Merge pull request #354 from AllenInstitute/dev

Dev

.codespellrc

@@ -0,0 +1,8 @@
+[codespell]
+# Ref: https://github.com/codespell-project/codespell#using-a-config-file
+skip = .git,.codespellrc
+check-hidden = true
+# Ignore embedded or returned images in ipynb and some acronyms
+ignore-regex = ((^\s*"image/\S+": "|<img src='data:image/\S+;base64,).*|\bSOM\b)
+#ignore-regex = image/\S+.*
+ignore-words-list = nin

.github/workflows/codespell.yml

@@ -0,0 +1,23 @@
+# Codespell configuration is within .codespellrc
+---
+name: Codespell
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+jobs:
+  codespell:
+    name: Check for spelling errors
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2

data/contributors.csv

@@ -0,0 +1,17 @@
+Name,ORCID,Institution,Email,Github,Funding,Role
+Katrina Ager,,Arizona State University,[email protected],https://github.com/katrinaager,,"Processing"
+Ahad Bawany,,Allen Institute,[email protected],https://github.com/Ahad-Allen,,"Processing"
+Corbett Bennett,0009-0001-2847-7754,Allen Institute,[email protected],https://github.com/corbennett,,"Processing"
+Benjamin Dichter,0000-0001-5725-6910,CatalystNeuro,[email protected],https://github.com/bendichter,,"Conceptualization"
+Satrajit Ghosh,0000-0002-5312-6729,Massachusetts Institute of Technology,[email protected],https://github.com/satra,NIH R24MH117295,"Conceptualization"
+Colleen J. Gillon,0000-0002-2253-7816,Imperial College London,[email protected],https://github.com/colleenjg,,"Processing"
+Carly Kiselycznyk,,Allen Institute,[email protected],,,"Management"
+Jerome Lecoq,0000-0002-0131-0938,Allen Institute,[email protected],https://github.com/jeromelecoq,,"Conceptualization, Management"
+Mackenzie Mathis,0000-0001-7368-4456,Swiss Federal Institute of Technology in Lausanne,[email protected],https://github.com/MMathisLab,,"Review"
+NIH,,,,,,"Funding"
+R. Carter Peene,0009-0000-6660-2264,Allen Institute,[email protected],rcpeene,,"Conceptualization, Processing"
+Jason Pina,0000-0003-1385-8762,York University,[email protected],https://github.com/jayepi,,"Conceptualization"
+Hyeyoung Shin,,Seoul National University,[email protected],https://github.com/hs13,,"Conceptualization"
+Josh Siegle,,Allen Institute,[email protected],https://github.com/jsiegle,NIH U24,"Processing"
+Jacob Westerberg,0000-0001-5331-8707,Netherlands Institute for Neuroscience,[email protected],https://github.com/jakewesterberg,,"Conceptualization"
+Alex Williams,0000-0001-5853-103X,New York University,[email protected],https://github.com/ahwillia,,"Review"

data/ecephys_schema.csv

@@ -101,7 +101,7 @@ electrodes,Electrode IDs,array,nwb.electrodes.id,IDs column of the electrodes ta
 electrodes,Electrode X Coordinates,array,nwb.electrodes.x,CCF X coordinates column of the electrodes table. Represents the X location of electrodes along a probe.
 electrodes,Electrode Y Coordinates,array,nwb.electrodes.y,CCF Y coordinates column of the electrodes table. Represents the Y location of electrodes along a probe.
 electrodes,Electrode Z Coordinates,array,nwb.electrodes.z,CCF Z coordinates column of the electrodes table. Represents the Z location of electrodes along a probe.
-electrodes,Impedance,array,nwb.electrodes.imp,Impedence column of the electrodes table. Unused in our data.
+electrodes,Impedance,array,nwb.electrodes.imp,Impedance column of the electrodes table. Unused in our data.
 electrodes,Electrode Locations,array,nwb.electrodes.location,Brain region acronyms column of the electrodes table
 electrodes,Electrode Filters,array,nwb.electrodes.filtering,Column of the electrodes table describing the list of filters applied to each electrode.
 electrodes,Electrode Groups,array,nwb.electrodes.group,References to group object column of the electrodes table

databook_utils/cred_assign_utils.py

@@ -142,7 +142,7 @@ def create_roi_mask_contours(df_row, sess_idx=0, cw=1):
 
     Returns:
         - roi_masks (2D array):
-            ROI mask contour image (hei x wid), overlayed for all ROIs, 
+            ROI mask contour image (hei x wid), overlaid for all ROIs, 
             with 1s where mask contours are present, and 0s elsewhere.
     """
 

databook_utils/dandi_utils.py

@@ -1,12 +1,12 @@
 
 import h5py
 import os
+import remfile
+
 from random import randint
 
 from dandi import download
 from dandi import dandiapi
-from fsspec.implementations.cached import CachingFileSystem
-from fsspec import filesystem
 from pynwb import NWBHDF5IO
 
 
@@ -49,11 +49,7 @@ def dandi_stream_open(dandiset_id, dandi_filepath, dandi_api_key=None):
     base_url = file.client.session.head(file.base_download_url)
     file_url = base_url.headers["Location"]
 
