Coverage for biobb_ml/classification/random_forest_classifier.py: 83%
152 statements
« 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 RandomForestClassifier class and the command line interface."""
4import argparse
5import joblib
6import pandas as pd
7import numpy as np
8from biobb_common.generic.biobb_object import BiobbObject
9from sklearn.preprocessing import StandardScaler
10from sklearn.model_selection import train_test_split
11from sklearn.metrics import confusion_matrix, classification_report, log_loss
12from sklearn import ensemble
13from biobb_common.configuration import settings
14from biobb_common.tools import file_utils as fu
15from biobb_common.tools.file_utils import launchlogger
16from biobb_ml.classification.common import check_input_path, check_output_path, getHeader, getIndependentVars, getIndependentVarsList, getTarget, getTargetValue, getWeight, plotMultipleCM, plotBinaryClassifier
19class RandomForestClassifier(BiobbObject):
20 """
21 | biobb_ml RandomForestClassifier
22 | Wrapper of the scikit-learn RandomForestClassifier method.
23 | Trains and tests a given dataset and saves the model and scaler. Visit the `RandomForestClassifier documentation page <https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html>`_ in the sklearn official website for further information.
25 Args:
26 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/classification/dataset_random_forest_classifier.csv>`_. Accepted formats: csv (edam:format_3752).
27 output_model_path (str): Path to the output model file. File type: output. `Sample file <https://github.com/bioexcel/biobb_ml/raw/master/biobb_ml/test/reference/classification/ref_output_model_random_forest_classifier.pkl>`_. Accepted formats: pkl (edam:format_3653).
28 output_test_table_path (str) (Optional): Path to the test table file. File type: output. `Sample file <https://github.com/bioexcel/biobb_ml/raw/master/biobb_ml/test/reference/classification/ref_output_test_random_forest_classifier.csv>`_. Accepted formats: csv (edam:format_3752).
29 output_plot_path (str) (Optional): Path to the statistics plot. If target is binary it shows confusion matrix, distributions of the predicted probabilities of both classes and ROC curve. If target is non-binary it shows confusion matrix. File type: output. `Sample file <https://github.com/bioexcel/biobb_ml/raw/master/biobb_ml/test/reference/classification/ref_output_plot_random_forest_classifier.png>`_. Accepted formats: png (edam:format_3603).
30 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
31 * **independent_vars** (*dict*) - ({}) Independent variables you want to train from your dataset. 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.
32 * **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.
33 * **weight** (*dict*) - ({}) Weight variable 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.
34 * **n_estimators** (*int*) - (100) The number of trees in the forest.
35 * **bootstrap** (*bool*) - (True) Whether bootstrap samples are used when building trees. If False, the whole dataset is used to build each tree.
36 * **normalize_cm** (*bool*) - (False) Whether or not to normalize the confusion matrix.
37 * **random_state_method** (*int*) - (5) [1~1000|1] Controls the randomness of the estimator.
38 * **random_state_train_test** (*int*) - (5) [1~1000|1] Controls the shuffling applied to the data before applying the split.
39 * **test_size** (*float*) - (0.2) [0~1|0.05] Represents the proportion of the dataset to include in the test split. It should be between 0.0 and 1.0.
40 * **scale** (*bool*) - (False) Whether or not to scale the input dataset.
