Tutorial ppg #106

KarsVeldkamp · 2025-01-13T08:07:29Z

In this PR I created the tutorial for PPG but also did the following:

Changed the PPG preprocessing function (within preprocessing.py) to have a seperate io wrapper so I could load the tsdf data in memory before preprocessing. I did not include the loading function in the util.py while the other tsdf loading function is. Now I call it directly from tsdf --> what do you think of this?
Changed the ppg_analysis.ipynb accordingly
Changed from os.path.join to Path

… into heart_rate_estimation

…tead of imu

… into heart_rate_estimation

…rkinson/paradigma into pandas-to-numpy-ppg

… into pandas-to-numpy-ppg

…arkinson/paradigma into pandas-to-numpy-ppg

… into pandas-to-numpy-ppg

Erikpostt · 2025-01-13T15:01:03Z

docs/tutorials/heart_rate_analysis.ipynb

+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "For heart rate estimation, we extract segments of `config.tfd_length`. Using a 2-step approach, we calculate the smoothed-pseudo Wigner-Ville Distribution to obtain the frequency content of the PPG signal over time. For every 2-second window, we identified the frequency with the highest power for each data point and assigned the average of these frequency as the heart rate in that 2-second window. "


Also print the tsdf_length here.

What's the 2-step approach? Does it add value to mention it here?

Check the tense of your language: present vs past.

With data point you mean each timestamp constituting the 2-second window, right? How does each timestamp have a frequency spectrum? Does that have to do with the WVD?

And perhaps, could you explain what the relation is between "the average of these frequencies" and "the heart rate in that 2-second window"? I can't fully make that equation, might be useful to clarify how A represents B.

To comment on your last questions:

Yes WVD returns a frequency spectrum for every data point (because it uses every lag in the autocorrelation function)

We extract for every timestamp in that 2s window the frequency with the most power. This results in an array of "dominant" frequencies which I average.

I have tried to make this more self-explaining

Erikpostt · 2025-01-13T15:05:01Z

docs/tutorials/heart_rate_analysis.ipynb

+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>rel_time</th>\n",


What's relative time? Could you explain why this changed from time to rel_time?

Nothing, I'll adjust it to time ;)

Erikpostt · 2025-01-13T15:06:03Z

docs/tutorials/heart_rate_analysis.ipynb

+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The final step is to aggregate all 2-second heart rate estimates. In the current example, the mode and 99th percentile are calculated. The mode represent the resting heart rate while the 99th percentile indicates the maximum heart rate. In Parkinson's disease, we expect that these two measures could reflect autonomic (dys)functioning."


How is the mode representing the resting heart rate? Is this because the most prevalent heart rate is when we are resting?

Erikpostt · 2025-01-13T15:06:38Z

docs/tutorials/heart_rate_analysis.ipynb

+     "text": [
+      "{'hr_aggregates': {'99p_heart_rate': 86.62868369351669,\n",
+      "                   'mode_heart_rate': 84.8722986247544},\n",
+      " 'metadata': {'nr_hr_est': 6}}\n"


nr_hr_est is difficult for me to interpret, could you explain?

Erikpostt · 2025-01-13T15:08:31Z

src/paradigma/preprocessing.py

If people collect both accelerometer and PPG data, longitudinally, this function actually might make sense to have as a utility in the toolbox. I would move it to util.py therefore. I would leave all "necessary" functionalities in preprocessing.py.

I do think this functionality is tsdf-specific, so we should think about how a user using csv or other formats could do this.

I am not sure where you exactly referring to but I assume this is to scan_and_sync_segments? This is on my list to remove it from preprocessing and set it to util or another place and it is tsdf-specific indeed

Then also the extract_meta_from_tsdf_files will be removed in the preprocessing.py

Yes apologies, it's about scan_and_sync_segments. Check.

Erikpostt · 2025-01-13T15:09:05Z

src/paradigma/preprocessing.py

@@ -245,6 +245,21 @@ def preprocess_imu_data_io(path_to_input: str | Path, path_to_output: str | Path


 def scan_and_sync_segments(input_path_ppg, input_path_imu):


Please set strict data types for the input parameters.

