def test_rotate_axis0_input(self):
kws = self.default_kws.copy()
kws['rotate'] = True
kws['axis'] = 0
p = mat._DendrogramPlotter(self.df_norm.T, **kws)
npt.assert_array_equal(p.reordered_ind, self.x_norm_leaves)
def test_fastcluster_other_method(self):
import fastcluster
kws = self.default_kws.copy()
kws['method'] = 'average'
linkage = fastcluster.linkage(self.x_norm.T,
method='average',
metric='euclidean')
p = mat._DendrogramPlotter(self.x_norm, **kws)
npt.assert_array_equal(p.linkage, linkage)
def test_label_false(self):
kws = self.default_kws.copy()
kws['label'] = False
p = mat._DendrogramPlotter(self.df_norm, **kws)
assert p.xticks == []
assert p.yticks == []
assert p.xticklabels == []
assert p.yticklabels == []
assert p.xlabel == ""
assert p.ylabel == ""
def test_rotate_input(self):
kws = self.default_kws.copy()
kws['rotate'] = True
p = mat._DendrogramPlotter(self.df_norm, **kws)
npt.assert_array_equal(p.array.T, np.asarray(self.df_norm))
pdt.assert_frame_equal(p.data.T, self.df_norm)
npt.assert_array_equal(p.xticklabels, [])
npt.assert_array_equal(p.yticklabels, self.df_norm_leaves)
assert p.xlabel == ''
assert p.ylabel == 'letters'
def test_linkage_scipy(self):
p = mat._DendrogramPlotter(self.x_norm, **self.default_kws)
scipy_linkage = p._calculate_linkage_scipy()
from scipy.spatial import distance
from scipy.cluster import hierarchy
dists = distance.pdist(self.x_norm.T,
metric=self.default_kws['metric'])
linkage = hierarchy.linkage(dists, method=self.default_kws['method'])
npt.assert_array_equal(scipy_linkage, linkage)
def test_df_input(self):
p = mat._DendrogramPlotter(self.df_norm, **self.default_kws)
npt.assert_array_equal(p.array.T, np.asarray(self.df_norm))
pdt.assert_frame_equal(p.data.T, self.df_norm)
npt.assert_array_equal(p.linkage, self.x_norm_linkage)
assert p.dendrogram == self.x_norm_dendrogram
npt.assert_array_equal(
p.xticklabels,
np.asarray(self.df_norm.columns)[self.x_norm_leaves])
npt.assert_array_equal(p.yticklabels, [])
assert p.xlabel == 'letters'
assert p.ylabel == ''
def test_ndarray_input(self):
p = mat._DendrogramPlotter(self.x_norm, **self.default_kws)
npt.assert_array_equal(p.array.T, self.x_norm)
pdt.assert_frame_equal(p.data.T, pd.DataFrame(self.x_norm))
npt.assert_array_equal(p.linkage, self.x_norm_linkage)
assert p.dendrogram == self.x_norm_dendrogram
npt.assert_array_equal(p.reordered_ind, self.x_norm_leaves)
npt.assert_array_equal(p.xticklabels, self.x_norm_leaves)
npt.assert_array_equal(p.yticklabels, [])
assert p.xlabel is None
assert p.ylabel == ''
def test_axis0_input(self):
kws = self.default_kws.copy()
kws['axis'] = 0
p = mat._DendrogramPlotter(self.df_norm.T, **kws)
npt.assert_array_equal(p.array, np.asarray(self.df_norm.T))
pdt.assert_frame_equal(p.data, self.df_norm.T)
npt.assert_array_equal(p.linkage, self.x_norm_linkage)
assert p.dendrogram == self.x_norm_dendrogram
npt.assert_array_equal(p.xticklabels, self.df_norm_leaves)
npt.assert_array_equal(p.yticklabels, [])
assert p.xlabel == 'letters'
assert p.ylabel == ''
def test_df_multindex_input(self):
df = self.df_norm.copy()
index = pd.MultiIndex.from_tuples([("A", 1), ("B", 2), ("C", 3),
("D", 4)],
names=["letter", "number"])
index.name = "letter-number"
df.index = index
kws = self.default_kws.copy()
kws['label'] = True
p = mat._DendrogramPlotter(df.T, **kws)
xticklabels = ["A-1", "B-2", "C-3", "D-4"]
xticklabels = [xticklabels[i] for i in p.reordered_ind]
npt.assert_array_equal(p.xticklabels, xticklabels)
npt.assert_array_equal(p.yticklabels, [])
assert p.xlabel == "letter-number"
def test_custom_linkage(self):
kws = self.default_kws.copy()
try:
import fastcluster
linkage = fastcluster.linkage_vector(self.x_norm,
method='single',
metric='euclidean')
except ImportError:
d = distance.pdist(self.x_norm, metric='euclidean')
linkage = hierarchy.linkage(d, method='single')
dendrogram = hierarchy.dendrogram(linkage,
no_plot=True,
color_threshold=-np.inf)
kws['linkage'] = linkage
p = mat._DendrogramPlotter(self.df_norm, **kws)
npt.assert_array_equal(p.linkage, linkage)
assert p.dendrogram == dendrogram
def heatmap(df, corr_types=None, map_type='zaric', ax=None, face_color=None,
annot=None, cbar=True, cbar_kws=None, mask=None,
row_cluster=False, row_cluster_metric='euclidean',
row_cluster_method='average', row_cluster_linkage=None,
col_cluster=False, col_cluster_metric='euclidean',
col_cluster_method='average', col_cluster_linkage=None,
**kwargs):
"""
Plots a heatmap.
