def test_count():
out = np.array([[5, 5], [5, 5]], dtype='i4')
eq(c.points(df, 'x', 'y', ds.count('i32')), out)
eq(c.points(df, 'x', 'y', ds.count('i64')), out)
eq(c.points(df, 'x', 'y', ds.count()), out)
out = np.array([[4, 5], [5, 5]], dtype='i4')
eq(c.points(df, 'x', 'y', ds.count('f32')), out)
eq(c.points(df, 'x', 'y', ds.count('f64')), out)
def merged_images(x_range, y_range, w, h, how='log'):
cvs = ds.Canvas(plot_width=w, plot_height=h, x_range=x_range, y_range=y_range)
picks = cvs.points(sep_trips, 'pickup_x', 'pickup_y', ds.count('passenger_count'))
drops = cvs.points(sep_trips, 'dropoff_x', 'dropoff_y', ds.count('passenger_count'))
more_drops = tf.interpolate(drops.where(drops > picks), cmap=["lightblue", 'blue'], how=how)
more_picks = tf.interpolate(picks.where(picks > drops), cmap=["lightpink", 'red'], how=how)
img = tf.stack(more_picks,more_drops)
return tf.dynspread(img, threshold=0.1, max_px=4)
def test_count():
out = xr.DataArray(np.array([[5, 5], [5, 5]], dtype='i4'),
coords=coords, dims=dims)
assert_eq(c.points(ddf, 'x', 'y', ds.count('i32')), out)
assert_eq(c.points(ddf, 'x', 'y', ds.count('i64')), out)
assert_eq(c.points(ddf, 'x', 'y', ds.count()), out)
out = xr.DataArray(np.array([[4, 5], [5, 5]], dtype='i4'),
coords=coords, dims=dims)
assert_eq(c.points(ddf, 'x', 'y', ds.count('f32')), out)
assert_eq(c.points(ddf, 'x', 'y', ds.count('f64')), out)
def test_log_axis():
sol = np.array([[5, 5], [5, 5]], dtype='i4')
out = xr.DataArray(sol, coords=[np.array([0., 1.]), np.array([1., 10.])],
dims=dims)
assert_eq(c_logx.points(ddf, 'log_x', 'y', ds.count('i32')), out)
out = xr.DataArray(sol, coords=[np.array([1., 10.]), np.array([0., 1.])],
dims=dims)
assert_eq(c_logy.points(ddf, 'x', 'log_y', ds.count('i32')), out)
out = xr.DataArray(sol, coords=[np.array([1., 10.]), np.array([1., 10.])],
dims=dims)
assert_eq(c_logxy.points(ddf, 'log_x', 'log_y', ds.count('i32')), out)
def test_count():
out = xr.DataArray(np.array([[5, 5], [5, 5]], dtype='i4'),
coords=coords,
dims=dims)
assert_eq(c.points(df, 'x', 'y', ds.count('i32')), out)
assert_eq(c.points(df, 'x', 'y', ds.count('i64')), out)
assert_eq(c.points(df, 'x', 'y', ds.count()), out)
out = xr.DataArray(np.array([[4, 5], [5, 5]], dtype='i4'),
coords=coords,
dims=dims)
assert_eq(c.points(df, 'x', 'y', ds.count('f32')), out)
assert_eq(c.points(df, 'x', 'y', ds.count('f64')), out)
def test_log_axis_line():
# Upper bound for scale/index of x-axis
x_max_index = 10 ** (1 / (2 / np.log10(11)))
sol = np.array([[5, 5], [5, 5]], dtype='i4')
out = xr.DataArray(sol, coords=[np.array([0., 1.]), np.array([1., x_max_index])],
dims=dims)
assert_eq(c_logx.line(ddf, 'log_x', 'y', ds.count('i32')), out)
out = xr.DataArray(sol, coords=[np.array([1., x_max_index]), np.array([0., 1.])],
dims=dims)
assert_eq(c_logy.line(ddf, 'x', 'log_y', ds.count('i32')), out)
out = xr.DataArray(sol, coords=[np.array([1., x_max_index]), np.array([1., x_max_index])],
dims=dims)
assert_eq(c_logxy.line(ddf, 'log_x', 'log_y', ds.count('i32')), out)
def massive_scatterplot(
ax,
data,
x, y,
npxlx, npxly,
agg=ds.count(),
cmap=sns.cubehelix_palette(as_cmap=True),
vmin=0,
vmax=0,
vmaxp=99,
):
"""
"""
aggdata = agg_data(data, x, y, npxlx, npxly, agg)
if vmin==0 and vmax == 0:
vmin, vmax = set_vmin_vmax(aggdata.values, vmaxp)
imshow_routine(ax, aggdata, cmap=cmap,
vmin=vmin, vmax=vmax,
)
else:
imshow_routine(ax, aggdata, cmap=cmap,
vmin=vmin, vmax=vmax,
)
return ax
def test_line_autorange_axis1_x_constant():
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 9), 9)
xs = np.array([-4, 0, 4])
df = pd.DataFrame({
'y0': [0, 0],
'y1': [-4, 4],
'y2': [0, 0]
})
cvs = ds.Canvas(plot_width=9, plot_height=9)
agg = cvs.line(df,
xs,
['y0', 'y1', 'y2'],
ds.count(),
axis=1)
sol = np.array([[0, 0, 0, 0, 1, 0, 0, 0, 0],
[0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0],
[0, 1, 0, 0, 0, 0, 0, 1, 0],
[2, 0, 0, 0, 0, 0, 0, 0, 2],
[0, 1, 0, 0, 0, 0, 0, 1, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0],
[0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 1, 0, 0, 0, 0]], dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, lincoords],
dims=['y', 'x'])
assert_eq(agg, out)
def test_line_autorange(df, x, y, ax):
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 9), 9)
cvs = ds.Canvas(plot_width=9, plot_height=9)
agg = cvs.line(df,
x,
y,
ds.count(),
axis=ax)
sol = np.array([[0, 0, 0, 0, 2, 0, 0, 0, 0],
[0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0],
[0, 1, 0, 0, 0, 0, 0, 1, 0],
[1, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 0, 0, 1, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0],
[0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 2, 0, 0, 0, 0]], dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, lincoords],
dims=['y', 'x'])
assert_eq(agg, out)
def test_line_manual_range(df, x, y, ax):
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(
axis.compute_scale_and_translate((-3., 3.), 7), 7)
cvs = ds.Canvas(plot_width=7, plot_height=7,
