def test_nwk2tree_matrix():
newick = '(((a,b),(c,d)),e);'
matrix, taxa = tree.nwk2tree_matrix(newick)
assert taxa == Tree(newick).taxa
def test_nwk2tree_matrix(self):
matrix, taxa = tree.nwk2tree_matrix(self.newick)
assert taxa == self.tree.taxa
def plot_heatmap(wordlist,
filename="heatmap",
fileformat="pdf",
ref='cogid',
normalized=False,
refB='',
**keywords):
"""
Create a heatmap-representation of shared cognates for a given wordlist.
Parameters
----------
wordlist : lingpy.basic.wordlist.Wordlist
A Wordlist object containing cognate IDs.
filename : str (default="heatmap")
Name of the file to which the heatmap will be written.
fileformat : str (default="pdf")
A regular matplotlib-fileformat (pdf, png, pgf, svg).
ref : str (default="cogid')
The name of the column that contains the cognate identifiers.
normalized : {bool str} (default=True)
If set to c{False}, don't normalize the data. Otherwise, select the
normalization method, choose between:
* "jaccard" for the Jaccard-distance (see :evobib:`Bategelj1995` for
details), and
* "swadesh" for traditional lexicostatistical calculation of shared
cognate percentages.
cmap : matplotlib.cm (default=matplotlib.cm.jet)
The color scheme to be used for the heatmap.
steps : int (default=5)
The number of steps in which names of taxa will be written to the axes.
xrotation : int (default=45)
The rotation of the taxon-names on the x-axis.
colorbar : bool (default=True)
Specify, whether a colorbar should be added to the plot.
figsize : tuple (default=(10,10))
Specify the size of the figure.
tree : str (default='')
A tree passed for the taxa in Newick-format. If no tree is specified,
the method looks for a tree object in the Wordlist.
Notes
-----
This function plots shared cognate percentages.
"""
defaults = dict(
bottom=0.01, # rcParams['phybo_ylimb']
cmap=mpl.cm.jet,
colorbar=True,
colorbar_label="Shared Cognates",
colorbar_shrink=0.75,
colorbar_textsize=10,
figsize=(10, 5),
height=0.8,
labels={}, # taxon labels passed for the taxa,
left=0.01, # rcParams['phybo_xlimr'],
matrix=False,
normalization="jaccard",
right=0.95, # rcParams['phybo_xliml'],
scale=0.075,
show_tree=True,
steps=20,
textsize=5,
top=0.95, # rcParams['phybo_ylimt'],
tree='',
tree_bottom=0.1,
tree_left=0.1,
tree_width=0.2,
vmax=1.0,
vmin=0.0,
width=0.8,
xrotation=90,
distances=False)
for k in defaults:
if k not in keywords:
keywords[k] = defaults[k]
# access the reference tree of the wordlist and create a function that
# orders the taxa accordingly
if not keywords['tree']:
try:
tree = wordlist.tree
except:
raise ValueError("[i] No tree could be found")
else:
tree = keywords["tree"]
# check for normalization
if normalized:
if normalized not in ["jaccard", "swadesh"]:
raise ValueError(
"Keyword 'normalized' must be one of 'jaccard','swadesh',False."
)
# create an empty matrix
if not normalized:
matrix = np.zeros((wordlist.width, wordlist.width), dtype=int)
else:
matrix = np.zeros((wordlist.width, wordlist.width), dtype=float)
# create the figure
fig = plt.figure(figsize=keywords['figsize'])
# plot the reference tree
if keywords['show_tree']:
tree_matrix, taxa = nwk2tree_matrix(tree)
ax1 = fig.add_axes([
keywords['left'], keywords['bottom'], 0.25 * keywords['width'],
keywords['height']
])
# [0.01,0.1,0.2,0.7])
d = sch.dendrogram(
np.array(tree_matrix),
labels=[t for t in taxa],
orientation='left',
)
taxa = d['ivl'][::-1]
ax1.set_xticks([])
ax1.set_yticks([])
ax1.spines['bottom'].set_color('#ffffff')
ax1.spines['top'].set_color('#ffffff')
ax1.spines['left'].set_color('#ffffff')
ax1.spines['right'].set_color('#ffffff')
left = keywords['left'] + keywords['scale'] * keywords['width']
else:
left = keywords['left']
taxa = tree.taxa
# start iterating over taxa in order of the reference tree and fill in the
# matrix with numbers of shared cognates
if keywords['matrix']:
matrix = keywords['matrix']
else:
for i, taxonA in enumerate(taxa):
for j, taxonB in enumerate(taxa):
if i < j:
if normalized in [False, "jaccard"]:
cogsA = wordlist.get_list(taxa=taxonA,
flat=True,
entry=ref)
cogsB = wordlist.get_list(taxa=taxonB,
flat=True,
entry=ref)
cogsA, cogsB = set(cogsA), set(cogsB)
shared = len(cogsA.intersection(cogsB))
if normalized:
shared = shared / len(cogsA.union(cogsB))
else:
cogsA = wordlist.get_dict(taxa=taxonA, entry=ref)
cogsB = wordlist.get_dict(taxa=taxonB, entry=ref)
shared = 0
slots = 0
# iterate over cognate sets in meaning slots
for key in cogsA.keys():
# check whether keys are present, we follow the
# STARLING procedure in ignoring missing data
if key in cogsA and key in cogsB:
# check for shared items
if [k for k in cogsA[key] if k in cogsB[key]]:
shared += 1
slots += 1
try:
shared = shared / slots
except ZeroDivisionError:
log.warning(
str([
shared, slots,
len(cogsA),
len(cogsB), taxonA, taxonB
]))
shared = 0.0
matrix[i][j] = shared
# if refB is also a possibiltiy
if not refB:
matrix[j][i] = shared
elif i > j and refB:
if normalized in [False, "jaccard"]:
cogsA = wordlist.get_list(taxa=taxonA,
flat=True,
entry=refB)
cogsB = wordlist.get_list(taxa=taxonB,
flat=True,
entry=refB)
cogsA, cogsB = set(cogsA), set(cogsB)
shared = len(cogsA.intersection(cogsB))
if normalized:
shared = shared / len(cogsA.union(cogsB))
else:
cogsA = wordlist.get_dict(taxa=taxonA, entry=refB)
cogsB = wordlist.get_dict(taxa=taxonB, entry=refB)
shared = 0
slots = 0
# iterate over cognate sets in meaning slots
for key in cogsA.keys():
# check whether keys are present, we follow the
# STARLING procedure in ignoring missing data
if key in cogsA and key in cogsB:
# check for shared items
if [k for k in cogsA[key] if k in cogsB[key]]:
shared += 1
slots += 1
try:
shared = shared / slots
except ZeroDivisionError:
log.warning(
str([
shared, slots,
len(cogsA),
len(cogsB), taxonA, taxonB
]))
shared = 0.0
matrix[i][j] = shared
elif i == j:
cogs = wordlist.get_list(taxa=taxonA, flat=True, entry=ref)
if normalized:
matrix[i][j] = 1.0
else:
matrix[i][j] = len(set(cogs))
ax2 = fig.add_axes([
left, # keywords['left']+0.25 * keywords['width']+0.05,
keywords['bottom'],
keywords['width'],
keywords['height']
])
cmap = keywords['cmap']
# [0.15,0.1,0.7,0.7])
if 'distances' in keywords and keywords['distances']:
for i, line in enumerate(matrix):
for j, cell in enumerate(matrix):
matrix[i][j] = 1 - matrix[i][j]
nmatrix = [[keywords['vmax'], keywords['vmin']],
[keywords['vmin'], keywords['vmax']]]
im = ax2.matshow(nmatrix,
aspect='auto',
origin='lower',
interpolation='nearest',
cmap=keywords['cmap'],
vmax=keywords['vmax'],
vmin=keywords['vmin'])
# set the xticks
steps = int(len(taxa) / keywords['steps'] + 0.5)
start = int(steps / 2 + 0.5)
idxs = [0] + list(range(start, len(taxa), steps))
selected_taxa = [taxa[i] for i in idxs]
# modify taxon names if this is specified
for i, t in enumerate(selected_taxa):
if t in keywords['labels']:
selected_taxa[i] = keywords['labels'][t]
ax2.set_xticks([])
ax2.set_yticks([])
plt.xticks(idxs,
selected_taxa,
size=keywords['textsize'],
rotation=keywords['xrotation'],
rotation_mode="default")
plt.yticks(
idxs,
selected_taxa,
size=keywords['textsize'],
)
if keywords["colorbar"]:
plt.imshow(matrix,
cmap=keywords['cmap'],
visible=False,
vmax=keywords['vmax'])
c = plt.colorbar(im, shrink=keywords['colorbar_shrink'])
c.set_label(keywords["colorbar_label"],
size=keywords['colorbar_textsize'])
plt.subplots_adjust(left=keywords['left'],
right=keywords['right'],
top=keywords['top'],
bottom=keywords['bottom'])
plt.savefig(filename + '.' + fileformat)
f = open(filename + '.matrix', 'w')
for i, t in enumerate(taxa):
f.write('{0:20}'.format(t))
for j, c in enumerate(matrix[i]):
if not normalized:
f.write('\t{0:3}'.format(int(c)))
else:
f.write('\t{0:.2f}'.format(c))
f.write('\n')
f.close()
log.file_written(filename + '.' + fileformat)
def plot_heatmap(
wordlist,
filename="heatmap",
fileformat="pdf",
ref='cogid',
normalized=False,
refB='',
**keywords
):
"""
Create a heatmap-representation of shared cognates for a given wordlist.
