def summary_targets(dataset, targets_attr="targets", chunks_attr="chunks", maxc=30, maxt=20):
"""Provide summary statistics over the targets and chunks
Parameters
----------
dataset : `Dataset`
Dataset to operate on
targets_attr : str, optional
Name of sample attributes of targets
chunks_attr : str, optional
Name of sample attributes of chunks -- independent groups of samples
maxc : int
Maximal number of chunks when provide details
maxt : int
Maximal number of targets when provide details
"""
# We better avoid bound function since if people only
# imported Dataset without miscfx it would fail
spcl = get_samples_per_chunk_target(dataset, targets_attr=targets_attr, chunks_attr=chunks_attr)
# XXX couldn't they be unordered?
ul = dataset.sa[targets_attr].unique.tolist()
uc = dataset.sa[chunks_attr].unique.tolist()
s = ""
if len(ul) < maxt and len(uc) < maxc:
s += "\nCounts of targets in each chunk:"
# only in a reasonable case do printing
table = [[" %s\\%s" % (chunks_attr, targets_attr)] + ul]
table += [[""] + ["---"] * len(ul)]
for c, counts in zip(uc, spcl):
table.append([str(c)] + counts.tolist())
s += "\n" + table2string(table)
else:
s += "No details due to large number of targets or chunks. " "Increase maxc and maxt if desired"
def cl_stats(axis, u, name1, name2):
"""Compute statistics per target
"""
stats = {
"min": np.min(spcl, axis=axis),
"max": np.max(spcl, axis=axis),
"mean": np.mean(spcl, axis=axis),
"std": np.std(spcl, axis=axis),
"#%s" % name2: np.sum(spcl > 0, axis=axis),
}
entries = [" " + name1, "mean", "std", "min", "max", "#%s" % name2]
table = [entries]
for i, l in enumerate(u):
d = {" " + name1: l}
d.update(dict([(k, stats[k][i]) for k in stats.keys()]))
table.append([("%.3g", "%s")[isinstance(d[e], basestring)] % d[e] for e in entries])
return "\nSummary for %s across %s\n" % (name1, name2) + table2string(table)
if len(ul) < maxt:
s += cl_stats(0, ul, targets_attr, chunks_attr)
if len(uc) < maxc:
s += cl_stats(1, uc, chunks_attr, targets_attr)
return s
def cl_stats(axis, u, name1, name2):
"""Compute statistics per target
"""
stats = {
"min": np.min(spcl, axis=axis),
"max": np.max(spcl, axis=axis),
"mean": np.mean(spcl, axis=axis),
"std": np.std(spcl, axis=axis),
"#%s" % name2: np.sum(spcl > 0, axis=axis),
}
entries = [" " + name1, "mean", "std", "min", "max", "#%s" % name2]
table = [entries]
for i, l in enumerate(u):
d = {" " + name1: l}
d.update(dict([(k, stats[k][i]) for k in stats.keys()]))
table.append([("%.3g", "%s")[isinstance(d[e], basestring)] % d[e] for e in entries])
return "\nSummary for %s across %s\n" % (name1, name2) + table2string(table)
def cl_stats(axis, u, name1, name2):
"""Compute statistics per target
"""
stats = {'min': np.min(spcl, axis=axis),
'max': np.max(spcl, axis=axis),
'mean': np.mean(spcl, axis=axis),
'std': np.std(spcl, axis=axis),
'#%s' % name2: np.sum(spcl>0, axis=axis)}
entries = [' ' + name1, 'mean', 'std', 'min', 'max', '#%s' % name2]
table = [ entries ]
for i, l in enumerate(u):
d = {' ' + name1 : l}
d.update(dict([ (k, stats[k][i]) for k in stats.keys()]))
table.append( [ ('%.3g', '%s')[isinstance(d[e], basestring)]
% d[e] for e in entries] )
return '\nSummary for %s across %s\n' % (name1, name2) \
+ table2string(table)
def _compute(self):
"""Compute stats and string representation
"""
# Do actual computation
order = self.order
seq = list(self._seq) # assure list
nsamples = len(seq) # # of samples/targets
utargets = sorted(list(set(seq))) # unique targets
ntargets = len(utargets) # # of targets
# mapping for targets
targets_map = dict([(l, i) for i, l in enumerate(utargets)])
# map sequence first
seqm = [targets_map[i] for i in seq]
# npertarget = np.bincount(seqm)
res = dict(utargets=utargets)
# Estimate counter-balance
cbcounts = np.zeros((order, ntargets, ntargets), dtype=int)
for cb in xrange(order):
for i, j in zip(seqm[:-(cb + 1)], seqm[cb + 1:]):
cbcounts[cb, i, j] += 1
res['cbcounts'] = cbcounts
"""
Lets compute relative counter-balancing
Ideally, npertarget[i]/ntargets should precede each target
"""
# Autocorrelation
corr = []
# for all possible shifts:
for shift in xrange(1, nsamples):
shifted = seqm[shift:] + seqm[:shift]
# ??? User pearsonsr with p may be?
corr += [np.corrcoef(seqm, shifted)[0, 1]]