x_range=(-3, 3), y_range=(-3, 3))
agg = cvs.line(df,
x,
y,
ds.count(),
axis=ax)
sol = np.array([[0, 0, 1, 0, 1, 0, 0],
[0, 1, 0, 0, 0, 1, 0],
[1, 0, 0, 0, 0, 0, 1],
[0, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0],
[0, 0, 1, 0, 1, 0, 0]], dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, lincoords],
dims=['y', 'x'])
assert_eq(agg, out)
def _get_points(self):
embeddings = self.embeddings
classes = self.classes
if (self.label_flag) and (classes is not None):
data = pd.DataFrame(embeddings)
data.columns = ['ivis 1', 'ivis 2']
data['label'] = classes
num_ks = len(np.unique(classes))
color_key = list(enumerate(Sets1to3[0:num_ks]))
embed = {
k: hv.Points(data.values[classes == k, :],
['ivis 1', 'ivis 2'],
'k',
label=str(k)).opts(color=v, size=0)
for k, v in color_key
}
dse = dynspread(
datashade(hv.NdOverlay(embed, kdims=['k']),
aggregator=ds.by('k', ds.count())))
color_points = hv.NdOverlay({
k: hv.Points([0, 0]).opts(color=v, size=0)
for k, v in color_key
})
points = color_points * dse
else:
points = datashade(hv.Points(embeddings))
points.opts(height=400, width=500, xaxis=None, yaxis=None)
return points
def test_multipolygon_subpixel_horizontal(DataFrame, scale):
df = GeoDataFrame({
'geometry':
MultiPolygonArray([[
[[0, 0, 1, 0, 1, 1, 0, 1, 0, 0]],
[[0, 2, 1, 2, 1, 3, 0, 3, 0, 2]],
]])
})
cvs = ds.Canvas(plot_height=8,
plot_width=8,
x_range=(-2 * scale, 2 * scale),
y_range=(0, 4))
agg = cvs.polygons(df, 'geometry', agg=ds.count())
sol = np.array([[0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 1, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 1, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0]],
dtype=np.int32)
axis = ds.core.LinearAxis()
lincoords_x = axis.compute_index(
axis.compute_scale_and_translate((-2 * scale, 2 * scale), 8), 8)
lincoords_y = axis.compute_index(
axis.compute_scale_and_translate((0, 4), 8), 8)
out = xr.DataArray(sol, coords=[lincoords_y, lincoords_x], dims=['y', 'x'])
assert_eq_xr(agg, out)
def test_pipeline(self):
df = pd.DataFrame({
'x': np.array(([0.] * 10 + [1] * 10)),
'y': np.array(([0.] * 5 + [1] * 5 + [0] * 5 + [1] * 5)),
'f64': np.arange(20, dtype='f8')
})
df.f64.iloc[2] = np.nan
cvs = ds.Canvas(plot_width=2, plot_height=2, x_range=(0, 1), y_range=(0, 1))
pipeline = ds.Pipeline(df, ds.Point('x', 'y'))
img = pipeline((0, 1), (0, 1), 2, 2)
agg = cvs.points(df, 'x', 'y', ds.count())
self.assertTrue(img.equals(tf.shade(agg)))
color_fn = lambda agg: tf.shade(agg, 'pink', 'red')
pipeline.color_fn = color_fn
img = pipeline((0, 1), (0, 1), 2, 2)
self.assertTrue(img.equals(color_fn(agg)))
transform_fn = lambda agg: agg + 1
pipeline.transform_fn = transform_fn
img = pipeline((0, 1), (0, 1), 2, 2)
self.assertTrue(img.equals(color_fn(transform_fn(agg))))
pipeline = ds.Pipeline(df, ds.Point('x', 'y'), ds.sum('f64'))
img = pipeline((0, 1), (0, 1), 2, 2)
agg = cvs.points(df, 'x', 'y', ds.sum('f64'))
self.assertTrue(img.equals(tf.shade(agg)))
def __call__(self, dset, **params):
self.p = ParamOverrides(self, params)
if self.p.vdim is None:
vdim = dset.vdims[0].name
else:
vdim = self.p.vdim
pts = hv.util.Dynamic(dset, operation=skypoints,
streams=[self.p.filter_stream])
if self.p.aggregator == 'mean':
aggregator = ds.mean(vdim)
elif self.p.aggregator == 'std':
aggregator = ds.std(vdim)
elif self.p.aggregator == 'count':
aggregator = ds.count()
decimate_opts = dict(plot={'tools': ['hover',
'box_select']},
style={'alpha': 0,
'size': self.p.decimate_size,
'nonselection_alpha': 0})
decimated = decimate(pts).opts(**decimate_opts)
raster_ = rasterize(pts, aggregator=aggregator)
color_gadget = raster_.opts(cmap=Viridis[256], colorbar=True, alpha=0)
sky_shaded = shade(raster_, cmap=viridis)
plot = dynspread(sky_shaded) * decimated * color_gadget
return plot.options(bgcolor="black", responsive=True, min_height=100)
def test_area_to_zero_autorange_gap(df, x, y, ax):
axis = ds.core.LinearAxis()
lincoords_y = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 7), 7)
lincoords_x = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 13), 13)
cvs = ds.Canvas(plot_width=13, plot_height=7)
ddf = dd.from_pandas(df, npartitions=2)
agg = cvs.area(ddf, x, y, ds.count(), axis=ax)
sol = np.array([[0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0]],
dtype='i4')
out = xr.DataArray(sol, coords=[lincoords_y, lincoords_x],
dims=['y', 'x'])
assert_eq(agg, out)
def _process(self, element, key=None):
if isinstance(element, TriMesh):
x, y = element.nodes.kdims[:2]
else:
x, y = element.kdims
info = self._get_sampling(element, x, y)
(x_range, y_range), _, (width, height), (xtype, ytype) = info
cvs = ds.Canvas(plot_width=width, plot_height=height,
x_range=x_range, y_range=y_range)
agg = self.p.aggregator
if not (element.vdims or element.nodes.vdims):
if not isinstance(agg, (rd.count, rd.any)) and agg.column is not None:
raise ValueError("Aggregation column %s not found on TriMesh element. "
"The supplied TriMesh does not define any value "
"dimensions.")