Parameters
----------
wordlist : lingpy.basic.wordlist.Wordlist
A Wordlist object containing cognate IDs.
filename : str (default="heatmap")
Name of the file to which the heatmap will be written.
fileformat : str (default="pdf")
A regular matplotlib-fileformat (pdf, png, pgf, svg).
ref : str (default="cogid')
The name of the column that contains the cognate identifiers.
normalized : {bool str} (default=True)
If set to c{False}, don't normalize the data. Otherwise, select the
normalization method, choose between:
* "jaccard" for the Jaccard-distance (see :evobib:`Bategelj1995` for
details), and
* "swadesh" for traditional lexicostatistical calculation of shared
cognate percentages.
cmap : matplotlib.cm (default=matplotlib.cm.jet)
The color scheme to be used for the heatmap.
steps : int (default=5)
The number of steps in which names of taxa will be written to the axes.
xrotation : int (default=45)
The rotation of the taxon-names on the x-axis.
colorbar : bool (default=True)
Specify, whether a colorbar should be added to the plot.
figsize : tuple (default=(10,10))
Specify the size of the figure.
tree : str (default='')
A tree passed for the taxa in Newick-format. If no tree is specified,
the method looks for a tree object in the Wordlist.
Notes
-----
This function plots shared cognate percentages.
"""
defaults = dict(
bottom=0.01, # rcParams['phybo_ylimb']
cmap=mpl.cm.jet,
colorbar=True,
colorbar_label="Shared Cognates",
colorbar_shrink=0.75,
colorbar_textsize=10,
figsize=(10, 5),
height=0.8,
labels={}, # taxon labels passed for the taxa,
left=0.01, # rcParams['phybo_xlimr'],
matrix=False,
normalization="jaccard",
right=0.95, # rcParams['phybo_xliml'],
scale=0.075,
show_tree=True,
steps=20,
textsize=5,
top=0.95, # rcParams['phybo_ylimt'],
tree='',
tree_bottom=0.1,
tree_left=0.1,
tree_width=0.2,
vmax=1.0,
vmin=0.0,
width=0.8,
xrotation=90,
distances=False
)
for k in defaults:
if k not in keywords:
keywords[k] = defaults[k]
# access the reference tree of the wordlist and create a function that
# orders the taxa accordingly
if not keywords['tree']:
try:
tree = wordlist.tree
except:
raise ValueError("[i] No tree could be found")
else:
tree = keywords["tree"]
# check for normalization
if normalized:
if normalized not in ["jaccard", "swadesh"]:
raise ValueError(
"Keyword 'normalized' must be one of 'jaccard','swadesh',False.")
# create an empty matrix
if not normalized:
matrix = np.zeros((wordlist.width, wordlist.width), dtype=int)
else:
matrix = np.zeros((wordlist.width, wordlist.width), dtype=float)
# create the figure
fig = plt.figure(figsize=keywords['figsize'])
# plot the reference tree
if keywords['show_tree']:
tree_matrix, taxa = nwk2tree_matrix(tree)
ax1 = fig.add_axes(
[
keywords['left'],
keywords['bottom'],
0.25 * keywords['width'],
keywords['height']
]
)
# [0.01,0.1,0.2,0.7])
d = sch.dendrogram(
np.array(tree_matrix),
labels=[t for t in taxa],
orientation='left',
)
taxa = d['ivl'][::-1]
ax1.set_xticks([])
ax1.set_yticks([])
ax1.spines['bottom'].set_color('#ffffff')
ax1.spines['top'].set_color('#ffffff')
ax1.spines['left'].set_color('#ffffff')
ax1.spines['right'].set_color('#ffffff')
left = keywords['left'] + keywords['scale'] * keywords['width']
else:
left = keywords['left']
taxa = tree.taxa
# start iterating over taxa in order of the reference tree and fill in the
# matrix with numbers of shared cognates
if keywords['matrix']:
matrix = keywords['matrix']
else:
for i, taxonA in enumerate(taxa):
for j, taxonB in enumerate(taxa):
if i < j:
if normalized in [False, "jaccard"]:
cogsA = wordlist.get_list(
taxa=taxonA,
flat=True,
entry=ref
)
cogsB = wordlist.get_list(
taxa=taxonB,
flat=True,
entry=ref
)
cogsA, cogsB = set(cogsA), set(cogsB)