Arguments:
df: The dataframe to plot.
corr_types: Optionally specify correlation type using a dataframe of
CorrType enums for each entry (can be obtained from the corr
function). When specified, numeric correlations are plotted using
different markers.
map_type: One of 'zaric', 'standard', 'dendrograms':
* 'zaric' (default): a special heatmap, where magnitude is
indicated by size of the elements as well as their colour.
* 'standard': a standard heatmap plotted using sns.heatmap;
* 'dendrograms': a heatmap with dendrograms, using sns.clustermap.
ax: The matplotlib axis to use for the plotting (not supported for
map_type 'dendrograms').
annot: Whether to also annotate the squares with numbers (defaults to
True for map_type 'standard' and 'dendrograms'; for 'zaric'
annotations are currently not displayed).
cbar: Whether to include a colorbar.
cbar_kws: Additional kwargs to use when plotting the colorbar.
mask: An array or a dataframe that indicates whether a value should
be masked out (True) or displayed (False).
row_cluster: Whether to use hierarchical clustering to reorder the rows.
row_cluster_metric: The metric to use for clustering the rows
(see _DendrogramPlotter in seaborn.matrix).
row_cluster_method: The method to use for clustering the rows
(see _DendrogramPlotter in seaborn.matrix).
row_cluster_linkage: The linkage to use for clustering the rows
(see _DendrogramPlotter in seaborn.matrix).
col_cluster: Whether to use hierarchical clustering to reorder the cols.
col_cluster_metric: The metric to use for clustering the columns
(see _DendrogramPlotter in seaborn.matrix).
col_cluster_method: The method to use for clustering the columns
(see _DendrogramPlotter in seaborn.matrix).
col_cluster_linkage: The linkage to use for clustering the columns
(see _DendrogramPlotter in seaborn.matrix).
square: Whether equal aspect ratio should be used for the axes or not
(defaults to True).
**kwargs: Any remaining kwargs are passed to the plotting function.
"""
if map_type == 'dendrograms':
if not ax is None:
raise ValueError("Argument 'ax' is not supported for map_type == 'dendrograms'.")
else:
if ax is None:
ax = plt.gca()
if not mask is None:
mask = np.asarray(mask)
if not corr_types is None:
corr_types = np.asarray(corr_types)
if row_cluster and not map_type == 'dendrograms':
row_ind = _DendrogramPlotter(
df, axis=0, metric=row_cluster_metric,
method=row_cluster_method, linkage=row_cluster_linkage,
label=False, rotate=False
).reordered_ind
df = df.reindex(df.index[row_ind])
if not mask is None:
mask = mask[row_ind, :]
if not corr_types is None:
corr_types = corr_types[row_ind, :]
if col_cluster and not map_type == 'dendrograms':
col_ind = _DendrogramPlotter(
df, axis=1, metric=col_cluster_metric,
method=col_cluster_method, linkage=col_cluster_linkage,
label=False, rotate=False
).reordered_ind
df = df.reindex(df.columns[col_ind], axis=1)
if not mask is None:
mask = mask[:, col_ind]
if not corr_types is None:
corr_types = corr_types[:, col_ind]
if map_type == "zaric":
l = np.asarray(list(itertools.product(df.index, df.columns)))
x = l[:, 0]
y = l[:, 1]
v = df.values.reshape(-1)
m = mask.reshape(-1) if not mask is None else None
circ = np.zeros(len(x))
if not corr_types is None:
circ[np.where(corr_types.reshape(-1) == CorrType.num_vs_num)] = True
default_kwargs = dict(
color=v,
size=np.abs(v),
circular=circ
)
default_kwargs.update(**kwargs)
kwargs = default_kwargs
_zaric_heatmap(
x, y,
ax=ax,
face_color=face_color,
cbar=cbar,
cbar_kws=cbar_kws,
mask=m,
x_order=df.columns,
y_order=df.index,
**kwargs
)
ax.set_xlabel(df.columns.name)
ax.set_ylabel(df.index.name)
elif map_type == 'standard' or map_type == 'dendrograms':
if annot is None:
annot = True
if face_color is None:
face_color = 'black'
default_kwargs = dict(center=0, square=True, linewidths=1,
annot=annot)
default_kwargs.update(**kwargs)
kwargs = default_kwargs
if map_type == 'dendrograms':
del kwargs['square']
sns.clustermap(df, cbar=cbar, cbar_kws=cbar_kws,
mask=mask, **kwargs)
else:
sns.heatmap(df, ax=ax, cbar=cbar, cbar_kws=cbar_kws,
mask=mask, **kwargs)
if ax is None: ax = plt.gcf().axes[2]
ax.set_facecolor(face_color)
ax.xaxis.set_tick_params(rotation=45)
plt.setp(ax.get_xticklabels(),
rotation_mode="anchor", horizontalalignment="right")
else:
raise ValueError("Unknown map_type '{}'.".format(map_type))