self.p.aggregator = ds.count() if not isinstance(agg, ds.any) else agg
return aggregate._process(self, element, key)
elif element._plot_id in self._precomputed:
precomputed = self._precomputed[element._plot_id]
else:
precomputed = self._precompute(element)
simplices = precomputed['simplices']
pts = precomputed['vertices']
mesh = precomputed['mesh']
if self.p.precompute:
self._precomputed = {element._plot_id: precomputed}
vdim = element.vdims[0] if element.vdims else element.nodes.vdims[0]
interpolate = bool(self.p.interpolation)
agg = cvs.trimesh(pts, simplices, agg=self._get_aggregator(element),
interp=interpolate, mesh=mesh)
params = dict(get_param_values(element), kdims=[x, y],
datatype=['xarray'], vdims=[vdim])
return Image(agg, **params)
def test_line_manual_range(df, x, y, ax):
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(
axis.compute_scale_and_translate((-3., 3.), 7), 7)
cvs = ds.Canvas(plot_width=7, plot_height=7,
x_range=(-3, 3), y_range=(-3, 3))
agg = cvs.line(df,
x,
y,
ds.count(),
axis=ax)
sol = np.array([[0, 0, 1, 0, 1, 0, 0],
[0, 1, 0, 0, 0, 1, 0],
[1, 0, 0, 0, 0, 0, 1],
[0, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 1, 0],
[0, 0, 1, 0, 1, 0, 0]], dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, lincoords],
dims=['y', 'x'])
assert_eq(agg, out)
def test_area_to_line_autorange_gap(df, x, y, y_stack, ax):
axis = ds.core.LinearAxis()
lincoords_y = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 7), 7)
lincoords_x = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 13), 13)
cvs = ds.Canvas(plot_width=13, plot_height=7)
ddf = dd.from_pandas(df, npartitions=2)
# When a line is specified to fill to, this line is not included in
# the fill. So we expect the y=0 line to not be filled.
agg = cvs.area(ddf, x, y, ds.count(), y_stack=y_stack, axis=ax)
sol = np.array([[0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0]],
dtype='i4')
out = xr.DataArray(sol, coords=[lincoords_y, lincoords_x],
dims=['y', 'x'])
assert_eq(agg, out)
def test_line_autorange(df, x, y, ax):
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 9), 9)
cvs = ds.Canvas(plot_width=9, plot_height=9)
agg = cvs.line(df,
x,
y,
ds.count(),
axis=ax)
sol = np.array([[0, 0, 0, 0, 2, 0, 0, 0, 0],
[0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0],
[0, 1, 0, 0, 0, 0, 0, 1, 0],
[1, 0, 0, 0, 0, 0, 0, 0, 1],
[0, 1, 0, 0, 0, 0, 0, 1, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0],
[0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 2, 0, 0, 0, 0]], dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, lincoords],
dims=['y', 'x'])
assert_eq(agg, out)
def test_area_to_zero_fixedrange(df, x, y, ax):
axis = ds.core.LinearAxis()
lincoords_y = axis.compute_index(
axis.compute_scale_and_translate((-2.25, 2.25), 5), 5)
lincoords_x = axis.compute_index(
axis.compute_scale_and_translate((-3.75, 3.75), 9), 9)
cvs = ds.Canvas(plot_width=9, plot_height=5,
x_range=[-3.75, 3.75], y_range=[-2.25, 2.25])
ddf = dd.from_pandas(df, npartitions=2)
agg = cvs.area(ddf, x, y, ds.count(), axis=ax)
sol = np.array([[0, 1, 1, 0, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 0, 1, 1, 1],
[0, 0, 0, 0, 0, 0, 1, 1, 1],
[0, 0, 0, 0, 0, 0, 1, 1, 0]],
dtype='i4')
out = xr.DataArray(sol, coords=[lincoords_y, lincoords_x],
dims=['y', 'x'])
assert_eq(agg, out)
def test_line_autorange(DataFrame, df_args, x, y, ax):
if cudf and DataFrame is cudf_DataFrame:
if isinstance(getattr(df_args[0].get('x', []), 'dtype', ''),
RaggedDtype):
pytest.skip("cudf DataFrames do not support extension types")
df = DataFrame(*df_args)
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 9), 9)
cvs = ds.Canvas(plot_width=9, plot_height=9)
agg = cvs.line(df, x, y, ds.count(), axis=ax)
sol = np.array([[0, 0, 0, 0, 2, 0, 0, 0, 0], [0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0], [0, 1, 0, 0, 0, 0, 0, 1, 0],
[1, 0, 0, 0, 0, 0, 0, 0, 1], [0, 1, 0, 0, 0, 0, 0, 1, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0], [0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 2, 0, 0, 0, 0]],
dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, lincoords], dims=['y', 'x'])
assert_eq_xr(agg, out)
def test_area_to_zero_fixedrange(DataFrame, df_kwargs, cvs_kwargs):
if DataFrame is dask_cudf_DataFrame:
if df_kwargs.get('dtype', '').startswith('Ragged'):
pytest.skip("Ragged array not supported with cudf")
axis = ds.core.LinearAxis()
lincoords_y = axis.compute_index(
axis.compute_scale_and_translate((-2.25, 2.25), 5), 5)
lincoords_x = axis.compute_index(
axis.compute_scale_and_translate((-3.75, 3.75), 9), 9)
cvs = ds.Canvas(plot_width=9, plot_height=5,
x_range=[-3.75, 3.75], y_range=[-2.25, 2.25])
ddf = DataFrame(**df_kwargs)
agg = cvs.area(ddf, agg=ds.count(), **cvs_kwargs)
sol = np.array([[0, 1, 1, 0, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 0, 1, 1, 1],
[0, 0, 0, 0, 0, 0, 1, 1, 1],
[0, 0, 0, 0, 0, 0, 1, 1, 0]],
dtype='i4')
out = xr.DataArray(sol, coords=[lincoords_y, lincoords_x],
dims=['y', 'x'])
assert_eq_xr(agg, out)
def test_area_to_zero_fixedrange(DataFrame, df_kwargs, x, y, ax):
if cudf and DataFrame is cudf_DataFrame:
if isinstance(getattr(df_kwargs['data'].get('x', []), 'dtype', ''),
RaggedDtype):
pytest.skip("cudf DataFrames do not support extension types")
df = DataFrame(**df_kwargs)
axis = ds.core.LinearAxis()
lincoords_y = axis.compute_index(
axis.compute_scale_and_translate((-2.25, 2.25), 5), 5)
lincoords_x = axis.compute_index(
