Deprecate processing.bincount2D (moved to iblutil) (#638)

chris-langfield · web-flow · commit d0997f911d2f · 2023-08-10T10:06:36.000-04:00
* deprecate

* undo version bump

* flake
diff --git a/brainbox/behavior/dlc.py b/brainbox/behavior/dlc.py
@@ -12,7 +12,7 @@
 from scipy.stats import zscore
 
 from neurodsp.smooth import smooth_interpolate_savgol
-from brainbox.processing import bincount2D
+from iblutil.numerical import bincount2D
 import brainbox.behavior.wheel as bbox_wheel
 
 logger = logging.getLogger('ibllib')
diff --git a/brainbox/ephys_plots.py b/brainbox/ephys_plots.py
@@ -3,7 +3,8 @@
 import matplotlib.pyplot as plt
 from brainbox.plot_base import (ImagePlot, ScatterPlot, ProbePlot, LinePlot, plot_line,
                                 plot_image, plot_probe, plot_scatter, arrange_channels2banks)
-from brainbox.processing import bincount2D, compute_cluster_average
+from brainbox.processing import compute_cluster_average
+from iblutil.numerical import bincount2D
 from ibllib.atlas.regions import BrainRegions
 
 
diff --git a/brainbox/examples/dim_reduction.py b/brainbox/examples/dim_reduction.py
@@ -8,7 +8,7 @@
 from sklearn.decomposition import PCA, FactorAnalysis, FastICA
 from one.api import ONE
 
-from brainbox.processing import bincount2D
+from iblutil.numerical import bincount2D
 
 
 def find_nearest(array, value):
diff --git a/brainbox/examples/raster_cluster_ordered.py b/brainbox/examples/raster_cluster_ordered.py
@@ -5,7 +5,7 @@
 from oneibl.one import ONE
 import alf.io as ioalf
 import ibllib.plots as iblplt
-from brainbox.processing import bincount2D
+from iblutil.numerical import bincount2D
 
 T_BIN = 0.01
 
diff --git a/brainbox/examples/raster_clusters.py b/brainbox/examples/raster_clusters.py
@@ -6,7 +6,7 @@
 import alf.io as ioalf
 import ibllib.plots as iblplt
 
-from brainbox.processing import bincount2D
+from iblutil.numerical import bincount2D
 
 T_BIN = 0.01
 
diff --git a/brainbox/examples/raster_depths.py b/brainbox/examples/raster_depths.py
@@ -8,7 +8,7 @@
 from oneibl.one import ONE
 import ibllib.plots as iblplt
 
-from brainbox.processing import bincount2D
+from iblutil.numerical import bincount2D
 from brainbox.io import one as bbone
 
 T_BIN = 0.05
diff --git a/brainbox/examples/raster_per_trial.py b/brainbox/examples/raster_per_trial.py
@@ -1,6 +1,6 @@
 import numpy as np
 import alf.io
-from brainbox.processing import bincount2D
+from iblutil.numerical import bincount2D
 import matplotlib.pyplot as plt
 import ibllib.plots as iblplt
 
diff --git a/brainbox/examples/xcorr_numpy.py b/brainbox/examples/xcorr_numpy.py
@@ -5,7 +5,7 @@
 from oneibl.one import ONE
 import alf.io as ioalf
 
-from brainbox.processing import bincount2D
+from iblutil.numerical import bincount2D
 
 
 class Bunch(dict):
diff --git a/brainbox/metrics/electrode_drift.py b/brainbox/metrics/electrode_drift.py
@@ -1,7 +1,7 @@
 import numpy as np
 
 from neurodsp import smooth, utils, fourier
-from brainbox.processing import bincount2D
+from iblutil.numerical import bincount2D
 
 
 def estimate_drift(spike_times, spike_amps, spike_depths, display=False):
diff --git a/brainbox/metrics/single_units.py b/brainbox/metrics/single_units.py
@@ -26,12 +26,11 @@
 import spikeglx
 from phylib.stats import correlograms
 from iblutil.util import Bunch
-from iblutil.numerical import ismember, between_sorted
+from iblutil.numerical import ismember, between_sorted, bincount2D
 from slidingRP import metrics
 
 from brainbox import singlecell
 from brainbox.io.spikeglx import extract_waveforms
-from brainbox.processing import bincount2D
 from brainbox.metrics import electrode_drift
 
 
diff --git a/brainbox/plot.py b/brainbox/plot.py
@@ -26,8 +26,8 @@
 # from matplotlib.ticker import StrMethodFormatter
 from brainbox import singlecell
 from brainbox.metrics import single_units
-from brainbox.processing import bincount2D
 from brainbox.io.spikeglx import extract_waveforms
+from iblutil.numerical import bincount2D
 import spikeglx
 
 
diff --git a/brainbox/plot_base.py b/brainbox/plot_base.py
@@ -229,9 +229,9 @@ def __init__(self, img, x, y, cmap=None):
         """
 
