def plot_stat_distributions(stats, group_names):
# Show the distribution of stats, to see if there are
# reliable group differences.
fh4 = plt.figure(figsize=(18, 8))
lbls = ['%s vs. %s' % (gn1, gn2)
for gi, gn1 in enumerate(group_names)
for gn2 in group_names[gi + 1:]]
pi = 1
for si, stat_name in enumerate(['mean', 'var']):
stat_vals = np.asarray([ss[:, si * 2] for ss in stats])
pvals = np.asarray([ss[:, si * 2 + 1] for ss in stats])
for li, lbl in enumerate(lbls):
ax1 = fh4.add_subplot(2, len(lbls), pi)
plot_normalized_hist(pvals[:, li], ax=ax1, bins=[0.0001, 0.001, 0.01, 0.05, 0.10, 0.20, 0.30, 0.40, 0.50, 0.60])
ax1.set_title(lbl)
if li == 0:
ax1.set_ylabel(stat_name)
pi += 1
equalize_xlims(fh4)
equalize_ylims(fh4)
means = np.asarray([ss[:, 0] for ss in stats])
stds = np.asarray([ss[:, 2] for ss in stats])
good_idx = ~np.logical_or(np.isnan(means.sum(1)), np.isnan(stds.sum(1)))
fh = plt.figure(figsize=(18, 8))
ax1 = fh.add_subplot(1, 2, 1)
plot_normalized_hist(means[good_idx], ax=ax1, bins=25)
ax1.set_xlabel('mean')
ax2 = fh.add_subplot(1, 2, 2)
plot_normalized_hist(stds[good_idx], ax=ax2, bins=25)
ax2.set_xlabel('standard deviation')
ax2.legend(group_names)
def compare_group_asymmetry(data, xaxis_key, yaxis_key, grouping_keys, plots, measure_key):
""" Groups data according to grouping_keys, computes
asymmetry index for key, and graphs."""
group_names, grouping_index = get_groupings(data, grouping_keys)
x_data = np.asarray(data[xaxis_key].tolist())
prop_ai = get_asymmetry_index(data, yaxis_key)
n_subplots = len(group_names)
n_rows = 1 # int(np.round(np.sqrt(n_subplots)))
n_cols = n_subplots # int(np.ceil(n_subplots / float(n_rows)))
if 'regressions' in plots:
fh1 = plt.figure(figsize=(18, 7))
# fh1.suptitle('%s regression' % yaxis_key)
if 'distributions' in plots:
fh2 = plt.figure(figsize=(18, 7))
fh2.suptitle('%s distributions' % yaxis_key)
n_bins = 15
bins = np.linspace(prop_ai[~np.isnan(prop_ai)].min(),
prop_ai[~np.isnan(prop_ai)].max(),
n_bins + 2)[1:-1]
group_samples = []
regressions = []
for gi, group_name in enumerate(group_names):
# Index the current group
if group_name == 'all':
idx = np.ones((len(data.values()[0]),), dtype=bool)
else:
idx = grouping_index[gi]
# Select data within the group
cur_x = x_data[idx]
group_ai = prop_ai[idx]
# Remove bad data
bad_idx = np.logical_or(np.isnan(cur_x), np.isnan(group_ai))
good_idx = np.logical_not(bad_idx)
cur_x = cur_x[good_idx]
group_ai = group_ai[good_idx]
group_samples.append(group_ai)
regressions.append(scipy.stats.linregress(cur_x, group_ai))
# Plot the regression result
params = dict(xlabel=xaxis_key, ylabel='Asymmetry Index (LH - RH)',
title='Group: %s (n=%d)' % (group_name, len(group_ai)))
if 'regressions' in plots:
if gi > 0:
del params['ylabel']
# ax1 = fh1.add_subplot(n_rows, n_cols, gi + 1)
ax1 = fh1.gca()
do_and_plot_regression(cur_x, group_ai, ax=ax1, colori=gi,
show_std=(len(cur_x) > 200), **params)
ax1.set_title(measure_key) # ax1.get_title().split('\n')[0])
# Plot the distribution result
if 'distributions' in plots:
ax2 = fh2.add_subplot(n_rows, n_cols, gi + 1)
plot_normalized_hist(group_ai, ax2, bins=bins)
ax2.set_title(params['title'])
ax2.set_xlabel(params['ylabel'])
ax2.set_ylims([0, 0.25])
regressions = np.asarray(regressions)
# stats[:, n]: 0:mean_stat: 1:mean_pval; 2:std_stat, 3:std_pval
# shape: n_compares x 4
stats = np.asarray([(scipy.stats.ttest_ind(gsamps1, gsamps2) +
scipy.stats.levene(gsamps1, gsamps2))
for gi, gsamps1 in enumerate(group_samples)
for gsamps2 in group_samples[gi + 1:]])
# Test whether variances differ
if 'stats' in plots:
dist_mat = scipy.spatial.distance.squareform(stats[:, 2])
sig_mat = stats[:, 3] <= (0.05 / stats.shape[0])
fh3 = plt.figure()
fh3.suptitle(str(['%.2e' % s for s in stats[:, 3]]))
ax1 = fh3.add_subplot(1, 2, 1)
plot_symmetric_matrix_as_triangle(dist_mat, ax=ax1, labels=group_names)
ax2 = fh3.add_subplot(1, 2, 2, axisbg=fh3.get_facecolor())
plot_symmetric_matrix_as_triangle(sig_mat, ax=ax2, labels=group_names)
if 'distributions' in plots:
equalize_xlims(fh2)
equalize_ylims(fh2)
return group_names, stats, regressions, group_samples
