Skip to content

ENH/TSBAD autodl datasets #41

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Jad-yehya merged 7 commits into from
May 21, 2026
Merged

ENH/TSBAD autodl datasets #41

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
840b23e
Update pre-commit configuration
Jad-yehya May 19, 2026
ba8140e
Merge pull request #2 from benchopt:UPD/pre-commit
Jad-yehya May 19, 2026
b60069f
Merge branch 'benchopt:main' into main
Jad-yehya May 19, 2026
5454c64
Merge branch 'benchopt:main' into main
Jad-yehya May 20, 2026
2dcfeba
Merge branch 'benchopt:main' into main
Jad-yehya May 21, 2026
27908a4
Refactor dataset loading to use fetch_tsb_uad and remove config depen…
Jad-yehya May 21, 2026
929dd5c
Refactor dataset loading to use fetch_tsb_uad and remove config depen…
Jad-yehya May 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions datasets/daphnet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,11 @@
from benchopt import BaseDataset, config
from benchopt import BaseDataset

from pathlib import Path
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

PATH = config.get_data_path("DAPHNET")
from benchmark_utils.download import fetch_tsb_uad


def load_data(db_path, record_ids=None, verbose=False, number=-1):
Expand Down Expand Up @@ -104,6 +104,8 @@ def load_data(db_path, record_ids=None, verbose=False, number=-1):
class Dataset(BaseDataset):
name = "DAPHNET"

requirements = ["pip:pooch"]

parameters = {
# "recordings_id": [["S01R02E0"]],
"recordings_id": [None], # [["S01R02E0"]],
Expand All @@ -118,11 +120,13 @@ class Dataset(BaseDataset):
def get_data(self):
"""Load the DAPHNET dataset."""

path = fetch_tsb_uad("DAPHNET")

# X shape (n_recordings, n_samples)
# y shape (n_recordings, n_samples)
if self.recordings_id in (["all"], "all"):
self.recordings_id = None
X, y_true = load_data(PATH, self.recordings_id, number=self.number)
X, y_true = load_data(path, self.recordings_id, number=self.number)

X_test = X.copy()
y_test = y_true.copy()
Expand Down
10 changes: 7 additions & 3 deletions datasets/ecg.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
from benchopt import BaseDataset, config
from benchopt import BaseDataset

from pathlib import Path
import numpy as np
import pandas as pd

PATH = config.get_data_path("ECG")
from benchmark_utils.download import fetch_tsb_uad


def load_data(db_path, record_ids=None, verbose=False, number=-1):
Expand Down Expand Up @@ -95,6 +95,8 @@ def load_data(db_path, record_ids=None, verbose=False, number=-1):
class Dataset(BaseDataset):
name = "ECG"

requirements = ["pip:pooch"]

parameters = {
"recordings_id": [["1", "2"]],
"debug": [False],
Expand All @@ -103,11 +105,13 @@ class Dataset(BaseDataset):

def get_data(self):
"""Load the MITDB dataset."""
path = fetch_tsb_uad("ECG")

# X shape (n_recordings, n_samples)
# y shape (n_recordings, n_samples)
if self.recordings_id in (["all"], "all"):
self.recordings_id = None
X, y_true = load_data(PATH, self.recordings_id, number=self.number)
X, y_true = load_data(path, self.recordings_id, number=self.number)

X_test = X.copy()
y_test = y_true.copy()
Expand Down
10 changes: 7 additions & 3 deletions datasets/genesis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
from benchopt import BaseDataset, config
from benchopt import BaseDataset

from pathlib import Path
import numpy as np
import pandas as pd

PATH = config.get_data_path("GENESIS")
from benchmark_utils.download import fetch_tsb_uad


def load_data(db_path, record_ids=None, verbose=False):
Expand Down Expand Up @@ -91,6 +91,8 @@ def load_data(db_path, record_ids=None, verbose=False):
class Dataset(BaseDataset):
name = "GENESIS"

requirements = ["pip:pooch"]

parameters = {
"recordings_id": [["1", "2"]],
"debug": [False],
Expand All @@ -99,9 +101,11 @@ class Dataset(BaseDataset):
def get_data(self):
"""Load the GENESIS dataset."""

path = fetch_tsb_uad("GENESIS")

# X shape (n_recordings, n_samples)
# y shape (n_recordings, n_samples)
X, y_true = load_data(PATH, self.recordings_id)
X, y_true = load_data(path, self.recordings_id)

