def test_default_dendrogram(self):
X = np.array([[1, 2, 3, 4], [1, 1, 3, 4], [1, 2, 1, 4], [1, 2, 3, 1]])
dendro = tls.FigureFactory.create_dendrogram(X=X)
expected_dendro = go.Figure(
data=go.Data([
go.Scatter(x=np.array([25., 25., 35., 35.]),
y=np.array([0., 1., 1., 0.]),
marker=go.Marker(color='rgb(61,153,112)'),
mode='lines',
xaxis='x',
yaxis='y'),
go.Scatter(x=np.array([15., 15., 30., 30.]),
y=np.array([0., 2.23606798, 2.23606798, 1.]),
marker=go.Marker(color='rgb(61,153,112)'),
mode='lines',
xaxis='x',
yaxis='y'),
go.Scatter(x=np.array([5., 5., 22.5, 22.5]),
y=np.array([0., 3.60555128, 3.60555128,
2.23606798]),
marker=go.Marker(color='rgb(0,116,217)'),
mode='lines',
xaxis='x',
yaxis='y')
]),
layout=go.Layout(autosize=False,
height='100%',
hovermode='closest',
showlegend=False,
width='100%',
xaxis=go.XAxis(mirror='allticks',
rangemode='tozero',
showgrid=False,
showline=True,
showticklabels=True,
tickmode='array',
ticks='outside',
ticktext=np.array(
['3', '2', '0', '1']),
tickvals=[5.0, 15.0, 25.0, 35.0],
type='linear',
zeroline=False),
yaxis=go.YAxis(mirror='allticks',
rangemode='tozero',
showgrid=False,
showline=True,
showticklabels=True,
ticks='outside',
type='linear',
zeroline=False)))
self.assertEqual(len(dendro['data']), 3)
# this is actually a bit clearer when debugging tests.
self.assert_dict_equal(dendro['data'][0], expected_dendro['data'][0])
self.assert_dict_equal(dendro['data'][1], expected_dendro['data'][1])
self.assert_dict_equal(dendro['data'][2], expected_dendro['data'][2])
self.assert_dict_equal(dendro['layout'], expected_dendro['layout'])
def make_violin_rugplot(vals, pdf_max, distance, color='#1f77b4'):
"""
Returns a rugplot fig for a violin plot.
"""
return graph_objs.Scatter(y=vals,
x=[-pdf_max - distance] * len(vals),
marker=graph_objs.Marker(color=color,
symbol='line-ew-open'),
mode='markers',
name='',
showlegend=False,
hoverinfo='y')
def get_dendrogram_traces(self, X, colorscale):
from plotly.graph_objs import graph_objs
Z = sch.linkage(X, method=self.method, metric=self.metric)
P = sch.dendrogram(Z,
orientation=self.orientation,
labels=self.labels,
no_plot=True)
icoord = scp.array(P['icoord'])
dcoord = scp.array(P['dcoord'])
ordered_labels = scp.array(P['ivl'])
color_list = scp.array(P['color_list'])
colors = self.get_color_dict(colorscale)
trace_list = []
def trace_axis(axis):
try:
return axis[0] + str(int(axis[-1]))
except:
return axis[0]
for xs, ys, color_key in zip(icoord, dcoord, color_list):
if self.orientation not in ['top', 'bottom']:
xs, ys = ys, xs
trace = graph_objs.Scatter(
x=xs * self.sign[self.xaxis],
y=ys * self.sign[self.yaxis],
mode='lines',
xaxis=trace_axis(self.xaxis),
yaxis=trace_axis(self.yaxis),
marker=graph_objs.Marker(color=colors[color_key]),
)
trace_list.append(trace)
return trace_list, icoord, dcoord, ordered_labels, P['leaves']
def test_dendrogram_colorscale(self):
X = np.array([[1, 2, 3, 4], [1, 1, 3, 4], [1, 2, 1, 4], [1, 2, 3, 1]])
greyscale = [
'rgb(0,0,0)', # black
'rgb(05,105,105)', # dim grey
'rgb(128,128,128)', # grey
'rgb(169,169,169)', # dark grey
'rgb(192,192,192)', # silver
'rgb(211,211,211)', # light grey
'rgb(220,220,220)', # gainsboro
'rgb(245,245,245)'
] # white smoke
dendro = tls.FigureFactory.create_dendrogram(X, colorscale=greyscale)
