fix: resolve ruff linting issues and add CI workflow

.github/workflows/ruff.yml

@@ -0,0 +1,14 @@
+name: Ruff
+
+on: [push, pull_request]
+
+jobs:
+  ruff:
+    if: github.event_name == 'push' || (github.event_name == 'pull_request' && github.event.pull_request.head.repo.fork == true)
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/ruff-action@v3
+        with:
+          version: "0.15.6"
+          args: "check --exclude examples/"

.gitignore

@@ -165,3 +165,4 @@ cython_debug/
 *.bak
 
 docs/source/generated/
+gsoc_env/

examples/sensorium/data.ipynb

@@ -11,9 +11,7 @@
     "%load_ext autoreload\n",
     "%autoreload 2\n",
     "\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "import torch"
+    "import matplotlib.pyplot as plt"
    ]
   },
   {

examples/sensorium/experiment.ipynb

@@ -14,7 +14,6 @@
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
     "import matplotlib.animation as animation\n",
-    "from pathlib import Path\n",
     "from IPython.display import HTML"
    ]
   },
@@ -33,9 +32,7 @@
     "if p not in sys.path:\n",
     "    sys.path.append(p)\n",
     "\n",
-    "from experanto.experiment import Experiment\n",
-    "from experanto.interpolators import Interpolator\n",
-    "from experanto.interpolators import ScreenInterpolator"
+    "from experanto.experiment import Experiment"
    ]
   },
   {

examples/sensorium/sensorium_min_example.ipynb

@@ -32,7 +32,6 @@
     "import numpy as np\n",
     "from tqdm import tqdm\n",
     "import matplotlib.pyplot as plt\n",
-    "from torch.utils.data import DataLoader\n",
     "from collections import OrderedDict"
    ]
   },
@@ -444,8 +443,6 @@
     "\n",
     "set_random_seed(seed)\n",
     "\n",
-    "from sensorium.datasets.mouse_video_loaders import mouse_video_loader\n",
-    "from sensorium.utility.scores import get_correlations\n",
     "from nnfabrik.builder import get_trainer\n",
     "from sensorium.models.make_model import make_video_model"
    ]
@@ -744,7 +741,6 @@
    "source": [
     "import yaml\n",
     "import os\n",
-    "from tqdm import tqdm\n",
     "from collections import Counter"
    ]
   },

experanto/configs.py

@@ -37,8 +37,7 @@
 
 from pathlib import Path
 
-from hydra import compose, initialize, initialize_config_dir
-from omegaconf import OmegaConf, open_dict
+from omegaconf import OmegaConf
 
 # get config relative to this file
 script_dir = Path(__file__).parent

experanto/dataloaders.py

@@ -1,13 +1,8 @@
 import logging
-import os
-import time
 import warnings
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Type, Union
+from typing import Dict, List, Optional, Union
 
-import numpy as np
 from omegaconf import DictConfig
-from torch.utils.data import DataLoader
 
 from .datasets import ChunkDataset
 from .utils import (
@@ -158,7 +153,6 @@ def get_multisession_concat_dataloader(
     datasets = []
     session_names = []
 
-    start_time = time.time()
     for i, (path, cfg) in enumerate(zip(paths, configs)):
         # Create dataset with deterministic seed
         path_hash = hash(path) % 10000

experanto/datasets.py

@@ -1,35 +1,31 @@
 from __future__ import annotations
 
-import functools
 import importlib
 import json
 import logging
 import os
 from collections.abc import Iterable
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional
 
 import numpy as np
 import torch
 import torchvision
 from hydra.utils import instantiate
-from omegaconf import DictConfig, ListConfig, OmegaConf
+from omegaconf import DictConfig, ListConfig
 from torch.utils.data import Dataset
-from torchvision.transforms import v2
 from torchvision.transforms.v2 import Compose, Lambda, ToTensor
 
 from .configs import DEFAULT_MODALITY_CONFIG
 from .experiment import Experiment
-from .interpolators import ImageTrial, VideoTrial
 from .intervals import (
     TimeInterval,
     find_intersection_between_two_interval_arrays,
     get_stats_for_valid_interval,
 )
-from .utils import add_behavior_as_channels, replace_nan_with_batch_mean
+from .utils import add_behavior_as_channels
 
