Enhancements and refactoring: Ruff checks resolved

aeon/README.md

@@ -1 +1 @@
-#
+# README # noqa D100

aeon/__init__.py

@@ -1,3 +1,5 @@
+"""Top-level package for aeon."""
+
 from importlib.metadata import PackageNotFoundError, version
 
 try:

aeon/analysis/__init__.py

@@ -0,0 +1 @@
+"""Utilities for analyzing data."""

aeon/analysis/block_plotting.py

@@ -26,15 +26,19 @@
 patch_markers_linestyles = ["solid", "dash", "dot", "dashdot", "longdashdot"]
 
 
-def gen_hex_grad(hex_col, vals, min_l=0.3):
+def gen_hex_grad(hex_col, vals, min_lightness=0.3):
     """Generates an array of hex color values based on a gradient defined by unit-normalized values."""
     # Convert hex to rgb to hls
-    h, l, s = rgb_to_hls(*[int(hex_col.lstrip("#")[i : i + 2], 16) / 255 for i in (0, 2, 4)])  # noqa: E741
+    hue, lightness, saturation = rgb_to_hls(
+        *[int(hex_col.lstrip("#")[i : i + 2], 16) / 255 for i in (0, 2, 4)]
+    )
     grad = np.empty(shape=(len(vals),), dtype="<U10")  # init grad
     for i, val in enumerate(vals):
-        cur_l = (l * val) + (min_l * (1 - val))  # get cur lightness relative to `hex_col`
-        cur_l = max(min(cur_l, l), min_l)  # set min, max bounds
-        cur_rgb_col = hls_to_rgb(h, cur_l, s)  # convert to rgb
+        curl_lightness = (lightness * val) + (
+            min_lightness * (1 - val)
+        )  # get cur lightness relative to `hex_col`
+        curl_lightness = max(min(curl_lightness, lightness), min_lightness)  # set min, max bounds
+        cur_rgb_col = hls_to_rgb(hue, curl_lightness, saturation)  # convert to rgb
         cur_hex_col = "#{:02x}{:02x}{:02x}".format(
             *tuple(int(c * 255) for c in cur_rgb_col)
         )  # convert to hex
@@ -55,19 +59,21 @@ def conv2d(arr, kernel):
 
 def gen_subject_colors_dict(subject_names):
     """Generates a dictionary of subject colors based on a list of subjects."""
-    return {s: c for s, c in zip(subject_names, subject_colors)}
+    return dict(zip(subject_names, subject_colors, strict=False))
 
 
 def gen_patch_style_dict(patch_names):
-    """Based on a list of patches, generates a dictionary of:
+    """Based on a list of patches, generates a dictionary of the following items.
+
     - patch_colors_dict: patch name to color
     - patch_markers_dict: patch name to marker
     - patch_symbols_dict: patch name to symbol
     - patch_linestyles_dict: patch name to linestyle
+
     """
     return {
-        "colors": {p: c for p, c in zip(patch_names, patch_colors)},
-        "markers": {p: m for p, m in zip(patch_names, patch_markers)},
-        "symbols": {p: s for p, s in zip(patch_names, patch_markers_symbols)},
-        "linestyles": {p: ls for p, ls in zip(patch_names, patch_markers_linestyles)},
+        "colors": dict(zip(patch_names, patch_colors, strict=False)),
+        "markers": dict(zip(patch_names, patch_markers, strict=False)),
+        "symbols": dict(zip(patch_names, patch_markers_symbols, strict=False)),
+        "linestyles": dict(zip(patch_names, patch_markers_linestyles, strict=False)),
     }

aeon/analysis/movies.py

@@ -1,3 +1,5 @@
+"""Helper functions for processing video data."""
+
 import math
 
 import cv2

aeon/analysis/plotting.py

@@ -1,3 +1,5 @@
+"""Helper functions for plotting data."""
+
 import math
 
 import matplotlib.pyplot as plt

aeon/analysis/utils.py

@@ -1,3 +1,5 @@
+"""Helper functions for data analysis and visualization."""
+
 import numpy as np
 import pandas as pd
 
@@ -59,7 +61,10 @@ def visits(data, onset="Enter", offset="Exit"):
     # duplicate offsets indicate missing data from previous pairing
     missing_data = data.duplicated(subset=time_offset, keep="last")
     if missing_data.any():
-        data.loc[missing_data, ["duration"] + [name for name in data.columns if rsuffix in name]] = pd.NA
+        data.loc[
+            missing_data,
+            ["duration"] + [name for name in data.columns if rsuffix in name],
+        ] = pd.NA
 
