def test_load_recording():
recording.get_demo_recordings()
nems_dir = os.path.abspath(os.path.dirname(__file__) + '/..')
targz = nems_dir + '/recordings/TAR010c-18-1.tgz'
rec = recording.load_recording(targz)
def test_load_recording():
get_demo_recordings(name='TAR010c.NAT.fs100.ch18.tgz')
targz = join(RECORDING_DIR, 'TAR010c.NAT.fs100.ch18.tgz')
rec = load_recording(targz)
def main():
import argparse
relative_signals_dir = '/../recordings'
signals_dir = os.path.dirname(nems.uri.__file__) + relative_signals_dir
signals_dir = os.path.abspath(signals_dir)
parser = argparse.ArgumentParser('Download NEMS demo data')
parser.add_argument(
'--directory',
type=str,
default=signals_dir,
help=
'Storage location for recordings (defaults to <nemspath>/recordings)',
)
parser.add_argument(
'--unpack',
action='store_true',
help='Recordings compressed by default, set --unpack to decompress')
args = parser.parse_args()
directory = args.directory if args.directory else None
unpack = args.unpack if args.unpack else None
get_demo_recordings(directory, unpack)
def test_plots():
recording.get_demo_recordings(name=recording_file)
rec = recording.load_recording(uri)
resp = rec['resp'].rasterize()
stim = rec['stim'].rasterize()
epoch_regex = "^STIM_"
stim_epochs = ep.epoch_names_matching(resp.epochs, epoch_regex)
r = resp.as_matrix(stim_epochs) * resp.fs
s = stim.as_matrix(stim_epochs)
repcount = np.sum(np.isfinite(r[:, :, 0, 0]), axis=1)
max_rep_id, = np.where(repcount == np.max(repcount))
t = np.arange(r.shape[-1]) / resp.fs
plt.figure()
ax = plt.subplot(3, 1, 1)
nplt.plot_spectrogram(s[max_rep_id[-1], 0, :, :],
fs=stim.fs,
ax=ax,
title="cell {} - stim".format(cellid))
ax = plt.subplot(3, 1, 2)
nplt.raster(t, r[max_rep_id[-1], :, 0, :], ax=ax, title='raster')
ax = plt.subplot(3, 1, 3)
nplt.psth_from_raster(t,
r[max_rep_id[-1], :, 0, :],
ax=ax,
title='raster',
ylabel='spk/s')
plt.tight_layout()
import nems.initializers
import nems.recording as recording
import nems.uri
from nems.fitters.api import scipy_minimize
from nems.signal import RasterizedSignal
log = logging.getLogger(__name__)
# CONFIGURATION
# figure out data and results paths:
signals_dir = Path(nems.NEMS_PATH) / 'recordings'
modelspecs_dir = Path(nems.NEMS_PATH) / 'modelspecs'
# download demo data
recording.get_demo_recordings(signals_dir)
datafile = signals_dir / 'TAR010c-18-1.pkl'
# LOAD AND FORMAT RECORDING DATA
with open(datafile, 'rb') as f:
#cellid, recname, fs, X, Y, X_val, Y_val = pickle.load(f)
cellid, recname, fs, X, Y, epochs = pickle.load(f)
# create NEMS-format recording objects from the raw data
resp = RasterizedSignal(fs, Y, 'resp', recname, chans=[cellid])
stim = RasterizedSignal(fs, X, 'stim', recname)
# create the recording object from the signals
signals = {'resp': resp, 'stim': stim}
est = recording.Recording(signals)
import nems.xforms as xforms
# ----------------------------------------------------------------------------
# GLOBAL CONFIGURATION
log = logging.getLogger(__name__)
# figure out data and results paths:
results_dir = nems.get_setting('NEMS_RESULTS_DIR')
signals_dir = nems.get_setting('NEMS_RECORDINGS_DIR')
# ----------------------------------------------------------------------------
# DATA LOADING & PRE-PROCESSING
# Download demo recordings
recording.get_demo_recordings()
datafile = os.path.join(signals_dir, "TAR010c.NAT.fs100.ch18.tgz")
exptid = "TAR010c"
batch = 271
cellid = "TAR010c-18-2"
# SINGLE MODEL SPEC
# LN model
modelspecname = 'dlog-wc.18x3.g-fir.3x15-relu.1'
# Simple CNN
#modelspecname = 'wc.18x3-fir.1x10x3-relu.3-wc.3xR-lvl.R'
import nems.recording as recording
import nems.xforms as xforms
import nems.tf.cnn as cnn
import nems.tf.cnnlink as cnnlink
log = logging.getLogger(__name__)
# ----------------------------------------------------------------------------
# CONFIGURATION
# figure out data and results paths:
results_dir = nems.get_setting('NEMS_RESULTS_DIR')
signals_dir = nems.get_setting('NEMS_RECORDINGS_DIR')
# ----------------------------------------------------------------------------
# DATA LOADING & PRE-PROCESSING
"""
recording.get_demo_recordings(name="TAR010c-18-1.pkl")
datafile = os.path.join(signals_dir, "TAR010c-18-1.pkl")
load_command = 'nems.demo.loaders.demo_loader'
exptid = "TAR010c"
batch = 271
cellid = "TAR010c-18-1"
"""
datafile = os.path.join(
signals_dir, "TAR010c_272b438ce3a5643e3e474206861096ce3ffdc000.tgz")
load_command = 'nems.demo.loaders.demo_loader'
exptid = "TAR010c"
batch = 271
siteid = "TAR010c"
import os
from nems.recording import load_recording, get_demo_recordings
import nems.plots.api as nplt
import nems.epoch as ep
#site = "TAR010c"
# site = "BRT033b"
site = "bbl099g"