-    fs = CachingFileSystem(
-        fs=filesystem("http")
-    )
-
-    f = fs.open(file_url, "rb")
-    file = h5py.File(f)
-    io = NWBHDF5IO(file=file, mode='r', load_namespaces=True)
+    rem_file = remfile.File(file_url)
+    h5py_file = h5py.File(rem_file, "r")
+    io = NWBHDF5IO(file=h5py_file, mode="r", load_namespaces=True)
     return io

databook_utils/insert_authors_version.py

@@ -1,6 +1,7 @@
-import os
+import csv
 import subprocess
 
+
 from docutils import nodes
 from docutils.parsers.rst import Directive
 
@@ -14,30 +15,30 @@ def setstring_to_set(setstring):
 # possible todo: replace this with ast.eval_literal
 def dictstring_to_dict(dictstring):
 	dictstring = dictstring.replace(", ", ",")
-	dictstring = dictstring.replace(": ", ":")
+	dictstring = dictstring.replace("-- ", "--")
 	dictlist = dictstring.split(",")
 
 	this_dict = {}
 	for elem in dictlist:
 		try:
-			key, val = elem.split(":")
+			key, val = elem.split("--")
 		except:
 			raise ValueError("Aliases should be formatted in key value pairs, delimited by a colon")
 		if key not in this_dict:
 			this_dict[key] = val
 	return this_dict
 
 
-class AuthorsList(Directive):
+class Committers(Directive):
 
 	optional_arguments = 3
 	option_spec = {"blacklist": setstring_to_set, "additional_authors": setstring_to_set, "aliases": dictstring_to_dict}
 
 	def run(self):
-		blacklist= self.options.get("blacklist", set())
+		blacklist= self.options.get("blacklist", "blah")
 		additional_authors = self.options.get("additional_authors", set()) 
 		aliases = self.options.get("aliases", {})
-
+		
 		log = subprocess.Popen(["git", "log"], stdout=subprocess.PIPE, text=True)
 		shortlog = subprocess.check_output(["git", "shortlog", "-sn"], stdin=log.stdout, encoding="utf8")
 		print(shortlog)
@@ -54,6 +55,28 @@ def run(self):
 		return [emphasis_node]
 
 
+class Authors(Directive):
+
+	optional_arguments = 1
+	option_spec = {"role": str}
+
+	def run(self):
+		authors = []
+
+		selected_role = self.options.get("role", "")
+
+		table = list(csv.reader(open("./data/contributors.csv")))
+		role_idx = table[0].index("Role")
+		name_idx = table[0].index("Name")
+		for contributor in table[1:]:
+			contributor_roles = contributor[role_idx].split(", ")
+			if selected_role == "" or selected_role in contributor_roles:
+				authors.append(contributor[name_idx])
+
+		emphasis_node = nodes.emphasis(text=", ".join(authors))
+		return [emphasis_node]
+
+
 class VersionNumber(Directive):
 
 	optional_arguments = 1
@@ -74,9 +97,38 @@ def run(self):
 		return [paragraph_node]
 
 
+class AuthorsIndex(Directive):
+
+	def run(self):
+		table = list(csv.reader(open("./data/contributors.csv")))
+
+		section = nodes.section(ids=["contributorsblock"])
+		section += nodes.title("","Contributors")
+		for idx, properties in enumerate(table):
+			if idx == 0:
+				continue
+			entry = nodes.section(ids=["contributorentry"])
+
+			name = properties[0]
+			entry.append(nodes.strong(text=name))
+
+			line_block = nodes.line_block()				
+			for property in properties[1:]:
+				if property != "":
+					line_block.append(nodes.line(text=property))
+			line_block.append(nodes.line(text=""))
+
+			entry.append(line_block)
+			section.append(entry)
+
+		return [section]
+
+
 def setup(app):
-	app.add_directive("authors", AuthorsList)
+	app.add_directive("committers", Committers)
 	app.add_directive("version", VersionNumber)
+	app.add_directive("authors", Authors)
+	app.add_directive("authors_index", AuthorsIndex)
 
 	return {
 		'version': '0.1',

docs/_config.yml

@@ -23,6 +23,7 @@ sphinx:
   extra_extensions:
     - insert_authors_version
     - sphinx.ext.intersphinx
+
 repository:
   url: https://github.com/AllenInstitute/openscope_databook
   path_to_book: docs

docs/_toc.yml

@@ -48,7 +48,9 @@ parts:
   - file: methods/jupyter_book.md
   - file: methods/github.md
   - file: methods/environments.md
-- caption: Bibliography and FAQ
+- caption: Appendix
   chapters:
+  - file: contribution.md
   - file: bibliography.md
-  - file: FAQ.md
+  - file: authors_index.md
+  - file: FAQ.md

docs/authors_index.md

@@ -0,0 +1,3 @@
+
+```{authors_index}
+```

docs/basics/download_nwb.ipynb

@@ -26,7 +26,7 @@
    "outputs": [],
    "source": [
     "try:\n",
-    "    from dandi_utils import dandi_stream_open\n",
+    "    from databook_utils.dandi_utils import dandi_stream_open\n",
     "except:\n",
     "    !git clone https://github.com/AllenInstitute/openscope_databook.git\n",
     "    %cd openscope_databook\n",