def test_fit_1():
"""
This function tests the first way of fitting the descriptor: the data is passed by first creating compounds and then
the descriptors are created from the compounds.
"""
test_dir = os.path.dirname(os.path.realpath(__file__))
filenames = glob.glob(test_dir + "/CN_isobutane/*.xyz")
energies = np.loadtxt(test_dir + '/CN_isobutane/prop_kjmol_training.txt',
usecols=[1])
filenames.sort()
estimator = ARMP(representation="acsf")
estimator.generate_compounds(filenames[:50])
estimator.set_properties(energies[:50])
estimator.generate_representation()
idx = np.arange(0, 50)
estimator.fit(idx)
"acut": 5,
"zeta": 220.127,
"eta": 30.8065
}
estimator = ARMP(iterations=6000,
representation_name='acsf',
representation_params=acsf_params,
l1_reg=0.0,
l2_reg=0.0,
scoring_function="rmse",
tensorboard=False,
store_frequency=10,
learning_rate=0.075)
estimator.set_properties(energies[:100])
estimator.generate_compounds(filenames[:100])
estimator.generate_representation(method="tf")
print(estimator.representation.shape)
idx = list(range(100))
idx_train, idx_test = modsel.train_test_split(idx,
test_size=0,
random_state=42,
shuffle=True)
estimator.fit(idx_train)
score = estimator.score(idx_train)
print("The RMSE is %s kcal/mol." % (str(score)))
from qml.aglaia.aglaia import ARMP
import glob
import numpy as np
from sklearn import model_selection as modsel
test_dir = "/Volumes/Transcend/repositories/my_qml_fork/qml/test/"
filenames = glob.glob(test_dir + "/qm7/*.xyz")
energies = np.loadtxt(test_dir + '/data/hof_qm7.txt', usecols=[1])
filenames.sort()
n_samples = 500
estimator = ARMP(representation_name="acsf", iterations=100)
estimator.generate_compounds(filenames[:n_samples])
estimator.set_properties(energies[:n_samples])
estimator.generate_representation(method="fortran")
idx = np.arange(0, n_samples)
idx_train, idx_test = modsel.train_test_split(idx,
random_state=42,
shuffle=True,
test_size=0.1)
estimator.fit(idx_train)
estimator.score(idx_train)
import numpy as np
import os
## ------------- ** Loading the data ** ---------------
current_dir = os.path.dirname(os.path.realpath(__file__))
filenames = glob.glob(current_dir + '/../test/CN_isobutane/*.xyz')
energies = np.loadtxt(current_dir + '/../test/CN_isobutane/prop_kjmol_training.txt', usecols=[1])
filenames.sort()
## ------------- ** Setting up the estimator ** ---------------
estimator = ARMP(iterations=10, representation='acsf', representation_params={"radial_rs": np.arange(0, 10, 1), "angular_rs": np.arange(0.5, 10.5, 1),
"theta_s": np.arange(0, 5, 1)}, tensorboard=False)
estimator.generate_compounds(filenames)
estimator.set_properties(energies)
estimator.generate_representation()
## ------------- ** Fitting to the data ** ---------------
idx = np.arange(0,100)
estimator.fit(idx)
## ------------- ** Predicting and scoring ** ---------------
score = estimator.score(idx)