axis.compute_scale_and_translate((-3.75, 3.75), 9), 9)
cvs = ds.Canvas(plot_width=9,
plot_height=5,
x_range=[-3.75, 3.75],
y_range=[-2.25, 2.25])
agg = cvs.area(df, x, y, ds.count(), axis=ax)
sol = np.array([[0, 1, 1, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 0, 1, 1, 1], [0, 0, 0, 0, 0, 0, 1, 1, 1],
[0, 0, 0, 0, 0, 0, 1, 1, 0]],
dtype='i4')
out = xr.DataArray(sol, coords=[lincoords_y, lincoords_x], dims=['y', 'x'])
assert_eq_xr(agg, out)
def test_line_x_constant_autorange():
# axis1 y constant
df = pd.DataFrame({
'y0': [0, 0, 0],
'y1': [-4, 0, 4],
'y2': [0, 0, 0],
})
x = np.array([-4, 0, 4])
y = ['y0', 'y1', 'y2']
ax = 1
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 9), 9)
ddf = dd.from_pandas(df, npartitions=2)
cvs = ds.Canvas(plot_width=9, plot_height=9)
agg = cvs.line(ddf, x, y, ds.count(), axis=ax)
sol = np.array([[0, 0, 0, 0, 1, 0, 0, 0, 0], [0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0], [0, 1, 0, 0, 0, 0, 0, 1, 0],
[3, 1, 1, 1, 1, 1, 1, 1, 3], [0, 1, 0, 0, 0, 0, 0, 1, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0], [0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 1, 0, 0, 0, 0]],
dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, lincoords], dims=['y', 'x'])
assert_eq(agg, out)
def test_uniform_diagonal_points(low, high):
bounds = (low, high)
x_range, y_range = bounds, bounds
width = x_range[1] - x_range[0]
height = y_range[1] - y_range[0]
n = width * height
df = pd.DataFrame({
'time':
np.ones(n, dtype='i4'),
'x':
np.array([np.arange(*x_range, dtype='f8')] * width).flatten(),
'y':
np.array([np.arange(*y_range, dtype='f8')] * height).flatten()
})
cvs = ds.Canvas(plot_width=2,
plot_height=2,
x_range=x_range,
y_range=y_range)
agg = cvs.points(df, 'x', 'y', ds.count('time'))
diagonal = agg.data.diagonal(0)
assert sum(diagonal) == n
assert abs(bounds[1] - bounds[0]) % 2 == abs(diagonal[1] / high -
diagonal[0] / high)
def test_area_to_line_autorange_gap(df, x, y, y_stack, ax):
axis = ds.core.LinearAxis()
lincoords_y = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 7), 7)
lincoords_x = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 13), 13)
cvs = ds.Canvas(plot_width=13, plot_height=7)
df = pd.DataFrame({
'x': [-4, -2, 0, np.nan, 2, 4],
'y0': [0, -4, 0, np.nan, 4, 0],
'y1': [0, 0, 0, np.nan, 0, 0],
})
# When a line is specified to fill to, this line is not included in
# the fill. So we expect the y=0 line to not be filled.
agg = cvs.area(df, 'x', 'y0', ds.count(), y_stack='y1')
sol = np.array([[0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0]],
dtype='i4')
out = xr.DataArray(sol, coords=[lincoords_y, lincoords_x],
dims=['y0', 'x'])
assert_eq(agg, out)
def update_image(dataframe):
global dims
dims_data = dims.data
if not dims_data['width'] or not dims_data['height']:
return
plot_width = int(math.ceil(dims_data['width'][0]))
plot_height = int(math.ceil(dims_data['height'][0]))
x_range = (dims_data['xmin'][0], dims_data['xmax'][0])
y_range = (dims_data['ymin'][0], dims_data['ymax'][0])
canvas = ds.Canvas(plot_width=plot_width,
plot_height=plot_height,
x_range=x_range,
y_range=y_range)
agg = canvas.points(dataframe, 'dropoff_x', 'dropoff_y',
ds.count('trip_distance'))
img = tf.shade(agg, cmap=BuGn9, how='log')
new_data = {}
new_data['image'] = [img.data]
new_data['x'] = [x_range[0]]
new_data['y'] = [y_range[0]]
new_data['dh'] = [y_range[1] - y_range[0]]
new_data['dw'] = [x_range[1] - x_range[0]]
image_source.stream(new_data, 1)
def edges_plot(edges, name=None, canvas=None, kwargs=cvsopts):
'''
Plot edges using datashader Canvas functions.
returns datashader.transfer_functions.shade().
'''
canvas = ds.Canvas(**kwargs) if canvas is None else canvas
return tf.shade(canvas.line(edges, 'x', 'y', agg=ds.count()), name=name)
def ds_shade_waveforms(waveforms, canvas_width=400, canvas_height=400, color_maps=None, y_min_uv=-500, y_max_uv=400,
how='log'):
n_samples = waveforms.shape[0]
n_channels = waveforms.shape[1]
if color_maps is None:
color_maps = DS_CMAPS
if n_channels > len(color_maps):
color_maps *= len(color_maps) // n_channels + 1
cvs = ds.Canvas(plot_height=canvas_height, plot_width=canvas_width,
x_range=(0, waveforms.shape[0] - 1),
y_range=(y_min_uv / 0.195, y_max_uv / 0.195))
shades = []
for ch in range(n_channels):
df = pd.DataFrame(waveforms[:, ch, :].T)
agg = cvs.line(df, x=np.arange(n_samples), y=list(range(n_samples)), agg=ds.count(), axis=1)
with np.errstate(invalid='ignore'):
img = tf.shade(agg, how=how, cmap=plt.cm.get_cmap(color_maps[ch]))
shades.append(img)
# If we wanted to use all channels together, we have to create a categorical column for the selection
# df = pd.DataFrame(wv_reshaped)
# df['channel'] = pd.Categorical(np.tile(np.arange(n_channels), wv_reshaped.shape[0]//n_channels))
# wv_reshaped = waveforms.reshape(n_samples, -1).T
# agg = cvs.line(df, x=np.arange(n_samples), y=list(range(32)), agg=ds.count_cat('channel'), axis=1)
return shades
def test_area_to_line_autorange_gap(DataFrame, df_kwargs, x, y, y_stack, ax):
if DataFrame is dask_cudf_DataFrame:
if df_kwargs.get('dtype', '').startswith('Ragged'):
pytest.skip("Ragged array not supported with cudf")
axis = ds.core.LinearAxis()
lincoords_y = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 7), 7)
lincoords_x = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 13), 13)
cvs = ds.Canvas(plot_width=13, plot_height=7)
ddf = DataFrame(**df_kwargs)
