paradigma 0.4.7__py3-none-any.whl → 1.0.0__py3-none-any.whl

paradigma/feature_extraction.py

@@ -597,11 +597,9 @@ def pca_transform_gyroscope(
         df: pd.DataFrame,
         y_gyro_colname: str,
         z_gyro_colname: str,
-        pred_colname: str | None = None,
 ) -> np.ndarray:
     """
-    Perform principal component analysis (PCA) on gyroscope data to estimate velocity. If pred_colname is provided, 
-    the PCA is fitted on the predicted gait data. Otherwise, the PCA is fitted on the entire dataset.
+    Perform principal component analysis (PCA) on gyroscope data to estimate velocity.
     
     Parameters
     ----------
@@ -611,8 +609,6 @@ def pca_transform_gyroscope(
         The column name for the y-axis gyroscope data.
     z_gyro_colname : str
         The column name for the z-axis gyroscope data.
-    pred_colname : str, optional
-        The column name for the predicted gait (default: None).
         
     Returns
     -------
@@ -623,19 +619,9 @@ def pca_transform_gyroscope(
     y_gyro_array = df[y_gyro_colname].to_numpy()
     z_gyro_array = df[z_gyro_colname].to_numpy()
 
-    # Filter data based on predicted gait if pred_colname is provided
-    if pred_colname is not None:
-        pred_mask = df[pred_colname] == 1
-        y_gyro_fit_array = y_gyro_array[pred_mask]
-        z_gyro_fit_array = z_gyro_array[pred_mask]
-
-        # Fit PCA on predicted gait data
-        fit_data = np.column_stack((y_gyro_fit_array, z_gyro_fit_array))
-        full_data = np.column_stack((y_gyro_array, z_gyro_array))
-    else:
-        # Fit PCA on entire dataset
-        fit_data = np.column_stack((y_gyro_array, z_gyro_array))
-        full_data = fit_data
+    # Fit PCA
+    fit_data = np.column_stack((y_gyro_array, z_gyro_array))
+    full_data = fit_data
 
     pca = PCA(n_components=2, svd_solver='auto', random_state=22)
     pca.fit(fit_data)

paradigma/pipelines/gait_pipeline.py

@@ -1,20 +1,17 @@
 import numpy as np
-import os
 import pandas as pd
-from pathlib import Path
 from scipy.signal import periodogram
 from typing import List, Tuple
-import tsdf
 
 from paradigma.classification import ClassifierPackage
-from paradigma.constants import DataColumns, TimeUnit
+from paradigma.constants import DataColumns
 from paradigma.config import GaitConfig
 from paradigma.feature_extraction import pca_transform_gyroscope, compute_angle, remove_moving_average_angle, \
     extract_angle_extremes, compute_range_of_motion, compute_peak_angular_velocity, compute_statistics, \
     compute_std_euclidean_norm, compute_power_in_bandwidth, compute_dominant_frequency, compute_mfccs, \
     compute_total_power
 from paradigma.segmenting import tabulate_windows, create_segments, discard_segments, categorize_segments, WindowedDataExtractor
-from paradigma.util import aggregate_parameter, merge_predictions_with_timestamps, read_metadata, write_df_data, get_end_iso8601
+from paradigma.util import aggregate_parameter
 
 
 def extract_gait_features(
@@ -160,66 +157,35 @@ def detect_gait(
 
 
 def extract_arm_activity_features(
+        df: pd.DataFrame, 
         config: GaitConfig,
-        df_timestamps: pd.DataFrame, 
-        df_predictions: pd.DataFrame,
-        threshold: float
     ) -> pd.DataFrame:
     """
     Extract features related to arm activity from a time-series DataFrame.
 
     This function processes a DataFrame containing accelerometer, gravity, and gyroscope signals, 
     and extracts features related to arm activity by performing the following steps:
-    1. Merges the gait predictions with timestamps by expanding overlapping windows into individual timestamps.
-    2. Computes the angle and velocity from gyroscope data.
-    3. Filters the data to include only predicted gait segments.
-    4. Groups the data into segments based on consecutive timestamps and pre-specified gaps.
-    5. Removes segments that do not meet predefined criteria.
-    6. Creates fixed-length windows from the time series data.
-    7. Extracts angle-related features, temporal domain features, and spectral domain features.
+    1. Computes the angle and velocity from gyroscope data.
+    2. Filters the data to include only predicted gait segments.
+    3. Groups the data into segments based on consecutive timestamps and pre-specified gaps.
+    4. Removes segments that do not meet predefined criteria.
+    5. Creates fixed-length windows from the time series data.
+    6. Extracts angle-related features, temporal domain features, and spectral domain features.
 
