1_ann_data.py

import simbench as sb
grid_code = "1-HV-urban--0-sw"
net = sb.get_simbench_net(grid_code)
profiles = sb.get_absolute_values(net, profiles_instead_of_study_cases=True)

sgen_p = profiles[("sgen", "p_mw")]
load_p = profiles[("load", "p_mw")]
load_q = profiles[("load", "q_mvar")]

import pandas as pd
X = pd.concat([sgen_p, load_p, load_q], axis=1)
y = pd.read_json("./res_line/loading_percent.json")

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.1)

from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

import numpy as np
np.save("X_train.npy", X_train)
np.save("X_test.npy", X_test)
np.save("y_train.npy", y_train)
np.save("y_test.npy", y_test)

print(X.shape)
print(X_train.shape)
print(X_test.shape)