Documentation Improvement

docs/dataclass.md

@@ -1,9 +1,5 @@
-In the following the KielMAT dataclass is described.
-The dataclass is used to store motion data in a standardized way. We provide some small set of import functions, each of which returns a `pandas.DataFrame` or a dict.
-User should easily be able to write their own import functions, to get the their data into the provided dataclass (this step might take some thinking).
-After the data is in the dataclass, running functions on the data from our toolbox should be really straight forward.
+In the following, the KielMAT dataclass is described. The dataclass is used to store motion data in a standardized way. We provide a small set of import functions, each of which returns a `pandas.DataFrame` or a dict. Users should easily be able to write their own import functions to get their data into the provided dataclass (this step might take some thinking). After the data is in the dataclass, running functions on the data from our toolbox should be really straightforward.
 
-## KielMAT data class
 ```mermaid
 classDiagram
    class KielMATRecording {

docs/index.md

@@ -17,123 +17,27 @@ The toolbox is aimed at motion researchers who want to use Python-based open-sou
 
 The table below provides an overview of key modules, their functionalities, input data, validation datasets, and outputs.
 
-<div style="width: 100%; text-align: left; margin-top: 20px; background-color: transparent; padding: 0; border: none;">
-
-    <table style="width: 100%; border-collapse: collapse; font-size: 0.9em; background-color: transparent; border: none;">
-
-        <thead style="background-color: #f2f2f2;">
-        <tr>
-            <th style="padding: 10px; border-bottom: 1px solid #ddd;">Module</th>
-            <th style="padding: 10px; border-bottom: 1px solid #ddd;">Description</th>
-            <th style="padding: 10px; border-bottom: 1px solid #ddd;">Input Data</th>
-            <th style="padding: 10px; border-bottom: 1px solid #ddd;">Validation Dataset</th>
-            <th style="padding: 10px; border-bottom: 1px solid #ddd;">Event Type</th>
-            <th style="padding: 10px; border-bottom: 1px solid #ddd;">Output Parameters</th>
-        </tr>
-        </thead>
-
-        <tbody>
-        <tr>
-            <td style="padding: 8px;"><a href="https://neurogeriatricskiel.github.io/KielMAT/modules/gsd/">Gait Sequence Detection</a></td>
-            <td style="padding: 8px;">Detects gait sequences</td>
-            <td style="padding: 8px;">3D accelerations from lower back IMU</td>
-            <td style="padding: 8px;"><a href="https://neurogeriatricskiel.github.io/KielMAT/datasets/mobilised/">Mobilise-D</a> and <a href="https://neurogeriatricskiel.github.io/KielMAT/datasets/keepcontrol/">KeepControl</a></td>
-            <td style="padding: 8px;">gait sequence</td>
-            <td style="padding: 8px;">-</td>
-        </tr>
-
-        <tr>
-            <td style="padding: 8px;"><a href="https://neurogeriatricskiel.github.io/KielMAT/modules/icd/">Initial Contact Detection</a></td>
-            <td style="padding: 8px;">Detects initial and final contacts within each gait cycle</td>
-            <td style="padding: 8px;">3D accelerations from lower back IMU</td>
-            <td style="padding: 8px;"><a href="https://neurogeriatricskiel.github.io/KielMAT/datasets/mobilised/">Mobilise-D</a> and <a href="https://neurogeriatricskiel.github.io/KielMAT/datasets/keepcontrol/">KeepControl</a></td>
-            <td style="padding: 8px;">initial contact, final contact</td>
-            <td style="padding: 8px;">Temporal parameters (e.g., step time, stride time)</td>
-        </tr>
-
-        <tr>
-            <td style="padding: 8px;"><a href="https://neurogeriatricskiel.github.io/KielMAT/modules/pam/">Physical Activity Monitoring</a></td>
-            <td style="padding: 8px;">Monitors physical activity levels</td>
-            <td style="padding: 8px;">3D accelerations from wrist IMU</td>
-            <td style="padding: 8px;"><a href="https://www.fairpark2.eu/">Fair Park Ⅱ</a></td>