expected_dendro = go.Figure(
data=go.Data([
go.Scatter(x=np.array([25., 25., 35., 35.]),
y=np.array([0., 1., 1., 0.]),
marker=go.Marker(color='rgb(128,128,128)'),
mode='lines',
xaxis='x',
yaxis='y'),
go.Scatter(x=np.array([15., 15., 30., 30.]),
y=np.array([0., 2.23606798, 2.23606798, 1.]),
marker=go.Marker(color='rgb(128,128,128)'),
mode='lines',
xaxis='x',
yaxis='y'),
go.Scatter(x=np.array([5., 5., 22.5, 22.5]),
y=np.array([0., 3.60555128, 3.60555128,
2.23606798]),
marker=go.Marker(color='rgb(0,0,0)'),
mode='lines',
xaxis='x',
yaxis='y')
]),
layout=go.Layout(autosize=False,
height='100%',
hovermode='closest',
showlegend=False,
width='100%',
xaxis=go.XAxis(mirror='allticks',
rangemode='tozero',
showgrid=False,
showline=True,
showticklabels=True,
tickmode='array',
ticks='outside',
ticktext=np.array(
['3', '2', '0', '1']),
tickvals=[5.0, 15.0, 25.0, 35.0],
type='linear',
zeroline=False),
yaxis=go.YAxis(mirror='allticks',
rangemode='tozero',
showgrid=False,
showline=True,
showticklabels=True,
ticks='outside',
type='linear',
zeroline=False)))
self.assertEqual(len(dendro['data']), 3)
# this is actually a bit clearer when debugging tests.
self.assert_dict_equal(dendro['data'][0], expected_dendro['data'][0])
self.assert_dict_equal(dendro['data'][1], expected_dendro['data'][1])
self.assert_dict_equal(dendro['data'][2], expected_dendro['data'][2])
def test_dendrogram_random_matrix(self):
# create a random uncorrelated matrix
X = np.random.rand(5, 5)
# variable 2 is correlated with all the other variables
X[2, :] = sum(X, 0)
names = ['Jack', 'Oxana', 'John', 'Chelsea', 'Mark']
dendro = tls.FigureFactory.create_dendrogram(X, labels=names)
expected_dendro = go.Figure(
data=go.Data([
go.Scatter(marker=go.Marker(color='rgb(61,153,112)'),
mode='lines',
xaxis='x',
yaxis='y'),
go.Scatter(marker=go.Marker(color='rgb(61,153,112)'),
mode='lines',
xaxis='x',
yaxis='y'),
go.Scatter(marker=go.Marker(color='rgb(61,153,112)'),
mode='lines',
xaxis='x',
yaxis='y'),
go.Scatter(marker=go.Marker(color='rgb(0,116,217)'),
mode='lines',
xaxis='x',
yaxis='y')
]),
layout=go.Layout(autosize=False,
height='100%',
hovermode='closest',
showlegend=False,
width='100%',
xaxis=go.XAxis(
mirror='allticks',
rangemode='tozero',
showgrid=False,
showline=True,
showticklabels=True,
tickmode='array',
ticks='outside',
tickvals=[5.0, 15.0, 25.0, 35.0, 45.0],
type='linear',
zeroline=False),
yaxis=go.YAxis(mirror='allticks',
rangemode='tozero',
showgrid=False,
showline=True,
showticklabels=True,
ticks='outside',
type='linear',
zeroline=False)))
self.assertEqual(len(dendro['data']), 4)
# it's random, so we can only check that the values aren't equal
y_vals = [
dendro['data'][0].pop('y'), dendro['data'][1].pop('y'),
dendro['data'][2].pop('y'), dendro['data'][3].pop('y')
]
for i in range(len(y_vals)):
for j in range(len(y_vals)):
if i != j:
self.assertFalse(np.allclose(y_vals[i], y_vals[j]))
x_vals = [
dendro['data'][0].pop('x'), dendro['data'][1].pop('x'),
dendro['data'][2].pop('x'), dendro['data'][3].pop('x')
]
for i in range(len(x_vals)):
for j in range(len(x_vals)):
if i != j:
self.assertFalse(np.allclose(x_vals[i], x_vals[j]))
# we also need to check the ticktext manually
xaxis_ticktext = dendro['layout']['xaxis'].pop('ticktext')
self.assertEqual(xaxis_ticktext[0], 'John')