# When a line is specified to fill to, this line is not included in
# the fill. So we expect the y=0 line to not be filled.
agg = cvs.area(ddf, x, y, ds.count(), y_stack=y_stack, axis=ax)
sol = np.array([[0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0]],
dtype='i4')
out = xr.DataArray(sol, coords=[lincoords_y, lincoords_x], dims=['y', 'x'])
assert_eq_xr(agg, out)
def test_line_manual_range(DataFrame, df_kwargs, x, y, ax):
if DataFrame is dask_cudf_DataFrame:
if df_kwargs.get('dtype', '').startswith('Ragged'):
pytest.skip("Ragged array not supported with cudf")
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(
axis.compute_scale_and_translate((-3., 3.), 7), 7)
ddf = DataFrame(**df_kwargs)
cvs = ds.Canvas(plot_width=7,
plot_height=7,
x_range=(-3, 3),
y_range=(-3, 3))
agg = cvs.line(ddf, x, y, ds.count(), axis=ax)
sol = np.array(
[[0, 0, 1, 0, 1, 0, 0], [0, 1, 0, 0, 0, 1, 0], [1, 0, 0, 0, 0, 0, 1],
[1, 1, 1, 1, 1, 1, 1], [1, 0, 0, 0, 0, 0, 1], [0, 1, 0, 0, 0, 1, 0],
[0, 0, 1, 0, 1, 0, 0]],
dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, lincoords], dims=['y', 'x'])
assert_eq_xr(agg, out)
def update_image(dataframe):
global dims
dims_data = dims.data
if not dims_data['width'] or not dims_data['height']:
return
plot_width = int(math.ceil(dims_data['width'][0]))
plot_height = int(math.ceil(dims_data['height'][0]))
x_range = (dims_data['xmin'][0], dims_data['xmax'][0])
y_range = (dims_data['ymin'][0], dims_data['ymax'][0])
canvas = ds.Canvas(plot_width=plot_width,
plot_height=plot_height,
x_range=x_range,
y_range=y_range)
agg = canvas.points(dataframe, 'dropoff_x', 'dropoff_y',
ds.count('trip_distance'))
img = tf.shade(agg, cmap=BuGn9, how='log')
new_data = {}
new_data['image'] = [img.data]
new_data['x'] = [x_range[0]]
new_data['y'] = [y_range[0]]
new_data['dh'] = [y_range[1] - y_range[0]]
new_data['dw'] = [x_range[1] - x_range[0]]
image_source.stream(new_data, 1)
def test_area_to_line_autorange(DataFrame, df_kwargs, x, y, y_stack, ax):
if cudf and DataFrame is cudf_DataFrame:
if isinstance(getattr(df_kwargs['data'].get('x', []), 'dtype', ''),
RaggedDtype):
pytest.skip("cudf DataFrames do not support extension types")
df = DataFrame(**df_kwargs)
axis = ds.core.LinearAxis()
lincoords_y = axis.compute_index(
axis.compute_scale_and_translate((-4., 0.), 7), 7)
lincoords_x = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 13), 13)
cvs = ds.Canvas(plot_width=13, plot_height=7)
agg = cvs.area(df, x, y, ds.count(), axis=ax, y_stack=y_stack)
sol = np.array([[0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0, 0],
[0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0],
[0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]],
dtype='i4')
out = xr.DataArray(sol, coords=[lincoords_y, lincoords_x], dims=['y', 'x'])
assert_eq_xr(agg, out)
class AggregationOperation(ResamplingOperation):
"""
AggregationOperation extends the ResamplingOperation defining an
aggregator parameter used to define a datashader Reduction.
"""
aggregator = param.ClassSelector(class_=(ds.reductions.Reduction,
basestring),
default=ds.count(),
doc="""
Datashader reduction function used for aggregating the data.
The aggregator may also define a column to aggregate; if
no column is defined the first value dimension of the element
will be used. May also be defined as a string.""")
_agg_methods = {
'any': rd.any,
'count': rd.count,
'first': rd.first,
'last': rd.last,
'mode': rd.mode,
'mean': rd.mean,
'sum': rd.sum,
'var': rd.var,
'std': rd.std,
'min': rd.min,
'max': rd.max
}
def _get_aggregator(self, element, add_field=True):
agg = self.p.aggregator
if isinstance(agg, basestring):
if agg not in self._agg_methods:
agg_methods = sorted(self._agg_methods)
raise ValueError('Aggregation method %r is not known; '
'aggregator must be one of: %r' %
(agg, agg_methods))
agg = self._agg_methods[agg]()
elements = element.traverse(lambda x: x, [Element])
if add_field and agg.column is None and not isinstance(
agg, (rd.count, rd.any)):
if not elements:
raise ValueError('Could not find any elements to apply '
'%s operation to.' % type(self).__name__)
inner_element = elements[0]
if inner_element.vdims:
field = inner_element.vdims[0].name
elif isinstance(inner_element,
TriMesh) and inner_element.nodes.kdims:
field = inner_element.nodes.vdims[0].name
elif isinstance(element, NdOverlay):
field = element.kdims[0].name
else:
raise ValueError('Could not determine dimension to apply '
'%s operation to. Declare the dimension '
'to aggregate as part of the datashader '
'aggregator.' % type(self).__name__)
agg = type(agg)(field)
return agg
def test_line_autorange(DataFrame, df_kwargs, cvs_kwargs):
if DataFrame is dask_cudf_DataFrame:
dtype = df_kwargs.get('dtype', '')
if dtype.startswith('Ragged') or dtype.startswith('Line'):
pytest.skip("Ragged array not supported with cudf")
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 9), 9)
ddf = DataFrame(geo='geometry' in cvs_kwargs, **df_kwargs)
cvs = ds.Canvas(plot_width=9, plot_height=9)
agg = cvs.line(ddf, agg=ds.count(), **cvs_kwargs)
sol = np.array([[0, 0, 0, 0, 3, 0, 0, 0, 0],
[0, 0, 0, 1, 1, 1, 0, 0, 0],
[0, 0, 1, 0, 1, 0, 1, 0, 0],
[0, 1, 0, 0, 1, 0, 0, 1, 0],
[1, 0, 0, 0, 1, 0, 0, 0, 1],
[0, 1, 0, 0, 1, 0, 0, 1, 0],
[0, 0, 1, 0, 1, 0, 1, 0, 0],
[0, 0, 0, 1, 1, 1, 0, 0, 0],
[0, 0, 0, 0, 3, 0, 0, 0, 0]], dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, lincoords],
