Pre-release test version v2 (#127)

* Bump for pypi versioning (#124) * Bump for pypi versioning * Change authors * Update abstract readme and authorship * Update badge to general DOI * Change pathing to absolute * Bump versioning
biomarkersParkinson · Jan 21, 2025 · 09db1f7 · 09db1f7
1 parent 2887d24
commit 09db1f7
Show file tree

Hide file tree

Showing 4 changed files with 28 additions and 30 deletions.
diff --git a/docs/tutorials/gait_analysis.ipynb b/docs/tutorials/gait_analysis.ipynb
@@ -409,7 +409,8 @@
     "df_preprocessed = preprocess_imu_data(\n",
     "    df=df_imu, \n",
     "    config=config,\n",
-    "    sensor='both'\n",
+    "    sensor='both',\n",
+    "    watch_side='left',\n",
     ")\n",
     "\n",
     "print(f\"The dataset of {df_preprocessed.shape[0] / config.sampling_frequency} seconds is automatically resampled to {config.sampling_frequency} Hz.\")\n",
@@ -728,7 +729,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Out of 725 predictions, 53 (7.3%) were predicted as gait, and 672 (92.7%) as non-gait.\n"
+      "Out of 725 windows, 53 (7.3%) were predicted as gait, and 672 (92.7%) as non-gait.\n"
      ]
     },
     {
@@ -801,13 +802,13 @@
     }
    ],
    "source": [
+    "from importlib.resources import files\n",
     "from paradigma.classification import ClassifierPackage\n",
     "from paradigma.pipelines.gait_pipeline import detect_gait\n",
     "\n",
     "# Set the path to the classifier package\n",
-    "path_to_assets = Path('../../src/paradigma/assets')\n",
     "classifier_package_filename = 'gait_detection_clf_package.pkl'\n",
-    "full_path_to_classifier_package = path_to_assets / classifier_package_filename\n",
+    "full_path_to_classifier_package = files('paradigma') / 'assets' / classifier_package_filename\n",
     "\n",
     "# Load the classifier package\n",
     "clf_package = ClassifierPackage.load(full_path_to_classifier_package)\n",
@@ -1131,7 +1132,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Out of 50 predictions, 0 (0.0%) were predicted as no_other_arm_activity, and 50 (100.0%) as other_arm_activity.\n"
+      "Out of 50 windows, 0 (0.0%) were predicted as no_other_arm_activity, and 50 (100.0%) as other_arm_activity.\n"
      ]
     },
     {
@@ -1209,7 +1210,7 @@
     "\n",
     "# Set the path to the classifier package\n",
     "classifier_package_filename = 'gait_filtering_clf_package.pkl'\n",
-    "full_path_to_classifier_package = path_to_assets / classifier_package_filename\n",
+    "full_path_to_classifier_package = files('paradigma') / 'assets' / classifier_package_filename\n",
     "\n",
     "# Load the classifier package\n",
     "clf_package = ClassifierPackage.load(full_path_to_classifier_package)\n",
@@ -1221,8 +1222,6 @@
     "    clf_package=clf_package\n",
     ")\n",
     "\n",
-    "\n",
-    "\n",
     "n_windows = df_arm_activity.shape[0]\n",
     "n_predictions_no_other_arm_activity = df_arm_activity.loc[df_arm_activity['pred_no_other_arm_activity_proba']>=clf_package.threshold].shape[0]\n",
     "perc_predictions_no_other_arm_activity = round(100 * n_predictions_no_other_arm_activity / n_windows, 1)\n",
@@ -1435,16 +1434,16 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'long': {'time_s': 3.0,\n",
-      "          'median_range_of_motion': 14.612862824791089,\n",
-      "          '95p_range_of_motion': 19.29924826375146,\n",
-      "          'median_peak_velocity': 78.64563778043262,\n",
-      "          '95p_peak_velocity': 98.26817330011067},\n",
-      " 'moderately_long': {'time_s': 13.5,\n",
+      "{'moderately_long': {'time_s': 13.5,\n",
       "                     'median_range_of_motion': 14.394662839301768,\n",
       "                     '95p_range_of_motion': 22.658748546739268,\n",
       "                     'median_peak_velocity': 59.475147961606005,\n",
       "                     '95p_peak_velocity': 105.31356363194875},\n",
+      " 'long': {'time_s': 3.0,\n",
+      "          'median_range_of_motion': 14.612862824791089,\n",
+      "          '95p_range_of_motion': 19.29924826375146,\n",
+      "          'median_peak_velocity': 78.64563778043262,\n",
+      "          '95p_peak_velocity': 98.26817330011067},\n",
       " 'all_segment_categories': {'time_s': 16.5,\n",
       "                            'median_range_of_motion': 14.57460571480515,\n",
       "                            '95p_range_of_motion': 22.180208543070503,\n",