-            <td style="padding: 8px;">-</td>
-            <td style="padding: 8px;">Mean and duration of activity level</td>
-        </tr>
-
-        <tr>
-            <td style="padding: 8px;"><a href="https://neurogeriatricskiel.github.io/KielMAT/modules/ptd/">Postural Transition Detection</a></td>
-            <td style="padding: 8px;">Detects sit-to-stand and stand-to-sit transitions</td>
-            <td style="padding: 8px;">3D acceleration and gyroscope data from lower back IMU</td>
-            <td style="padding: 8px;"><a href="https://neurogeriatricskiel.github.io/KielMAT/datasets/keepcontrol/">KeepControl</a> and <a href="https://pmc.ncbi.nlm.nih.gov/articles/PMC4460963/">SENSE-PARK</a></td>
-            <td style="padding: 8px;">sit-to-stand, stand-to-sit</td>
-            <td style="padding: 8px;">Spatio-temporal parameters (e.g., postural transition angle)</td>
-        </tr>
-
-        <tr>
-            <td style="padding: 8px;"><a href="https://neurogeriatricskiel.github.io/KielMAT/modules/td/">Turn Detection</a></td>
-            <td style="padding: 8px;">Detects turn movements</td>
-            <td style="padding: 8px;">3D acceleration and gyroscope data from lower back IMU</td>
-            <td style="padding: 8px;"><a href="https://neurogeriatricskiel.github.io/KielMAT/datasets/keepcontrol/">KeepControl</a> and <a href="https://pmc.ncbi.nlm.nih.gov/articles/PMC4460963/">SENSE-PARK</a></td>
-            <td style="padding: 8px;">turn</td>
-            <td style="padding: 8px;">Spatio-temporal parameters (e.g., turn angle)</td>
-        </tr>
-
-        </tbody>
-    </table>
-</div>
+| Module | Description | Input Data | Validation Dataset | Event Type | Output Parameters |
+|--------|-------------|------------|--------------------|------------|-------------------|
+| [Gait Sequence Detection](https://neurogeriatricskiel.github.io/KielMAT/modules/gsd/) | Detects gait sequences | 3D accelerations from lower back IMU | [Mobilise-D](https://neurogeriatricskiel.github.io/KielMAT/datasets/mobilised/) and [KeepControl](https://neurogeriatricskiel.github.io/KielMAT/datasets/keepcontrol/) | gait sequence | - |
+| [Initial Contact Detection](https://neurogeriatricskiel.github.io/KielMAT/modules/icd/) | Detects initial and final contacts within each gait cycle | 3D accelerations from lower back IMU | [Mobilise-D](https://neurogeriatricskiel.github.io/KielMAT/datasets/mobilised/) and [KeepControl](https://neurogeriatricskiel.github.io/KielMAT/datasets/keepcontrol/) | initial contact, final contact | Temporal parameters (e.g., step time, stride time) |
+| [Physical Activity Monitoring](https://neurogeriatricskiel.github.io/KielMAT/modules/pam/) | Monitors physical activity levels | 3D accelerations from wrist IMU | [Fair Park Ⅱ](https://www.fairpark2.eu/) | - | Mean and duration of activity level |
+| [Postural Transition Detection](https://neurogeriatricskiel.github.io/KielMAT/modules/ptd/) | Detects sit-to-stand and stand-to-sit transitions | 3D acceleration and gyroscope data from lower back IMU | [KeepControl](https://neurogeriatricskiel.github.io/KielMAT/datasets/keepcontrol/) and [SENSE-PARK](https://pmc.ncbi.nlm.nih.gov/articles/PMC4460963/) | sit-to-stand, stand-to-sit | Spatio-temporal parameters (e.g., postural transition angle) |
+| [Turn Detection](https://neurogeriatricskiel.github.io/KielMAT/modules/td/) | Detects turn movements | 3D acceleration and gyroscope data from lower back IMU | [KeepControl](https://neurogeriatricskiel.github.io/KielMAT/datasets/keepcontrol/) and [SENSE-PARK](https://pmc.ncbi.nlm.nih.gov/articles/PMC4460963/) | turn | Spatio-temporal parameters (e.g., turn angle) |
 
 
 ## Units
 
 The table below provides an overview of commonly used value types and their corresponding units. Before starting work with modules in the toolbox, ensure that all data is in standard SI units as specified. This ensures compatibility with the algorithms, which are designed to expect inputs in these units.
