def train(validate, dset=None):
sv = Server()
sv.load_data('cn_model_v1.0.csv')
sv.train(validate=validate, selection_set=dset)
sv.use(dset=dset)
sv.errors('rmse', 'med_abs_error', 'mean_abs_error', 'r2', dset=dset)
def create_project():
sv = Server()
sv.load_data('cn_model_v1.0.csv')
sv.create_project('use_project', num_pools=2, num_candidates=2)
sv.train()
sv.save_project()
def predict(input_txt,
results_file,
prj_file,
form='name',
temp_db='_new_mols.csv',
clean_up=True):
'''Predicts values for new data using pre-existing .prj file
Args:
input_txt (str): path to .txt file containing either molecule names or
SMILES strings
results_file (str): path to results file generated by this function
prj_file (str): path to pre-existing .prj file
form (str): `name` if supplying molecule names, `SMILES` if supplying
SMILES strings
temp_db (str): path to temporary database generated by this function
clean_up (bool): if True, cleans up all files generated during this
function (except for input/results files)
'''
logger.stream_level = 'disable'
sv = Server(prj_file=prj_file)
input_names = sv._df.input_names
create_db(input_txt, temp_db, form=form, clean_up=clean_up)
new_data = DataFrame(temp_db)
new_data.set_inputs(input_names)
sv._df = new_data
sv.use(output_filename=results_file)
if clean_up:
remove(temp_db)
rmtree(prj_file.replace('.prj', ''))
def test_load_data(self):
print('\nUNIT TEST: Server.load_data')
sv = Server()
sv.load_data(DB_LOC)
self.assertEqual(len(sv._df), 482)
self.assertEqual(type(sv._sets), PackagedData)
remove('config.yml')
def main():
logger.stream_level = 'debug'
sv = Server(num_processes=4)
sv.load_data('../kv_model_v1.0.csv')
sv.create_project('kinetic_viscosity', num_pools=5, num_candidates=25)
sv.train(shuffle='train',
split=[0.7, 0.2, 0.1],
validate=True,
selection_set='test')
sv.save_project(del_candidates=True)
def test_use_project(self):
print('\nUNIT TEST: Server.use')
sv = Server()
sv.load_data(DB_LOC, random=True, split=[0.7, 0.2, 0.1])
sv.create_project('test_project', 2, 2)
sv._vars['epochs'] = 100
sv.train()
results = sv.use()
self.assertEqual(len(results), len(sv._df))
remove('config.yml')
rmtree('test_project')
def test_create_project(self):
print('\nUNIT TEST: Server.create_project')
sv = Server()
sv.create_project('test_project', 3, 5)
for pool in range(3):
for candidate in range(5):
self.assertTrue(
isdir(
join('test_project', 'pool_{}'.format(pool),
'candidate_{}'.format(candidate))))
remove('config.yml')
rmtree('test_project')
def test_init(self):
print('\nUNIT TEST: Server init')
sv = Server()
self.assertTrue(exists('config.yml'))
self.assertEqual(sv._vars, default_config())
remove('config.yml')
def test_server_limit(self):
print('\nUNIT TEST: limit_rforest (Server)')
sv = Server()
sv.load_data(DB_LOC)
sv.limit_inputs(2, output_filename='cn_limited.csv')
self.assertEqual(len(sv._df._input_names), 2)
self.assertEqual(len(sv._sets.learn_x[0]), 2)
sv.load_data('cn_limited.csv')
self.assertEqual(len(sv._df._input_names), 2)
self.assertEqual(len(sv._sets.learn_x[0]), 2)
remove('cn_limited.csv')
remove('config.yml')
def main():
logger.stream_level = 'info'
sv = Server(prj_file='kinetic_viscosity.prj')
train_exp = []
train_exp.extend(y for y in sv._sets.learn_y)
train_exp.extend(y for y in sv._sets.valid_y)
train_pred = sv.use(dset='train')
train_errors = sv.errors('rmse', 'r2', dset='train')
test_exp = sv._sets.test_y
test_pred = sv.use(dset='test')
test_errors = sv.errors('rmse', 'r2', dset='test')
kv_plot = ParityPlot(
title='Predicted vs. Experimental Kinematic Viscosity',
x_label='Experimental KV',
y_label='Predicted KV')
kv_plot.add_series(train_exp,
train_pred,
name='Training Set',
color='blue')
kv_plot.add_series(test_exp, test_pred, name='Test Set', color='red')
kv_plot.add_error_bars(test_errors['rmse'], label='Test RMSE')
kv_plot._add_label('Test R-Squared', test_errors['r2'])
kv_plot._add_label('Train RMSE', train_errors['rmse'])
kv_plot._add_label('Train R-Squared', train_errors['r2'])