dims=['y', 'x'])
assert_eq_xr(agg, out)
def test_line_autorange_axis1_x_constant():
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 9), 9)
xs = np.array([-4, 0, 4])
df = pd.DataFrame({
'y0': [0, 0],
'y1': [-4, 4],
'y2': [0, 0]
})
cvs = ds.Canvas(plot_width=9, plot_height=9)
agg = cvs.line(df,
xs,
['y0', 'y1', 'y2'],
ds.count(),
axis=1)
sol = np.array([[0, 0, 0, 0, 1, 0, 0, 0, 0],
[0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0],
[0, 1, 0, 0, 0, 0, 0, 1, 0],
[2, 0, 0, 0, 0, 0, 0, 0, 2],
[0, 1, 0, 0, 0, 0, 0, 1, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0],
[0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 1, 0, 0, 0, 0]], dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, lincoords],
dims=['y', 'x'])
assert_eq(agg, out)
def test_line_autorange_axis1_ragged():
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 9), 9)
df = pd.DataFrame({
'x': pd.array([[4, 0], [0, -4, 0, 4]], dtype='Ragged[float32]'),
'y': pd.array([[0, -4], [-4, 0, 4, 0]], dtype='Ragged[float32]')
})
cvs = ds.Canvas(plot_width=9, plot_height=9)
agg = cvs.line(df,
'x',
'y',
ds.count(),
axis=1)
sol = np.array([[0, 0, 0, 0, 2, 0, 0, 0, 0],
[0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0],
[0, 1, 0, 0, 0, 0, 0, 1, 0],
[1, 0, 0, 0, 0, 0, 0, 0, 2],
[0, 1, 0, 0, 0, 0, 0, 1, 0],
[0, 0, 1, 0, 0, 0, 1, 0, 0],
[0, 0, 0, 1, 0, 1, 0, 0, 0],
[0, 0, 0, 0, 1, 0, 0, 0, 0]], dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, lincoords],
dims=['y', 'x'])
assert_eq(agg, out)
def test_area_to_line_autorange(DataFrame, df_kwargs, cvs_kwargs):
if DataFrame is dask_cudf_DataFrame:
if df_kwargs.get('dtype', '').startswith('Ragged'):
pytest.skip("Ragged array not supported with cudf")
axis = ds.core.LinearAxis()
lincoords_y = axis.compute_index(
axis.compute_scale_and_translate((-4., 0.), 7), 7)
lincoords_x = axis.compute_index(
axis.compute_scale_and_translate((-4., 4.), 13), 13)
cvs = ds.Canvas(plot_width=13, plot_height=7)
ddf = DataFrame(**df_kwargs)
agg = cvs.area(ddf, agg=ds.count(), **cvs_kwargs)
sol = np.array([[0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0],
[0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0, 0],
[0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0],
[0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]],
dtype='i4')
out = xr.DataArray(sol, coords=[lincoords_y, lincoords_x],
dims=['y', 'x'])
assert_eq_xr(agg, out)
def test_log_axis_line():
axis = ds.core.LogAxis()
logcoords = axis.compute_index(axis.compute_scale_and_translate((1, 10), 2), 2)
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(axis.compute_scale_and_translate((0, 1), 2), 2)
sol = np.array([[5, 5], [5, 5]], dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, logcoords],
dims=['y', 'log_x'])
assert_eq(c_logx.line(ddf, 'log_x', 'y', ds.count('i32')), out)
out = xr.DataArray(sol, coords=[logcoords, lincoords],
dims=['log_y', 'x'])
assert_eq(c_logy.line(ddf, 'x', 'log_y', ds.count('i32')), out)
out = xr.DataArray(sol, coords=[logcoords, logcoords],
dims=['log_y', 'log_x'])
assert_eq(c_logxy.line(ddf, 'log_x', 'log_y', ds.count('i32')), out)
def test_auto_range_points():
n = 10
data = np.arange(n, dtype='i4')
df = pd.DataFrame({'time': np.arange(n),
'x': data,
'y': data})
ddf = dd.from_pandas(df, npartitions=2)
cvs = ds.Canvas(plot_width=n, plot_height=n)
agg = cvs.points(ddf, 'x', 'y', ds.count('time'))
sol = np.zeros((n, n), int)
np.fill_diagonal(sol, 1)
np.testing.assert_equal(agg.data, sol)
cvs = ds.Canvas(plot_width=n+1, plot_height=n+1)
agg = cvs.points(ddf, 'x', 'y', ds.count('time'))
sol = np.zeros((n+1, n+1), int)
np.fill_diagonal(sol, 1)
sol[5, 5] = 0
np.testing.assert_equal(agg.data, sol)
n = 4
data = np.arange(n, dtype='i4')
df = pd.DataFrame({'time': np.arange(n),
'x': data,
'y': data})
ddf = dd.from_pandas(df, npartitions=2)
cvs = ds.Canvas(plot_width=2*n, plot_height=2*n)
agg = cvs.points(ddf, 'x', 'y', ds.count('time'))
sol = np.zeros((2*n, 2*n), int)
np.fill_diagonal(sol, 1)
sol[[range(1, 4, 2)]] = 0
sol[[range(4, 8, 2)]] = 0
np.testing.assert_equal(agg.data, sol)
cvs = ds.Canvas(plot_width=2*n+1, plot_height=2*n+1)
agg = cvs.points(ddf, 'x', 'y', ds.count('time'))
sol = np.zeros((2*n+1, 2*n+1), int)
sol[0, 0] = 1
sol[3, 3] = 1
sol[6, 6] = 1
sol[8, 8] = 1
np.testing.assert_equal(agg.data, sol)
def test_multiple_aggregates():
agg = c.points(ddf, 'x', 'y',
f64=dict(std=ds.std('f64'), mean=ds.mean('f64')),
i32_sum=ds.sum('i32'),
i32_count=ds.count('i32'))
eq(agg.f64.std, df.f64.reshape((2, 2, 5)).std(axis=2).T)
eq(agg.f64.mean, df.f64.reshape((2, 2, 5)).mean(axis=2).T)
eq(agg.i32_sum, df.i32.reshape((2, 2, 5)).sum(axis=2).T)
eq(agg.i32_count, np.array([[5, 5], [5, 5]], dtype='i4'))
def test_uniform_points():
n = 101
df = pd.DataFrame({'time': np.ones(2*n, dtype='i4'),
'x': np.concatenate((np.arange(n, dtype='f8'),
np.arange(n, dtype='f8'))),
'y': np.concatenate(([0.] * n, [1.] * n))})
cvs = ds.Canvas(plot_width=10, plot_height=2, y_range=(0, 1))
agg = cvs.points(df, 'x', 'y', ds.count('time'))
sol = np.array([[10] * 9 + [11], [10] * 9 + [11]], dtype='i4')
np.testing.assert_equal(agg.data, sol)
def tests_datashader():
import datashader as ds
import datashader.transfer_functions as tf
import pandas as pd
df = pd.read_csv('/Users/iregon/C3S/dessaps/test_data/imma_converter/observations-sst-2014-6.psv',usecols=[6,7,14],sep="|",skiprows=0)