# this is actually a bit clearer when debugging tests.
self.assert_dict_equal(dendro['data'][0], expected_dendro['data'][0])
self.assert_dict_equal(dendro['data'][1], expected_dendro['data'][1])
self.assert_dict_equal(dendro['data'][2], expected_dendro['data'][2])
self.assert_dict_equal(dendro['data'][3], expected_dendro['data'][3])
self.assert_dict_equal(dendro['layout'], expected_dendro['layout'])
def get_dendrogram_traces(self, X, colorscale, distfun, linkagefun,
hovertext):
"""
Calculates all the elements needed for plotting a dendrogram.
:param (ndarray) X: Matrix of observations as array of arrays
:param (list) colorscale: Color scale for dendrogram tree clusters
:param (function) distfun: Function to compute the pairwise distance
from the observations
:param (function) linkagefun: Function to compute the linkage matrix
from the pairwise distances
:param (list) hovertext: List of hovertext for constituent traces of dendrogram
:rtype (tuple): Contains all the traces in the following order:
(a) trace_list: List of Plotly trace objects for dendrogram tree
(b) icoord: All X points of the dendrogram tree as array of arrays
with length 4
(c) dcoord: All Y points of the dendrogram tree as array of arrays
with length 4
(d) ordered_labels: leaf labels in the order they are going to
appear on the plot
(e) P['leaves']: left-to-right traversal of the leaves
"""
d = distfun(X)
Z = linkagefun(d)
P = sch.dendrogram(Z,
orientation=self.orientation,
labels=self.labels,
no_plot=True)
icoord = scp.array(P['icoord'])
dcoord = scp.array(P['dcoord'])
ordered_labels = scp.array(P['ivl'])
color_list = scp.array(P['color_list'])
colors = self.get_color_dict(colorscale)
trace_list = []
for i in range(len(icoord)):
# xs and ys are arrays of 4 points that make up the '∩' shapes
# of the dendrogram tree
if self.orientation in ['top', 'bottom']:
xs = icoord[i]
else:
xs = dcoord[i]
if self.orientation in ['top', 'bottom']:
ys = dcoord[i]
else:
ys = icoord[i]
color_key = color_list[i]
hovertext_label = None
if hovertext:
hovertext_label = hovertext[i]
trace = graph_objs.Scatter(
x=np.multiply(self.sign[self.xaxis], xs),
y=np.multiply(self.sign[self.yaxis], ys),
mode='lines',
marker=graph_objs.Marker(color=colors[color_key]),
text=hovertext_label,
hoverinfo='text')
try:
x_index = int(self.xaxis[-1])
except ValueError:
x_index = ''
try:
y_index = int(self.yaxis[-1])
except ValueError:
y_index = ''
trace['xaxis'] = 'x' + x_index
trace['yaxis'] = 'y' + y_index
trace_list.append(trace)
return trace_list, icoord, dcoord, ordered_labels, P['leaves']