def load_dataset_chbmit(path_save: str,
n_samples=200,
random_state=42,
pre_load=False) -> [array]:
"""Read the chbmit database, and return data and class.
Split the dataset to the appropriate size.
Parameters
----------
random_state : int
n_samples: int
path_save: str
Returns
-------
X : array-like, shape (n_samples, n_features)
Data vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like, shape (n_samples,)
Target values.
"""
data_frame_non = []
data_frame_seiz = []
path_dataset = join(path_save, "as_dataset")
name_dataset_non = join(path_dataset, "data_frame_non.parquet")
name_dataset_seiz = join(path_dataset, "data_frame_seiz.parquet")
if not check_exist(path_save, "as_dataset") and not pre_load:
print("Loading the files to create dataset")
for person_id in range(1, 11):
print("Loading Patients nº {}".format(person_id))
pat = Patient(person_id, path_save)
non_epoch_array = list(map(split_4096, pat.get_non_seizures()))
data_frame_non.append(concatenate(non_epoch_array))
s_clips = pat.get_seizure_clips()
if s_clips != []:
seiz_epoch = list(filter_empty(list(map(split_4096, s_clips))))
data_frame_seiz.append(concatenate(seiz_epoch))
data_frame_non = DataFrame(concatenate(data_frame_non))
data_frame_non["class"] = [0] * len(data_frame_non)
data_frame_non.columns = data_frame_non.columns.astype(str)
data_frame_non.to_parquet(name_dataset_non, engine="pyarrow")
data_frame_seiz = DataFrame(concatenate(data_frame_seiz))
data_frame_seiz["class"] = [1] * len(data_frame_seiz)
data_frame_seiz.columns = data_frame_seiz.columns.astype(str)
data_frame_seiz.to_parquet(name_dataset_seiz, engine="pyarrow")
else:
if not pre_load:
print("Reading as dataframe")
data_frame_non = read_parquet(name_dataset_non, engine="pyarrow")
data_frame_seiz = read_parquet(name_dataset_seiz, engine="pyarrow")
else:
data_frame = read_parquet(path_save + "sampled_dataset.parquet",
engine="pyarrow")
return data_frame.drop("class",
1).to_numpy(), data_frame["class"].values
sample_non = data_frame_non.sample(n=n_samples, random_state=random_state)
sample_seiz = data_frame_seiz.sample(n=n_samples,
random_state=random_state)
data_frame = sample_non.append(sample_seiz)
data_frame.columns = data_frame.columns.astype(str)
data_frame.to_parquet(path_save + "sampled_dataset.parquet",
engine="pyarrow")
return data_frame.drop("class", 1).to_numpy(), data_frame["class"].values