         # Make sure we have inputs as lists, can get input from arrange_channels2banks
-        assert type(img) == list
-        assert type(x) == list
-        assert type(y) == list
+        assert isinstance(img, list)
+        assert isinstance(x, list)
+        assert isinstance(y, list)
 
         data = Bunch({'x': x, 'y': y, 'c': img})
         super().__init__('probe', data)
diff --git a/brainbox/population/cca.py b/brainbox/population/cca.py
@@ -1,6 +1,6 @@
 import numpy as np
 import matplotlib.pylab as plt
-from brainbox.processing import bincount2D
+from iblutil.numerical import bincount2D
 
 
 def _smooth(data, sd):
diff --git a/brainbox/processing.py b/brainbox/processing.py
@@ -7,7 +7,13 @@
 import pandas as pd
 from scipy import interpolate, sparse
 from brainbox import core
+from iblutil.numerical import bincount2D as _bincount2D
 from iblutil.util import Bunch
+import logging
+import warnings
+import traceback
+
+_logger = logging.getLogger(__name__)
 
 
 def sync(dt, times=None, values=None, timeseries=None, offsets=None, interp='zero',
@@ -131,45 +137,14 @@ def bincount2D(x, y, xbin=0, ybin=0, xlim=None, ylim=None, weights=None):
     :param weights: (optional) defaults to None, weights to apply to each value for aggregation
     :return: 3 numpy arrays MAP [ny,nx] image, xscale [nx], yscale [ny]
     """
-    # if no bounds provided, use min/max of vectors
-    if xlim is None:
-        xlim = [np.min(x), np.max(x)]
-    if ylim is None:
-        ylim = [np.min(y), np.max(y)]
-
-    def _get_scale_and_indices(v, bin, lim):
-        # if bin is a nonzero scalar, this is a bin size: create scale and indices
-        if np.isscalar(bin) and bin != 0:
-            scale = np.arange(lim[0], lim[1] + bin / 2, bin)
-            ind = (np.floor((v - lim[0]) / bin)).astype(np.int64)
-        # if bin == 0, aggregate over unique values
-        else:
-            scale, ind = np.unique(v, return_inverse=True)
-        return scale, ind
-
-    xscale, xind = _get_scale_and_indices(x, xbin, xlim)
-    yscale, yind = _get_scale_and_indices(y, ybin, ylim)
-    # aggregate by using bincount on absolute indices for a 2d array
-    nx, ny = [xscale.size, yscale.size]
-    ind2d = np.ravel_multi_index(np.c_[yind, xind].transpose(), dims=(ny, nx))
-    r = np.bincount(ind2d, minlength=nx * ny, weights=weights).reshape(ny, nx)
-
-    # if a set of specific values is requested output an array matching the scale dimensions
-    if not np.isscalar(xbin) and xbin.size > 1:
-        _, iout, ir = np.intersect1d(xbin, xscale, return_indices=True)
-        _r = r.copy()
-        r = np.zeros((ny, xbin.size))
-        r[:, iout] = _r[:, ir]
-        xscale = xbin
-
-    if not np.isscalar(ybin) and ybin.size > 1:
-        _, iout, ir = np.intersect1d(ybin, yscale, return_indices=True)
-        _r = r.copy()
-        r = np.zeros((ybin.size, r.shape[1]))
-        r[iout, :] = _r[ir, :]
-        yscale = ybin
-
-    return r, xscale, yscale
+    for line in traceback.format_stack():
+        print(line.strip())
+    warning_text = """Deprecation warning: bincount2D() is now a part of iblutil.
+                    brainbox.processing.bincount2D is deprecated and will be removed in
+                    future versions. Please replace imports with iblutil.numerical.bincount2D."""
+    _logger.warning(warning_text)
+    warnings.warn(warning_text, DeprecationWarning)
+    return _bincount2D(x, y, xbin, ybin, xlim, ylim, weights)
 
 
 def compute_cluster_average(spike_clusters, spike_var):
diff --git a/brainbox/task/passive.py b/brainbox/task/passive.py
@@ -2,7 +2,7 @@
 Functions dealing with passive task
 """
 import numpy as np
-from brainbox.processing import bincount2D
+from iblutil.numerical import bincount2D
 from scipy.linalg import svd
 