     Parameters
     ----------
-    config : GaitConfig
-        Configuration object containing column names and parameters for feature extraction.
-
-    df_timestamps : pd.DataFrame
-        A DataFrame containing the raw sensor data, including accelerometer, gravity, and gyroscope columns.
-
-    df_predictions : pd.DataFrame
-        A DataFrame containing the predicted probabilities for gait activity per window.
+    df: pd.DataFrame
+        The input DataFrame containing accelerometer, gravity, and gyroscope data of predicted gait.
 
     config : ArmActivityFeatureExtractionConfig
         Configuration object containing column names and parameters for feature extraction.
 
-    path_to_classifier_input : str | Path
-        The path to the directory containing the classifier files and other necessary input files for feature extraction.
-    
     Returns
     -------
     pd.DataFrame
         A DataFrame containing the extracted arm activity features, including angle, velocity, 
         temporal, and spectral features.
     """
-    if not any(df_predictions[DataColumns.PRED_GAIT_PROBA] >= threshold):
-        raise ValueError("No gait detected in the input data.")
-    
-    # Merge gait predictions with timestamps
-    gait_preprocessing_config = GaitConfig(step='gait')
-    df = merge_predictions_with_timestamps(
-        df_ts=df_timestamps, 
-        df_predictions=df_predictions, 
-        pred_proba_colname=DataColumns.PRED_GAIT_PROBA,
-        window_length_s=gait_preprocessing_config.window_length_s,
-        fs=gait_preprocessing_config.sampling_frequency
-    )
-    
-    # Add a column for predicted gait based on a fitted threshold
-    df[DataColumns.PRED_GAIT] = (df[DataColumns.PRED_GAIT_PROBA] >= threshold).astype(int)
-
-    # Filter the DataFrame to only include predicted gait (1)
-    df = df.loc[df[DataColumns.PRED_GAIT]==1].reset_index(drop=True)
-
     # Group consecutive timestamps into segments, with new segments starting after a pre-specified gap
     df[DataColumns.SEGMENT_NR] = create_segments(
         time_array=df[DataColumns.TIME], 
@@ -315,8 +281,8 @@ def filter_gait(
     ----------
     df : pd.DataFrame
         The input DataFrame containing features extracted from gait data.
-    full_path_to_classifier_package : str | Path
-        The path to the pre-trained classifier file.
+    clf_package: ClassifierPackage
+        The pre-trained classifier package containing the classifier, threshold, and scaler.
     parallel : bool, optional, default=False
         If `True`, enables parallel processing.
 
@@ -351,10 +317,10 @@ def filter_gait(
 
 def quantify_arm_swing(
         df: pd.DataFrame, 
-        max_segment_gap_s: float, 
-        min_segment_length_s: float,
         fs: int,
         filtered: bool = False,
+        max_segment_gap_s: float = 1.5,
+        min_segment_length_s: float = 1.5
     ) -> Tuple[dict[str, pd.DataFrame], dict]:
     """
     Quantify arm swing parameters for segments of motion based on gyroscope data.
@@ -362,28 +328,27 @@ def quantify_arm_swing(
     Parameters
     ----------
     df : pd.DataFrame
-        A DataFrame containing the raw sensor data, including gyroscope columns. Should include a column
+        A DataFrame containing the raw sensor data of predicted gait timestamps. Should include a column
         for predicted no other arm activity based on a fitted threshold if filtered is True.
 
-    max_segment_gap_s : float
-        The maximum gap allowed between segments.
-
-    min_segment_length_s : float
-        The minimum length required for a segment to be considered valid.
-
     fs : int
         The sampling frequency of the sensor data.
 
     filtered : bool, optional, default=True
         If `True`, the gyroscope data is filtered to only include predicted no other arm activity.
 
