df['log_CT_CS'] = np.log(df['CT_CS'])
df['log_CT_MCR'] = np.log(df['CT_MCR'])
df['LMP_Model'] = df.apply(lambda x:
1e-3 * x['CT_Temp'] * (np.log(x['CT_RT']) + 25), axis=1)
features = [i for i in df.columns if i not in ['CT_RT', 'CT_Temp',
'ID', 'CT_CS', 'LMP_Model', 'CT_MCR']]
df = df[df['CT_RT'] < 200000]
X = df[features].to_numpy(np.float32)
y = df['LMP_Model'].to_numpy(np.float32)
y2 = df[['ID', 'CT_RT', 'CT_Temp', 'CT_CS']].values.tolist()
pdata = ProcessData(X=X, y=y, y2=y2, features=features)
pdata.clean_data()
data = pdata.get_data()
scale = pdata.scale
del pdata
CT_RT = np.array([i[1] for i in data['y2']])
CT_Temp = np.array([i[2] for i in data['y2']])
CT_CS = np.array([i[3] for i in data['y2']])
ID = [i[0] for i in data['y2']]
C = np.array([25 for i in ID])
skreg = SKREG(X=data['X'],
y=data['y'],
estimator="LR",
validation="3-Fold",
CT_Temp=CT_Temp,
CT_RT=CT_RT,
ID = [1, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38,
43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 58, 59, 60,
61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76,
77, 78, 79, 82]
ID = ['9Cr-{}'.format(str(i).zfill(3)) for i in ID]
df = df[df.ID.isin(ID)]
df['log_CT_CS'] = np.log(df['CT_CS'])
X = df[[i for i in df.columns if i not in ['ID', 'CT_RT',
'CT_Temp', 'CT_CS']]].to_numpy(dtype=np.float)
df['LMP'] = df.apply(lambda x: 1e-3*(x['CT_Temp'])*(np.log(x['CT_RT'])
+data[x['ID']]['C']), axis=1)
y = df['LMP'].to_numpy()
dprocess = ProcessData(X=X, y=y, metadata=[i for i in df.columns
if i not in ['ID', 'CT_RT', 'CT_Temp', 'CT_CS']])
dprocess.clean_data()
X, y, metadata = dprocess.get_data()
del dprocess
df = pd.DataFrame(X, columns=metadata)
df['LMP'] = y
#Initialize the model
bframe = BayesFrame(df=df, target="LMP", val_scheme='5-Fold',
bic_scheme="per_n", model_scheme=["selection"])
#Print the best model
print(bframe.zoo)
np.save('best_model.npy', bframe.zoo)