agg_mean = cvs.points(df, 'longitude', 'latitude', ds.mean('observation_value'))
agg_max = cvs.points(df, 'longitude', 'latitude', ds.max('observation_value'))
agg_min = cvs.points(df, 'longitude', 'latitude', ds.min('observation_value'))
agg_count = cvs.points(df, 'longitude', 'latitude', ds.count('observation_value'))
def create_image(x_range=x_range, y_range=y_range, w=plot_width, h=plot_height,
aggregator=ds.count(), categorical=None, black=False, cmap=None):
opts={}
if categorical and cmap:
opts['color_key'] = categorical_color_key(len(df[aggregator.column].unique()),cmap)
cvs = ds.Canvas(plot_width=w, plot_height=h, x_range=x_range, y_range=y_range)
agg = cvs.line(df, 'longitude', 'latitude', aggregator)
img = tf.shade(agg, cmap=inferno, **opts)
if black: img = tf.set_background(img, 'black')
return img
def test_multiple_aggregates():
agg = c.points(ddf, 'x', 'y',
ds.summary(f64_std=ds.std('f64'),
f64_mean=ds.mean('f64'),
i32_sum=ds.sum('i32'),
i32_count=ds.count('i32')))
f = lambda x: xr.DataArray(x, coords=coords, dims=dims)
assert_eq(agg.f64_std, f(np.nanstd(df.f64.values.reshape((2, 2, 5)), axis=2).T))
assert_eq(agg.f64_mean, f(np.nanmean(df.f64.values.reshape((2, 2, 5)), axis=2).T))
assert_eq(agg.i32_sum, f(df.i32.values.reshape((2, 2, 5)).sum(axis=2, dtype='f8').T))
assert_eq(agg.i32_count, f(np.array([[5, 5], [5, 5]], dtype='i4')))
def waveforms_datashader(waveforms, x_values, dir_name = "datashader_temp"):
# Make a pandas dataframe with two columns, x and y, holding all the data. The individual waveforms are separated by a row of NaNs
# First downsample the waveforms 10 times (to remove the effects of 10 times upsampling during de-jittering)
waveforms = waveforms[:, ::10]
# Then make a new array of waveforms - the last element of each waveform is a NaN
new_waveforms = np.zeros((waveforms.shape[0], waveforms.shape[1] + 1))
new_waveforms[:, -1] = np.nan
new_waveforms[:, :-1] = waveforms
# Now make an array of x's - the last element is a NaN
x = np.zeros(x_values.shape[0] + 1)
x[-1] = np.nan
x[:-1] = x_values
# Now make the dataframe
df = pd.DataFrame({'x': np.tile(x, new_waveforms.shape[0]), 'y': new_waveforms.flatten()})
# Datashader function for exporting the temporary image with the waveforms
export = partial(export_image, background = "white", export_path=dir_name)
# Produce a datashader canvas
canvas = ds.Canvas(x_range = (np.min(x_values), np.max(x_values)),
y_range = (df['y'].min() - 10, df['y'].max() + 10),
plot_height=1200, plot_width=1600)
# Aggregate the data
agg = canvas.line(df, 'x', 'y', ds.count())
# Transfer the aggregated data to image using log transform and export the temporary image file
export(tf.shade(agg, how='eq_hist'),'tempfile')
# Read in the temporary image file
img = imread(dir_name + "/tempfile.png")
# Figure sizes chosen so that the resolution is 100 dpi
fig,ax = plt.subplots(1, 1, figsize = (8,6), dpi = 200)
# Start plotting
ax.imshow(img)
# Set ticks/labels - 10 on each axis
ax.set_xticks(np.linspace(0, 1600, 10))
ax.set_xticklabels(np.floor(np.linspace(np.min(x_values), np.max(x_values), 10)))
ax.set_yticks(np.linspace(0, 1200, 10))
ax.set_yticklabels(np.floor(np.linspace(df['y'].max() + 10, df['y'].min() - 10, 10)))
# Delete the dataframe
del df, waveforms, new_waveforms
# Also remove the directory with the temporary image files
shutil.rmtree(dir_name, ignore_errors = True)
# Return and figure and axis for adding axis labels, title and saving the file
return fig, ax
def test_auto_range_line():
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(axis.compute_scale_and_translate((-10., 10.), 5), 5)
df = pd.DataFrame({'x': [-10, 0, 10, 0, -10],
'y': [ 0, 10, 0, -10, 0]})
cvs = ds.Canvas(plot_width=5, plot_height=5)
agg = cvs.line(df, 'x', 'y', ds.count())
sol = np.array([[0, 0, 1, 0, 0],
[0, 1, 0, 1, 0],
[2, 0, 0, 0, 1],
[0, 1, 0, 1, 0],
[0, 0, 1, 0, 0]], dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, lincoords],
dims=['y', 'x'])
assert_eq(agg, out)
def test_line():
df = pd.DataFrame({'x': [4, 0, -4, -3, -2, -1.9, 0, 10, 10, 0, 4],
'y': [0, -4, 0, 1, 2, 2.1, 4, 20, 30, 4, 0]})
cvs = ds.Canvas(plot_width=7, plot_height=7,
x_range=(-3, 3), y_range=(-3, 3))
agg = cvs.line(df, 'x', 'y', ds.count())
sol = np.array([[0, 0, 1, 0, 1, 0, 0],
[0, 1, 0, 0, 0, 1, 0],
[1, 0, 0, 0, 0, 0, 1],
[0, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 1],
[0, 2, 0, 0, 0, 1, 0],
[0, 0, 1, 0, 1, 0, 0]], dtype='i4')
out = xr.DataArray(sol, coords=[np.arange(-3, 4), np.arange(-3, 4)],
dims=['y_axis', 'x_axis'])
assert_eq(agg, out)
def test_uniform_diagonal_points(low, high):
bounds = (low, high)
x_range, y_range = bounds, bounds
width = x_range[1] - x_range[0]
height = y_range[1] - y_range[0]
n = width * height
df = pd.DataFrame({'time': np.ones(n, dtype='i4'),
'x': np.array([np.arange(*x_range, dtype='f8')] * width).flatten(),
'y': np.array([np.arange(*y_range, dtype='f8')] * height).flatten()})
cvs = ds.Canvas(plot_width=2, plot_height=2, x_range=x_range, y_range=y_range)
agg = cvs.points(df, 'x', 'y', ds.count('time'))
diagonal = agg.data.diagonal(0)
assert sum(diagonal) == n
assert abs(bounds[1] - bounds[0]) % 2 == abs(diagonal[1] / high - diagonal[0] / high)
def test_bug_570():
# See https://github.com/pyviz/datashader/issues/570
df = pd.DataFrame({
'Time': [1456353642.2053893, 1456353642.2917893],
'data': [-59.4948743433377, 506.4847376716022],