41 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
42 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
44 Examples:
45 This is a use example of how to use the building block from Python::
47 from biobb_ml.classification.random_forest_classifier import random_forest_classifier
48 prop = {
49 'independent_vars': {
50 'columns': [ 'column1', 'column2', 'column3' ]
51 },
52 'target': {
53 'column': 'target'
54 },
55 'n_estimators': 100,
56 'test_size': 0.2
57 }
58 random_forest_classifier(input_dataset_path='/path/to/myDataset.csv',
59 output_model_path='/path/to/newModel.pkl',
60 output_test_table_path='/path/to/newTable.csv',
61 output_plot_path='/path/to/newPlot.png',
62 properties=prop)
64 Info:
65 * wrapped_software:
66 * name: scikit-learn RandomForestClassifier
67 * version: >=0.24.2
68 * license: BSD 3-Clause
69 * ontology:
70 * name: EDAM
71 * schema: http://edamontology.org/EDAM.owl
73 """
75 def __init__(self, input_dataset_path, output_model_path,
76 output_test_table_path=None, output_plot_path=None, properties=None, **kwargs) -> None:
77 properties = properties or {}
79 # Call parent class constructor
80 super().__init__(properties)
81 self.locals_var_dict = locals().copy()
83 # Input/Output files
84 self.io_dict = {
85 "in": {"input_dataset_path": input_dataset_path},
86 "out": {"output_model_path": output_model_path, "output_test_table_path": output_test_table_path, "output_plot_path": output_plot_path}
87 }
89 # Properties specific for BB
90 self.independent_vars = properties.get('independent_vars', {})
91 self.target = properties.get('target', {})
92 self.weight = properties.get('weight', {})
93 self.n_estimators = properties.get('n_estimators', 100)
94 self.bootstrap = properties.get('bootstrap', True)
95 self.normalize_cm = properties.get('normalize_cm', False)
96 self.random_state_method = properties.get('random_state_method', 5)
97 self.random_state_train_test = properties.get('random_state_train_test', 5)
98 self.test_size = properties.get('test_size', 0.2)
99 self.scale = properties.get('scale', False)
100 self.properties = properties
102 # Check the properties
103 self.check_properties(properties)
104 self.check_arguments()
106 def check_data_params(self, out_log, err_log):
107 """ Checks all the input/output paths and parameters """
108 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__)
109 self.io_dict["out"]["output_model_path"] = check_output_path(self.io_dict["out"]["output_model_path"], "output_model_path", False, out_log, self.__class__.__name__)
110 if self.io_dict["out"]["output_test_table_path"]:
111 self.io_dict["out"]["output_test_table_path"] = check_output_path(self.io_dict["out"]["output_test_table_path"], "output_test_table_path", True, out_log, self.__class__.__name__)
112 if self.io_dict["out"]["output_plot_path"]:
113 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__)
115 @launchlogger
116 def launch(self) -> int:
117 """Execute the :class:`RandomForestClassifier <classification.random_forest_classifier.RandomForestClassifier>` classification.random_forest_classifier.RandomForestClassifier object."""
119 # check input/output paths and parameters
120 self.check_data_params(self.out_log, self.err_log)
122 # Setup Biobb
123 if self.check_restart():
124 return 0
125 self.stage_files()
127 # load dataset
128 fu.log('Getting dataset from %s' % self.io_dict["in"]["input_dataset_path"], self.out_log, self.global_log)
129 if 'columns' in self.independent_vars:
130 labels = getHeader(self.io_dict["in"]["input_dataset_path"])
131 skiprows = 1
132 else:
133 labels = None
134 skiprows = None
135 data = pd.read_csv(self.io_dict["in"]["input_dataset_path"], header=None, sep="\\s+|;|:|,|\t", engine="python", skiprows=skiprows, names=labels)
137 # declare inputs, targets and weights
138 # the inputs are all the independent variables
139 X = getIndependentVars(self.independent_vars, data, self.out_log, self.__class__.__name__)
140 fu.log('Independent variables: [%s]' % (getIndependentVarsList(self.independent_vars)), self.out_log, self.global_log)
141 # target
142 y = getTarget(self.target, data, self.out_log, self.__class__.__name__)
143 fu.log('Target: %s' % (getTargetValue(self.target)), self.out_log, self.global_log)
144 # weights
145 if self.weight:
146 w = getWeight(self.weight, data, self.out_log, self.__class__.__name__)
147 fu.log('Weight column provided', self.out_log, self.global_log)
149 # train / test split
150 fu.log('Creating train and test sets', self.out_log, self.global_log)
151 arrays_sets = (X, y)
152 # if user provide weights
153 if self.weight:
154 arrays_sets = arrays_sets + (w,)
155 X_train, X_test, y_train, y_test, w_train, w_test = train_test_split(*arrays_sets, test_size=self.test_size, random_state=self.random_state_train_test)
156 else:
157 X_train, X_test, y_train, y_test = train_test_split(*arrays_sets, test_size=self.test_size, random_state=self.random_state_train_test)
159 # scale dataset
160 if self.scale:
161 fu.log('Scaling dataset', self.out_log, self.global_log)
162 scaler = StandardScaler()
163 X_train = scaler.fit_transform(X_train)
165 # classification
166 fu.log('Training dataset applying random forest classification', self.out_log, self.global_log)
167 model = ensemble.RandomForestClassifier(n_estimators=self.n_estimators, bootstrap=self.bootstrap, random_state=self.random_state_method)
168 arrays_fit = (X_train, y_train)
169 # if user provide weights
170 if self.weight:
171 arrays_fit = arrays_fit + (w_train,)
173 model.fit(*arrays_fit)
175 y_hat_train = model.predict(X_train)
176 # classification report
177 cr_train = classification_report(y_train, y_hat_train)
178 # log loss
179 yhat_prob_train = model.predict_proba(X_train)
180 l_loss_train = log_loss(y_train, yhat_prob_train)
181 fu.log('Calculating scores and report for training dataset\n\nCLASSIFICATION REPORT\n\n%s\nLog loss: %.3f\n' % (cr_train, l_loss_train), self.out_log, self.global_log)
183 # compute confusion matrix
184 cnf_matrix_train = confusion_matrix(y_train, y_hat_train)
185 np.set_printoptions(precision=2)
186 if self.normalize_cm:
187 cnf_matrix_train = cnf_matrix_train.astype('float') / cnf_matrix_train.sum(axis=1)[:, np.newaxis]
188 cm_type = 'NORMALIZED CONFUSION MATRIX'
189 else:
190 cm_type = 'CONFUSION MATRIX, WITHOUT NORMALIZATION'
192 fu.log('Calculating confusion matrix for training dataset\n\n%s\n\n%s\n' % (cm_type, cnf_matrix_train), self.out_log, self.global_log)
194 # testing
195 if self.scale:
196 X_test = scaler.transform(X_test)
197 y_hat_test = model.predict(X_test)
198 test_table = pd.DataFrame()
199 y_hat_prob = model.predict_proba(X_test)
200 y_hat_prob = np.around(y_hat_prob, decimals=2)
201 y_hat_prob = tuple(map(tuple, y_hat_prob))
202 test_table['P' + np.array2string(np.unique(y_test))] = y_hat_prob
203 y_test = y_test.reset_index(drop=True)
204 test_table['target'] = y_test
205 fu.log('Testing\n\nTEST DATA\n\n%s\n' % test_table, self.out_log, self.global_log)
207 # classification report
208 cr = classification_report(y_test, y_hat_test)
209 # log loss
210 yhat_prob = model.predict_proba(X_test)
211 l_loss = log_loss(y_test, yhat_prob)
212 fu.log('Calculating scores and report for testing dataset\n\nCLASSIFICATION REPORT\n\n%s\nLog loss: %.3f\n' % (cr, l_loss), self.out_log, self.global_log)
214 # compute confusion matrix
215 cnf_matrix = confusion_matrix(y_test, y_hat_test)
216 np.set_printoptions(precision=2)
217 if self.normalize_cm:
218 cnf_matrix = cnf_matrix.astype('float') / cnf_matrix.sum(axis=1)[:, np.newaxis]
219 cm_type = 'NORMALIZED CONFUSION MATRIX'
220 else:
221 cm_type = 'CONFUSION MATRIX, WITHOUT NORMALIZATION'
223 fu.log('Calculating confusion matrix for testing dataset\n\n%s\n\n%s\n' % (cm_type, cnf_matrix), self.out_log, self.global_log)
225 if (self.io_dict["out"]["output_test_table_path"]):
