Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

WIP: Rewrite and simplify postprocessing using Dask #236

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
126 changes: 51 additions & 75 deletions nanshe_ipython.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -1201,15 +1201,7 @@
"### Postprocessing\n",
"\n",
"* `significance_threshold` (`float`): number of standard deviations below which to include in \"noise\" estimate\n",
"* `wavelet_scale` (`int`): scale of wavelet transform to apply (should be the same as the one used above)\n",
"* `noise_threshold` (`float`): number of units of \"noise\" above which something needs to be to be significant\n",
"* `accepted_region_shape_constraints` (`dict`): if ROIs don't match this, reduce the `wavelet_scale` once.\n",
"* `percentage_pixels_below_max` (`float`): upper bound on ratio of ROI pixels not at max intensity vs. all ROI pixels\n",
"* `min_local_max_distance` (`float`): minimum allowable euclidean distance between two ROIs maximum intensities\n",
"* `accepted_neuron_shape_constraints` (`dict`): shape constraints for ROI to be kept.\n",
"\n",
"* `alignment_min_threshold` (`float`): similarity measure of the intensity of two ROIs images used for merging.\n",
"* `overlap_min_threshold` (`float`): similarity measure of the masks of two ROIs used for merging."
"* `noise_threshold` (`float`): number of units of \"noise\" above which something needs to be to be significant"
]
},
{
Expand All @@ -1219,87 +1211,71 @@
"outputs": [],
"source": [
"significance_threshold = 3.0\n",
"wavelet_scale = 3\n",
"noise_threshold = 3.0\n",
"percentage_pixels_below_max = 0.8\n",
"min_local_max_distance = 16.0\n",
"noise_threshold = 2.5\n",
"\n",
"alignment_min_threshold = 0.6\n",
"overlap_min_threshold = 0.6\n",
"\n",
"\n",
"for k in zarr_store.get(subgroup_post, {}).keys():\n",
"for k in [\"post/zscore\", \"post/noise\", \"post/mask\"]:\n",
" with suppress(KeyError):\n",
" del dask_store[subgroup_post + \"/\" + k]\n",
" del dask_store[k]\n",
"with suppress(KeyError):\n",
" del zarr_store[subgroup_post]\n",
"zarr_store.require_group(subgroup_post)\n",
"\n",
"\n",
"imgs = dask_store._diskstore[subgroup_dict]\n",
"da_imgs = da.from_array(imgs, chunks=((1,) + imgs.shape[1:]))\n",
"\n",
"result = block_postprocess_data_parallel(client)(da_imgs,\n",
" **{\n",
" \"wavelet_denoising\" : {\n",
" \"estimate_noise\" : {\n",
" \"significance_threshold\" : significance_threshold\n",
" },\n",
" \"wavelet.transform\" : {\n",
" \"scale\" : wavelet_scale\n",
" },\n",
" \"significant_mask\" : {\n",
" \"noise_threshold\" : noise_threshold\n",
" },\n",
" \"accepted_region_shape_constraints\" : {\n",
" \"major_axis_length\" : {\n",
" \"min\" : 0.0,\n",
" \"max\" : 25.0\n",
" }\n",
" },\n",
" \"remove_low_intensity_local_maxima\" : {\n",
" \"percentage_pixels_below_max\" : percentage_pixels_below_max\n",
" },\n",
" \"remove_too_close_local_maxima\" : {\n",
" \"min_local_max_distance\" : min_local_max_distance\n",
" },\n",
" \"accepted_neuron_shape_constraints\" : {\n",
" \"area\" : {\n",
" \"min\" : 25,\n",
" \"max\" : 600\n",
" },\n",
" \"eccentricity\" : {\n",
" \"min\" : 0.0,\n",
" \"max\" : 0.9\n",
" }\n",
" }\n",
" },\n",
" \"merge_neuron_sets\" : {\n",
" \"alignment_min_threshold\" : alignment_min_threshold,\n",
" \"overlap_min_threshold\" : overlap_min_threshold,\n",
" \"fuse_neurons\" : {\n",
" \"fraction_mean_neuron_max_threshold\" : 0.01\n",
" }\n",
" }\n",
" }\n",
" del zarr_store[\"post\"]\n",
"zarr_store.require_group(\"post\")\n",
"\n",
"\n",
"da_imgs = dask_store[subgroup_dict]\n",
"\n",
"da_imgs_means = da_imgs.mean(axis=tuple(irange(1, da_imgs.ndim)), keepdims=True)\n",
"da_imgs_stds = da_imgs.std(axis=tuple(irange(1, da_imgs.ndim)), keepdims=True)\n",
"\n",
"da_imgs_zscore = (da_imgs - da_imgs_means) / da_imgs_stds\n",
"da_imgs_zscore_mag = abs(da_imgs_zscore)\n",
"\n",
"da_imgs_insignificant_mask = (da_imgs_zscore_mag < significance_threshold)\n",
"da_imgs_noise = da.atop(\n",
" lambda a, m: np.stack([np.nan_to_num(np.std(e_a[e_m])) for e_a, e_m in zip(a, m)]), (0,),\n",
" da_imgs, tuple(irange(da_imgs.ndim)),\n",
" da_imgs_insignificant_mask, tuple(irange(da_imgs.ndim)),\n",
" dtype=float,\n",
" concatenate=True\n",
")\n",
"da_imgs_noise = da_imgs_noise[(slice(None),) + (da_imgs.ndim - 1) * (None,)]\n",
"da_imgs_significant_mask = (da_imgs_zscore_mag >= (noise_threshold * da_imgs_noise / da_imgs_stds))\n",
"\n",
"# Store projections\n",
"dask_store.update(dict(zip(\n",
" [\"%s/%s\" % (subgroup_post, e) for e in result.dtype.names],\n",
" [result[e] for e in result.dtype.names]\n",
")))\n",
"\n",
"# dask_store[\"post2_mask\"] = da_imgs_significant_mask\n",
"dask_store.update({\n",
" \"post/noise\": da_imgs_noise,\n",
" \"post/zscore\": da_imgs_zscore,\n",
" \"post/mask\": da_imgs_significant_mask\n",
"})\n",
"\n",
"dask.distributed.progress(\n",
" dask.distributed.futures_of([\n",
" dask_store[\"%s/%s\" % (subgroup_post, e)]\n",
" for e in result.dtype.names\n",
" dask_store[\"post/noise\"],\n",
" dask_store[\"post/zscore\"],\n",
" dask_store[\"post/mask\"],\n",
" ]),\n",
" notebook=False\n",
")\n",
"print(\"\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"da_imgs = dask_store[\"post/mask\"].astype(np.uint8)\n",
"\n",
"mplsv = plt.figure(FigureClass=MPLViewer)\n",
"mplsv.set_images(\n",
" da_imgs,\n",
" vmin=0,\n",
" vmax=1\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down