Erikpostt · 2025-01-13T15:10:49Z

src/paradigma/preprocessing.py

+        Metadata for the IMU data.
+    output_path : Union[str, Path]
+        Path to store the preprocessed data.
+    ppg_config : PPGPreprocessingConfig


THis is very old documentation ;)

Erikpostt · 2025-01-13T15:10:55Z

src/paradigma/preprocessing.py

+    output_path : Union[str, Path]
+        Path to store the preprocessed data.
+    ppg_config : PPGPreprocessingConfig
+        Configuration object for PPG preprocessing.


Erikpostt · 2025-01-13T15:11:11Z

src/paradigma/preprocessing.py

+        Configuration object for PPG preprocessing.
+    imu_config : IMUPreprocessingConfig
+        Configuration object for IMU preprocessing.
+    sensor: str


This parameter is removed.

Erikpostt

I have raised some questions and made some suggestions. Let me know what you think.

… into tutorial-ppg

…/paradigma into tutorial-ppg

KarsVeldkamp · 2025-01-13T16:44:28Z

@Erikpostt I have made changes based on your feedback (visible in commit 40e768a. Let me know what you think of this

Erikpostt · 2025-01-13T17:46:16Z

docs/tutorials/heart_rate_analysis.ipynb

-    "The first step after loading the data is to preprocess the data. Preprocessing starts by extracting the data where there is both PPG and IMU data. In this way, we discard the the first or last part of the segment when e.g. the PPG segment is recorded longer than the accelerometer. After this step, the preprocess_ppg_data function  resamples the values of both PPG and accelerometer data using uniformly distributed timestamps, since the sampling rate of both sensors is fixed but not uniform. After this, a bandpass filter (butterworth, 4th-order, cut-off frequencies: [0.4, 3.5]) is applied to the PPG signal and a high-pass (butterworth, 4th-order, cut-off: 0.2 Hz) filter is applied to the accelerometer. "
+    "The first step after loading the data is preprocessing. This begins by isolating segments containing both PPG and IMU data, discarding portions where one modality (e.g., PPG) extends beyond the other, such as when the PPG recording is longer than the accelerometer data. After this step, the preprocess_ppg_data function resamples the PPG and accelerometer data to uniformly distributed timestamps, addressing the fixed but non-uniform sampling rates of the sensors. After this, a bandpass Butterworth filter (4th-order, bandpass frequencies: 0.4--3.5 Hz) is applied to the PPG signal, while a high-pass Butterworth filter (4th-order, cut-off frequency: 0.2 Hz) is applied to the accelerometer data.\n",
+    "\n",
+    "Note: the printed shapes are the data points (rows) and the data columns (rows x columns). The number of rows of the overlapping segments of PPG and accelerometer are not exactly the same due to sampling differences (other sensors and possibly other sampling frequencies). "


I think you meant to say (rows, columns), with each row corresponding to a single data points? Now it looks like rows are data points, and rows x columns are data columns.

Yes I made slight adjustments in this sentence

Erikpostt · 2025-01-13T17:47:43Z

docs/tutorials/heart_rate_analysis.ipynb

@@ -953,7 +968,7 @@
   "cell_type": "markdown",
   "metadata": {},
   "source": [
-    "A trained logistic classifier is used to classify PPG signal quality and returns the `pred_sqa_proba`, which is the posterior probability of a PPG window to look like the typical PPG morphology (higher probability indicates toward the typical PPG morphology). The relative power feature from the accelerometer is compared to a threshold for periodic artifacts and therefore `pred_sqa_acc_label` returns a label indicating probably periodic motion artifacts (label 0) or no periodic motion artifacts (label 1). "
+    "A trained logistic classifier is used to predicts PPG signal quality and returns the `pred_sqa_proba`, which is the posterior probability of a PPG window to look like the typical PPG morphology (higher probability indicates toward the typical PPG morphology). The relative power feature from the accelerometer is compared to a threshold for periodic artifacts and therefore `pred_sqa_acc_label` returns a label indicating predicted periodic motion artifacts (label 0) or no periodic motion artifacts (label 1). "


predicts = predict
returns = return (as in, "is used to return", but could also be "returns" as in "and it returns")

