=args.output_plot_path,
225 properties=properties)
228if __name__ == '__main__':
229 main()