update tutorial with best practices and Black formatting (#1656)

* update tutorial with best practices and Black formatting

* update tutorial with best practices and Black formatting

* Update docs/gallery/advanced_io/linking_data.py

* Update docs/gallery/advanced_io/linking_data.py

* Update docs/gallery/advanced_io/plot_iterative_write.py

* Apply default black to gallery files

* Fixes

* Bug fix

* Use isort in gallery files

* downgrade flake8

* Fix

* Fix windows issue

* Update req-dev

---------

Co-authored-by: Ryan Ly <[email protected]>

Author: bendichter

docs/gallery/advanced_io/h5dataio.py

@@ -1,11 +1,11 @@
-'''
+"""
 Defining HDF5 Dataset I/O Settings (chunking, compression, etc.)
 ================================================================
 
 The HDF5 storage backend supports a broad range of advanced dataset I/O options, such as,
 chunking and compression. Here we demonstrate how to use these features
 from PyNWB.
-'''
+"""
 
 ####################
 # Wrapping data arrays with :py:class:`~hdmf.backends.hdf5.h5_utils.H5DataIO`
@@ -19,30 +19,33 @@
 #
 
 from datetime import datetime
+
 from dateutil.tz import tzlocal
+
 from pynwb import NWBFile
 
 start_time = datetime(2017, 4, 3, 11, tzinfo=tzlocal())
-create_date = datetime(2017, 4, 15, 12, tzinfo=tzlocal())
 
-nwbfile = NWBFile(session_description='demonstrate advanced HDF5 I/O features',
-                  identifier='NWB123',
-                  session_start_time=start_time,
-                  file_create_date=create_date)
+nwbfile = NWBFile(
+    session_description="demonstrate advanced HDF5 I/O features",
+    identifier="NWB123",
+    session_start_time=start_time,
+)
 
 
 ####################
 # Normally if we create a :py:class:`~pynwb.file.TimeSeries` we would do
 
-from pynwb import TimeSeries
 import numpy as np
 
+from pynwb import TimeSeries
+
 data = np.arange(100, 200, 10)
 timestamps = np.arange(10)
 test_ts = TimeSeries(
-    name='test_regular_timeseries',
+    name="test_regular_timeseries",
     data=data,
-    unit='SIunit',
+    unit="SIunit",
     timestamps=timestamps,
 )
 nwbfile.add_acquisition(test_ts)
@@ -52,10 +55,11 @@
 # :py:class:`~hdmf.backends.hdf5.h5_utils.H5DataIO`. Everything else remains the same
 
 from hdmf.backends.hdf5.h5_utils import H5DataIO
+
 test_ts = TimeSeries(
-    name='test_compressed_timeseries',
-    data=H5DataIO(data=data, compression=True),   # <----
-    unit='SIunit',
+    name="test_compressed_timeseries",
+    data=H5DataIO(data=data, compression=True),  # <----
+    unit="SIunit",
     timestamps=timestamps,
 )
 nwbfile.add_acquisition(test_ts)
@@ -91,13 +95,13 @@
 data = np.arange(10000).reshape((1000, 10))
 wrapped_data = H5DataIO(
     data=data,
-    chunks=True,          # <---- Enable chunking
+    chunks=True,  # <---- Enable chunking
     maxshape=(None, 10),  # <---- Make the time dimension unlimited and hence resizable
 )
 test_ts = TimeSeries(
-    name='test_chunked_timeseries',
-    data=wrapped_data,    # <----
-    unit='SIunit',
+    name="test_chunked_timeseries",
+    data=wrapped_data,  # <----
+    unit="SIunit",
     starting_time=0.0,
     rate=10.0,
 )
@@ -122,7 +126,7 @@
 
 ####################
 # Compression and Other I/O Filters
-# -----------------------------------
+# ---------------------------------
 #
 # HDF5 supports I/O filters, i.e, data transformation (e.g, compression) that are applied transparently on
 # read/write operations.  I/O filters operate on a per-chunk basis in HDF5 and as such require the use of chunking.
@@ -133,13 +137,13 @@
 
 wrapped_data = H5DataIO(
     data=data,
-    compression='gzip',              # <---- Use GZip
-    compression_opts=4,              # <---- Optional GZip aggression option
+    compression="gzip",  # <---- Use GZip
+    compression_opts=4,  # <---- Optional GZip aggression option
 )
 test_ts = TimeSeries(
-    name='test_gzipped_timeseries',
-    data=wrapped_data,                # <----
-    unit='SIunit',
+    name="test_gzipped_timeseries",
+    data=wrapped_data,  # <----
+    unit="SIunit",
     starting_time=0.0,
     rate=10.0,
 )
@@ -160,7 +164,7 @@
 
 from pynwb import NWBHDF5IO
 
-with NWBHDF5IO('advanced_io_example.nwb', 'w') as io:
+with NWBHDF5IO("advanced_io_example.nwb", "w") as io:
     io.write(nwbfile)
 
 ####################
@@ -170,17 +174,17 @@
 #
 # Nothing has changed for read. All the above advanced I/O features are handled transparently.
 