X_test = X.copy()
y_test = y_true.copy()
Expand Down
10 changes: 7 additions & 3 deletions datasets/ghl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
from benchopt import BaseDataset, config
from benchopt import BaseDataset

from pathlib import Path
import numpy as np
import pandas as pd

PATH = config.get_data_path("GHL")
from benchmark_utils.download import fetch_tsb_uad


def load_data(db_path, record_ids=None, verbose=False):
Expand Down Expand Up @@ -95,6 +95,8 @@ def load_data(db_path, record_ids=None, verbose=False):
class Dataset(BaseDataset):
name = "GHL"

requirements = ["pip:pooch"]

parameters = {
"recordings_id": [["1", "2"]],
"debug": [False],
Expand All @@ -103,9 +105,11 @@ class Dataset(BaseDataset):
def get_data(self):
"""Load the GHL dataset."""

path = fetch_tsb_uad("GHL")

# X shape (n_recordings, n_samples)
# y shape (n_recordings, n_samples)
X, y_true = load_data(PATH, self.recordings_id)
X, y_true = load_data(path, self.recordings_id)

X_test = X.copy()
y_test = y_true.copy()
Expand Down
11 changes: 7 additions & 4 deletions datasets/iops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,10 @@
from benchopt import BaseDataset, config
from benchopt import BaseDataset

from pathlib import Path
import numpy as np
import pandas as pd

PATH = config.get_data_path("IOPS")
PATH = "/data/parietal/store2/data/tsb-uad/TSB-UAD-Public/IOPS/"
from benchmark_utils.download import fetch_tsb_uad


def load_data(db_path, verbose=False):
Expand Down Expand Up @@ -110,16 +109,20 @@ def load_data(db_path, verbose=False):
class Dataset(BaseDataset):
name = "IOPS"

requirements = ["pip:pooch"]

parameters = {
"debug": [False],
}

def get_data(self):
"""Load the IOPS dataset."""

path = fetch_tsb_uad("IOPS")

# X shape (n_recordings, n_samples)
# y shape (n_recordings, n_samples)
X_train, X_test, y_test = load_data(PATH)
X_train, X_test, y_test = load_data(path)

if self.debug:
X_train = X_train[:, :1000]
Expand Down
10 changes: 7 additions & 3 deletions datasets/kdd21.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
from benchopt import BaseDataset, config
from benchopt import BaseDataset

from pathlib import Path
import numpy as np
import pandas as pd

PATH = config.get_data_path("KDD21")
from benchmark_utils.download import fetch_tsb_uad


def load_data(db_path, record_ids=None, verbose=False):
Expand Down Expand Up @@ -89,6 +89,8 @@ def load_data(db_path, record_ids=None, verbose=False):
class Dataset(BaseDataset):
name = "KDD21"

requirements = ["pip:pooch"]

parameters = {
"recordings_id": [["1", "2"]],
"debug": [False],
Expand All @@ -97,9 +99,11 @@ class Dataset(BaseDataset):
def get_data(self):
"""Load the KDD21 dataset."""

path = fetch_tsb_uad("KDD21")

# X shape (n_recordings, n_samples)
# y shape (n_recordings, n_samples)
X, y_true = load_data(PATH, self.recordings_id)
X, y_true = load_data(path, self.recordings_id)

X_test = X.copy()
y_test = y_true.copy()
Expand Down
10 changes: 7 additions & 3 deletions datasets/mgab.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
from benchopt import BaseDataset, config
from benchopt import BaseDataset

from pathlib import Path
import numpy as np
import pandas as pd

PATH = config.get_data_path("MGAB")
from benchmark_utils.download import fetch_tsb_uad


def load_data(db_path, record_ids=None, verbose=False):
Expand Down Expand Up @@ -86,6 +86,8 @@ def load_data(db_path, record_ids=None, verbose=False):
class Dataset(BaseDataset):
name = "MGAB"

requirements = ["pip:pooch"]

parameters = {
"recordings_id": [["1", "2"]],
"debug": [False],
Expand All @@ -94,9 +96,11 @@ class Dataset(BaseDataset):
def get_data(self):
"""Load the MITDB dataset."""

path = fetch_tsb_uad("MGAB")

# X shape (n_recordings, n_samples)
# y shape (n_recordings, n_samples)
X, y_true = load_data(PATH, self.recordings_id)
X, y_true = load_data(path, self.recordings_id)
n_recordings, _ = X.shape