+    max_segment_gap_s : float, optional, default=1.5
+        The maximum gap in seconds between consecutive timestamps to group them into segments.
+    
+    min_segment_length_s : float, optional, default=1.5
+        The minimum length in seconds for a segment to be considered valid.
+
     Returns
     -------
     Tuple[pd.DataFrame, dict]
         A tuple containing a dataframe with quantified arm swing parameters and a dictionary containing 
         metadata for each segment.
     """
-    
     # Group consecutive timestamps into segments, with new segments starting after a pre-specified gap.
     # Segments are made based on predicted gait
     df[DataColumns.SEGMENT_NR] = create_segments(
@@ -391,6 +356,10 @@ def quantify_arm_swing(
         max_segment_gap_s=max_segment_gap_s
     )
 
+    # Segment category is determined based on predicted gait, hence it is set
+    # before filtering the DataFrame to only include predicted no other arm activity
+    df[DataColumns.SEGMENT_CAT] = categorize_segments(df=df, fs=fs)
+
     # Remove segments that do not meet predetermined criteria
     df = discard_segments(
         df=df,
@@ -401,40 +370,51 @@ def quantify_arm_swing(
     )
 
     if df.empty:
-        raise ValueError("No segments found in the input data.")
+        raise ValueError("No segments found in the input data after discarding segments of invalid shape.")
 
     # If no arm swing data is remaining, return an empty dictionary
     if filtered and df.loc[df[DataColumns.PRED_NO_OTHER_ARM_ACTIVITY]==1].empty:
         raise ValueError("No gait without other arm activities to quantify.")
-        
-    df[DataColumns.SEGMENT_CAT] = categorize_segments(df=df, fs=fs)
-
-    # Group and process segments
-    arm_swing_quantified = []
-    segment_meta = {}
-
-    if filtered:
+    elif filtered:
         # Filter the DataFrame to only include predicted no other arm activity (1)
         df = df.loc[df[DataColumns.PRED_NO_OTHER_ARM_ACTIVITY]==1].reset_index(drop=True)
 
-        # Group consecutive timestamps into segments, with new segments starting after a pre-specified gap
-        # Now segments are based on predicted gait without other arm activity for subsequent processes
+        # Group consecutive timestamps into segments of filtered gait
         df[DataColumns.SEGMENT_NR] = create_segments(
             time_array=df[DataColumns.TIME], 
             max_segment_gap_s=max_segment_gap_s
         )
 
-        pred_colname_pca = DataColumns.PRED_NO_OTHER_ARM_ACTIVITY
-    else:
-        pred_colname_pca = None
+        # Remove segments that do not meet predetermined criteria
+        df = discard_segments(
+            df=df,
+            segment_nr_colname=DataColumns.SEGMENT_NR,
+            min_segment_length_s=min_segment_length_s,
+            fs=fs,
+        )
+
+        if df.empty:
+            raise ValueError("No filtered gait segments found in the input data after discarding segments of invalid shape.")
+
+    arm_swing_quantified = []
+    segment_meta = {
+        'aggregated': {
+            'all': {
+                'duration_s': len(df[DataColumns.TIME]) / fs
+            },
+        },
+        'per_segment': {}
+    }
 
+    # PCA is fitted on only predicted gait without other arm activity if filtered, otherwise
+    # it is fitted on the entire gyroscope data
     df[DataColumns.VELOCITY] = pca_transform_gyroscope(
         df=df,
         y_gyro_colname=DataColumns.GYROSCOPE_Y,
         z_gyro_colname=DataColumns.GYROSCOPE_Z,
-        pred_colname=pred_colname_pca
     )
 
+    # Group and process segments
     for segment_nr, group in df.groupby(DataColumns.SEGMENT_NR, sort=False):
         segment_cat = group[DataColumns.SEGMENT_CAT].iloc[0]
         time_array = group[DataColumns.TIME].to_numpy()
@@ -452,8 +432,10 @@ def quantify_arm_swing(
             fs=fs,
         )
 
-        segment_meta[segment_nr] = {
-            'time_s': len(angle_array) / fs,
+        segment_meta['per_segment'][segment_nr] = {
+            'start_time_s': time_array.min(),
+            'end_time_s': time_array.max(),
+            'duration_s': len(angle_array) / fs,
             DataColumns.SEGMENT_CAT: segment_cat
         }
 