# ??? report high (anti)correlations?
res['corrcoef'] = corr = np.array(corr)
res['sumabscorr'] = sumabscorr = np.sum(np.abs(corr))
self.update(res)
# Assign textual summary
# XXX move into a helper function and do on demand
t = [[""] * (1 + self.order * (ntargets + 1))
for i in xrange(ntargets + 1)]
t[0][0] = "Targets/Order"
for i, l in enumerate(utargets):
t[i + 1][0] = '%s:' % l
for cb in xrange(order):
t[0][1 + cb * (ntargets + 1)] = "O%d" % (cb + 1)
for i in xrange(ntargets + 1):
t[i][(cb + 1) * (ntargets + 1)] = " | "
m = cbcounts[cb]
# ??? there should be better way to get indexes
ind = np.where(~np.isnan(m))
for i, j in zip(*ind):
t[1 + i][1 + cb * (ntargets + 1) + j] = '%d' % m[i, j]
sout = "Sequence statistics for %d entries" \
" from set %s\n" % (len(seq), utargets) + \
"Counter-balance table for orders up to %d:\n" % order \
+ table2string(t)
if len(corr):
sout += "Correlations: min=%.2g max=%.2g mean=%.2g sum(abs)=%.2g" \
% (min(corr), max(corr), np.mean(corr), sumabscorr)
self._str_stats = sout
def summary_targets(dataset,
targets_attr='targets',
chunks_attr='chunks',
maxc=30,
maxt=20):
"""Provide summary statistics over the targets and chunks
Parameters
----------
dataset : `Dataset`
Dataset to operate on
targets_attr : str, optional
Name of sample attributes of targets
chunks_attr : str, optional
Name of sample attributes of chunks -- independent groups of samples
maxc : int
Maximal number of chunks when provide details
maxt : int
Maximal number of targets when provide details
"""
# We better avoid bound function since if people only
# imported Dataset without miscfx it would fail
spcl = get_samples_per_chunk_target(dataset,
targets_attr=targets_attr,
chunks_attr=chunks_attr)
# XXX couldn't they be unordered?
ul = dataset.sa[targets_attr].unique.tolist()
uc = dataset.sa[chunks_attr].unique.tolist()
s = ""
if len(ul) < maxt and len(uc) < maxc:
s += "\nCounts of targets in each chunk:"
# only in a reasonable case do printing
table = [[' %s\\%s' % (chunks_attr, targets_attr)] + ul]
table += [[''] + ['---'] * len(ul)]
for c, counts in zip(uc, spcl):
table.append([str(c)] + counts.tolist())
s += '\n' + table2string(table)
else:
s += "No details due to large number of targets or chunks. " \
"Increase maxc and maxt if desired"
def cl_stats(axis, u, name1, name2):
"""Compute statistics per target
"""
stats = {
'min': np.min(spcl, axis=axis),
'max': np.max(spcl, axis=axis),
'mean': np.mean(spcl, axis=axis),
'std': np.std(spcl, axis=axis),
'#%s' % name2: np.sum(spcl > 0, axis=axis)
}
entries = [' ' + name1, 'mean', 'std', 'min', 'max', '#%s' % name2]
table = [entries]
for i, l in enumerate(u):
d = {' ' + name1: l}
d.update(dict([(k, stats[k][i]) for k in stats.keys()]))
table.append([
('%.3g', '%s')[isinstance(d[e], basestring) or d[e] is None] %
d[e] for e in entries
])
return '\nSummary for %s across %s\n' % (name1, name2) \
+ table2string(table)
if len(ul) < maxt:
s += cl_stats(0, ul, targets_attr, chunks_attr)
if len(uc) < maxc:
s += cl_stats(1, uc, chunks_attr, targets_attr)
return s
def _compute(self):
"""Compute stats and string representation
"""
# Do actual computation
order = self.order
seq = list(self._seq) # assure list
nsamples = len(seq) # # of samples/targets
utargets = sorted(list(set(seq))) # unique targets
ntargets = len(utargets) # # of targets
# mapping for targets
targets_map = dict([(l, i) for i, l in enumerate(utargets)])
# map sequence first
seqm = [targets_map[i] for i in seq]
# npertarget = np.bincount(seqm)
res = dict(utargets=utargets)
# Estimate counter-balance
cbcounts = np.zeros((order, ntargets, ntargets), dtype=int)
for cb in xrange(order):
for i, j in zip(seqm[: -(cb + 1)], seqm[cb + 1 :]):
cbcounts[cb, i, j] += 1
res["cbcounts"] = cbcounts
"""
Lets compute relative counter-balancing
Ideally, npertarget[i]/ntargets should precede each target
"""
# Autocorrelation
corr = []
# for all possible shifts:
for shift in xrange(1, nsamples):
shifted = seqm[shift:] + seqm[:shift]
# ??? User pearsonsr with p may be?
corr += [np.corrcoef(seqm, shifted)[0, 1]]
# ??? report high (anti)correlations?
res["corrcoef"] = corr = np.array(corr)
res["sumabscorr"] = sumabscorr = np.sum(np.abs(corr))
self.update(res)
# Assign textual summary
# XXX move into a helper function and do on demand
t = [[""] * (1 + self.order * (ntargets + 1)) for i in xrange(ntargets + 1)]
t[0][0] = "Targets/Order"
for i, l in enumerate(utargets):
t[i + 1][0] = "%s:" % l
for cb in xrange(order):
t[0][1 + cb * (ntargets + 1)] = "O%d" % (cb + 1)
for i in xrange(ntargets + 1):
t[i][(cb + 1) * (ntargets + 1)] = " | "
m = cbcounts[cb]
# ??? there should be better way to get indexes
ind = np.where(~np.isnan(m))
for i, j in zip(*ind):
t[1 + i][1 + cb * (ntargets + 1) + j] = "%d" % m[i, j]
sout = "Sequence statistics for %d entries" " from set %s\n" % (
len(seq),
utargets,
) + "Counter-balance table for orders up to %d:\n" % order + table2string(t)
if len(corr):
sout += "Correlations: min=%.2g max=%.2g mean=%.2g sum(abs)=%.2g" % (
min(corr),
max(corr),
np.mean(corr),
sumabscorr,
)
self._str_stats = sout