Erikpostt · 2025-01-13T17:48:46Z

docs/tutorials/heart_rate_analysis.ipynb

@@ -1090,14 +1105,21 @@
   "cell_type": "markdown",
   "metadata": {},
   "source": [
-    "For heart rate estimation, we extract segments of `config.tfd_length`. Using a 2-step approach, we calculate the smoothed-pseudo Wigner-Ville Distribution to obtain the frequency content of the PPG signal over time. For every 2-second window, we identified the frequency with the highest power for each data point and assigned the average of these frequency as the heart rate in that 2-second window. "
+    "For heart rate estimation, we extract segments of `config.tfd_length`. We calculate the smoothed-pseudo Wigner-Ville Distribution (SPWVD) to obtain the frequency content of the PPG signal over time. We extract for every timestamp in the SPWVD for the frequency with the highest power. For every non-overlapping 2-second window we average the corresponding frequencies to obtain a heart rate per window. "


"... SPWVD for the ..." should be "... SPWVD the ..."

Erikpostt · 2025-01-13T17:50:54Z

docs/tutorials/heart_rate_analysis.ipynb

@@ -1193,7 +1216,7 @@
   "cell_type": "markdown",
   "metadata": {},
   "source": [
-    "The final step is to aggregate all 2-second heart rate estimates. In the current example, the mode and 99th percentile are calculated. The mode represent the resting heart rate while the 99th percentile indicates the maximum heart rate. In Parkinson's disease, we expect that these two measures could reflect autonomic (dys)functioning."
+    "The final step is to aggregate all 2-second heart rate estimates. In the current example, the mode and 99th percentile are calculated. We hypothesize that the mode gives representation of the resting heart rate while the 99th percentile indicates the maximum heart rate. In Parkinson's disease, we expect that these two measures could reflect autonomic (dys)functioning. The `nr_hr_est` in the metadata indicates on how many 2-second windows these aggregates are determined."


Not sure, but should "... indicates on how many ..." be "... indicates based on how many ..."?

Also try to be consistent in using "2-second" or "2 s". I think I saw "2 s" somewhere.

Erikpostt · 2025-01-13T17:52:53Z

docs/tutorials/heart_rate_analysis.ipynb

    "ppg_config = SignalQualityFeatureExtractionConfig()\n",
    "acc_config = SignalQualityFeatureExtractionAccConfig()\n",
+    "print(\"The default window length for the signal quality feature extraction is set to\", ppg_config.window_length_s, \"seconds.\")\n",


This cell is a bit cluttered. Try to add some whitespaces

imports

configs

prints

function

print

This also applies to some other cells.

Erikpostt

I've made some small suggestions, otherwise ready to merge.

KarsVeldkamp · 2025-01-14T06:33:01Z

@Erikpostt Thanks for your feedback, I have made the last adjustments and will merge it now!