226 fu.log('Saving testing data to %s' % self.io_dict["out"]["output_test_table_path"], self.out_log, self.global_log)
227 test_table.to_csv(self.io_dict["out"]["output_test_table_path"], index=False, header=True)
229 # plot
230 if self.io_dict["out"]["output_plot_path"]:
231 vs = y.unique().tolist()
232 vs.sort()
233 if len(vs) > 2:
234 plot = plotMultipleCM(cnf_matrix_train, cnf_matrix, self.normalize_cm, vs)
235 fu.log('Saving confusion matrix plot to %s' % self.io_dict["out"]["output_plot_path"], self.out_log, self.global_log)
236 else:
237 plot = plotBinaryClassifier(model, yhat_prob_train, yhat_prob, cnf_matrix_train, cnf_matrix, y_train, y_test, normalize=self.normalize_cm)
238 fu.log('Saving binary classifier evaluator plot to %s' % self.io_dict["out"]["output_plot_path"], self.out_log, self.global_log)
239 plot.savefig(self.io_dict["out"]["output_plot_path"], dpi=150)
241 # save model, scaler and parameters
242 tv = y.unique().tolist()
243 tv.sort()
244 variables = {
245 'target': self.target,
246 'independent_vars': self.independent_vars,
247 'scale': self.scale,
248 'target_values': tv
249 }
250 fu.log('Saving model to %s' % self.io_dict["out"]["output_model_path"], self.out_log, self.global_log)
251 with open(self.io_dict["out"]["output_model_path"], "wb") as f:
252 joblib.dump(model, f)
253 if self.scale:
254 joblib.dump(scaler, f)
255 joblib.dump(variables, f)
257 # Copy files to host
258 self.copy_to_host()
260 self.tmp_files.extend([
261 self.stage_io_dict.get("unique_dir")
262 ])
263 self.remove_tmp_files()
265 self.check_arguments(output_files_created=True, raise_exception=False)
267 return 0
270def random_forest_classifier(input_dataset_path: str, output_model_path: str, output_test_table_path: str = None, output_plot_path: str = None, properties: dict = None, **kwargs) -> int:
271 """Execute the :class:`RandomForestClassifier <classification.random_forest_classifier.RandomForestClassifier>` class and
272 execute the :meth:`launch() <classification.random_forest_classifier.RandomForestClassifier.launch>` method."""
274 return RandomForestClassifier(input_dataset_path=input_dataset_path,
275 output_model_path=output_model_path,
276 output_test_table_path=output_test_table_path,
277 output_plot_path=output_plot_path,
278 properties=properties, **kwargs).launch()
281def main():
282 """Command line execution of this building block. Please check the command line documentation."""
283 parser = argparse.ArgumentParser(description="Wrapper of the scikit-learn RandomForestClassifier method.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
284 parser.add_argument('--config', required=False, help='Configuration file')
286 # Specific args of each building block
287 required_args = parser.add_argument_group('required arguments')
288 required_args.add_argument('--input_dataset_path', required=True, help='Path to the input dataset. Accepted formats: csv.')
289 required_args.add_argument('--output_model_path', required=True, help='Path to the output model file. Accepted formats: pkl.')
290 parser.add_argument('--output_test_table_path', required=False, help='Path to the test table file. Accepted formats: csv.')
291 parser.add_argument('--output_plot_path', required=False, help='Path to the statistics plot. If target is binary it shows confusion matrix, distributions of the predicted probabilities of both classes and ROC curve. If target is non-binary it shows confusion matrix. Accepted formats: png.')
293 args = parser.parse_args()
294 args.config = args.config or "{}"
295 properties = settings.ConfReader(config=args.config).get_prop_dic()
297 # Specific call of each building block
298 random_forest_classifier(input_dataset_path=args.input_dataset_path,
299 output_model_path=args.output_model_path,
300 output_test_table_path=args.output_test_table_path,
301 output_plot_path=args.output_plot_path,
302 properties=properties)
305if __name__ == '__main__':
306 main()