def cv_info(self):
if self._cv_results is None:
raise ValueError(
f"CV: no cross-validation was performed. Use mu='auto' to perform cross-validation."
)
cv_results = sorted(self._cv_results, key=attrgetter('mu'))
criteria = ('cross-fit', 'l2/mu')
best_mu = {criterion: self.cv_mu(criterion) for criterion in criteria}
table = fmtxt.Table('lllll')
table.cells('mu', 'cross-fit', 'l2-error', 'weighted l2-error',
'ES metric')
table.midrule()
fmt = '%.5f'
for result in cv_results:
table.cell(fmtxt.stat(result.mu, fmt=fmt))
star = 1 if result.mu is best_mu['cross-fit'] else 0
table.cell(fmtxt.stat(result.cross_fit, fmt, star, 1))
star = 1 if result.mu is best_mu['l2/mu'] else 0
table.cell(fmtxt.stat(result.l2_error, fmt, star, 1))
table.cell(fmtxt.stat(result.weighted_l2_error, fmt=fmt))
table.cell(fmtxt.stat(result.estimation_stability, fmt=fmt))
# warnings
mus = [res.mu for res in self._cv_results]
warnings = []
if self.mu == min(mus):
warnings.append(f"Best mu is smallest mu")
if warnings:
table.caption(f"Warnings: {'; '.join(warnings)}")
return table
def reduction_table(self, labels=None, vertical=False):
"""Table with steps of model reduction
Parameters
----------
labels : dict {str: str}
Substitute new labels for predictors.
vertical : bool
Orient table vertically.
"""
if not self._reduction_results:
self.execute()
if labels is None:
labels = {}
n_steps = len(self._reduction_results)
# find terms
terms = []
for ress in self._reduction_results:
terms.extend(term for term in ress.keys() if term not in terms)
n_terms = len(terms)
# cell content
cells = {}
for x in terms:
for i, ress in enumerate(self._reduction_results):
if x in ress:
res = ress[x]
pmin = res.p.min()
t_cell = fmtxt.stat(res.t.max(), stars=pmin)
p_cell = fmtxt.p(pmin)
else:
t_cell = p_cell = ''
cells[i, x] = t_cell, p_cell
if vertical:
t = fmtxt.Table('ll' + 'l' * n_terms)
t.cells('Step', '')
for x in terms:
t.cell(labels.get(x, x))
t.midrule()
for i in range(n_steps):
t_row = t.add_row()
p_row = t.add_row()
t_row.cells(i + 1, fmtxt.symbol('t', 'max'))
p_row.cells('', fmtxt.symbol('p'))
for x in terms:
t_cell, p_cell = cells[i, x]
t_row.cell(t_cell)
p_row.cell(p_cell)
else:
t = fmtxt.Table('l' + 'rr' * n_steps)
t.cell()
for _ in range(n_steps):
t.cell(fmtxt.symbol('t', 'max'))
t.cell(fmtxt.symbol('p'))
t.midrule()
for x in terms:
t.cell(labels.get(x, x))
for i in range(n_steps):
t.cells(*cells[i, x])
return t
def table(self, title=None, caption=None):
"""Table with effects and smallest p-value"""
if self.test_type is LMGroup:
cols = sorted(
{col
for res in self.values() for col in res.column_names})
table = fmtxt.Table('l' * (1 + len(cols)),
title=title,
caption=caption)
table.cell('')
table.cells(*cols)
table.midrule()
for key, lmg in self.items():
table.cell(key)
for res in (lmg.tests[c] for c in cols):
pmin = res.p.min()
table.cell(fmtxt.FMText([fmtxt.p(pmin), star(pmin)]))
elif self.test_type is anova:
table = fmtxt.Table('lllll', title=title, caption=caption)
table.cells('Test', 'Effect',
fmtxt.symbol(self.test_type._statistic, 'max'),
fmtxt.symbol('p'), 'sig')
table.midrule()
for key, res in self.items():
