All_files_dataset

Data inputted in the simulation were generated by two Python scripts: "GENERATE_SAMPLES.py" and "GENERATE_RESAMPLING_DATA.py".<br>1. "GENERATE_SAMPLES.py": In this Python script, we aim to generate a) "DataSet_n[N]_p[p].pickle" where N is replaced by 500 or 5000, p is replaced by 2 or 10. This Python object contains: a1. the explicative variables "X", a2. the responses "Y", a3. the knots "knots", a4. the target tail index parameters "gamma0", a5. the k-different ranndom state responses "Yk" with k=1,..,100. To read these data, you should run the following python code (take n=5000 and p=10 for example) import pickle with open('DataSet_n5000_p10.pickle', 'rb') as handle: X = pickle.load(handle) Y = pickle.load(handle) knots = pickle.load(handle) gamma0 = pickle.load(handle) Yk = pickle.load(handle)<br> b) "gridX_p[p].picke" where p is replaced by 2 or 10. This Python object contains: b1. the setting points "gridX" which correspond to (x(1)_(m1),...,x(p)_(mp)) in the paper, b2. "prefactor" corresponds to \Delta(p)x in the paper b3. "gamma0_gridX corresponds to gamma0(gridX) To read these data, you should run the following python code (take p=10 for example) import pickle with open('gridX_p10.pickle', 'rb') as handle: gridX = pickle.load(handle) prefactor = pickle.load(handle) gamma0_gridX = pickle.load(handle)<br>2. "GENERATE_RESAMPLING_DATA.py": In this Python script, we aim to generate: a) "DataSet_Resampling_n[N]_p[p]_w_replacement.pickle" where N is replaced by 500 or 5000, p is replaced by 2 or 10. This Python object contains: a1. the resampling explicative variables "X_resample", a2. the knots "knots", a3. the resampling k-different random state response "Y_resample". To read these data, you should run the following python code (take N=5000 and p=10 for example) import pickle with open('DataSet_Resampling_n5000_p10_w_replacement.pickle', 'rb') as handle: X_resample = pickle.load(handle) ignored = pickle.load(handle) Y_resample = pickle.load(handle)