 
-<div style="width: 50%; text-align: left; margin-top: 20px; overflow: hidden; padding: 0; background-color: transparent;">
-
-    <table style="width: 100%; border-collapse: collapse; font-size: 0.9em; border: none; background-color: transparent;">
-
-        <thead style="background-color: #f2f2f2;">
-        <tr>
-            <th style="padding: 10px; border-bottom: 1px solid #ddd;">Value</th>
-            <th style="padding: 10px; border-bottom: 1px solid #ddd;">Unit</th>
-        </tr>
-        </thead>
-
-        <tbody>
-        <tr>
-            <td style="padding: 8px;">Acceleration</td>
-            <td style="padding: 8px;">m/s²</td>
-        </tr>
-
-        <tr>
-            <td style="padding: 8px;">Angular Velocity</td>
-            <td style="padding: 8px;">deg/s</td>
-        </tr>
-
-        <tr>
-            <td style="padding: 8px;">Velocity</td>
-            <td style="padding: 8px;">m/s</td>
-        </tr>
-
-        <tr>
-            <td style="padding: 8px;">Distance</td>
-            <td style="padding: 8px;">m</td>
-        </tr>
-
-        <tr>
-            <td style="padding: 8px;">Time</td>
-            <td style="padding: 8px;">s</td>
-        </tr>
-
-        <tr>
-            <td style="padding: 8px;">Sampling Rate</td>
-            <td style="padding: 8px;">Hz</td>
-        </tr>
-
-        </tbody>
-    </table>
-</div>
-
-
+| Value             | Unit   | Channel Type  |
+|-------------------|--------|---------------|
+| Acceleration      | m/s²   | ACCEL         |
+| Angular Velocity  | deg/s  | GYRO          |
+| Velocity          | m/s    | VEL           |
+| Distance          | m      | POS           |
+| Time              | s      |               |
+| Sampling Rate     | Hz     |               |
 
 ## Installation
 The toolbox has been released on [pypi](https://pypi.org/project/kielmat/) and can be installed via pip:
@@ -149,7 +53,7 @@ The idea is that various motion data can be loaded into our dedicated dataclass
 
 Motion data is recorded with many different systems and modalities, each with their own proprietary data format. KielMAT deals with this by organizing both data and metadata in a [BIDS-like format](https://bids-specification.readthedocs.io/en/stable/modality-specific-files/motion.html). The BIDS format suggests that [motion recording data](https://bids-specification.readthedocs.io/en/stable/modality-specific-files/motion.html#motion-recording-data) from a single tracking system is organized in a single `*_tracksys-<label>_motion.tsv` file.
 
-> [!NOTE]
+> !!! note
 > A tracking system is defined as a group of motion channels that share hardware properties (the recording device) and software properties (the recording duration and number of samples).
 
 In KielMAT, data from a single tracking system is therefore loaded into a single `pandas.DataFrame`. The column headers of this `pandas.DataFrame` refer to the channels, and the corresponding [channels information](https://bids-specification.readthedocs.io/en/stable/modality-specific-files/motion.html#channels-description-_channelstsv) is likewise available as a `pandas.DataFrame`.

kielmat/datasets/keepcontrol.py

@@ -7,6 +7,7 @@
 from kielmat.utils.kielmat_dataclass import REQUIRED_COLUMNS
 import logging
 import warnings
+from tqdm import tqdm 
 
 # Dict of valid tracked points for the Keep Control dataset for each tracking system
 VALID_TRACKED_POINTS = {
@@ -84,6 +85,7 @@
 
 
 def fetch_dataset(
+    progressbar: bool = True,
     dataset_path: str | Path = Path(__file__).parent / "_keepcontrol",
 ) -> None:
     """Fetch the Keep Control dataset from the OpenNeuro repository.