diff --git a/docs/tutorials/heart_rate_analysis.ipynb b/docs/tutorials/heart_rate_analysis.ipynb
@@ -36,7 +36,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -582,7 +582,7 @@
     "print(f\"Original data shapes:\\n- PPG data: {df_ppg.shape}\\n- Accelerometer data: {df_imu.shape}\")\n",
     "df_ppg_proc, df_acc_proc = preprocess_ppg_data(\n",
     "    df_ppg=df_ppg, \n",
-    "    df_imu=df_imu, \n",
+    "    df_acc=df_acc, \n",
     "    ppg_config=ppg_config, \n",
     "    imu_config=imu_config, \n",
     "    start_time_ppg=metadata_time_ppg.start_iso8601,\n",
@@ -1038,18 +1038,18 @@
     }
    ],
    "source": [
+    "from importlib.resources import files\n",
     "from paradigma.pipelines.heart_rate_pipeline import signal_quality_classification\n",
     "\n",
-    "path_to_assets = Path('../../src/paradigma/assets') \n",
     "ppg_quality_classifier_package_filename = 'ppg_quality_clf_package.pkl'\n",
-    "path_to_classifier_package = path_to_assets / ppg_quality_classifier_package_filename\n",
+    "full_path_to_classifier_package = files('paradigma') / 'assets' / ppg_quality_classifier_package_filename\n",
     "\n",
     "config = HeartRateConfig()\n",
     "\n",
     "df_sqa = signal_quality_classification(\n",
     "    df=df_features, \n",
     "    config=config, \n",
-    "    full_path_to_classifier_package=path_to_classifier_package\n",
+    "    full_path_to_classifier_package=full_path_to_classifier_package\n",
     ")\n",
     "\n",
     "df_sqa"
@@ -1219,7 +1219,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "paradigma-8ps1bg0Z-py3.12",
+   "display_name": "paradigma-Fn6RLG4_-py3.11",
    "language": "python",
    "name": "python3"
   },
@@ -1233,7 +1233,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.6"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,

diff --git a/docs/tutorials/tremor_analysis.ipynb b/docs/tutorials/tremor_analysis.ipynb
@@ -30,7 +30,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -221,7 +221,6 @@
     "# Set the path to where the prepared data is saved and load the data.\n",
     "# Note: the test data is stored in TSDF, but you can load your data in your own way\n",
     "path_to_data =  Path('../../tests/data')\n",
-    "path_to_assets = Path('../../src/paradigma/assets')\n",
     "path_to_prepared_data = path_to_data / '1.prepared_data' / 'imu'\n",
     "\n",
     "df_data, metadata_time, metadata_values = load_tsdf_dataframe(path_to_prepared_data, prefix='IMU')\n",
@@ -394,7 +393,7 @@
     "config = IMUConfig()\n",
     "print(f'The data is resampled to {config.sampling_frequency} Hz.')\n",
     "\n",
-    "df_preprocessed_data = preprocess_imu_data(df_data, config, sensor='gyroscope')\n",
+    "df_preprocessed_data = preprocess_imu_data(df_data, config, sensor='gyroscope', watch_side='left')\n",
     "\n",
     "df_preprocessed_data"
    ]
@@ -755,7 +754,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -917,20 +916,20 @@
        "[182 rows x 5 columns]"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "from importlib.resources import files\n",
     "from paradigma.pipelines.tremor_pipeline import detect_tremor\n",
     "\n",
     "print(f'A threshold of {config.movement_threshold} deg\\u00b2/s\\u00b2 is used to determine whether the arm is at rest or in stable posture.')\n",
     "\n",
     "# Load the pre-trained logistic regression classifier\n",
-    "path_to_assets = Path('../../src/paradigma/assets') \n",
     "tremor_detection_classifier_package_filename = 'tremor_detection_clf_package.pkl'\n",
-    "full_path_to_classifier_package = path_to_assets / tremor_detection_classifier_package_filename\n",
+    "full_path_to_classifier_package = files('paradigma') / 'assets' / tremor_detection_classifier_package_filename\n",
     "\n",
     "# Use the logistic regression classifier to detect tremor and check for rest tremor\n",
     "df_predictions = detect_tremor(df_features, config, full_path_to_classifier_package)\n",
@@ -954,7 +953,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {

diff --git a/src/paradigma/pipelines/gait_pipeline.py b/src/paradigma/pipelines/gait_pipeline.py
@@ -479,7 +479,7 @@ def quantify_arm_swing(
             # 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
             df_focus[DataColumns.SEGMENT_NR] = create_segments(
-                time_array=df[DataColumns.TIME], 
+                time_array=df_focus[DataColumns.TIME], 
                 max_segment_gap_s=max_segment_gap_s
             )
         else: