-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add sample notebooks for NWB and SLEAP analyses. Closes #13
- Loading branch information
1 parent
9230c28
commit 04851ba
Showing
7 changed files
with
430 additions
and
19 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,4 +1,4 @@ | ||
| __version__ = "0.6.0" | ||
| __version__ = "0.6.1" | ||
|
|
||
| # Suppress tensorflow import text... | ||
| import os | ||
|
|
||
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,200 @@ | ||
| { | ||
| "cells": [ | ||
| { | ||
| "attachments": {}, | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "# Demo workflow\n", | ||
| "\n", | ||
| "Demonstrate simple workflow for case where only pose data is available (no behavior labels)" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "from ethome import create_dataset, interpolate_lowconf_points\n", | ||
| "from ethome.io import get_sample_nwb_paths\n", | ||
| "from ethome.unsupervised import compute_umap_embedding\n", | ||
| "from ethome.plot import plot_embedding, interactive_tracks" | ||
| ] | ||
| }, | ||
| { | ||
| "attachments": {}, | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "Gather some sample tracking files to play with" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "nwb_file = get_sample_nwb_paths()" | ||
| ] | ||
| }, | ||
| { | ||
| "attachments": {}, | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "Nwb files already contain metedata about the tracking, so we don't have to provide this ourselves:" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "#%% Create dataset\n", | ||
| "dataset = create_dataset(nwb_file)\n", | ||
| "dataset" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "dataset.pose.body_parts" | ||
| ] | ||
| }, | ||
| { | ||
| "attachments": {}, | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "Checkout the tracks with a widget" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "%matplotlib inline\n", | ||
| "filename = dataset.metadata.videos[0]\n", | ||
| "interactive_tracks(dataset,\n", | ||
| " filename)" | ||
| ] | ||
| }, | ||
| { | ||
| "attachments": {}, | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "Smooth over low-confidence points" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "interpolate_lowconf_points(dataset)" | ||
| ] | ||
| }, | ||
| { | ||
| "attachments": {}, | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "Now create features on this dataset. Can use pre-built featuresets, or make your own. \n", | ||
| "As we don't have a resident-intruder setup, here we use generic featuresets. " | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "dataset.features.add('distances')" | ||
| ] | ||
| }, | ||
| { | ||
| "attachments": {}, | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## Unsupervised learning" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "#%%################\n", | ||
| "## Dim reduction ##\n", | ||
| "###################\n", | ||
| "\n", | ||
| "embedding = compute_umap_embedding(dataset, dataset.features.active, N_rows = 10000)\n", | ||
| "dataset[['embedding_0', 'embedding_1']] = embedding" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "fig, ax = plot_embedding(dataset) " | ||
| ] | ||
| }, | ||
| { | ||
| "attachments": {}, | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## Post processing\n", | ||
| "\n", | ||
| "Now we have our model we can make a video of its predictions. Provide the column names whose state we're going to overlay on the video, along with the directory to output the videos.\n", | ||
| "\n", | ||
| "NOTE: need to have provided 'video' column in the metadata to make movies." | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "dataset.io.save_movie(['label', 'prediction'], '.')" | ||
| ] | ||
| } | ||
| ], | ||
| "metadata": { | ||
| "kernelspec": { | ||
| "display_name": "ethome", | ||
| "language": "python", | ||
| "name": "python3" | ||
| }, | ||
| "language_info": { | ||
| "codemirror_mode": { | ||
| "name": "ipython", | ||
| "version": 3 | ||
| }, | ||
| "file_extension": ".py", | ||
| "mimetype": "text/x-python", | ||
| "name": "python", | ||
| "nbconvert_exporter": "python", | ||
| "pygments_lexer": "ipython3", | ||
| "version": "3.8.10" | ||
| }, | ||
| "orig_nbformat": 4 | ||
| }, | ||
| "nbformat": 4, | ||
| "nbformat_minor": 2 | ||
| } |
Oops, something went wrong.