@@ -487,12 +469,20 @@ def quantify_arm_swing(
 
                 df_params_segment = pd.DataFrame({
                     DataColumns.SEGMENT_NR: segment_nr,
+                    DataColumns.SEGMENT_CAT: segment_cat,
                     DataColumns.RANGE_OF_MOTION: rom,
                     DataColumns.PEAK_VELOCITY: pav
                 })
 
                 arm_swing_quantified.append(df_params_segment)
 
+    # Combine segment categories
+    segment_categories = set([segment_meta['per_segment'][x][DataColumns.SEGMENT_CAT] for x in segment_meta['per_segment'].keys()])
+    for segment_cat in segment_categories:
+        segment_meta['aggregated'][segment_cat] = {
+            'duration_s': sum([segment_meta['per_segment'][x]['duration_s'] for x in segment_meta['per_segment'].keys() if segment_meta['per_segment'][x][DataColumns.SEGMENT_CAT] == segment_cat])
+        }
+
     arm_swing_quantified = pd.concat(arm_swing_quantified, ignore_index=True)
             
     return arm_swing_quantified, segment_meta
@@ -527,7 +517,7 @@ def aggregate_arm_swing_params(df_arm_swing_params: pd.DataFrame, segment_meta:
         cat_segments = [x for x in segment_meta.keys() if segment_meta[x][DataColumns.SEGMENT_CAT] == segment_cat]
 
         aggregated_results[segment_cat] = {
-            'time_s': sum([segment_meta[x]['time_s'] for x in cat_segments])
+            'duration_s': sum([segment_meta[x]['duration_s'] for x in cat_segments])
         }
 
         df_arm_swing_params_cat = df_arm_swing_params[df_arm_swing_params[DataColumns.SEGMENT_NR].isin(cat_segments)]
@@ -537,7 +527,7 @@ def aggregate_arm_swing_params(df_arm_swing_params: pd.DataFrame, segment_meta:
                 aggregated_results[segment_cat][f'{aggregate}_{arm_swing_parameter}'] = aggregate_parameter(df_arm_swing_params_cat[arm_swing_parameter], aggregate)
 
     aggregated_results['all_segment_categories'] = {
-        'time_s': sum([segment_meta[x]['time_s'] for x in segment_meta.keys()])
+        'duration_s': sum([segment_meta[x]['duration_s'] for x in segment_meta.keys()])
     }
 
     for arm_swing_parameter in arm_swing_parameters:

paradigma/pipelines/tremor_pipeline.py

@@ -163,8 +163,8 @@ def aggregate_tremor(df: pd.DataFrame, config: TremorConfig):
     Returns
     -------
     dict
-        A dictionary with the aggregated tremor time and tremor power measures, as well as the total number of windows
-        available in the input dataframe, and the number of windows at rest.
+        A dictionary with the aggregated tremor time and tremor power measures, as well as the number of valid days,
+        the total number of windows, and the number of windows at rest available in the input dataframe.
 
     Notes
     -----
@@ -173,7 +173,7 @@ def aggregate_tremor(df: pd.DataFrame, config: TremorConfig):
     - The modal tremor power is computed based on gaussian kernel density estimation.
   
     """
-
+    nr_valid_days = df['time_dt'].dt.date.unique().size # number of valid days in the input dataframe
     nr_windows_total = df.shape[0] # number of windows in the input dataframe
 
     # remove windows with detected non-tremor arm movements to control for the amount of arm activities performed
@@ -216,6 +216,7 @@ def aggregate_tremor(df: pd.DataFrame, config: TremorConfig):
     # store aggregates in json format
     d_aggregates = {
         'metadata': {
+            'nr_valid_days': nr_valid_days,
             'nr_windows_total': nr_windows_total,
             'nr_windows_rest': nr_windows_rest
         },

paradigma/preprocessing.py

@@ -17,7 +17,9 @@ def resample_data(
     df: pd.DataFrame,
     time_column : str,
     values_column_names: List[str],
+    sampling_frequency: int,
     resampling_frequency: int,
+    tolerance: float | None = None
 ) -> pd.DataFrame:
     """
     Resamples sensor data to a specified frequency using cubic interpolation.
@@ -30,8 +32,14 @@ def resample_data(
         The name of the column containing the time data.
     values_column_names : List[str]
         A list of column names that should be resampled.
+    sampling_frequency : int
+        The original sampling frequency of the data (in Hz).
     resampling_frequency : int
         The frequency to which the data should be resampled (in Hz).
+    tolerance : float, optional
+        The tolerance added to the expected difference when checking 
+        for contiguous timestamps. If not provided, it defaults to
+        twice the expected interval.
 