@@ -104,6 +106,10 @@ def fetch_dataset(
             dataset="ds005258",  # this is the example Keep Control dataset on OpenNeuro, maintained by Julius Welzel
             target_dir=dataset_path,
         )
+
+    else:
+        if progressbar:
+            print("Dataset already downloaded, skipping download.")
     return
 
 

kielmat/modules/ptd/_pham.py

@@ -88,7 +88,7 @@ def __init__(
             cutoff_freq_hz (float, optional): Cutoff frequency for low-pass Butterworth filer. Default is 5.0.
             thr_accel_var (float): Threshold value for identifying periods where the acceleartion variance is low. Default is 0.5.
             thr_gyro_var (float): Threshold value for identifying periods where the gyro variance is low. Default is 2e-4.
-            min_turn_angle_deg (float): Minimum angle which is considered as postural transition in degrees. Default is 15.0.
+            min_postural_transition_angle_deg (float): Minimum angle which is considered as postural transition in degrees. Default is 15.0.
         """
         self.cutoff_freq_hz = cutoff_freq_hz
         self.thr_accel_var = thr_accel_var
@@ -104,7 +104,7 @@ def detect(
         tracking_system: Optional[str] = None,
         tracked_point: Optional[str] = None,
         plot_results: bool = False,
-    ) -> "PhamPosturalTransitionDetection":
+    ) -> pd.DataFrame:
         """
         Detects postural transitions based on the input accelerometer and gyro data.
 
@@ -460,7 +460,7 @@ def detect(
         # Return an instance of the class
         return self
 
-    def spatio_temporal_parameters(self) -> None:
+    def spatio_temporal_parameters(self) -> pd.DataFrame:
         """
         Extracts spatio-temporal parameters of the detected postural transitions.
 

kielmat/modules/td/_pham.py

@@ -105,7 +105,7 @@ def detect(
         tracking_system: Optional[str] = None,
         tracked_point: Optional[str] = None,
         plot_results: bool = False,
-    ) -> "PhamTurnDetection":
+    ) -> pd.DataFrame:
         """
         Detects truns based on the input accelerometer and gyro data.
 
@@ -450,7 +450,7 @@ def detect(
         # Return an instance of the class
         return self
 
-    def spatio_temporal_parameters(self) -> None:
+    def spatio_temporal_parameters(self) -> pd.DataFrame:
         """
         Extracts spatio-temporal parameters of the detected turns.
 

kielmat/utils/importers.py

@@ -7,7 +7,7 @@
 from pathlib import Path
 
 
-def import_axivity(file_path: str, tracked_point: str):
+def import_axivity(file_path: str, tracked_point: str) -> tuple[pd.DataFrame, pd.DataFrame]:
     """
     Imports Axivity data from the specified file path and
     return the data and channel formatted to be used in a KielMATRecording object.
@@ -52,7 +52,7 @@ def import_axivity(file_path: str, tracked_point: str):
     col_names = [f"{tracked_point}_{s}_{x}" for s in ["ACCEL"] for x in ["x", "y", "z"]]
 
     # Create the channel dictionary following the BIDS naming conventions
-    channels = {
+    channels_dict  = {
         "name": col_names,
         "component": ["x", "y", "z"] * (n_channels // 3),
         "type": ["ACCEL"] * (n_channels),
@@ -61,6 +61,9 @@ def import_axivity(file_path: str, tracked_point: str):
         "sampling_frequency": [info["ResampleRate"]] * n_channels,
     }
 
+    # Convert channels dictionary to a DataFrame
+    channels = pd.DataFrame(channels_dict)
+
     return data, channels
 
 
@@ -74,16 +77,16 @@ def import_mobilityLab(
 
     Args:
         file_name (str or Path): The absolute or relative path to the data file.
-        tracked_point (str or list of str]):
+        tracked_points (str or list of str]):
             Defines for which tracked points data are to be returned.
 
     Returns:
         dict, dict: The loaded data and channels as dictionaries.
 
     Examples:
         >>> file_path = "/path/to/sensor_data.h5"
-        >>> tracked_point = "Lumbar"
-        >>> recording = import_mobilityLab(file_path, tracked_point)
+        >>> tracked_points = "Lumbar"
+        >>> recording = import_mobilityLab(file_path, tracked_points)
     """
     # Convert file_name to a Path object if it is a string
     if isinstance(file_name, str):

kielmat/utils/kielmat_dataclass.py

@@ -77,7 +77,7 @@ def __post_init__(self):
         # Validate channels when an instance is created
         self.validate_channels()
 
-    def validate_channels(self):
+    def validate_channels(self) -> str:
         """
         Validates the channel dataframes for each system.