X_test = X.copy()
Expand Down
10 changes: 7 additions & 3 deletions datasets/occupancy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
from benchopt import BaseDataset, config
from benchopt import BaseDataset

from pathlib import Path
import numpy as np
import pandas as pd

PATH = config.get_data_path("OCCUPANCY")
from benchmark_utils.download import fetch_tsb_uad


def load_data(db_path, record_ids=None, verbose=False):
Expand Down Expand Up @@ -111,6 +111,8 @@ def load_data(db_path, record_ids=None, verbose=False):
class Dataset(BaseDataset):
name = "OCCUPANCY"

requirements = ["pip:pooch"]

parameters = {
"recordings_id": [None],
"debug": [False],
Expand All @@ -119,9 +121,11 @@ class Dataset(BaseDataset):
def get_data(self):
"""Load the OCCUPANCY dataset."""

path = fetch_tsb_uad("OCCUPANCY")

# X shape (n_recordings, n_samples)
# y shape (n_recordings, n_samples)
X_train, X_test, y_test = load_data(PATH, self.recordings_id)
X_train, X_test, y_test = load_data(path, self.recordings_id)

if self.debug:
X_train = X_train[:, :1000]
Expand Down
10 changes: 7 additions & 3 deletions datasets/opportunity.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
from benchopt import BaseDataset, config
from benchopt import BaseDataset

from pathlib import Path
import numpy as np
import pandas as pd

PATH = config.get_data_path("OPPORTUNITY")
from benchmark_utils.download import fetch_tsb_uad


def load_data(db_path, record_ids=None, verbose=False):
Expand Down Expand Up @@ -91,6 +91,8 @@ def load_data(db_path, record_ids=None, verbose=False):
class Dataset(BaseDataset):
name = "OPPORTUNITY"

requirements = ["pip:pooch"]

parameters = {
"recordings_id": [["1", "2"]],
"debug": [False],
Expand All @@ -99,9 +101,11 @@ class Dataset(BaseDataset):
def get_data(self):
"""Load the OPPORTUNITY dataset."""

path = fetch_tsb_uad("OPPORTUNITY")

# X shape (n_recordings, n_samples)
# y shape (n_recordings, n_samples)
X, y_true = load_data(PATH, self.recordings_id)
X, y_true = load_data(path, self.recordings_id)

X_test = X.copy()
y_test = y_true.copy()
Expand Down
10 changes: 7 additions & 3 deletions datasets/sensorscope.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
from benchopt import BaseDataset, config
from benchopt import BaseDataset

from pathlib import Path
import numpy as np
import pandas as pd

PATH = config.get_data_path("SENSORSCOPE")
from benchmark_utils.download import fetch_tsb_uad


def load_data(db_path, record_ids=None, verbose=False):
Expand Down Expand Up @@ -90,6 +90,8 @@ def load_data(db_path, record_ids=None, verbose=False):
class Dataset(BaseDataset):
name = "SENSORSCOPE"

requirements = ["pip:pooch"]

parameters = {
"recordings_id": [["10", "11"]],
"debug": [False],
Expand All @@ -98,9 +100,11 @@ class Dataset(BaseDataset):
def get_data(self):
"""Load the SENSORSCOPE dataset."""

path = fetch_tsb_uad("SENSORSCOPE")

# X shape (n_recordings, n_samples)
# y shape (n_recordings, n_samples)
X, y_true = load_data(PATH, self.recordings_id)
X, y_true = load_data(path, self.recordings_id)

X_test = X.copy()
y_test = y_true.copy()
Expand Down
10 changes: 7 additions & 3 deletions datasets/smd.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
from benchopt import BaseDataset, config
from benchopt import BaseDataset

from pathlib import Path
import numpy as np
import pandas as pd

PATH = config.get_data_path("SMD")
from benchmark_utils.download import fetch_tsb_uad


def load_data(db_path, record_ids=None):
Expand Down Expand Up @@ -94,6 +94,8 @@ def load_data(db_path, record_ids=None):
class Dataset(BaseDataset):
name = "SMD"

requirements = ["pip:pooch"]

parameters = {
"recordings_id": [["1", "2"]],
"debug": [False],
Expand All @@ -102,9 +104,11 @@ class Dataset(BaseDataset):
def get_data(self):
"""Load the SMD dataset."""

path = fetch_tsb_uad("SMD")

# X shape (n_recordings, n_samples)
# y shape (n_recordings, n_samples)
X, y_true = load_data(PATH, self.recordings_id)
X, y_true = load_data(path, self.recordings_id)

X_test = X.copy()
y_test = y_true.copy()
Expand Down
Loading
Loading