     Returns
     -------
@@ -46,23 +54,35 @@ def resample_data(
 
     Notes
     -----
-    The function uses cubic interpolation to resample the data to the specified frequency.
-    It requires the input time array to be strictly increasing.
+    - Uses cubic interpolation for smooth resampling if there are enough points.
+    - If only two timestamps are available, it falls back to linear interpolation.
     """
+    # Set default tolerance if not provided to twice the expected interval
+    if tolerance is None:
+        tolerance = 2 * 1 / sampling_frequency
 
-    # Extract time and values from DataFrame
+    # Extract time and values
     time_abs_array = np.array(df[time_column])
     values_array = np.array(df[values_column_names])
 
     # Ensure the time array is strictly increasing
     if not np.all(np.diff(time_abs_array) > 0):
-        raise ValueError("time_abs_array is not strictly increasing")
+        raise ValueError("Time array is not strictly increasing")
+    
+    # Ensure the time array is contiguous
+    expected_interval = 1 / sampling_frequency
+    timestamp_diffs = np.diff(time_abs_array)
+    if np.any(np.abs(timestamp_diffs - expected_interval) > tolerance):
+        raise ValueError("Time array is not contiguous")
 
     # Resample the time data using the specified frequency
     t_resampled = np.arange(time_abs_array[0], time_abs_array[-1], 1 / resampling_frequency)
     
-    # Interpolate the data using cubic interpolation
-    interpolator = interp1d(time_abs_array, values_array, axis=0, kind="cubic")
+    # Choose interpolation method
+    interpolation_kind = "cubic" if len(time_abs_array) > 3 else "linear"
+    interpolator = interp1d(time_abs_array, values_array, axis=0, kind=interpolation_kind, fill_value="extrapolate")
+    
+    # Interpolate
     resampled_values = interpolator(t_resampled)
 
     # Create a DataFrame with the resampled data
@@ -186,7 +206,8 @@ def preprocess_imu_data(df: pd.DataFrame, config: IMUConfig, sensor: str, watch_
     df = resample_data(
         df=df,
         time_column=DataColumns.TIME,
-        values_column_names = values_colnames,
+        values_column_names=values_colnames,
+        sampling_frequency=config.sampling_frequency,
         resampling_frequency=config.sampling_frequency
     )
 
@@ -259,6 +280,7 @@ def preprocess_ppg_data(df_ppg: pd.DataFrame, df_acc: pd.DataFrame, ppg_config:
         df=df_acc_overlapping,
         time_column=DataColumns.TIME,
         values_column_names = list(imu_config.d_channels_accelerometer.keys()),
+        sampling_frequency=imu_config.sampling_frequency,
         resampling_frequency=imu_config.sampling_frequency
     )
 
@@ -267,6 +289,7 @@ def preprocess_ppg_data(df_ppg: pd.DataFrame, df_acc: pd.DataFrame, ppg_config:
         df=df_ppg_overlapping,
         time_column=DataColumns.TIME,
         values_column_names = list(ppg_config.d_channels_ppg.keys()),
+        sampling_frequency=ppg_config.sampling_frequency,
         resampling_frequency=ppg_config.sampling_frequency
     )
 

paradigma/segmenting.py

@@ -168,7 +168,7 @@ def create_segments(
     gap_exceeds = time_diff > max_segment_gap_s
 
     # Create the segment number based on the cumulative sum of the gap_exceeds mask
-    segments = gap_exceeds.cumsum() + 1  # +1 to start enumeration from 1
+    segments = gap_exceeds.cumsum()
 
     return segments
 
@@ -236,6 +236,9 @@ def discard_segments(
 
     df = df[valid_segment_mask].copy()
 