     # rename columns and sort data
     data.rename({time_onset: lonset, id_onset: "id", time_offset: loffset}, axis=1, inplace=True)
@@ -99,7 +104,14 @@ def rate(events, window, frequency, weight=1, start=None, end=None, smooth=None,
 
 
 def get_events_rates(
-    events, window_len_sec, frequency, unit_len_sec=60, start=None, end=None, smooth=None, center=False
+    events,
+    window_len_sec,
+    frequency,
+    unit_len_sec=60,
+    start=None,
+    end=None,
+    smooth=None,
+    center=False,
 ):
     """Computes the event rate from a sequence of events over a specified window."""
     # events is an array with the time (in seconds) of event occurence

aeon/dj_pipeline/__init__.py

@@ -1,9 +1,13 @@
+"""DataJoint pipeline for Aeon."""
+
 import hashlib
 import os
 import uuid
 
 import datajoint as dj
 
+logger = dj.logger
+
 _default_database_prefix = os.getenv("DJ_DB_PREFIX") or "aeon_"
 _default_repository_config = {"ceph_aeon": "/ceph/aeon"}
 
@@ -46,7 +50,12 @@ def fetch_stream(query, drop_pk=True):
     df.rename(columns={"timestamps": "time"}, inplace=True)
     df.set_index("time", inplace=True)
     df.sort_index(inplace=True)
-    df = df.convert_dtypes(convert_string=False, convert_integer=False, convert_boolean=False, convert_floating=False)
+    df = df.convert_dtypes(
+        convert_string=False,
+        convert_integer=False,
+        convert_boolean=False,
+        convert_floating=False,
+    )
     return df
 
 
@@ -57,5 +66,5 @@ def fetch_stream(query, drop_pk=True):
         from .utils import streams_maker
 
         streams = dj.VirtualModule("streams", streams_maker.schema_name)
-    except:
-        pass
+    except Exception as e:
+        logger.debug(f"Could not import streams module: {e}")

aeon/dj_pipeline/acquisition.py

@@ -1,22 +1,24 @@
+"""DataJoint schema for the acquisition pipeline."""
+
 import datetime
 import json
 import pathlib
 import re
 
 import datajoint as dj
-import numpy as np
 import pandas as pd
 
-from aeon.analysis import utils as analysis_utils
 from aeon.dj_pipeline import get_schema_name, lab, subject
 from aeon.dj_pipeline.utils import paths
 from aeon.io import api as io_api
 from aeon.io import reader as io_reader
 from aeon.schema import schemas as aeon_schemas
 
-logger = dj.logger
 schema = dj.schema(get_schema_name("acquisition"))
 
+logger = dj.logger
+
+
 # ------------------- Some Constants --------------------------
 
 _ref_device_mapping = {
@@ -35,7 +37,7 @@ class ExperimentType(dj.Lookup):
     experiment_type: varchar(32)
     """
 
-    contents = zip(["foraging", "social"])
+    contents = zip(["foraging", "social"], strict=False)
 
 
 @schema
@@ -63,7 +65,7 @@ class DevicesSchema(dj.Lookup):
     devices_schema_name: varchar(32)
     """
 
-    contents = zip(aeon_schemas.__all__)
+    contents = zip(aeon_schemas.__all__, strict=False)
 
 
 # ------------------- Data repository/directory ------------------------
@@ -75,7 +77,7 @@ class PipelineRepository(dj.Lookup):
     repository_name: varchar(16)
     """
 
-    contents = zip(["ceph_aeon"])
+    contents = zip(["ceph_aeon"], strict=False)
 
 
 @schema
@@ -84,7 +86,7 @@ class DirectoryType(dj.Lookup):
     directory_type: varchar(16)
     """
 
-    contents = zip(["raw", "processed", "qc"])
+    contents = zip(["raw", "processed", "qc"], strict=False)
 
 
 # ------------------- GENERAL INFORMATION ABOUT AN EXPERIMENT --------------------
@@ -136,6 +138,7 @@ class Note(dj.Part):
 