 
diff --git a/brainbox/task/trials.py b/brainbox/task/trials.py
@@ -1,5 +1,4 @@
-from iblutil.numerical import ismember
-from brainbox.processing import bincount2D
+from iblutil.numerical import ismember, bincount2D
 import numpy as np
 
 
diff --git a/brainbox/tests/test_processing.py b/brainbox/tests/test_processing.py
@@ -1,6 +1,7 @@
 from brainbox import processing, core
 import unittest
 import numpy as np
+import datetime
 
 
 class TestProcessing(unittest.TestCase):
@@ -62,41 +63,14 @@ def test_sync(self):
         self.assertTrue(times2.min() >= resamp2.times.min())
         self.assertTrue(times2.max() <= resamp2.times.max())
 
-    def test_bincount_2d(self):
-        # first test simple with indices
-        x = np.array([0, 1, 1, 2, 2, 3, 3, 3])
-        y = np.array([3, 2, 2, 1, 1, 0, 0, 0])
-        r, xscale, yscale = processing.bincount2D(x, y, xbin=1, ybin=1)
-        r_ = np.zeros_like(r)
-        # sometimes life would have been simpler in c:
-        for ix, iy in zip(x, y):
-            r_[iy, ix] += 1
-        self.assertTrue(np.all(np.equal(r_, r)))
-        # test with negative values
-        y = np.array([3, 2, 2, 1, 1, 0, 0, 0]) - 5
-        r, xscale, yscale = processing.bincount2D(x, y, xbin=1, ybin=1)
-        self.assertTrue(np.all(np.equal(r_, r)))
-        # test unequal bins
-        r, xscale, yscale = processing.bincount2D(x / 2, y / 2, xbin=1, ybin=2)
-        r_ = np.zeros_like(r)
-        for ix, iy in zip(np.floor(x / 2), np.floor((y / 2 + 2.5) / 2)):
-            r_[int(iy), int(ix)] += 1
-        self.assertTrue(np.all(r_ == r))
-        # test with weights
-        w = np.ones_like(x) * 2
-        r, xscale, yscale = processing.bincount2D(x / 2, y / 2, xbin=1, ybin=2, weights=w)
-        self.assertTrue(np.all(r_ * 2 == r))
-        # test aggregation instead of binning
-        x = np.array([0, 1, 1, 2, 2, 4, 4, 4])
-        y = np.array([4, 2, 2, 1, 1, 0, 0, 0])
-        r, xscale, yscale = processing.bincount2D(x, y)
-        self.assertTrue(np.all(xscale == yscale) and np.all(xscale == np.array([0, 1, 2, 4])))
-        # test aggregation on a fixed scale
-        r, xscale, yscale = processing.bincount2D(x + 10, y + 10, xbin=np.arange(5) + 10,
-                                                  ybin=np.arange(3) + 10)
-        self.assertTrue(np.all(xscale == np.arange(5) + 10))
-        self.assertTrue(np.all(yscale == np.arange(3) + 10))
-        self.assertTrue(np.all(r.shape == (3, 5)))
+    def test_bincount2D_deprecation(self):
+        # Timer to remove bincount2D (now in iblutil)
+        # Once this test fails:
+        # - Remove the bincount2D method in processing.py
+        # - Remove the import from iblutil at the top of that file
+        # - Delete this test
+        if datetime.datetime.now() > datetime.datetime(2024, 6, 30):
+            raise NotImplementedError
 
     def test_compute_cluster_averag(self):
         # Create fake data for 3 clusters
diff --git a/examples/loading_data/loading_spikesorting_data.ipynb b/examples/loading_data/loading_spikesorting_data.ipynb
@@ -213,7 +213,7 @@
    "outputs": [],
    "source": [
     "from brainbox.ephys_plots import image_fr_plot\n",
-    "from brainbox.processing import bincount2D\n",
+    "from iblutil.numerical import bincount2D\n",
     "import numpy as np\n",
     "\n",
     "time_bin = 0.05 # time bin in seconds\n",
diff --git a/ibllib/atlas/flatmaps.py b/ibllib/atlas/flatmaps.py
@@ -293,7 +293,7 @@ def plot_swanson_vector(acronyms=None, values=None, ax=None, hemisphere=None, br
                     vertices_inv[:, 1] = -1 * vertices_inv[:, 1] + (sw_shape[0] * 2)
                     plot_polygon_with_hole(ax, vertices_inv, codes, col_l, reg_id, **kwargs)
         else:
-            coords = [coords] if type(coords) == dict else coords
+            coords = [coords] if isinstance(coords, dict) else coords
             for c in coords:
                 if orientation == 'portrait':
                     xy = np.c_[c['y'], c['x']]
diff --git a/ibllib/atlas/plots.py b/ibllib/atlas/plots.py
@@ -193,7 +193,7 @@ def _plot_slice_vector(coords, slice, values, mapping, empty_color='silver', cle
         if len(coords) == 0:
             continue
 