}, columns=['Time', 'data'])
x_range = (1456323293.9859753, 1456374687.0009754)
y_range = (-228.56721300380943, 460.4042291124646)
cvs = ds.Canvas(x_range=x_range, y_range=y_range,
plot_height=300, plot_width=1000)
agg = cvs.line(df, 'Time', 'data', agg=ds.count())
# Check location of line
yi, xi = np.where(agg.values == 1)
assert np.array_equal(yi, np.arange(73, 300))
assert np.array_equal(xi, np.array([590] * len(yi)))
def test_lines_on_edge():
df = pd.DataFrame(dict(x=[0, 3, 3, 0],
y=[0, 0, 3, 3]))
canvas = ds.Canvas(plot_width=3, plot_height=3,
x_range=(0, 3), y_range=(0, 3))
agg = canvas.line(df, 'x', 'y', agg=ds.count())
sol = np.array([[1, 1, 1],
[0, 0, 1],
[1, 1, 1]], dtype='int32')
out = xr.DataArray(sol,
coords=[('x', [0.5, 1.5, 2.5]),
('y', [0.5, 1.5, 2.5])],
dims=['y', 'x'])
assert_eq(agg, out)
def test_line():
axis = ds.core.LinearAxis()
lincoords = axis.compute_index(axis.compute_scale_and_translate((-3., 3.), 7), 7)
df = pd.DataFrame({'x': [4, 0, -4, -3, -2, -1.9, 0, 10, 10, 0, 4],
'y': [0, -4, 0, 1, 2, 2.1, 4, 20, 30, 4, 0]})
cvs = ds.Canvas(plot_width=7, plot_height=7,
x_range=(-3, 3), y_range=(-3, 3))
agg = cvs.line(df, 'x', 'y', ds.count())
sol = np.array([[0, 0, 1, 0, 1, 0, 0],
[0, 1, 0, 0, 0, 1, 0],
[1, 0, 0, 0, 0, 0, 1],
[0, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 1],
[0, 2, 0, 0, 0, 1, 0],
[0, 0, 1, 0, 1, 0, 0]], dtype='i4')
out = xr.DataArray(sol, coords=[lincoords, lincoords],
dims=['y', 'x'])
assert_eq(agg, out)
def test_pipeline():
pipeline = ds.Pipeline(df, ds.Point('x', 'y'))
img = pipeline((0, 1), (0, 1), 2, 2)
agg = cvs.points(df, 'x', 'y', ds.count())
assert img.equals(tf.interpolate(agg))
color_fn = lambda agg: tf.interpolate(agg, 'pink', 'red')
pipeline.color_fn = color_fn
img = pipeline((0, 1), (0, 1), 2, 2)
assert img.equals(color_fn(agg))
transform_fn = lambda agg: agg + 1
pipeline.transform_fn = transform_fn
img = pipeline((0, 1), (0, 1), 2, 2)
assert img.equals(color_fn(transform_fn(agg)))
pipeline = ds.Pipeline(df, ds.Point('x', 'y'), ds.sum('f64'))
img = pipeline((0, 1), (0, 1), 2, 2)
agg = cvs.points(df, 'x', 'y', ds.sum('f64'))
assert img.equals(tf.interpolate(agg))
def create_image(x_range, y_range, w, h):
cvs = ds.Canvas(plot_width=w, plot_height=h, x_range=x_range, y_range=y_range)
agg = cvs.points(picks, 'x', 'y', ds.count('visibility'))
img = tf.interpolate(agg, cmap=Hot, how='eq_hist')
return tf.dynspread(img, threshold=0.5, max_px=4)
def create_image(x_range, y_range, w, h):
cvs = ds.Canvas(plot_width=w, plot_height=h, x_range=x_range, y_range=y_range)
agg = cvs.points(df, 'web_long', 'web_lat', ds.count('trip_distance'))
img = tf.interpolate(agg, cmap=Hot, how='eq_hist')
return tf.dynspread(img, threshold=0.5, max_px=4)
def test_count():
out = np.array([[5, 5], [5, 5]], dtype='i4')
eq(c.points(ddf, 'x', 'y', agg=ds.count('i32')).agg, out)
eq(c.points(ddf, 'x', 'y', agg=ds.count('i64')).agg, out)
eq(c.points(ddf, 'x', 'y', agg=ds.count('f32')).agg, out)
eq(c.points(ddf, 'x', 'y', agg=ds.count('i64')).agg, out)
def edgesplot(edges, name=None, canvas=None):
canvas = ds.Canvas(**cvsopts) if canvas is None else canvas
return tf.shade(canvas.line(edges, 'x','y', agg=ds.count()), name=name)
def test_log_axis():
out = np.array([[5, 5], [5, 5]], dtype='i4')
eq(c_logx.points(df, 'log_x', 'y', ds.count('i32')), out)
eq(c_logy.points(df, 'x', 'log_y', ds.count('i32')), out)
eq(c_logxy.points(df, 'log_x', 'log_y', ds.count('i32')), out)
for descriptor in descriptor_list:
descriptors[descriptor] = dict()
for vari in vars_in:
descriptors[descriptor][vari] = dict()
i = 1
for yr in range(y_ini,y_end + 1):
for mo in range(1,13):
logging.info('{0}-{1}'.format(yr,mo))
mm = '{:02d}'.format(mo)
# Read monthly data (header and observed vars) to df indexed by report_id
df_mo = read_monthly_data()
# For each observed variable in df, compute stats and aggregate to its monhtly composite.
for vari in vars_in:
if mm in descriptors['counts'][vari].keys():
descriptors['counts'][vari][mm] = descriptors['counts'][vari][mm] + cvs.points(df_mo[['latitude','longitude',vari]], 'longitude', 'latitude', ds.count(vari))
descriptors['max'][vari][mm] = np.fmax(descriptors['max'][vari][mm],cvs.points(df_mo[['latitude','longitude',vari]], 'longitude', 'latitude', ds.max(vari)))
descriptors['min'][vari][mm] = np.fmin(descriptors['min'][vari][mm],cvs.points(df_mo[['latitude','longitude',vari]], 'longitude', 'latitude', ds.min(vari)))
# All this mess, because addition propagates nan's in xarrays!
mean_mm = cvs.points(df_mo[['latitude','longitude',vari]], 'longitude', 'latitude', ds.mean(vari))
max_frame = np.fmax(descriptors['ave'][vari][mm],mean_mm)
min_frame = np.fmin(descriptors['ave'][vari][mm],mean_mm)
descriptors['ave'][vari][mm] = 0.5*max_frame + 0.5*min_frame
else:
descriptors['counts'][vari][mm] = cvs.points(df_mo[['latitude','longitude',vari]], 'longitude', 'latitude', ds.count(vari)) # <class 'xarray.core.dataarray.DataArray'>
descriptors['max'][vari][mm] = cvs.points(df_mo[['latitude','longitude',vari]], 'longitude', 'latitude', ds.max(vari))
descriptors['min'][vari][mm] = cvs.points(df_mo[['latitude','longitude',vari]], 'longitude', 'latitude', ds.min(vari))
mean_mm = cvs.points(df_mo[['latitude','longitude',vari]], 'longitude', 'latitude', ds.mean(vari))
descriptors['ave'][vari][mm] = mean_mm
# Also add monthly stats to the global aggregate