def make_pred_data_file_from(df):
tc = 0.0
yx = []
zatom2 = 1 # atomic number Z : 1
atom2 = periodic_table.get_el_sp(zatom2) # atom2 : H
for zatom1 in trange(3, 5, desc='1st loop'):
# for zatom1 in trange(3, 86, desc='1st loop'):
atom1 = periodic_table.get_el_sp(zatom1)
if (not atom1.is_noble_gas):
for natom1 in trange(1, 11, desc='2nd loop'):
for natom2 in trange(1, 11, desc='3rd loop'):
for p in trange(50, 550, 50, desc='4th loop'):
str_mat = str(atom1) + str(natom1) + str(atom2) + str(
natom2)
material = Composition(str_mat)
temp = [material.reduced_formula, tc, float(p)]
temp.extend(get_parameters(material.reduced_formula))
yx.append(temp[:])
properties = df.columns.values
df_test = pd.DataFrame(yx, columns=properties)
# material.reduced_formulaにより重複行が発生したため、drop_duplicatesで削除する
df_test = df_test.drop_duplicates()
df_test.to_csv(pred_dat_f)
return df_test
df['Tc'] = df[' Tc [K]'].apply(float)
df['P'] = df[' P [GPa]'].apply(float)
df['list'] = df['formula'].apply(get_parameters)
df['formula'] = df['formula'].apply(lambda x: x.strip())
for i in range(len(get_parameters('H3S'))):
name = 'prm' + str(i)
df[name] = df['list'].apply(lambda x: x[i])
df = df.drop([' Tc [K]', ' P [GPa]', 'list'], axis=1)
df.to_csv("tc_train.csv")
print(df.head(5))
tc = 0.0
yx = []
zatom2 = 1
atom2 = periodic_table.get_el_sp(zatom2)
for zatom1 in range(3, 10):
atom1 = periodic_table.get_el_sp(zatom1)
if (not atom1.is_noble_gas):
for natom1 in range(1, 6):
for natom2 in range(1, 6):
for ip in range(100, 500, 100):
str_mat = str(atom1) + str(natom1) + str(atom2) + str(
natom2)
material = Composition(str_mat)
temp = [material.reduced_formula, tc, float(ip)]
temp.extend(get_parameters(material.reduced_formula))
yx.append(temp[:])
properties = df.columns.values
df_test = pd.DataFrame(yx, columns=properties)
# visualize
fig = yyplot(y_train, y_pred)
#%%
# Novelty detection by One Class SVM with optimized hyperparameter
clf = OneClassSVM(nu=0.003, kernel=gscv.best_params_['model__kernel'],
gamma=gscv.best_params_['model__gamma'])
clf.fit(X_train)
y_pred = gscv.predict(X_test) # predicted y
reliability = clf.predict(X_test) # outliers = -1
data = []
output = 'test2.csv'
for i in range(len(X_test)):
satom1 = periodic_table.get_el_sp(int(X_test[i][0]))
satom2 = periodic_table.get_el_sp(int(X_test[i][1]))
natom1 = int(X_test[i][2])
natom2 = int(X_test[i][3])
str_mat = str(satom1) + str(natom1) + str(satom2) + str(natom2)
formula = Composition(str_mat).reduced_formula
temp = (formula, int(X_test[i][4]), int(y_pred[i]), reliability[i])
data.append(temp)
properties=['formula','P', 'Tc', 'AD']
df = pd.DataFrame(data, columns=properties)
df.sort_values('Tc', ascending=False, inplace=True)
df.to_csv(output, index=False)
#df_in_ = df[df.AD == 1]
#df_in_.to_csv(output, index=False)
print('Predicted Tc is written in file {}'.format(output))
features.append(tc)
features.extend(atomicNo)
features.extend(natom)
features.append(pressure)
yx.append(features[:])
yx = np.array(yx)
y_train = yx[:, 0]
X_train = yx[:, 1:]
ltest = False
if (ltest):
X = X_train
print(X[0][:4])
atom1 = periodic_table.get_el_sp(X[0][0])
atom2 = periodic_table.get_el_sp(X[0][1])
str_mat = str(atom1) + str(X[0][2]) + str(atom2) + str(X[0][3])
material = Composition(str_mat)
print(type(material.reduced_formula))
for i in range(1, 2):
print(periodic_table.get_el_sp(i))
properties = ['Tc', 'Z1', 'Z2', 'N1', 'N2', 'P']
df = pd.DataFrame(yx, columns=properties)
df.to_csv("tc_train.csv")
tc = 0.0
yx = []
zatom2 = 1
atom2 = periodic_table.get_el_sp(zatom2)
