Coverage for biobb_ml/neural_networks/neural_network_predict.py: 63%
104 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 PredictNeuralNetwork class and the command line interface."""
4import argparse
5import h5py
6import json
7import csv
8import numpy as np
9import pandas as pd
10from biobb_common.generic.biobb_object import BiobbObject
11from tensorflow.python.keras.saving import hdf5_format
12from sklearn.preprocessing import scale
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.neural_networks.common import check_input_path, check_output_path, getHeader, getTargetValue, get_list_of_predictors, get_keys_of_predictors, get_num_cols
19class PredictNeuralNetwork(BiobbObject):
20 """
21 | biobb_ml PredictNeuralNetwork
22 | Makes predictions from an input dataset and a given model.
23 | Makes predictions from an input dataset (provided either as a file or as a dictionary property) and a given model trained with `TensorFlow Keras Sequential <https://www.tensorflow.org/api_docs/python/tf/keras/Sequential>`_ and `TensorFlow Keras LSTM <https://www.tensorflow.org/api_docs/python/tf/keras/layers/LSTM>`_
25 Args:
26 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/neural_networks/input_model_predict.h5>`_. Accepted formats: h5 (edam:format_3590).
27 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/neural_networks/dataset_predict.csv>`_. Accepted formats: csv (edam:format_3752).
28 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/neural_networks/ref_output_predict.csv>`_. Accepted formats: csv (edam:format_3752).
29 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
30 * **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.
31 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
32 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
34 Examples:
35 This is a use example of how to use the building block from Python::
37 from biobb_ml.neural_networks.neural_network_predict import neural_network_predict
38 prop = {
39 'predictions': [
40 {
41 'var1': 1.0,
42 'var2': 2.0
43 },
44 {
45 'var1': 4.0,
46 'var2': 2.7
47 }
48 ]
49 }
50 neural_network_predict(input_model_path='/path/to/myModel.h5',
51 input_dataset_path='/path/to/myDataset.csv',
52 output_results_path='/path/to/newPredictedResults.csv',
53 properties=prop)
55 Info:
56 * wrapped_software:
57 * name: TensorFlow
58 * version: >2.1.0
59 * license: MIT
60 * ontology:
61 * name: EDAM
62 * schema: http://edamontology.org/EDAM.owl
64 """
66 def __init__(self, input_model_path, output_results_path,
67 input_dataset_path=None, properties=None, **kwargs) -> None:
68 properties = properties or {}
70 # Call parent class constructor
71 super().__init__(properties)
72 self.locals_var_dict = locals().copy()
74 # Input/Output files
75 self.io_dict = {
76 "in": {"input_model_path": input_model_path, "input_dataset_path": input_dataset_path},
77 "out": {"output_results_path": output_results_path}
78 }
80 # Properties specific for BB
81 self.predictions = properties.get('predictions', [])
82 self.properties = properties
84 # Check the properties
85 self.check_properties(properties)
86 self.check_arguments()
88 def check_data_params(self, out_log, err_log):
89 """ Checks all the input/output paths and parameters """
90 self.io_dict["in"]["input_model_path"] = check_input_path(self.io_dict["in"]["input_model_path"], "input_model_path", False, out_log, self.__class__.__name__)
91 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__)
92 if self.io_dict["in"]["input_dataset_path"]:
93 self.io_dict["in"]["input_dataset_path"] = check_input_path(self.io_dict["in"]["input_dataset_path"], "input_dataset_path", False, out_log, self.__class__.__name__)
95 @launchlogger
96 def launch(self) -> int:
97 """Execute the :class:`PredictNeuralNetwork <neural_networks.neural_network_predict.PredictNeuralNetwork>` neural_networks.neural_network_predict.PredictNeuralNetwork object."""