kv_plot.save('../kv_parity_plot.png')
def test_train_project(self):
print('\nUNIT TEST: Server.train')
sv = Server()
sv.load_data(DB_LOC, random=True, split=[0.7, 0.2, 0.1])
sv.create_project('test_project', 2, 2)
sv._vars['epochs'] = 100
sv.train()
for pool in range(2):
self.assertTrue(
exists(join('test_project', 'pool_{}'.format(pool),
'model.h5')))
for candidate in range(2):
self.assertTrue(
exists(
join('test_project', 'pool_{}'.format(pool),
'candidate_{}'.format(candidate), 'model.h5')))
remove('config.yml')
rmtree('test_project')
def test_multiprocessing_train(self):
print('\nUNIT TEST: multiprocessing training')
sv = Server(num_processes=8)
sv.load_data(DB_LOC)
sv.create_project('test_project', 2, 4)
sv._vars['epochs'] = 100
sv.train()
for pool in range(2):
self.assertTrue(
exists(join('test_project', 'pool_{}'.format(pool),
'model.h5')))
for candidate in range(4):
self.assertTrue(
exists(
join('test_project', 'pool_{}'.format(pool),
'candidate_{}'.format(candidate), 'model.h5')))
remove('config.yml')
rmtree('test_project')
def main():
logger.stream_level = 'debug'
sv = Server(num_processes=4)
sv.load_data('../kv_model_v1.0.csv')
sv.tune_hyperparameters(20,
20,
shuffle='train',
split=[0.7, 0.2, 0.1],
eval_set='test')
def tune(num_processes,
shuffle=None,
split=[0.7, 0.2, 0.1],
validate=True,
eval_set=None,
eval_fn='rmse'):
logger.stream_level = 'debug'
sv = Server(num_processes=num_processes)
sv.load_data('cn_model_v1.0.csv', random=True, split=split)
sv.tune_hyperparameters(2,
2,
shuffle=shuffle,
split=split,
validate=validate,
eval_set=eval_set,
eval_fn=eval_fn)
def retrain():
sv = Server(prj_file='_training_test.prj')
sv.load_data('cn_model_v1.0.csv')
sv.train(retrain=True)
sv.save_project(del_candidates=True)
def train_project(validate,
shuffle,
split=[0.7, 0.2, 0.1],
num_processes=1,
dset=None,
sel_fn='rmse',
output_filename=None):
sv = Server(num_processes=num_processes)
sv.load_data('cn_model_v1.0.csv')
sv.create_project('_training_test', num_pools=2, num_candidates=2)
sv.train(shuffle=shuffle,
split=split,
selection_set=dset,
selection_fn=sel_fn,
validate=validate)
sv.use(dset=dset, output_filename=output_filename)
sv.errors('rmse', 'med_abs_error', 'mean_abs_error', 'r2')
sv.save_project()
def create_model(prop_abvr: str, smiles: list = None, targets: list = None,
db_name: str = None, qspr_backend: str = 'padel',
create_plots: bool = True, data_split: list = [0.7, 0.2, 0.1],
log_level: str = 'info', log_to_file: bool = True,
num_processes: int = 1):
''' create_model: ECRL's database/model creation workflow for all
publications
Args:
prop_abvr (str): abbreviation for the property name (e.g. CN)
smiles (list): if supplied with targets, creates a new database
targets (list): if supplied with smiles, creates a new database
db_name (str): you may supply an existing ECNet-formatted database
qspr_backend (str): if creating new database, generation software to
use (`padel`, `alvadesc`)
create_plots (bool): if True, creates plots for median absolute error
vs. number of descriptors as inputs, parity plot for all sets
data_split (list): [learn %, valid %, test %] for all supplied data
log_level (str): `debug`, `info`, `warn`, `error`, `crit`
log_to_file (bool): if True, saves workflow logs to a file in `logs`
directory
num_processes (int): number of concurrent processes to use for various
tasks
'''
# Initialize logging
logger.stream_level = log_level
if log_to_file:
logger.file_level = log_level
# If database not supplied, create database from supplied SMILES, targets
if db_name is None:
if smiles is None or targets is None:
raise ValueError('Must supply SMILES and target values')
db_name = datetime.now().strftime('{}_model_%Y%m%d.csv'.format(
prop_abvr
))
logger.log('info', 'Creating database {}...'.format(db_name),
'WORKFLOW')
create_db(smiles, db_name, targets, prop_abvr, backend=qspr_backend)
logger.log('info', 'Created database {}'.format(db_name), 'WORKFLOW')