 # see .configs.py for the definition of DEFAULT_MODALITY_CONFIG
-DEFAULT_MODALITY_CONFIG = dict()
 
 logger = logging.getLogger(__name__)
 
@@ -768,7 +764,6 @@ def __getitem__(self, idx: int) -> dict:
         for device_name in self.device_names:
             sampling_rate = self.sampling_rates[device_name]
             chunk_size = self.chunk_sizes[device_name]
-            chunk_s = chunk_size / sampling_rate
 
             # convert everything to int to avoid numerical issues
             start_time = int(round(s * self.scale_precision))

experanto/experiment.py

@@ -1,11 +1,9 @@
 from __future__ import annotations
 
 import logging
-import re
 import warnings
-from collections.abc import Sequence
 from pathlib import Path
-from typing import Optional, Union
+from typing import Union
 
 import numpy as np
 from hydra.utils import instantiate

experanto/interpolators.py

@@ -12,7 +12,6 @@
 
 import cv2
 import numpy as np
-import numpy.lib.format as fmt
 import yaml
 from numba import njit, prange
 from scipy.ndimage import gaussian_filter1d
@@ -326,7 +325,7 @@ def interpolate(
 
         else:
             raise NotImplementedError(
-                f"interpolation_mode should be linear or nearest_neighbor"
+                "interpolation_mode should be linear or nearest_neighbor"
             )
 
     def close(self) -> None:
@@ -454,7 +453,7 @@ def interpolate(
 
         else:
             raise NotImplementedError(
-                f"interpolation_mode should be linear or nearest_neighbor"
+                "interpolation_mode should be linear or nearest_neighbor"
             )
 
 

experanto/intervals.py

@@ -236,7 +236,7 @@ def get_stats_for_valid_interval(
     """
     total_duration = end_time - start_time
     if total_duration <= 0:
-        return f"Error: Invalid time range (end_time <= start_time). Total duration must be positive."
+        return "Error: Invalid time range (end_time <= start_time). Total duration must be positive."
 
     # Ensure intervals are unique and sorted, then clamp them to the analysis window
     unique_intervals = uniquefy_interval_array(intervals)

experanto/utils.py

@@ -1,28 +1,15 @@
 import bisect
 import logging
-import math
-import multiprocessing
 
 # inbuilt libraries
-import os
-import queue
-import random
-import threading
-import time
-import warnings
 from collections import defaultdict
-from copy import deepcopy
-from functools import partial
-from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
 
 # third-party libraries
 import numpy as np
 import torch
-from omegaconf import DictConfig
-from torch.utils.data import ConcatDataset, DataLoader, Dataset, Sampler
+from torch.utils.data import DataLoader, Dataset, Sampler
 
 # local libraries
-from .intervals import TimeInterval
 
 logger = logging.getLogger(__name__)
 
@@ -58,7 +45,7 @@ def add_behavior_as_channels(data: dict[str, torch.Tensor]) -> dict:
 
     # Process eye_tracker
     if len(eye_tracker.shape) == 2:  # (t, c_eye)
-        c_eye = eye_tracker.shape[1]
+
         # Reshape to (c_eye, t, h, w)
         eye_tracker = eye_tracker.transpose(0, 1)  # (c_eye, t)
         eye_tracker = eye_tracker.unsqueeze(-1).unsqueeze(-1)  # (c_eye, t, 1, 1)
@@ -69,7 +56,7 @@ def add_behavior_as_channels(data: dict[str, torch.Tensor]) -> dict:
 
     # Process treadmill
     if len(treadmill.shape) == 2:  # (t, c_tread)
-        c_tread = treadmill.shape[1]
+
         # Reshape to (c_tread, t, h, w)
         treadmill = treadmill.transpose(0, 1)  # (c_tread, t)
         treadmill = treadmill.unsqueeze(-1).unsqueeze(-1)  # (c_tread, t, 1, 1)