 

kielmat/utils/preprocessing.py

@@ -75,15 +75,15 @@ def resample_interpolate(
     return resampled_signal
 
 
-def lowpass_filter(signal, method="savgol", order=None, **kwargs):
+def lowpass_filter(signal, method="savgol", order=None, **kwargs:dict):
     """
     Apply a low-pass filter to the input signal.
 
     Args:
         signal (numpy.ndarray): The input signal to be filtered.
         method (str): The filter method to use ("savgol", "butter", or "fir").
         order (int): The order of the filter (applicable for "butter" method).
-        param (**kwargs): Additional keyword arguments specific to the Savitzky-Golay filter method or other methods.
+        **kwargs: Additional keyword arguments specific to the Savitzky-Golay filter method or other methods.
 
     Returns:
         filt_signal (numpy.ndarray): The filtered signal.
@@ -165,18 +165,17 @@ def lowpass_filter(signal, method="savgol", order=None, **kwargs):
         raise ValueError("Invalid filter method specified")
 
 
-def highpass_filter(signal, sampling_frequency=40, method="iir", **kwargs):
+def highpass_filter(signal, sampling_frequency=40, method="iir"):
     """
     Apply a high-pass filter to the input signal using the specified method.
 
     Args:
         signal (np.ndarray): The input signal to be filtered.
         sampling_frequency (float): The sampling frequency of the input signal.
         method (str): The filtering method to be used.
-        **kwargs: Additional keyword arguments specific to the filtering method.
 
     Returns:
-        np.ndarray: The filtered signal.
+        filtered_signal (np.ndarray): The filtered signal.
 
     """
     # Error handling for invalid input data
@@ -441,7 +440,7 @@ def find_consecutive_groups(input_signal):
     the start index of the group and the second column containing the end index of the group.
 
     Parameters:
-        input_array (ndarray): The input array.
+        input_signal (ndarray): The input array.
 
     Returns:
         ind (ndarray): A 2D array where each row represents a group of consecutive non-zero values.
@@ -1085,13 +1084,13 @@ def wavelet_decomposition(data, level, wavetype):
 
 
 # Function for computing moving variance
-def moving_var(data, window):
+def moving_var(data, window) -> np.ndarray:
     """
     Compute the centered moving variance.
 
     Args:
-        Data (int) : Data to take the moving variance on window
-        Window size (int) : Window size for the moving variance.
+        data (int) : Data to take the moving variance on window
+        window size (int) : Window size for the moving variance.
 
     Returns:
         m_var (numpy.ndarray) : Moving variance

kielmat/utils/quaternion.py

@@ -292,10 +292,8 @@ def rotm2quat(R: np.ndarray, method: int | str = "auto") -> np.ndarray:
 
     Args:
         R (np.ndarray): A rotation matrix with shape (3, 3).
-        scalar_first (bool, optional): If True, sets the first element as the scalar part.
-            If False, sets the last element as the scalar part is the last element. Default is True.
-        channels_last (bool, optional): If True, assumes the channels are the last dimension.
-            If False, assumes the channels are the first dimension. Default is True.
+        method (int | str, optional): The method to use for conversion.
+            Can be "auto" (default), "copysign", or a number (0, 1, 2, or 3).
 
     Returns:
         np.ndarray: The quaternion corresponding to the rotation matrix.

mkdocs.yml

@@ -47,6 +47,9 @@ nav:
     - Events in dataclass: examples/basic_02_events.md
     - Gait Sequence Detection: examples/modules_01_gsd.md
     - Initial Contact Detection: examples/modules_02_icd.md
+    - Physical Activity Monitoring: examples/modules_03_pam.md
+    - Postural Transition Detection: examples/modules_04_ptd.md
+    - Turn Detection: examples/modules_05_td.md
   - Dataclass: dataclass.md 
   - Modules: 
     - modules/index.md