+    if df.empty:
+        raise ValueError("All segments were removed.")
+
     # Reset segment numbers in a single step
     unique_segments = pd.factorize(df[segment_nr_colname])[0] + 1
     df[segment_nr_colname] = unique_segments

paradigma/testing.py

@@ -16,7 +16,7 @@ from paradigma.pipelines.tremor_pipeline import extract_tremor_features, detect_
 from paradigma.pipelines.heart_rate_pipeline import extract_signal_quality_features, signal_quality_classification, \
     aggregate_heart_rate
 from paradigma.preprocessing import preprocess_imu_data, preprocess_ppg_data
-from paradigma.util import read_metadata, write_df_data, get_end_iso8601
+from paradigma.util import read_metadata, write_df_data, get_end_iso8601, merge_predictions_with_timestamps
 
 
 def preprocess_imu_data_io(path_to_input: str | Path, path_to_output: str | Path, 
@@ -208,13 +208,27 @@ def extract_arm_activity_features_io(
 
     clf_package = ClassifierPackage.load(full_path_to_classifier_package)
 
+    gait_preprocessing_config = GaitConfig(step='gait')
+
+    df = merge_predictions_with_timestamps(
+        df_ts=df_ts, 
+        df_predictions=df_pred_gait, 
+        pred_proba_colname=DataColumns.PRED_GAIT_PROBA,
+        window_length_s=gait_preprocessing_config.window_length_s,
+        fs=gait_preprocessing_config.sampling_frequency
+    )
+
+    # Add a column for predicted gait based on a fitted threshold
+    df[DataColumns.PRED_GAIT] = (df[DataColumns.PRED_GAIT_PROBA] >= clf_package.threshold).astype(int)
+
+    # Filter the DataFrame to only include predicted gait (1)
+    df = df.loc[df[DataColumns.PRED_GAIT]==1].reset_index(drop=True)
+
     # Extract arm activity features
     config = GaitConfig(step='arm_activity')
     df_features = extract_arm_activity_features(
+        df=df, 
         config=config,
-        df_timestamps=df_ts, 
-        df_predictions=df_pred_gait, 
-        threshold=clf_package.threshold
     )
 
     end_iso8601 = get_end_iso8601(metadata_ts_values.start_iso8601, df_features[DataColumns.TIME][-1:].values[0] + config.window_length_s)

paradigma/util.py

@@ -1,9 +1,7 @@
-import json
 import os
 import numpy as np
 import pandas as pd
-from pathlib import Path
-from datetime import timedelta
+from datetime import datetime, timedelta
 from dateutil import parser
 from typing import List, Tuple
 
@@ -432,3 +430,61 @@ def merge_predictions_with_timestamps(
     df_ts = df_ts.dropna(subset=[pred_proba_colname])
 
     return df_ts
+
+
+def select_hours(df: pd.DataFrame, select_hours_start: str, select_hours_end: str) -> pd.DataFrame:
+    
+    """
+    Select hours of interest from the data to include in the aggregation step.
+
+    Parameters
+    ----------
+    df : pd.DataFrame
+        Input data.
+
+    select_hours_start: str
+        The start time of the selected hours in "HH:MM" format.
+    
+    select_hours_end: str
+            The end time of the selected hours in "HH:MM" format.
+
+    Returns
+    -------
+    pd.DataFrame
+        The selected data.
+
+    """
+
+    select_hours_start = datetime.strptime(select_hours_start, '%H:%M').time() # convert to time object
+    select_hours_end = datetime.strptime(select_hours_end, '%H:%M').time() 
+    df_subset = df[df['time_dt'].dt.time.between(select_hours_start, select_hours_end)] # select the hours of interest
+
+    return df_subset
+
+def select_days(df: pd.DataFrame, min_hours_per_day: int) -> pd.DataFrame:
+
+    """
+    Select days of interest from the data to include in the aggregation step.
+
+    Parameters
+    ----------
+    df : pd.DataFrame
+        Input data with column 'time_dt' in which the date is stored.
+
+    min_hours_per_day: int
+        The minimum number of hours per day required for including the day in the aggregation step.
+
+
+    Returns
+    -------
+    pd.DataFrame
+        The selected data.
+
+    """
+
+    min_s_per_day = min_hours_per_day * 3600
+    window_length_s = df['time_dt'].diff().dt.total_seconds()[1] # determine the length of the first window in seconds
+    min_windows_per_day = min_s_per_day / window_length_s
+    df_subset = df.groupby(df['time_dt'].dt.date).filter(lambda x: len(x) >= min_windows_per_day)
+
+    return df_subset

