def oneway(Y, X, match=None, sub=None, par=True, title=None):
"data: for should iter over groups/treatments"
data, datalabels, names, within = _split_Y(Y, X, match=match, sub=sub)
test = _oneway(data, parametric=par, within=within)
template = "{test}: {statistic}={value}{stars}, p={p}"
out = template.format(**test)
return out
def pairwise(Y, X, match=None, sub=None, # data in
par=True, corr='Hochberg', trend=True, # stats
title='{desc}', mirror=False, # layout
):
"""
pairwise comparison according to factor structure
"""
# ct = celltable(Y, X, match=match, sub=sub)
# test
data, datalabels, names, within = _split_Y(Y, X, match=match, sub=sub)
test = _pairwise(data, within=within, parametric=par, corr=corr, #levels=levels,
trend=trend)
# extract test results
k = len(data)
indexes = test['pw_indexes']
statistic = test['statistic']
_K = test[statistic]
_P = test['p']
if corr:
_Pc = mcp_adjust(_P, corr)
_df = test['df']
_NStars = test['stars']
symbols = test['symbols']
# create TABLE
table = textab.Table('l'+'l'*(k-1+mirror))
title_desc = "Pairwise {0}".format(test['test'])
table.title(title.format(desc=title_desc))
table.caption(test['caption'])
# headings
table.cell()
for name in names[1-mirror:]:
table.cell(name)
table.midrule()
tex_peq = textab.texstr("p=")
#tex_df = textab.Element(df, "_", digits=0)
if corr and not mirror:
subrows = range(3)
else:
subrows = range(2)
for row in range(0, k-1+mirror):
for subrow in subrows: # contains t/p
# names column
if subrow is 0:
table.cell(names[row], r"\textbf")
else:
table.cell()
# rows
for col in range(1-mirror, k):
if row == col:
table.cell()
elif col > row:
index = indexes[(row, col)]
#(col-1) + ((k-2)*row) sum(range(k-1, k-1-row, -1))
K = _K[index]
p = _P[index]
df = _df[index]
# nstars = _NStars[index]
if subrow is 0:
tex_cell = textab.eq(statistic, K, df=df,
stars=symbols[index],
of=3+trend)
elif subrow is 1:
tex_cell = textab.texstr([tex_peq, texstr(p, fmt='%.3f')],
mat=True)
elif subrow is 2:
tex_cell = textab.eq('p', _Pc[index], df='c',
fmt='%.3f', drop0=True)
table.cell(tex_cell)
else:
if mirror and corr and subrow==0:
index = indexes[(col, row)]
p = _Pc[index]
table.cell(p, fmt='%.3f', drop0=True)
else:
table.cell()
return table
def data(Y, X=None, match=None, cov=[], sub=None, fmt=None, labels=True,
showcase=True):
"""
return a textab.table (printed as tsv table by default)
parameters
----------
Y: variable to display (can be model with several dependents)
X: categories defining cells (factorial model)
match: factor to match values on and return repeated-measures table
cov: covariate to report (WARNING: only works with match, where each value
on the matching variable corresponds with one value in the covariate)
sub: boolean array specifying which values to include (generate e.g.
with 'sub=T==[1,2]')
fmt: Format string
labels: display labels for nominal variables (otherwise display codes)
"""
if hasattr(Y, '_items'): # dataframe
Y = Y._items
Y = _data.asmodel(Y)
if _data.isfactor(cov) or _data.isvar(cov):
cov = [cov]
data = []
names_yname = [] # names including Yi.name for matched table headers
ynames = [] # names of Yi for independent measures table headers
within_list = []
for Yi in Y.effects:
_data, datalabels, names, _within = _data._split_Y(Yi, X, match=match,
sub=sub, datalabels=match)
data += _data
names_yname += ['({c})'.format(c=n) for n in names]
ynames.append(Yi.name)
within_list.append(_within)
within = within_list[0]
assert all([w==within for w in within_list])
# table
n_dependents = len(Y.effects)
n_cells = int(len(data) / n_dependents)
if within:
n, k = len(data[0]), len(data)
table = textab.Table('l' * (k + showcase + len(cov)))
# header line 1
if showcase:
table.cell(match.name)
case_labels = datalabels[0]
assert all([np.all(case_labels==l) for l in datalabels[1:]])
for i in range(n_dependents):
for name in names:
table.cell(name.replace(' ','_'))
for c in cov:
table.cell(c.name)
# header line 2
if n_dependents > 1:
if showcase:
table.cell()
for name in ynames:
[table.cell('(%s)'%name) for i in range(n_cells)]
for c in cov:
table.cell()
# body
table.midrule()
for i in range(n):
case = case_labels[i]
if showcase:
table.cell(case)
for j in range(k):
table.cell(data[j][i], fmt=fmt)
# covariates
indexes = match==case
for c in cov:
# test it's all the same values
case_cov = c[indexes]
if len(np.unique(case_cov.x)) != 1:
msg = 'covariate for case "%s" has several values'%case
raise ValueError(msg)
# get value
first_i = np.nonzero(indexes)[0][0]
cov_value = c[first_i]
if _data.isfactor(c) and labels:
cov_value = c.cells[cov_value]
table.cell(cov_value, fmt=fmt)
else:
table = textab.Table('l'*(1 + n_dependents))
table.cell(X.name)
[table.cell(y) for y in ynames]
table.midrule()
# data is now sorted: (cell_i within dependent_i)
# sort data as (X-cell, dependent_i)
data_sorted = []
for i_cell in range(n_cells):
data_sorted.append([data[i_dep*n_cells + i_cell] for i_dep in \
range(n_dependents)])
# table
for name, cell_data in zip(names, data_sorted):
for i in range(len(cell_data[0])):
table.cell(name)
for dep_data in cell_data:
v = dep_data[i]
table.cell(v, fmt=fmt)
return table