99 # check input/output paths and parameters
100 self.check_data_params(self.out_log, self.err_log)
102 # Setup Biobb
103 if self.check_restart():
104 return 0
105 self.stage_files()
107 fu.log('Getting model from %s' % self.io_dict["in"]["input_model_path"], self.out_log, self.global_log)
108 with h5py.File(self.io_dict["in"]["input_model_path"], mode='r') as f:
109 variables = f.attrs['variables']
110 new_model = hdf5_format.load_model_from_hdf5(f)
112 # get dictionary with variables
113 vars_obj = json.loads(variables)
115 stringlist = []
116 new_model.summary(print_fn=lambda x: stringlist.append(x))
117 model_summary = "\n".join(stringlist)
118 fu.log('Model summary:\n\n%s\n' % model_summary, self.out_log, self.global_log)
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 'features' not in vars_obj:
124 # recurrent
125 labels = None
126 skiprows = None
127 with open(self.io_dict["in"]["input_dataset_path"]) as csvfile:
128 reader = csv.reader(csvfile, quoting=csv.QUOTE_NONNUMERIC) # change contents to floats
129 for row in reader: # each row is a list
130 self.predictions.append(row)
131 else:
132 # classification or regression
133 if 'columns' in vars_obj['features']:
134 labels = getHeader(self.io_dict["in"]["input_dataset_path"])
135 skiprows = 1
136 else:
137 labels = None
138 skiprows = None
139 new_data_table = pd.read_csv(self.io_dict["in"]["input_dataset_path"], header=None, sep="\\s+|;|:|,|\t", engine="python", skiprows=skiprows, names=labels)
140 else:
141 if vars_obj['type'] != 'recurrent':
142 new_data_table = pd.DataFrame(data=get_list_of_predictors(self.predictions), columns=get_keys_of_predictors(self.predictions))
143 else:
144 new_data_table = pd.DataFrame(data=self.predictions, columns=get_num_cols(vars_obj['window_size']))
146 # prediction
147 if vars_obj['type'] != 'recurrent':
148 # classification or regression
150 # new_data_table = pd.DataFrame(data=get_list_of_predictors(self.predictions),columns=get_keys_of_predictors(self.predictions))
151 new_data = new_data_table
152 if vars_obj['scale']:
153 new_data = scale(new_data)
155 predictions = new_model.predict(new_data)
156 predictions = np.around(predictions, decimals=2)
158 clss = ''
159 # if predictions.shape[1] > 1:
160 if vars_obj['type'] == 'classification':
161 # classification
162 pr = tuple(map(tuple, predictions))
163 clss = ' (' + ', '.join(str(x) for x in vars_obj['vs']) + ')'
164 else:
165 # regression
166 pr = np.squeeze(np.asarray(predictions))
168 new_data_table[getTargetValue(vars_obj['target']) + clss] = pr
170 else:
171 # recurrent
173 # new_data_table = pd.DataFrame(data=self.predictions, columns=get_num_cols(vars_obj['window_size']))
174 predictions = []
176 for r in self.predictions:
177 row = np.asarray(r).reshape((1, vars_obj['window_size'], 1))
179 pred = new_model.predict(row)
180 pred = np.around(pred, decimals=2)
182 predictions.append(pred[0][0])
184 # pd.set_option('display.float_format', lambda x: '%.2f' % x)
185 new_data_table["predictions"] = predictions
187 fu.log('Predicting results\n\nPREDICTION RESULTS\n\n%s\n' % new_data_table, self.out_log, self.global_log)
188 fu.log('Saving results to %s' % self.io_dict["out"]["output_results_path"], self.out_log, self.global_log)
189 new_data_table.to_csv(self.io_dict["out"]["output_results_path"], index=False, header=True, float_format='%.3f')
191 # Copy files to host
192 self.copy_to_host()
194 self.tmp_files.extend([
195 self.stage_io_dict.get("unique_dir")
196 ])
197 self.remove_tmp_files()
199 self.check_arguments(output_files_created=True, raise_exception=False)
201 return 0
204def neural_network_predict(input_model_path: str, output_results_path: str, input_dataset_path: str = None, properties: dict = None, **kwargs) -> int:
205 """Execute the :class:`PredictNeuralNetwork <neural_networks.neural_network_predict.PredictNeuralNetwork>` class and
206 execute the :meth:`launch() <neural_networks.neural_network_predict.PredictNeuralNetwork.launch>` method."""
208 return PredictNeuralNetwork(input_model_path=input_model_path,
209 output_results_path=output_results_path,
210 input_dataset_path=input_dataset_path,
211 properties=properties, **kwargs).launch()
214def main():
215 """Command line execution of this building block. Please check the command line documentation."""
216 parser = argparse.ArgumentParser(description="Makes predictions from an input dataset and a given classification model.", formatter_class=lambda prog: argparse.RawTextHelpFormatter(prog, width=99999))
217 parser.add_argument('--config', required=False, help='Configuration file')
219 # Specific args of each building block
220 required_args = parser.add_argument_group('required arguments')
221 required_args.add_argument('--input_model_path', required=True, help='Path to the input model. Accepted formats: h5.')
222 required_args.add_argument('--output_results_path', required=True, help='Path to the output results file. Accepted formats: csv.')
223 parser.add_argument('--input_dataset_path', required=False, help='Path to the dataset to predict. Accepted formats: csv.')
225 args = parser.parse_args()
226 args.config = args.config or "{}"
227 properties = settings.ConfReader(config=args.config).get_prop_dic()
229 # Specific call of each building block
230 neural_network_predict(input_model_path=args.input_model_path,
231 output_results_path=args.output_results_path,
232 input_dataset_path=args.input_dataset_path,
233 properties=properties)
236if __name__ == '__main__':
237 main()