* change test output * Update tremor_analysis.ipynb * add documentation * fix bug * remove irrelevant config * resolved comments PR reviewer * remove data type since it causes pytype error * Simplify * Updating Poetry * clear execution count * Remove angle and velocity from preprocessing * import heart_rate_estimation * Change rotation axes * Adjust parameters segmentation * Add flexibility for pathing * Return a Series instead of df * ensure features dont scale when storing * Update tabulate windows * Heart rate estimation (#85) * Start heart rate estimation including tfd * stash updates * update based on merge conflicts * update hr main function * update minor stuff matlab files * change tfd parameters to dict * Finalizing heart rate pipeline plus renaming preprocessing to acc instead of imu * setting execution count to null * fix output types * fixing pytype due to old configs * fix min_hr_samples pytype error * remove irrelevant config * resolved comments PR reviewer * remove data type since it causes pytype error * clear execution count * clear execution counts * execution counts + indentation + short documentation * update final comments + small matlab changes * merge updates * Solve pytype issue * Solve pytype issue * added suggestions * remove execution counts * update ppg_analysis * test update notebook * execution counts * Vectorize merging of predictions with timestamps * Add flexibility to filtering gait parameters * Remove redundant cells in notebooks * Solve bugs * Solve conflict * Continue process when dataframe is empty * Modify quantification * Modify quantification * Typo * Add flexibility for pred proba to merging * Add flexibility for pred proba to merging * Add flexibility for pred proba to merging * Solve numpy/list bug * Solve numpy/list bug * Solve numpy/list bug * Solve numpy/list bug * Start catching errors * Start catching errors * Fix np.nan issue * Fix np.nan issue * Reduce memory reqs * Temp for debugging * Temp for debugging * Typo * replace df to numpy arrays * fix notebook * adding accelerometer feature * fix type error list vs float * Expand feature extraction docs * change notebook accordingly * Update notebooks * Add '1' to MFCC filter points * implement accelerometer feature * update matlab file based on refactoring * fixing types, docstrings and readibility * adding documentation acc feature * add documentation of autocorrelation * Pandas to numpy ppg (#93) * Start heart rate estimation including tfd * stash updates * update based on merge conflicts * update hr main function * update minor stuff matlab files * change tfd parameters to dict * First steps to refactoring to numpy * Finalizing heart rate pipeline plus renaming preprocessing to acc instead of imu * setting execution count to null * fix output types * fixing pytype due to old configs * fix min_hr_samples pytype error * remove irrelevant config * resolved comments PR reviewer * remove data type since it causes pytype error * clear execution count * import heart_rate_estimation * merge updates * update ppg_analysis * replace df to numpy arrays * fix notebook * fix type error list vs float * fixing types, docstrings and readibility * add documentation of autocorrelation --------- Co-authored-by: Erikpostt <erik_post_6@hotmail.com> * Modify test data * Change mfcc param * Change mfcc param * Structure * Reset legacy for the time being * Adjust test scripts to changes * Adjust tremor to changes * structure docstrings * Improve consistency of docstrings * Structure testing * Update test data * Resolve pytype error * Adjust tabulate_windows to new version * Ensure first column is returned for PPG * modify mfcc calculation and update classifier * Made requested changes * fix config * modify test data * Adding accelerometer to ppg (#95) * Start heart rate estimation including tfd * stash updates * update based on merge conflicts * update hr main function * update minor stuff matlab files * change tfd parameters to dict * First steps to refactoring to numpy * Finalizing heart rate pipeline plus renaming preprocessing to acc instead of imu * setting execution count to null * fix output types * fixing pytype due to old configs * fix min_hr_samples pytype error * remove irrelevant config * resolved comments PR reviewer * remove data type since it causes pytype error * clear execution count * import heart_rate_estimation * merge updates * update ppg_analysis * replace df to numpy arrays * fix notebook * adding accelerometer feature * fix type error list vs float * implement accelerometer feature * update matlab file based on refactoring * fixing types, docstrings and readibility * adding documentation acc feature * add documentation of autocorrelation * Made requested changes * fix config --------- Co-authored-by: Erikpostt <erik_post_6@hotmail.com> * add tutorial * Solve issues raised by reviewer * Rerun notebooks ppg * Change scalers, classifiers and thresholds * Update test files * Add aggregation of quantification * modified tutorial * update tutorial * remove execution counts * Add ability to create classifier objects * Test to remove rom features * Test to remove rom features * adding aggregation heart rate * Adjust functions to classification package * Update package loading * Adjust gait pipeline to classifier packages * added suggestions * Change test data with new classifier * Adjust tests and ensure Path used in notebooks * Change pathing to fix poetry pytest * restructure functions * update test data * update tutorial * fixed typo's * Merge with main * update aggregates * remove config * Add files via upload * add start tutorial * aggregation implementation with dictionary * add lines for consistency * Add user guides for coordinate system and update index of docs * moved windoweddataextractor to segmenting * Displays outputs of data preparation tutorial * Heart rate aggregation (#102) * Start heart rate estimation including tfd * stash updates * update based on merge conflicts * update hr main function * update minor stuff matlab files * change tfd parameters to dict * First steps to refactoring to numpy * Finalizing heart rate pipeline plus renaming preprocessing to acc instead of imu * setting execution count to null * fix output types * fixing pytype due to old configs * fix min_hr_samples pytype error * remove irrelevant config * resolved comments PR reviewer * remove data type since it causes pytype error * clear execution count * import heart_rate_estimation * merge updates * update ppg_analysis * replace df to numpy arrays * fix notebook * adding accelerometer feature * fix type error list vs float * implement accelerometer feature * update matlab file based on refactoring * fixing types, docstrings and readibility * adding documentation acc feature * add documentation of autocorrelation * Made requested changes * fix config * adding aggregation heart rate * update aggregates * remove config * aggregation implementation with dictionary * add lines for consistency * moved windoweddataextractor to segmenting * updates based on review --------- Co-authored-by: Erikpostt <erik_post_6@hotmail.com> * resolve merge conflict * add tremor classifier package * update notebook * remove execution counts * Modify according to feedback of reviewer * update test function * Concat forward & backward pav to allow for dataframes * Renaming functions * Add error messages when df is empty * Print -> Raise eerror messages when df is empty * Also raise when no gait without other arm activity * Remove irrelevant test files and raise valuerrors * Reset to io wrappers * Update docstrings * update loading + preprocessing with seperate functionality * update tutorial notebook and corresponding notebook * change path usage * Update test to io function * Update README.md * print notebook output * change total psd * add function links * Faster computation using any() * Remove unnecessary improts * Tutorial ppg (#106) * Start heart rate estimation including tfd * stash updates * update based on merge conflicts * update hr main function * update minor stuff matlab files * change tfd parameters to dict * First steps to refactoring to numpy * Finalizing heart rate pipeline plus renaming preprocessing to acc instead of imu * setting execution count to null * fix output types * fixing pytype due to old configs * fix min_hr_samples pytype error * remove irrelevant config * resolved comments PR reviewer * remove data type since it causes pytype error * clear execution count * import heart_rate_estimation * merge updates * update ppg_analysis * replace df to numpy arrays * fix notebook * adding accelerometer feature * fix type error list vs float * implement accelerometer feature * update matlab file based on refactoring * fixing types, docstrings and readibility * adding documentation acc feature * add documentation of autocorrelation * Made requested changes * fix config * adding aggregation heart rate * update aggregates * remove config * add start tutorial * aggregation implementation with dictionary * add lines for consistency * moved windoweddataextractor to segmenting * resolve merge conflict * update loading + preprocessing with seperate functionality * update tutorial notebook and corresponding notebook * Update test to io function * update tutorial and notebook with simplified loading of the data * Reset execution counts in notebook cells * update execution_counts and output * Updates from PR feedback * fix type error * made final feedback --------- Co-authored-by: Erikpostt <erik_post_6@hotmail.com> Co-authored-by: Erik Post <57133568+Erikpostt@users.noreply.github.com> * Resolve merge conflict * add suggestions * Move notebooks to parent directory and remove subdirectories * change total_psd_calculation again * Modify structure of files * Update classifier, update test data, update dependencies, update testing gait pipeline * Update dtypes heart rate pipeline * Reset scikit version, update tremor values * Remove notebook temporarily to pass tests * Reduce no. of configs and change notebooks accordingly * Update test data * Remove redundant files * final suggestions * Modify tremor low freq power and slightly adjust tutorial * Change git attributes to ensure output in tutorials * Test displaying output tutorials * Test displaying output tutorials * Test II * Update config and remove nbstripout from gitattributes * Add tutorial outputs other domains * Merge conflict heart rate pipeline * Merge conflicts gait pipeline * Merge conflicts gait pipeline * Update notebooks * Revert time to first binary file * Add suggestions * Iterate on tutorial gait * Complete gait pipeline * Classifier package ppg (#109) * Start heart rate estimation including tfd * stash updates * update based on merge conflicts * update hr main function * update minor stuff matlab files * change tfd parameters to dict * First steps to refactoring to numpy * Finalizing heart rate pipeline plus renaming preprocessing to acc instead of imu * setting execution count to null * fix output types * fixing pytype due to old configs * fix min_hr_samples pytype error * remove irrelevant config * resolved comments PR reviewer * remove data type since it causes pytype error * clear execution count * import heart_rate_estimation * merge updates * update ppg_analysis * replace df to numpy arrays * fix notebook * adding accelerometer feature * fix type error list vs float * implement accelerometer feature * update matlab file based on refactoring * fixing types, docstrings and readibility * adding documentation acc feature * add documentation of autocorrelation * Made requested changes * fix config * adding aggregation heart rate * update aggregates * remove config * add start tutorial * aggregation implementation with dictionary * add lines for consistency * moved windoweddataextractor to segmenting * resolve merge conflict * update loading + preprocessing with seperate functionality * update tutorial notebook and corresponding notebook * Update test to io function * update tutorial and notebook with simplified loading of the data * Reset execution counts in notebook cells * update execution_counts and output * Updates from PR feedback * fix type error * remove unneccessary matlab files * update merge conflicts * update using classifier package * fix pkl feature names in scaler and delete old classifier files * renaming ppg to heart rate * rename files ppg to heart_rate * remove legacy classification * renaming clf_package * modify tutorial * update abs stats * update tutorial based on abs stats output * Remove redundant stuff from notebook * remove tremor txt files * update tutorial based on right config settings * type error fix * fix type error * update based on suggestions --------- Co-authored-by: Erikpostt <erik_post_6@hotmail.com> Co-authored-by: Erik Post <57133568+Erikpostt@users.noreply.github.com> * Add tutorial data * Update tutorial per reviewers remarks * Remove output notebooks * Update docs * DRAFT: Update sync functions (#115) * Start heart rate estimation including tfd * stash updates * update based on merge conflicts * update hr main function * update minor stuff matlab files * change tfd parameters to dict * First steps to refactoring to numpy * Finalizing heart rate pipeline plus renaming preprocessing to acc instead of imu * setting execution count to null * fix output types * fixing pytype due to old configs * fix min_hr_samples pytype error * remove irrelevant config * resolved comments PR reviewer * remove data type since it causes pytype error * clear execution count * import heart_rate_estimation * merge updates * update ppg_analysis * replace df to numpy arrays * fix notebook * adding accelerometer feature * fix type error list vs float * implement accelerometer feature * update matlab file based on refactoring * fixing types, docstrings and readibility * adding documentation acc feature * add documentation of autocorrelation * Made requested changes * fix config * adding aggregation heart rate * update aggregates * remove config * add start tutorial * aggregation implementation with dictionary * add lines for consistency * moved windoweddataextractor to segmenting * resolve merge conflict * update loading + preprocessing with seperate functionality * update tutorial notebook and corresponding notebook * Update test to io function * Update notebook with functional links * move scan_and_sync_segments to util with corresponding functions * remove ppp functionalities from util * Correct implementation of the extract_overlapping_segments * update tests without scan_and_sync_segments * updates based on suggestions * fix type error --------- Co-authored-by: Erikpostt <erik_post_6@hotmail.com> * Major reshuffling of files and directories * Adding nbsphinx * update tutorials functional links + preprocessing * Update readme contact (#119) --------- Co-authored-by: nienketimmermans <65012819+nienketimmermans@users.noreply.github.com> Co-authored-by: KarsVeldkamp <veldkampkars@gmail.com> Co-authored-by: KarsVeldkamp <105375796+KarsVeldkamp@users.noreply.github.com>