-        if type(coords) == list:
+        if isinstance(coords, list):
             vertices, codes = coords_for_poly_hole(coords)
             plot_polygon_with_hole(ax, vertices, codes, color, **kwargs)
         else:
diff --git a/ibllib/io/extractors/camera.py b/ibllib/io/extractors/camera.py
@@ -446,7 +446,7 @@ def align_with_gpio(timestamps, ttl, pin_state, count, extrapolate_missing=True,
 
     # Remove the rest of the dropped frames
     ts = ts[count]
-    assert np.searchsorted(ts, ttl['times'][0]) == first_uptick,\
+    assert np.searchsorted(ts, ttl['times'][0]) == first_uptick, \
         'time of first sync TTL doesn\'t match after alignment'
     if ts.size != count.size:
         _logger.error('number of timestamps and frames don\'t match after alignment')
diff --git a/ibllib/pipes/ephys_alignment.py b/ibllib/pipes/ephys_alignment.py
@@ -377,7 +377,7 @@ def arrange_into_regions(depth_coords, region_ids, distance, region_colours):
             all_y.append(y)
             all_x.append(x)
             col = region_colours[bound[iB]]
-            if type(col) != str:
+            if not isinstance(col, str):
                 col = '#FFFFFF'
             else:
                 col = '#' + col
diff --git a/ibllib/pipes/ephys_tasks.py b/ibllib/pipes/ephys_tasks.py
@@ -387,7 +387,7 @@ def __init__(self, *args, **kwargs):
         assert self.device_collection, "device_collection is a required argument"
         assert self.sync_collection, "sync_collection is a required argument"
         self.pname = [self.pname] if isinstance(self.pname, str) else self.pname
-        assert type(self.pname) == list, 'pname task argument should be a list or a string'
+        assert isinstance(self.pname, list), 'pname task argument should be a list or a string'
 
     @property
     def signature(self):
diff --git a/ibllib/pipes/tasks.py b/ibllib/pipes/tasks.py
@@ -495,7 +495,7 @@ def create_alyx_tasks(self, rerun__status__in=None, tasks_list=None):
 
         for t in task_items:
             # get the parents' alyx ids to reference in the database
-            if type(t) == dict:
+            if isinstance(t, dict):
                 t = Bunch(t)
                 executable = t.executable
                 arguments = t.arguments
diff --git a/ibllib/tests/test_io.py b/ibllib/tests/test_io.py
@@ -560,7 +560,7 @@ def test_read_yaml(self):
         self.assertCountEqual(self.fixture.keys(), data_keys)
 
     def test_patch_data(self):
-        with patch(session_params.__name__ + '.SPEC_VERSION', '1.0.0'),\
+        with patch(session_params.__name__ + '.SPEC_VERSION', '1.0.0'), \
                 self.assertLogs(session_params.__name__, logging.WARNING):
             data = session_params._patch_file({'version': '1.1.0'})
         self.assertEqual(data, {'version': '1.0.0'})
diff --git a/ibllib/tests/test_oneibl.py b/ibllib/tests/test_oneibl.py
@@ -64,7 +64,7 @@ def test_setup(self, _):
         # Silent mode off
         self.reset_params()
         self.one.alyx.silent = False
-        with mock.patch('builtins.input', new=self.mock_input),\
+        with mock.patch('builtins.input', new=self.mock_input), \
                 mock.patch('ibllib.oneibl.patcher.getpass', return_value='foobar'):
             patcher.FTPPatcher(one=self.one)
         self.assertEqual(self.one.alyx._par.FTP_DATA_SERVER_LOGIN, 'usr')
diff --git a/requirements.txt b/requirements.txt
@@ -23,7 +23,7 @@ seaborn>=0.9.0
 tqdm>=4.32.1
 # ibl libraries
 ibl-neuropixel>=0.4.0
-iblutil>=1.5.0
+iblutil>=1.7.0
 labcams  # widefield extractor
 ONE-api>=2.2
 slidingRP>=1.0.0  # steinmetz lab refractory period metrics