# use this line to load recording from server.
#uri = 'http://hearingbrain.org/tmp/'+site+'.tgz'
# alternatively download the file, save and load from local file:
filename = site + '.NAT.fs200.tgz'
recording_path = get_demo_recordings(name=filename)
# uri = '/path/to/recording/' + site + '.tgz'
uri = os.path.join(recording_path, filename)
rec = load_recording(uri)
epochs = rec.epochs
is_stim = epochs['name'].str.startswith('STIM')
stim_epoch_list = epochs[is_stim]['name'].tolist()
stim_epochs = list(set(stim_epoch_list))
stim_epochs.sort()
epoch = stim_epochs[11]
resp = rec['resp'].rasterize()
import nems.recording as recording
import nems.uri
import nems.xforms as xforms
# ----------------------------------------------------------------------------
# CONFIGURATION
log = logging.getLogger(__name__)
# figure out data and results paths:
results_dir = nems.get_setting('NEMS_RESULTS_DIR')
signals_dir = nems.get_setting('NEMS_RECORDINGS_DIR')
# ----------------------------------------------------------------------------
# DATA LOADING & PRE-PROCESSING
recording.get_demo_recordings(name="TAR010c-18-1.pkl")
datafile = os.path.join(signals_dir, "TAR010c-18-1.pkl")
load_command = 'nems.demo.loaders.demo_loader'
exptid = "TAR010c"
batch = 271
cellid = "TAR010c-18-1"
# MODEL SPEC
#modelspecname = 'wc.18x1.g-fir.1x15-lvl.1'
modelspecname = 'dlog-wc.18x1.g-fir.1x15-lvl.1-dexp.1'
#modelspecname = 'dlog-wc.18x1.g-stp.1.q.s-fir.1x15-lvl.1-dexp.1'
#modelspecname = 'dlog-wc.18x2.g-do.2x15-lvl.1-dexp.1'
#modelspecname = 'dlog.f-wc.18x1.g-stp.1.s-do.1x15-lvl.1'
#modelspecname = 'dlog.f-wc.18x1.g-stp2.1.s-do.1x15-lvl.1'
# figure out data and results paths:
nems_dir = os.path.abspath(os.path.dirname(recording.__file__) + '/..')
signals_dir = nems_dir + '/recordings'
modelspecs_dir = nems_dir + '/modelspecs'
# ----------------------------------------------------------------------------
# DATA LOADING
#
# GOAL: Get your data loaded into memory as a Recording object
logging.info('Loading data...')
# Method #1: Load the data from a local directory
# download demo data if necessary:
recording.get_demo_recordings(signals_dir, name="TAR010c-18-1.tgz")
# load into a recording object
rec = recording.load_recording(signals_dir + "/TAR010c-18-1.tgz")
# ----------------------------------------------------------------------------
# DATA PREPROCESSING
#
# GOAL: Split your data into estimation and validation sets so that you can
# know when your model exhibits overfitting.
if True:
# aside - generate datasets from scratch
X = rec['stim'].as_continuous()
Y = rec['resp'].as_continuous()
batch = 271
cellid = "TAR010c-18-2"
# 100Hz, no pupil
recording_file = "TAR010c.NAT.fs100.ch18.tgz"
# MODEL SPEC
modelname = 'ld-sev_dlog-wc.18x1.g-fir.1x15-lvl.1-dexp.1_init-basic'
# 50Hz, pupil
#recording_file = "TAR010c.NAT.fs50.ch18.pup.tgz"
# MODEL SPEC
#modelname = 'ld-st.pup-tev_dlog-wc.18x1.g-fir.1x15-lvl.1-stategain.2-dexp.1_init.st-basic'
recording.get_demo_recordings(name=recording_file)
recording_uri = os.path.join(get_setting('NEMS_RECORDINGS_DIR'),
recording_file)
# run and return
xfspec, ctx = fit_model_xform(cellid,
batch,
modelname,
recording_uri=recording_uri,
returnModel=True)
ex = gui.browse_xform_fit(ctx, xfspec)
# run and save to database
#saveuri = fit_model_xform(cellid, batch, modelname, recording_uri=recording_uri, saveInDB=True)