KarsVeldkamp and others added 30 commits December 3, 2024 08:36

Start heart rate estimation including tfd

0cb88b0

Merge branch 'main' of https://github.com/biomarkersParkinson/paradigma…

d1b0bca

… into heart_rate_estimation

stash updates

0c639e1

Merge branch 'main' of https://github.com/biomarkersParkinson/paradigma…

4d0b4ab

… into heart_rate_estimation

update based on merge conflicts

9b17130

update hr main function

6184107

Merge branch 'main' of https://github.com/biomarkersParkinson/paradigma…

747a427

… into heart_rate_estimation

update minor stuff matlab files

ab3e4bf

change tfd parameters to dict

44190aa

First steps to refactoring to numpy

e3c8703

Merge branch 'main' of https://github.com/biomarkersParkinson/paradigma…

53e9665

… into heart_rate_estimation

Finalizing heart rate pipeline plus renaming preprocessing to acc ins…

bd0f46f

…tead of imu

setting execution count to null

3aad804

fix output types

937ea0e

fixing pytype due to old configs

9938768

fix min_hr_samples pytype error

8ede2ae

remove irrelevant config

3037503

resolved comments PR reviewer

122f955

Merge branch 'main' of https://github.com/biomarkersParkinson/paradigma…

e59b811

… into heart_rate_estimation

remove data type since it causes pytype error

c720677

clear execution count

5a0ec6b

Merge branch 'pandas-to-numpy-ppg' of https://github.com/biomarkersPa…

dfa313d

…rkinson/paradigma into pandas-to-numpy-ppg

import heart_rate_estimation

8d76ba0

Merge branch 'main' of https://github.com/biomarkersParkinson/paradigma…

e3b526b

… into pandas-to-numpy-ppg

merge updates

2bff61c

Merge branch 'create-prepared-data' of https://github.com/biomarkersP…

6a1298f

…arkinson/paradigma into pandas-to-numpy-ppg

update ppg_analysis

e571514

Merge branch 'main' of https://github.com/biomarkersParkinson/paradigma…

b907cf6

… into pandas-to-numpy-ppg

replace df to numpy arrays

07072a9

fix notebook

0a1858a

Erikpostt reviewed Jan 13, 2025

View reviewed changes

Erikpostt requested changes Jan 13, 2025

View reviewed changes

KarsVeldkamp and others added 5 commits January 13, 2025 17:35

Updates from PR feedback

40e768a

Merge branch 'main' of https://github.com/biomarkersParkinson/paradigma…

9f1442e

… into tutorial-ppg

Merge branch 'main' into tutorial-ppg

854d5fc

Merge branch 'tutorial-ppg' of https://github.com/biomarkersParkinson…

81c6580

…/paradigma into tutorial-ppg

fix type error

440160c

KarsVeldkamp assigned Erikpostt and unassigned Erikpostt Jan 13, 2025

KarsVeldkamp requested a review from Erikpostt January 13, 2025 16:44

Erikpostt reviewed Jan 13, 2025

View reviewed changes

Erikpostt approved these changes Jan 13, 2025

View reviewed changes

made final feedback

529744e

KarsVeldkamp merged commit 3eafaf7 into main Jan 14, 2025
1 check passed

KarsVeldkamp deleted the tutorial-ppg branch January 14, 2025 06:33

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Tutorial ppg #106

Tutorial ppg #106

KarsVeldkamp commented Jan 13, 2025 •

edited

Loading

Erikpostt Jan 13, 2025

Erikpostt Jan 13, 2025

Erikpostt Jan 13, 2025

Erikpostt Jan 13, 2025

KarsVeldkamp Jan 13, 2025

KarsVeldkamp Jan 13, 2025

Erikpostt Jan 13, 2025

KarsVeldkamp Jan 13, 2025

Erikpostt Jan 13, 2025

KarsVeldkamp Jan 13, 2025

Erikpostt Jan 13, 2025

KarsVeldkamp Jan 13, 2025

Erikpostt Jan 13, 2025

Erikpostt Jan 13, 2025

KarsVeldkamp Jan 13, 2025

KarsVeldkamp Jan 13, 2025

Erikpostt Jan 13, 2025

Erikpostt Jan 13, 2025

Erikpostt Jan 13, 2025

KarsVeldkamp Jan 13, 2025

Erikpostt Jan 13, 2025

Erikpostt Jan 13, 2025

Erikpostt left a comment

KarsVeldkamp commented Jan 13, 2025

Erikpostt Jan 13, 2025

KarsVeldkamp Jan 14, 2025

Erikpostt Jan 13, 2025

Erikpostt Jan 13, 2025

Erikpostt Jan 13, 2025

Erikpostt Jan 13, 2025

Erikpostt Jan 13, 2025

Erikpostt left a comment

KarsVeldkamp commented Jan 14, 2025

		@@ -245,6 +245,21 @@ def preprocess_imu_data_io(path_to_input: str \| Path, path_to_output: str \| Path


		def scan_and_sync_segments(input_path_ppg, input_path_imu):

Tutorial ppg #106

Tutorial ppg #106

Conversation

KarsVeldkamp commented Jan 13, 2025 • edited Loading

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Erikpostt left a comment

Choose a reason for hiding this comment

KarsVeldkamp commented Jan 13, 2025

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Erikpostt left a comment

Choose a reason for hiding this comment

KarsVeldkamp commented Jan 14, 2025

KarsVeldkamp commented Jan 13, 2025 •

edited

Loading