shared = len(cogsA.intersection(cogsB))
if normalized:
shared = shared / len(cogsA.union(cogsB))
else:
cogsA = wordlist.get_dict(
taxa=taxonA,
entry=ref
)
cogsB = wordlist.get_dict(
taxa=taxonB,
entry=ref
)
shared = 0
slots = 0
# iterate over cognate sets in meaning slots
for key in cogsA.keys():
# check whether keys are present, we follow the
# STARLING procedure in ignoring missing data
if key in cogsA and key in cogsB:
# check for shared items
if [k for k in cogsA[key] if k in cogsB[key]]:
shared += 1
slots += 1
try:
shared = shared / slots
except ZeroDivisionError:
log.warning(str(
[shared, slots, len(cogsA), len(cogsB), taxonA, taxonB]))
shared = 0.0
matrix[i][j] = shared
# if refB is also a possibiltiy
if not refB:
matrix[j][i] = shared
elif i > j and refB:
if normalized in [False, "jaccard"]:
cogsA = wordlist.get_list(
taxa=taxonA,
flat=True,
entry=refB
)
cogsB = wordlist.get_list(
taxa=taxonB,
flat=True,
entry=refB
)
cogsA, cogsB = set(cogsA), set(cogsB)
shared = len(cogsA.intersection(cogsB))
if normalized:
shared = shared / len(cogsA.union(cogsB))
else:
cogsA = wordlist.get_dict(
taxa=taxonA,
entry=refB
)
cogsB = wordlist.get_dict(
taxa=taxonB,
entry=refB
)
shared = 0
slots = 0
# iterate over cognate sets in meaning slots
for key in cogsA.keys():
# check whether keys are present, we follow the
# STARLING procedure in ignoring missing data
if key in cogsA and key in cogsB:
# check for shared items
if [k for k in cogsA[key] if k in cogsB[key]]:
shared += 1
slots += 1
try:
shared = shared / slots
except ZeroDivisionError:
log.warning(str(
[shared, slots, len(cogsA), len(cogsB), taxonA, taxonB]))
shared = 0.0
matrix[i][j] = shared
elif i == j:
cogs = wordlist.get_list(
taxa=taxonA,
flat=True,
entry=ref
)
if normalized:
matrix[i][j] = 1.0
else:
matrix[i][j] = len(set(cogs))
ax2 = fig.add_axes(
[
left, # keywords['left']+0.25 * keywords['width']+0.05,
keywords['bottom'],
keywords['width'],
keywords['height']
]
)
cmap = keywords['cmap']
# [0.15,0.1,0.7,0.7])
if 'distances' in keywords and keywords['distances']:
for i, line in enumerate(matrix):
for j, cell in enumerate(matrix):
matrix[i][j] = 1 - matrix[i][j]
nmatrix = [
[keywords['vmax'], keywords['vmin']],
[keywords['vmin'], keywords['vmax']]
]
im = ax2.matshow(nmatrix, aspect='auto', origin='lower',
interpolation='nearest', cmap=keywords['cmap'],
vmax=keywords['vmax'], vmin=keywords['vmin']
)
# set the xticks
steps = int(len(taxa) / keywords['steps'] + 0.5)
start = int(steps / 2 + 0.5)
idxs = [0] + list(range(start, len(taxa), steps))
selected_taxa = [taxa[i] for i in idxs]
# modify taxon names if this is specified
for i, t in enumerate(selected_taxa):
if t in keywords['labels']:
selected_taxa[i] = keywords['labels'][t]
ax2.set_xticks([])
ax2.set_yticks([])
plt.xticks(
idxs,
selected_taxa,
size=keywords['textsize'],
rotation=keywords['xrotation'],
rotation_mode="default"
)
plt.yticks(
idxs,
selected_taxa,
size=keywords['textsize'],
)
if keywords["colorbar"]:
plt.imshow(matrix, cmap=keywords['cmap'], visible=False, vmax=keywords['vmax'])
c = plt.colorbar(im, shrink=keywords['colorbar_shrink'])
c.set_label(keywords["colorbar_label"], size=keywords['colorbar_textsize'])
plt.subplots_adjust(
left=keywords['left'],
right=keywords['right'],
top=keywords['top'],
bottom=keywords['bottom']
)
plt.savefig(filename + '.' + fileformat)
f = open(filename + '.matrix', 'w')
for i, t in enumerate(taxa):
f.write('{0:20}'.format(t))
for j, c in enumerate(matrix[i]):
if not normalized:
f.write('\t{0:3}'.format(int(c)))
else:
f.write('\t{0:.2f}'.format(c))
f.write('\n')
f.close()
log.file_written(filename + '.' + fileformat)
def test_nwk2tree_matrix(self):
matrix, taxa = tree.nwk2tree_matrix(self.newick)
assert taxa == self.tree.taxa
