def boxplot_panel(hit_vec, response_df):
"""
Draws a series of paired boxplots with the rows of the response_df
split according to hit_vec.
"""
b = response_df.copy()
b.columns = pd.MultiIndex.from_arrays([b.columns, hit_vec.ix[b.columns]])
b = b.T
v1, v2 = hit_vec.unique()
test = lambda v: Stats.anova(
v.reset_index(level=1)[v.index.names[1]],
v.reset_index(level=1)[v.name])
res = b.apply(test).T
p = res.p.order()
b = b.ix[:, p.index]
l1 = list(b.xs(v1, level=1).as_matrix().T)
l2 = list(b.xs(v2, level=1).as_matrix().T)
boxes = [x for t in zip(l1, l2) for x in t]
ax1, bp = paired_boxplot(boxes)
y_lim = (response_df.T.quantile(.9).max()) * 1.2
pts = [(i * 3.5 + .5, y_lim) for i, n in enumerate(p) if n < .00001]
if len(pts) > 0:
s1 = ax1.scatter(*zip(*pts), marker='$**$', label='$p<10^{-5}$', s=200)
else:
s1 = None
pts = [(i * 3.5 + .5, y_lim) for i, n in enumerate(p)
if (n < .01) and (n > .00001)]
if len(pts) > 0:
s2 = ax1.scatter(*zip(*pts), marker='$*$', label='$p<10^{-2}$', s=30)
else:
s2 = None
ax1.set_xticklabels(b.columns)
ax1.legend(bp['boxes'][:2] + [s2, s1],
(v1, v2, '$p<10^{-2}$', '$p<10^{-5}$'),
loc='best',
scatterpoints=1)
def boxplot_panel(hit_vec, response_df):
"""
Draws a series of paired boxplots with the rows of the response_df
split according to hit_vec.
"""
b = response_df.copy()
b.columns = pd.MultiIndex.from_arrays([b.columns, hit_vec.ix[b.columns]])
b = b.T
v1, v2 = hit_vec.unique()
test = lambda v: Stats.anova(v.reset_index(level=1)[v.index.names[1]],
v.reset_index(level=1)[v.name])
res = b.apply(test).T
p = res.p.order()
b = b.ix[:, p.index]
l1 = list(b.xs(v1, level=1).as_matrix().T)
l2 = list(b.xs(v2, level=1).as_matrix().T)
boxes = [x for t in zip(l1, l2) for x in t]
ax1, bp = paired_boxplot(boxes)
y_lim = (response_df.T.quantile(.9).max()) * 1.2
pts = [(i * 3.5 + .5, y_lim) for i, n in enumerate(p) if n < .00001]
if len(pts) > 0:
s1 = ax1.scatter(*zip(*pts), marker='$**$', label='$p<10^{-5}$', s=200)
else:
s1 = None
pts = [(i * 3.5 + .5, y_lim) for i, n in enumerate(p) if (n < .01)
and (n > .00001)]
if len(pts) > 0:
s2 = ax1.scatter(*zip(*pts), marker='$*$', label='$p<10^{-2}$', s=30)
else:
s2 = None
ax1.set_xticklabels(b.columns)
ax1.legend(bp['boxes'][:2] + [s2, s1],
(v1, v2, '$p<10^{-2}$', '$p<10^{-5}$'),
loc='best', scatterpoints=1)
def exp_change(s):
'''
Calculates an anova for the change in expression across a variable
on the second level of a MultiIndex. (eg. tumor/normal).
'''
return Tests.anova(pd.Series(s.index.get_level_values(1), s.index), s)
def exp_change(s):
'''
Calculates an anova for the change in expression across a variable
on the second level of a MultiIndex. (eg. tumor/normal).
'''
return Tests.anova(pd.Series(s.index.get_level_values(1), s.index), s)
