def get_data(normalize_y, sample_size):
radius = 3
max_neighbor_num = 10
training = 0.9
test = 0.1
df = pd.read_csv("./Data/metal-alloy-db.v2/00Total_DB.csv")
# df = df.sample(n=len(df))
df = df.sample(n=sample_size)
cifs = "./Data/metal-alloy-db.v2/" + df['DBname'] + ".cif"
structures = [IStructure.from_file(cif) for cif in cifs]
encoded_structures = [
structure_encoder(structure, radius, max_neighbor_num)
for structure in structures
]
x_data = np.array(encoded_structures)
formation_energy = df['FormationEnergy']
if normalize_y:
mean = formation_energy.mean()
std = formation_energy.std()
norm_form_energy = (df['FormationEnergy'] - mean) / std
def norm_back(val, mean, std):
return val * std + mean
y_data = [[val] for val in norm_form_energy]
else:
y_data = [[val] for val in formation_energy]
y_data = np.array(y_data)
total = len(df)
train = int(float(total) * training)
test = int(float(total) * test)
x_train = x_data[:train]
y_train = y_data[:train]
x_test = x_data[train:train + test]
y_test = y_data[train:train + test]
return x_train, y_train, x_test, y_test
if __name__ == "__main__":
radius = 3
max_neighbor_num = 10
training = 0.9
test = 0.1
df = pd.read_csv("./Data/metal-alloy-db.v1/00Total_DB.csv")
# df = df.sample(n=len(df))
df = df.sample(n=500)
cifs = "./Data/metal-alloy-db.v1/" + df['DBname'] + ".cif"
structures = [IStructure.from_file(cif) for cif in cifs]
encoded_structures = [structure_encoder(structure, radius, max_neighbor_num) for structure in structures]
x_data = np.array(encoded_structures)
x_data = np.expand_dims(x_data, axis=4)
formation_energy = df['FormationEnergy']
y_normalization = False
if y_normalization:
mean = formation_energy.mean()
std = formation_energy.std()
norm_form_energy = (df['FormationEnergy'] - mean) / std
def norm_back(val, mean, std):
return val * std + mean
y_data = [[val] for val in norm_form_energy]
else:
y_data = [[val] for val in formation_energy]
'''
formation_energy = df['FormationEnergy']
mean = formation_energy.mean()
std = formation_energy.std()
norm_form_energy = (df['FormationEnergy'] - mean) / std
def norm_back(val, mean, std):
return val * std + mean
y_data = [[val] for val in norm_form_energy]
y_data = np.array(y_data)
print("Done")
encoded_structures = [
structure_encoder(structure, radius, max_neighbor_num)
for structure in structures
]
x_atom_fea = []
x_nbr_fea_idx = []
x_nbr_fea = []
for i, each_structure in enumerate(encoded_structures):
x_atom_fea.append(each_structure[0])
x_nbr_fea_idx.append(each_structure[1])
x_nbr_fea.append(each_structure[2])
x_atom_fea = np.array(x_atom_fea, dtype='float32')
x_nbr_fea_idx = np.array(x_nbr_fea_idx, dtype='float32')
x_nbr_fea = np.array(x_nbr_fea, dtype='float32')
atom_fea = tf.placeholder(tf.float32, [None, None, 92])