for i, effect in enumerate(res.effects):
table.cells(key, effect)
pmin = res.p[i].min()
table.cell(fmtxt.stat(res._max_statistic(i)))
table.cell(fmtxt.p(pmin))
table.cell(star(pmin))
key = ''
else:
table = fmtxt.Table('llll', title=title, caption=caption)
table.cells('Effect',
fmtxt.symbol(self.test_type._statistic, 'max'),
fmtxt.symbol('p'), 'sig')
table.midrule()
for key, res in self.items():
table.cell(key)
pmin = res.p.min()
table.cell(fmtxt.stat(res._max_statistic()))
table.cell(fmtxt.p(pmin))
table.cell(star(pmin))
return table
def clusters(self, p=0.05):
"""Table with significant clusters"""
if self.test_type is TestType.TWO_STAGE:
raise NotImplementedError
else:
table = fmtxt.Table('lrrrrll')
table.cells('Effect', 't-start', 't-stop', fmtxt.symbol(self._statistic, 'max'), fmtxt.symbol('t', 'peak'), fmtxt.symbol('p'), 'sig', just='l')
table.midrule()
for key, res in self.items():
table.cell(key)
table.endline()
clusters = res.find_clusters(p, maps=True)
clusters.sort('tstart')
if self.test_type is not TestType.MULTI_EFFECT:
clusters[:, 'effect'] = ''
for effect, tstart, tstop, p_, sig, cmap in clusters.zip('effect', 'tstart', 'tstop', 'p', 'sig', 'cluster'):
max_stat, max_time = res._max_statistic(mask=cmap != 0, return_time=True)
table.cells(f' {effect}', ms(tstart), ms(tstop), fmtxt.stat(max_stat), ms(max_time), fmtxt.p(p_), sig)
return table
def anova(self):
"Return an ANOVA table"
# table head
table = fmtxt.Table("l" + "r" * 5)
if self.title:
table.title(self.title)
table.cell()
headers = ["SS", "df", "MS"]
headers += ["F", "p"]
for hd in headers:
table.cell(hd, r"\textbf", just="c")
table.midrule()
# table body
for name, F_test in zip(self.names, self.F_tests):
table.cell(name)
table.cell(fmtxt.stat(F_test.SS))
table.cell(fmtxt.stat(F_test.df, fmt="%i"))
table.cell(fmtxt.stat(F_test.MS))
if F_test.F:
stars = test.star(F_test.p)
table.cell(fmtxt.stat(F_test.F, stars=stars))
table.cell(fmtxt.p(F_test.p))
else:
table.cell()
table.cell()
# residuals
if self.X.df_error > 0:
table.empty_row()
table.cell("Residuals")
SS, df, MS = self.residuals
table.cell(SS)
table.cell(df, fmt="%i")
table.cell(MS)
table.endline()
# total
table.midrule()
table.cell("Total")
SS = np.sum((self.Y.x - self.Y.mean()) ** 2)
table.cell(fmtxt.stat(SS))
table.cell(fmtxt.stat(len(self.Y) - 1, fmt="%i"))
return table
def anova(self):
"Return ANOVA table"
if self.show_ems is None:
ems = defaults["show_ems"]
else:
ems = self.show_ems
# table head
table = textab.Table("l" + "r" * (5 + ems))
if self.title:
table.title(self.title)
table.cell()
headers = ["SS", "df", "MS"]
# if ems: headers += ["E(MS)"]
headers += ["F", "p"]
for hd in headers:
table.cell(hd, r"\textbf", just="c")
table.midrule()
# table body
for name, SS, df, MS, F, p in self._results_table:
table.cell(name)
table.cell(textab.stat(SS))
table.cell(textab.stat(df, fmt="%i"))
table.cell(textab.stat(MS))
if F:
stars = test.star(p)
table.cell(textab.stat(F, stars=stars))
table.cell(textab.p(p))
else:
table.cell()
table.cell()
# total
table.midrule()
table.cell("Total")
table.cell(textab.stat(self.Y.SS))
table.cell(textab.stat(self.Y.N - 1, fmt="%i"))
return table