# Create database split, each subset has proportionally equal number of
# compounds based on range of experimental/target values
logger.log('info', 'Creating optimal data split...', 'WORKFLOW')
prop_range_from_split(db_name, data_split)
logger.log('info', 'Created optimal data split', 'WORKFLOW')
df = DataFrame(db_name)
df.create_sets()
logger.log('info', '\tLearning set: {}'.format(len(df.learn_set)),
'WORKFLOW')
logger.log('info', '\tValidation set: {}'.format(len(df.valid_set)),
'WORKFLOW')
logger.log('info', '\tTest set: {}'.format(len(df.test_set)), 'WORKFLOW')
# Find optimal number of QSPR input variables
logger.log('info', 'Finding optimal number of inputs...', 'WORKFLOW')
errors, desc = find_optimal_num_inputs(db_name, 'valid', num_processes)
df = DataFrame(db_name)
df.set_inputs(desc)
df.save(db_name.replace('.csv', '_opt.csv'))
logger.log('info', 'Found optimal number of inputs', 'WORKFLOW')
logger.log('info', '\tNumber of inputs: {}'.format(len(df._input_names)),
'WORKFLOW')
# Plot the curve of MAE vs. num. desc. added, if desired
if create_plots:
logger.log('info', 'Creating plot of MAE vs. descriptors...',
'WORKFLOW')
num_add = [e[0] for e in errors]
maes = [e[1] for e in errors]
opt_num = len(desc)
plt.clf()
plt.rcParams['font.family'] = 'Times New Roman'
plt.plot(num_add, maes, c='blue')
plt.axvline(x=opt_num, c='red', linestyle='--')
plt.xlabel('Number of Descriptors as ANN Input Variables')
plt.ylabel('Median Absolute Error of {} Predictions'.format(prop_abvr))
plt.savefig(db_name.replace('.csv', '_desc_curve.png'))
logger.log('info', 'Created plot of MAE vs. descriptors', 'WORKFLOW')
# Tune ANN hyperparameters according to validation set performance
logger.log('info', 'Tuning ANN hyperparameters...', 'WORKFLOW')
config = default_config()
config = tune_hyperparameters(df, config, 25, 10, num_processes,
shuffle='train', split=[0.7, 0.2, 0.1],
validate=True, eval_set='valid',
eval_fn='med_abs_error', epochs=300)
config['epochs'] = default_config()['epochs']
config_filename = db_name.replace('.csv', '.yml')
save_config(config, config_filename)
logger.log('info', 'Tuned ANN hyperparameters', 'WORKFLOW')
logger.log('info', '\tLearning rate: {}'.format(config['learning_rate']),
'WORKFLOW')
logger.log('info', '\tLR decay: {}'.format(config['decay']), 'WORKFLOW')
logger.log('info', '\tBatch size: {}'.format(config['batch_size']),
'WORKFLOW')
logger.log('info', '\tPatience: {}'.format(config['patience']), 'WORKFLOW')
logger.log('info', '\tHidden layers: {}'.format(config['hidden_layers']),
'WORKFLOW')
# Create Model
logger.log('info', 'Generating ANN...', 'WORKFLOW')
sv = Server(db_name.replace('.csv', '.yml'), num_processes=num_processes)
sv.load_data(db_name.replace('.csv', '_opt.csv'))
sv.create_project(db_name.replace('.csv', ''), 5, 75)
sv.train(validate=True, selection_set='valid', shuffle='train',
split=[0.7, 0.2, 0.1], selection_fn='med_abs_error')
logger.log('info', 'ANN Generated', 'WORKFLOW')
logger.log('info', 'Measuring ANN performance...', 'WORKFLOW')
preds_test = sv.use(dset='test')
preds_train = sv.use(dset='train')
test_errors = sv.errors('r2', 'med_abs_error', dset='test')
train_errors = sv.errors('r2', 'med_abs_error', dset='train')
logger.log('info', 'Measured ANN performance', 'WORKFLOW')
logger.log('info', '\tTraining set:\t R2: {}\t MAE: {}'.format(
train_errors['r2'], train_errors['med_abs_error']), 'WORKFLOW')
logger.log('info', '\tTesting set:\t R2: {}\t MAE: {}'.format(
test_errors['r2'], test_errors['med_abs_error']), 'WORKFLOW')
sv.save_project(del_candidates=True)
if create_plots:
logger.log('info', 'Creating parity plot...', 'WORKFLOW')
plt.clf()
parity_plot = ParityPlot(
'',
'Experimental {} Value'.format(prop_abvr),
'Predicted {} Value'.format(prop_abvr)
)
parity_plot.add_series(concatenate(
(sv._sets.learn_y, sv._sets.valid_y)
), preds_train, 'Training Set', 'blue')
parity_plot.add_series(sv._sets.test_y, preds_test, 'Test Set', 'red')
parity_plot.add_error_bars(test_errors['med_abs_error'], 'Test MAE')