{paradigma-0.4.7.dist-info → paradigma-1.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: paradigma
-Version: 0.4.7
+Version: 1.0.0
 Summary: ParaDigMa - A toolbox for deriving Parkinson's disease Digital Markers from real-life wrist sensor data
 License: Apache-2.0
 Author: Erik Post
@@ -95,7 +95,7 @@ The ParaDigMa toolbox is designed for the analysis of passive monitoring data co
 Specific requirements include: 
 | Pipeline               | Sensor Configuration                                                                                                       | Context of Use                                                                                             |
 |------------------------|--------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------|
-| **All**               | - Sensor position: wrist-band on most or least affected side (validated for both, but different sensitivity for measuring disease progression for tremor and arm swing during gait).  <br> - Sensor orientation: orientation as described in [Coordinate System](https://biomarkersparkinson.github.io/paradigma/guides/coordinate_system.html). | - Population: persons with PD. <br> - Data collection protocol: passive monitoring in daily life. |
+| **All**               | - Sensor position: wrist-band on most or least affected side (validated for both, but different sensitivity for measuring disease progression for tremor and arm swing during gait).  <br> - Sensor orientation: orientation as described in [Coordinate System](https://biomarkersparkinson.github.io/paradigma/guides/coordinate_system.html). <br> - Timeframe: contiguous, strictly increasing timestamps. | - Population: persons with PD. <br> - Data collection protocol: passive monitoring in daily life. |
 | **Arm swing during gait** | - Accelerometer: minimum sampling rate of 100 Hz, minimum range of ± 4 g. <br> - Gyroscope: minimum sampling rate of 100 Hz, minimum range of ± 1000 degrees/sec. | - Population: no walking aid, no severe dyskinesia in the watch-sided arm. <br> - Compliance: for weekly measures: at least three compliant days (with ≥10 hours of data between 8 am and 10 pm), and at least 2 minutes of arm swing. |
 | **Tremor**            | - Gyroscope: minimum sampling rate of 100 Hz, minimum range of ± 1000 degrees/sec. | - Compliance: for weekly measures: at least three compliant days (with ≥10 hours of data between 8 am and 10 pm). |
 | **Pulse rate**        | - PPG*: minimum sampling rate of 30 Hz, green LED. <br> - Accelerometer: minimum sampling rate of 100 Hz, minimum range of ± 4 g. | - Population: no rhythm disorders (e.g. atrial fibrillation, atrial flutter). <br> - Compliance: for weekly measures: minimum average of 12 hours of data per day. |
@@ -111,8 +111,10 @@ We have included support for [TSDF](https://biomarkersparkinson.github.io/tsdf/)
 
 ## Scientific validation
 
-The pipelines were developed and validated using data from the Parkinson@Home Validation study [[Evers et al. 2020]](https://pmc.ncbi.nlm.nih.gov/articles/PMC7584982/) 
-and the Personalized Parkinson Project [[Bloem et al. 2019]](https://pubmed.ncbi.nlm.nih.gov/31315608/). Details and validation of the different pipelines shall be shared in upcoming scientific publications.
+The pipelines were developed and validated using data from the Parkinson@Home Validation study [[Evers et al. 2020]](https://pmc.ncbi.nlm.nih.gov/articles/PMC7584982/) and the Personalized Parkinson Project [[Bloem et al. 2019]](https://pubmed.ncbi.nlm.nih.gov/31315608/). The following publication contains the details and validation of the arm swing during gait pipeline:
+* [Post, E. et al. - Quantifying arm swing in Parkinson's disease: a method account for arm activities during free-living gait](https://doi.org/10.1186/s12984-025-01578-z)
+
+Details and validation of the other pipelines shall be shared in upcoming scientific publications.
 
