# Applicability Domain (inside: +1, outside: -1)
iappd = 1
if (iappd == 1):
y_appd = ad_knn(X_train, X_test)
else:
y_appd = ad_ocsvm(X_train, X_test)
data = []
for i in range(len(X_test)):
temp = (f_test[i], int(X_test[i][0]), int(y_pred[i]), y_appd[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))
#%%
niter = 10
if (True):
dcv_rgr(X_train, y_train, model, param_grid, niter)
y_randamization_rgr(X_train, y_train, model, param_grid, niter)
# print(X_train[:10])
print('{:.2f} seconds '.format(time() - start))
X_test = scaler.transform(X_test)
model = Ridge()
range_a = 0.01 * np.arange(1, 71, dtype=int)
param_grid = [{'alpha': range_a}]
cv = ShuffleSplit(n_splits=5, test_size=0.2)
cv = KFold(n_splits=5, shuffle=True)
gscv = GridSearchCV(model, param_grid, cv=cv)
gscv.fit(X_train, y_train)
print_gscv_score_rgr(gscv, X_train, X_test, y_train, y_test, cv)
# Predicted y
y_pred = gscv.predict(X_test)
# Applicability Domain (inside: +1, outside: -1)
y_appd = ad_knn(X_train, X_test)
results = np.c_[y_pred, y_test, y_appd]
columns = ['predicted y', 'observed y', 'AD']
df = pd.DataFrame(results, columns=columns)
# print(df[df.AD == 1])
print(df)
if (False):
dcv_rgr(X, y, model, param_grid, 10)
print('{:.2f} seconds '.format(time() - start))
# Applicability Domain (inside: +1, outside: -1)
y_appd = ad_knn(X_train, X_test)
data = []
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]), y_appd[i])
data.append(temp)
properties = ['formula', 'P', 'Tc', 'AD']
df = pd.DataFrame(data, columns=properties)
df.sort_values('Tc', ascending=False, inplace=True)
output = 'test2_Tc_kNN_AD_DCV.csv'
# 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))
if (True):
param_grid = [{'n_neighbors': range_k}]
dcv_rgr(X_train, y_train, model, param_grid, 10)
print('{:.2f} seconds '.format(time() - start))
y_appd = ad_knn(X, X_pred)
elif(iappd == 2):
y_appd = ad_ocsvm(X, X_pred)
else:
y_appd = ad_knn_list(X, X_pred, 10)
data = []
for i in range(len(X_pred)):
# temp = (f_pred[i], int(P_pred[i]), int(y_pred[i]), int(y_pred_db[i]), y_appd[i])
temp = (f_pred[i], int(P_pred[i]), int(y_pred[i]), int(y_pred_db[i]))
data.append(temp)
# properties=['formula','P', 'Tc(pred)', 'Tc(DB)','AD']
properties=['formula','P', 'Tc(pred)', 'Tc(DB)']
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)
df.to_csv(output, index=False)
print('Predicted Tc is written in file {}'.format(output))
#%%
niter=10
if(False):
dcv_rgr(X, y, model, param_grid, niter)
y_randamization_rgr(X, y, model, param_grid, niter)
print('{:.2f} seconds '.format(time() - start))