parity_plot._add_label('Test $R^2$', test_errors['r2'])
parity_plot._add_label('Training MAE', train_errors['med_abs_error'])
parity_plot._add_label('Training $R^2$', train_errors['r2'])
parity_plot.save(db_name.replace('.csv', '_parity.png'))
logger.log('info', 'Created parity plot', 'WORKFLOW')
def main():
logger.stream_level = 'debug'
sv = Server()
sv.load_data('cn_model_v1.0.csv')
sv.remove_outliers(output_filename='cn_no_outliers.csv')
def main():
logger.stream_level = 'debug'
sv = Server(prj_file='kinetic_viscosity.prj')
sv.use(dset='test', output_filename='../kv_test_results.csv')
sv.errors('rmse', 'mean_abs_error', 'med_abs_error', 'r2', dset='test')
def test_predict(self):
print('\nUNIT TEST: project.predict')
sv = Server()
sv.load_data('cn_model_v2.0.csv')
sv.create_project('test_project', 1, 1)
sv._vars['epochs'] = 100
sv.train()
sv.save_project()
results = predict(['CCC', 'CCCC'], 'test_project.prj', 'results.csv')
self.assertEqual(len(results), 2)
remove('test_project.prj')
remove('config.yml')
def test_save_project(self):
print('\nUNIT TEST: Server.save_project')
sv = Server()
sv.load_data(DB_LOC, random=True, split=[0.7, 0.2, 0.1])
sv.create_project('test_project', 2, 2)
sv._vars['epochs'] = 100
sv.train()
sv.save_project()
self.assertTrue(exists('test_project.prj'))
self.assertTrue(not isdir('test_project'))
remove('test_project.prj')
remove('config.yml')
def main():
logger.stream_level = 'debug'
sv = Server(num_processes=4)
sv.load_data('../kv_model_v1.0_full.csv')
sv.limit_inputs(15, output_filename='../kv_model_v1.0.csv')
def main(db_name: str):
# Set up logging
logger.stream_level = 'info'
logger.log_dir = db_name.replace('.csv', '') + '_logs'
logger.file_level = 'debug'
# Split database proportionally based on property value
# Proportions are 70% learn, 20% validate, 10% test
prop_range_from_split(db_name, [0.7, 0.2, 0.1])
# Find the optimal number of input variables
# Train (learn + valid) set used for evaluation
n_desc = len(find_optimal_num_inputs(db_name, 'train', _NUM_PROC)[1])
logger.log('info', 'Optimal number of input variables: {}'.format(n_desc))
# Create server object with base config
sv = Server(model_config=db_name.replace('.csv', '.yml'),
num_processes=_NUM_PROC)
# Load data
sv.load_data(db_name)
# Limit input variables to `n_desc` using Train set
# Outputs to relevant database name
sv.limit_inputs(
n_desc, eval_set='train',
output_filename=db_name.replace('.csv', '.{}.csv'.format(n_desc))
)
# Tune hyperparameters (architecture and ADAM)
# 20 employer bees, 10 search cycles
# Evaluation of solutions based on validation set median absolute error
sv.tune_hyperparameters(20, 10, eval_set='valid', eval_fn='med_abs_error')
# Create an ECNet project (saved and recalled later)
# 5 pools with 75 trials/pool, best ANNs selected from each pool
sv.create_project(db_name.replace('.csv', ''), 5, 75)
# Train project
# Select best candidates based on validation set median absolute error
sv.train(validate=True, selection_set='valid',
selection_fn='med_abs_error')
# Obtain learning, validation, testing set median absolute error, r-squared
err_l = sv.errors('med_abs_error', 'r2', dset='learn')
err_v = sv.errors('med_abs_error', 'r2', dset='valid')
err_t = sv.errors('med_abs_error', 'r2', dset='test')
logger.log('info', 'Learning set performance: {}'.format(err_l))
logger.log('info', 'Validation set performance: {}'.format(err_v))
logger.log('info', 'Testing set performance: {}'.format(err_t))
# Save the project, creating a .prj file and removing un-chosen candidates
sv.save_project(del_candidates=True)
def limit(num_processes, output_filename=None):
logger.stream_level = 'info'
sv = Server(num_processes=num_processes)
sv.load_data('cn_model_v1.0.csv')
sv.limit_inputs(3, output_filename=output_filename)
def use_project():
sv = Server(prj_file='use_project.prj')
sv.use('train', output_filename='use_project_train.csv')
sv.use('test', output_filename='use_project_test.csv')