 ## Contributing
 

{paradigma-0.4.7.dist-info → paradigma-1.0.0.dist-info}/RECORD

@@ -6,17 +6,17 @@ paradigma/assets/tremor_detection_clf_package.pkl,sha256=S-KsK1EcUBJX6oGGBo8GqU0
 paradigma/classification.py,sha256=sBJSePvwHZNPUQuLdx-pncfnDzMq-1naomsCxSJneWY,2921
 paradigma/config.py,sha256=72KkIEVV1v5dD9ZJDPI-mFNvorA8nBADEcA0A-jviHU,11163
 paradigma/constants.py,sha256=JlrD4Zx66g7myQALYAc4Gw_y6yW5EipZuvwj9_fjjpI,3543
-paradigma/feature_extraction.py,sha256=v_AwbBmvYo21XbULkOV6Ob_sZ1iboyXdDRRAsmCBh-Q,36061
+paradigma/feature_extraction.py,sha256=PAl9DgjTljxtifjPLpM1L_7xRs2fI6eUcybkaJ9kxAA,35323
 paradigma/pipelines/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-paradigma/pipelines/gait_pipeline.py,sha256=guz6RZlM0muarxG_GtOMf117XqV0YMNPrK2KlyIP4Jg,26426
+paradigma/pipelines/gait_pipeline.py,sha256=ZhAc2RZbBX52SJ8hvSRjb5THM47WCfY50iEdImlszJM,26231
 paradigma/pipelines/heart_rate_pipeline.py,sha256=0-D9KcW9nwE5sgXsWHONkeKrsX6qZ5BYqjDttoffwL8,17726
 paradigma/pipelines/heart_rate_utils.py,sha256=aV2mTMWrFWHZD0KpHqy3IIC1onZykbppyp7_OUWxFTU,26764
-paradigma/pipelines/tremor_pipeline.py,sha256=B5uZB3IP5pwb30PE4xztRbdYmZt4JQj193BRksC9N94,14590
-paradigma/preprocessing.py,sha256=-Vt_awvJe8MGqXACqWp7R6LWq6XFOcAVUyd0anNaytc,13506
-paradigma/segmenting.py,sha256=Jrz2JQX5eSfR9jBfpBhc6QV0SFmPVT5O6T8MyL0sdSw,13874
-paradigma/testing.py,sha256=DSbWeYl5HuZ-bNyOKwgwMHQGG8KlTabvGTR1Yzd-9CY,17955
-paradigma/util.py,sha256=MEoe0zWigxwqy6aVd8zKdHifiuUTc9Mqyrh4xsy1oHY,14759
-paradigma-0.4.7.dist-info/LICENSE,sha256=Lda8kIVC2kbmlSeYaUWwUwV75Q-q31idYvo18HUTfiw,9807
-paradigma-0.4.7.dist-info/METADATA,sha256=QIxavCCDzE1qxtls69w5vED0xgq8_tZB--qe1cXVfTE,11323
-paradigma-0.4.7.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
-paradigma-0.4.7.dist-info/RECORD,,
+paradigma/pipelines/tremor_pipeline.py,sha256=ihe6QeTk4MT_tXBE8PUN5rWNh2r5n5HCC1k4xyJjtUw,14761
+paradigma/preprocessing.py,sha256=OcrwiyNjZpw41IKCf9QRY75A-532kU4gSSSXjqWuTeE,14556
+paradigma/segmenting.py,sha256=hgT4dtg23eyvjUraEXCzX8u0kSRx4vArjQgF10r61P8,13909
+paradigma/testing.py,sha256=Ni68clfyHz_mQWBD8cDmls_uadd0rpKPq3-IKzolDZc,18547
+paradigma/util.py,sha256=E1keTX7vMDowSUG1AGx3juUMIXD7znaGwuqWDfQTpXo,16424
+paradigma-1.0.0.dist-info/LICENSE,sha256=Lda8kIVC2kbmlSeYaUWwUwV75Q-q31idYvo18HUTfiw,9807
+paradigma-1.0.0.dist-info/METADATA,sha256=rnOYOPZkoDVOMF0z9dDLfEulaCspPPjmGWjDtBgUDPI,11654
+paradigma-1.0.0.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
+paradigma-1.0.0.dist-info/RECORD,,

{paradigma-0.4.7.dist-info → paradigma-1.0.0.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 2.1.1
+Generator: poetry-core 2.1.2
 Root-Is-Purelib: true
 Tag: py3-none-any