     @classmethod
     def get_data_directory(cls, experiment_key, directory_type="raw", as_posix=False):
+        """Get the data directory for the specified ``experiment_key`` and ``directory_type``."""
         try:
             repo_name, dir_path = (
                 cls.Directory & experiment_key & {"directory_type": directory_type}
@@ -145,7 +148,8 @@ def get_data_directory(cls, experiment_key, directory_type="raw", as_posix=False
 
         dir_path = pathlib.Path(dir_path)
         if dir_path.exists():
-            assert dir_path.is_relative_to(paths.get_repository_path(repo_name))
+            if not dir_path.is_relative_to(paths.get_repository_path(repo_name)):
+                raise ValueError(f"{dir_path} is not relative to the repository path.")
             data_directory = dir_path
         else:
             data_directory = paths.get_repository_path(repo_name) / dir_path
@@ -155,6 +159,7 @@ def get_data_directory(cls, experiment_key, directory_type="raw", as_posix=False
 
     @classmethod
     def get_data_directories(cls, experiment_key, directory_types=None, as_posix=False):
+        """Get the data directories for the specified ``experiment_key`` and ``directory_types``."""
         if directory_types is None:
             directory_types = (cls.Directory & experiment_key).fetch(
                 "directory_type", order_by="load_order"
@@ -223,7 +228,11 @@ def ingest_epochs(cls, experiment_name):
             with cls.connection.transaction:
                 # insert new epoch
                 cls.insert1(
-                    {**epoch_key, **directory, "epoch_dir": epoch_dir.relative_to(raw_data_dir).as_posix()}
+                    {
+                        **epoch_key,
+                        **directory,
+                        "epoch_dir": epoch_dir.relative_to(raw_data_dir).as_posix(),
+                    }
                 )
                 epoch_list.append(epoch_key)
 
@@ -279,7 +288,7 @@ class Meta(dj.Part):
         -> master
         ---
         bonsai_workflow: varchar(36)
-        commit: varchar(64)   # e.g. git commit hash of aeon_experiment used to generated this particular epoch
+        commit: varchar(64) # e.g., git commit hash of aeon_experiment used to generate this epoch
         source='': varchar(16)  # e.g. aeon_experiment or aeon_acquisition (or others)
         metadata: longblob
         metadata_file_path: varchar(255)  # path of the file, relative to the experiment repository
@@ -300,6 +309,7 @@ class ActiveRegion(dj.Part):
         """
 
     def make(self, key):
+        """Ingest metadata into EpochConfig."""
         from aeon.dj_pipeline.utils import streams_maker
         from aeon.dj_pipeline.utils.load_metadata import (
             extract_epoch_config,
@@ -369,6 +379,7 @@ class File(dj.Part):
 
     @classmethod
     def ingest_chunks(cls, experiment_name):
+        """Ingest chunks for the specified ``experiment_name``."""
         device_name = _ref_device_mapping.get(experiment_name, "CameraTop")
 
         all_chunks, raw_data_dirs = _get_all_chunks(experiment_name, device_name)
@@ -516,6 +527,7 @@ class SubjectWeight(dj.Part):
         """
 
     def make(self, key):
+        """Ingest environment data into Environment table."""
         chunk_start, chunk_end = (Chunk & key).fetch1("chunk_start", "chunk_end")
 
         # Populate the part table
@@ -579,6 +591,7 @@ class Name(dj.Part):
         """
 
     def make(self, key):
+        """Ingest active configuration data into EnvironmentActiveConfiguration table."""
         chunk_start, chunk_end = (Chunk & key).fetch1("chunk_start", "chunk_end")
         data_dirs = Experiment.get_data_directories(key)
         devices_schema = getattr(
@@ -608,10 +621,13 @@ def make(self, key):
 
 
 def _get_all_chunks(experiment_name, device_name):
+    """Get all chunks for the specified ``experiment_name`` and ``device_name``."""
     directory_types = ["quality-control", "raw"]
     raw_data_dirs = {
         dir_type: Experiment.get_data_directory(
-            experiment_key={"experiment_name": experiment_name}, directory_type=dir_type, as_posix=False
+            experiment_key={"experiment_name": experiment_name},
+            directory_type=dir_type,
+            as_posix=False,
         )
         for dir_type in directory_types
     }
@@ -629,6 +645,7 @@ def _get_all_chunks(experiment_name, device_name):
 
 
 def _match_experiment_directory(experiment_name, path, directories):
+    """Match the path to the experiment directory."""
     for k, v in directories.items():
         raw_data_dir = v
         if pathlib.Path(raw_data_dir) in list(path.parents):

aeon/dj_pipeline/analysis/__init__.py

@@ -0,0 +1 @@
+"""Utilities for analyzing data."""