-io = NWBHDF5IO('advanced_io_example.nwb', 'r')
+io = NWBHDF5IO("advanced_io_example.nwb", "r")
 nwbfile = io.read()
 
 ####################
 # Now lets have a look to confirm that all our I/O settings where indeed used.
 
 for k, v in nwbfile.acquisition.items():
-    print("name=%s, chunks=%s, compression=%s, maxshape=%s" % (k,
-                                                               v.data.chunks,
-                                                               v.data.compression,
-                                                               v.data.maxshape))
+    print(
+        "name=%s, chunks=%s, compression=%s, maxshape=%s"
+        % (k, v.data.chunks, v.data.compression, v.data.maxshape)
+    )
 io.close()
 ####################
 #
@@ -228,8 +232,8 @@
 # This command automatically installs the filters. Here is an example of how you would use the Z Standard algorithm:
 
 import hdf5plugin
-
 from hdmf.backends.hdf5.h5_utils import H5DataIO
+
 from pynwb.file import TimeSeries
 
 wrapped_data = H5DataIO(
@@ -239,9 +243,9 @@
 )
 
 test_ts = TimeSeries(
-    name='test_gzipped_timeseries',
+    name="test_gzipped_timeseries",
     data=wrapped_data,
-    unit='SIunit',
+    unit="SIunit",
     starting_time=0.0,
     rate=10.0,
 )
@@ -262,7 +266,7 @@
 
 ####################
 # Disclaimer
-# ----------------
+# ----------
 #
 # External links included in the tutorial are being provided as a convenience and for informational purposes only;
 # they do not constitute an endorsement or an approval by the authors of any of the products, services or opinions of

docs/gallery/advanced_io/linking_data.py

@@ -60,60 +60,53 @@
 from datetime import datetime
 from uuid import uuid4
 
-from dateutil.tz import tzlocal
-from pynwb import NWBFile
-from pynwb import TimeSeries
-from pynwb import NWBHDF5IO
 import numpy as np
+from dateutil.tz import tzlocal
+
+from pynwb import NWBHDF5IO, NWBFile, TimeSeries
 
 # Create the base data
 start_time = datetime(2017, 4, 3, 11, tzinfo=tzlocal())
 data = np.arange(1000).reshape((100, 10))
 timestamps = np.arange(100)
-filename1 = 'external1_example.nwb'
-filename2 = 'external2_example.nwb'
-filename3 = 'external_linkcontainer_example.nwb'
-filename4 = 'external_linkdataset_example.nwb'
+filename1 = "external1_example.nwb"
+filename2 = "external2_example.nwb"
+filename3 = "external_linkcontainer_example.nwb"
+filename4 = "external_linkdataset_example.nwb"
 
 # Create the first file
 nwbfile1 = NWBFile(
-    session_description="my first synthetic recording",
+    session_description="demonstrate external files",
     identifier=str(uuid4()),
-    session_start_time=datetime.now(tzlocal()),
-    experimenter=["Baggins, Bilbo", ],
-    lab="Bag End Laboratory",
-    institution="University of Middle Earth at the Shire",
-    experiment_description="I went on an adventure to reclaim vast treasures.",
-    session_id="LONELYMTN001",
+    session_start_time=start_time,
 )
 # Create the second file
-test_ts1 = TimeSeries(name='test_timeseries1',
-                      data=data,
-                      unit='SIunit',
-                      timestamps=timestamps)
+test_ts1 = TimeSeries(
+    name="test_timeseries1", data=data, unit="SIunit", timestamps=timestamps
+)
 nwbfile1.add_acquisition(test_ts1)
 
 # Write the first file
-with NWBHDF5IO(filename1, 'w') as io:
+with NWBHDF5IO(filename1, "w") as io:
     io.write(nwbfile1)
 
