def _get_dl(self, s):
if self.dataset == "opportunity":
from filternet.datasets.opportunity import get_x_y_contig
elif self.dataset == "smartphone_hapt":
from filternet.datasets.smartphone_hapt import get_x_y_contig
elif self.dataset == "har":
from filternet.datasets.har import get_x_y_contig
elif self.dataset == "intention_recognition":
from filternet.datasets.intention_recognition import get_x_y_contig
else:
raise ValueError(f"Unknown dataset {self.dataset}")
kwargs = {}
if self.y_cols:
kwargs["y_cols"] = self.y_cols
if self.sensor_subset:
kwargs["sensor_subset"] = self.sensor_subset
Xc, ycs, data_spec = get_x_y_contig(s, **kwargs)
if s == "train":
# Training shuffles, and we set epoch size to length of the dataset. We can set train_step as
# small as we want to get more windows; we'll only run len(Sc)/win_len of them in each training
# epoch.
self.epoch_iters = int(len(Xc) / self.decimation)
X, ys = sliding_window_x_y(
Xc, ycs, win_len=self.win_len, step=self.train_step, shuffle=False
)
# Set the overall data spec using the training set,
# and modify later if more info is needed.
self.data_spec = data_spec
else:
# Val and test data are not shuffled.
# Each point is inferred ~twice b/c step = win_len/2
X, ys = sliding_window_x_y(
Xc,
ycs,
win_len=self.win_len,
step=int(self.win_len / 2),
shuffle=False, # Cannot be true with windows
)
dl = DataLoader(
TensorDataset(torch.Tensor(X), *[torch.Tensor(y).long() for y in ys]),
batch_size=self.batch_size,
shuffle=True if s == "train" else False,
)
return dl
def x_y_dict():
wl = 64
xys = {}
for which_set in ["train", "val", "test"]:
Xc, ycs, data_spec = opp.get_x_y_contig(which_set)
X, ys = sliding_window_x_y(Xc, ycs, win_len=wl)
assert X.shape[1] == 113
assert X.shape[2] == wl
assert ys[0].shape[1] == wl
xys["X_" + which_set] = torch.Tensor(X)
xys["ys_" + which_set] = [torch.Tensor(y).long() for y in ys]
xys["win_len"] = wl
return xys
def test_get_x_y(dfs_dict):
lens = {}
for which_set in ["train", "train+val", "val", "test"]:
Xc, ycs, data_spec = ds.get_x_y_contig(which_set, dfs_dict=dfs_dict)
wl = 128
X, ys = sliding_window_x_y(Xc, ycs, win_len=wl)
assert X.shape[1] == data_spec["input_channels"]
assert X.shape[2] == wl
for y in ys:
assert y.shape[1] == wl
lens[which_set] = len(Xc)
assert len(data_spec["input_features"]) == data_spec["input_channels"]
assert data_spec["n_outputs"] == len(data_spec["output_spec"])
for o in data_spec["output_spec"]:
assert "name" in o
assert o["num_classes"] == len(o["classes"])
assert "dataset_name" in data_spec
assert lens["train"] + lens["val"] == lens["train+val"]