 # Create the second file
 nwbfile2 = NWBFile(
-    session_description='demonstrate external files',
+    session_description="demonstrate external files",
     identifier=str(uuid4()),
     session_start_time=start_time,
 )
 # Create the second file
 test_ts2 = TimeSeries(
-    name='test_timeseries2',
+    name="test_timeseries2",
     data=data,
-    unit='SIunit',
+    unit="SIunit",
     timestamps=timestamps,
 )
 nwbfile2.add_acquisition(test_ts2)
 
 # Write the second file
-with NWBHDF5IO(filename2, 'w') as io:
+with NWBHDF5IO(filename2, "w") as io:
     io.write(nwbfile2)
 
 
@@ -128,7 +121,7 @@
 
 # Create the first file
 nwbfile4 = NWBFile(
-    session_description='demonstrate external files',
+    session_description="demonstrate external files",
     identifier=str(uuid4()),
     session_start_time=start_time,
 )
@@ -141,9 +134,9 @@
 #
 
 # Get the first timeseries
-io1 = NWBHDF5IO(filename1, 'r')
+io1 = NWBHDF5IO(filename1, "r")
 nwbfile1 = io1.read()
-timeseries_1 = nwbfile1.get_acquisition('test_timeseries1')
+timeseries_1 = nwbfile1.get_acquisition("test_timeseries1")
 timeseries_1_data = timeseries_1.data
 
 ####################
@@ -154,9 +147,9 @@
 
 # Create a new timeseries that links to our data
 test_ts4 = TimeSeries(
-    name='test_timeseries4',
-    data=timeseries_1_data,   # <-------
-    unit='SIunit',
+    name="test_timeseries4",
+    data=timeseries_1_data,  # <-------
+    unit="SIunit",
     timestamps=timestamps,
 )
 nwbfile4.add_acquisition(test_ts4)
@@ -172,10 +165,9 @@
 
 # Create another timeseries that links to the same data
 test_ts5 = TimeSeries(
-    name='test_timeseries5',
-    data=H5DataIO(data=timeseries_1_data,     # <-------
-                  link_data=True),            # <-------
-    unit='SIunit',
+    name="test_timeseries5",
+    data=H5DataIO(data=timeseries_1_data, link_data=True),  # <-------
+    unit="SIunit",
     timestamps=timestamps,
 )
 nwbfile4.add_acquisition(test_ts5)
@@ -184,9 +176,9 @@
 # Step 4: Write the data
 # ^^^^^^^^^^^^^^^^^^^^^^^
 #
-with NWBHDF5IO(filename4, 'w') as io4:
-    io4.write(nwbfile4,
-              link_data=True)     # <-------- Specify default behavior to link rather than copy data
+with NWBHDF5IO(filename4, "w") as io4:
+    # Use link_data=True to specify default behavior to link rather than copy data
+    io4.write(nwbfile4, link_data=True)
 io1.close()
 
 #####################
@@ -223,14 +215,14 @@
 #
 
 # Get the first timeseries
-io1 = NWBHDF5IO(filename1, 'r', manager=manager)
+io1 = NWBHDF5IO(filename1, "r", manager=manager)
 nwbfile1 = io1.read()
-timeseries_1 = nwbfile1.get_acquisition('test_timeseries1')
+timeseries_1 = nwbfile1.get_acquisition("test_timeseries1")
 
 # Get the second timeseries
-io2 = NWBHDF5IO(filename2, 'r', manager=manager)
+io2 = NWBHDF5IO(filename2, "r", manager=manager)
 nwbfile2 = io2.read()
-timeseries_2 = nwbfile2.get_acquisition('test_timeseries2')
+timeseries_2 = nwbfile2.get_acquisition("test_timeseries2")
 
 ####################
 # Step 2: Add the container to another NWBFile
@@ -243,15 +235,15 @@
 
 # Create a new NWBFile that links to the external timeseries
 nwbfile3 = NWBFile(
-    session_description='demonstrate external files',
+    session_description="demonstrate external files",
     identifier=str(uuid4()),
     session_start_time=start_time,
 )
-nwbfile3.add_acquisition(timeseries_1)             # <--------
-nwbfile3.add_acquisition(timeseries_2)             # <--------
+nwbfile3.add_acquisition(timeseries_1)  # <--------
+nwbfile3.add_acquisition(timeseries_2)  # <--------
 
 # Write our third file that includes our two timeseries as external links
-with NWBHDF5IO(filename3, 'w', manager=manager) as io3:
+with NWBHDF5IO(filename3, "w", manager=manager) as io3:
     io3.write(nwbfile3)
 io1.close()
 io2.close()