def plot_pooled_correlation_dists_by_condition(cfg):
"""
Plot the pooled (ie. combined, pooled) correlation distributions
separately for each of the conditions (each list in fname_group_list)
corresponds to a condition.
Parameters
----------
cfg : dict
the user-specified config dictionary.
The following keys are required::
"group_1_mat_fnames"
"group_2_mat_fnames"
"group_1_color"
"group_2_color"
"group_1_label"
"group_2_label"
Returns
-------
fig : the matplotlib figure object
"""
# CFGCHANGE?
config.require(cfg, [
"group_1_mat_fnames", "group_2_mat_fnames", "group_1_color",
"group_2_color", "group_1_label", "group_2_label"
])
fname_group_list = [cfg["group_1_mat_fnames"], cfg["group_2_mat_fnames"]]
colors = [cfg["group_1_color"], cfg["group_2_color"]]
labels = [cfg["group_1_label"], cfg["group_2_label"]]
n_bins = 100
corr_bins, corr_bin_centers = aux.get_lin_bins(n_bins, -1, 1.)
bin_counts = [np.zeros(n_bins) for f in fname_group_list]
fig = plt.figure()
ax = fig.add_subplot(111)
for i, fname_group in enumerate(fname_group_list):
for fname in fname_group:
flat_corr_mat = \
dataio.get_blacklist_filtered_and_flattened_adj_mat(
fname, cfg["blacklist_fname"]
)
bin_counts[i] += aux.get_bin_counts(flat_corr_mat, corr_bins)
# normalize
bin_counts[i] = bin_counts[i] / \
(np.sum(bin_counts[i] * (corr_bins[1] - corr_bins[0])))
ax.plot(corr_bin_centers,
bin_counts[i],
color=colors[i],
label=labels[i])
ax.set_xlabel(settings.get_prop_tex_name(settings.correlation_tag))
ax.set_ylabel(r"Probability density P(c)")
ax.legend(loc=0)
fig.savefig(cfg['outdata_dir'] + "pooledCorrDists.pdf",
format="pdf",
bbox_inches='tight')
return fig
def plot_pooled_corr_t_val_dists(cfg):
"""
Plot the tvalue distributions for movie and rest
Parameters
----------
config : dict
The following keys are required::
"group_1_mat_fnames"
"group_2_mat_fnames"
"group_1_color"
"group_2_color"
"group_1_label"
"group_2_label"
"outdata_dir"
"paired"
Returns
-------
fig : the matplotlib figure object
"""
config.require(cfg, [
"group_1_mat_fnames", "group_2_mat_fnames", "group_1_color",
"group_2_color", "group_1_label", "group_2_label", "outdata_dir",
"paired"
])
# get tvals
flat_mats = dataio.get_blacklist_filtered_and_flattened_adj_mats(
cfg["all_fnames"], cfg["blacklist_fname"])
if cfg["paired"]:
t_vals = measures.paired_t_value(flat_mats,
len(cfg['group_1_mat_fnames']))
else:
t_vals = measures.unpaired_t_value(flat_mats,
len(cfg['group_1_mat_fnames']))
minVal = np.min(t_vals)
maxVal = np.max(t_vals)
n_bins = 100
bins, binCenters = aux.get_lin_bins(n_bins,
minVal - (np.abs(minVal) * 0.1),
maxVal + (np.abs(maxVal) * 0.1))
bin_counts = aux.get_bin_counts(t_vals, bins)
fig = plt.figure()
ax = fig.add_subplot(111)
# normalize
bin_counts = bin_counts * 1. / (np.sum(bin_counts) * (bins[1] - bins[0]))
labels = cfg['group_1_label'], cfg["group_2_label"]
ax.plot(binCenters, bin_counts, label=r"" + labels[0] + "-" + labels[1])
ax.set_xlabel(settings.get_prop_tex_name(settings.tval_tag))
ax.set_ylabel(r"Probability density")
ax.legend(loc=0)
plt.savefig(cfg["outdata_dir"] + "tvalDist.pdf",
format="pdf",
bbox_inches='tight')
return fig
def plot_individual_correlation_dists(cfg):
"""
Plotting the individual correlation profiles to see the variations.
Parameters
----------
cfg : dict
the user-specified config dictionary.
The following keys are required::
"group_1_mat_fnames"
"group_2_mat_fnames"
"group_1_color"
"group_2_color"
"group_1_label"
"group_2_label"
"outdata_dir"
Returns
-------
fig : the matplotlib figure object
"""
# CFGCHANGE?
config.require(cfg, )
fname_group_list = [cfg["group_1_mat_fnames"], cfg["group_2_mat_fnames"]]
colors = [cfg["group_1_color"], cfg["group_2_color"]]
labels = [cfg["group_1_label"], cfg["group_2_label"]]
fig = plt.figure()
ax = fig.add_subplot(111)
n_bins = 100
corr_bins, corr_bin_centers = aux.get_lin_bins(n_bins, -1, 1.)
for i, fname_group in enumerate(fname_group_list):
for fname in fname_group:
flat_corr_mat = \
dataio.get_blacklist_filtered_and_flattened_adj_mat(
fname, cfg['blacklist_fname']
)
bin_counts = aux.get_bin_counts(flat_corr_mat, corr_bins)
# normalize
bin_counts = bin_counts / \
(np.sum(bin_counts * (corr_bins[1] - corr_bins[0])))
ax.plot(corr_bin_centers,
bin_counts,
color=colors[i],
label=labels[i])
ax.set_xlabel(settings.get_prop_tex_name("corr"))
ax.set_ylabel(r"Probability density P(c)")
ax.legend(loc=0)
fig.savefig(cfg['outdata_dir'] + "individualCorrDists.pdf",
format="pdf",
bbox_inches='tight')
return fig
def test_get_default_config(self):
cfg = config.get_default_config()
assert type(cfg) is dict
for key in config.CONFIG_KEYS:
assert key in cfg
for key in [
"all_fnames", "blacklist_fname", "group_1_mat_fnames",
"group_2_mat_fnames", "paired", "outdata_dir",
"node_info_fname", "paired"
]:
assert key in cfg
self.assertRaises(AssertionError, config.check_property, cfg, key)
keys = [
"bootstrap_samples", "bootstrap_coverage", "density",
"density_range", "group_1_label", "group_2_label", "group_1_color",
"group_2_color", "include_mst", "n_it_permutation"
]
config.require(cfg, keys)
def plot_link_dist_probs_by_condition(cfg):
"""
Plots the link distance PDFs pooled by condition.
Parameters
----------
cfg : dict
the user-specified config dictionary.
The following keys are required::
"group_1_mat_fnames"
"group_2_mat_fnames"
"group_1_color"
"group_2_color"
"group_1_label"
"group_2_label"
"outdata_dir"
Returns
-------
None
"""
# CFGCHANGE?
config.require(cfg, [
"group_1_mat_fnames", "group_2_mat_fnames", "group_1_color",
"group_2_color", "group_1_label", "group_2_label", "outdata_dir",
"density"
])
fname_group_list = [cfg["group_1_mat_fnames"], cfg["group_2_mat_fnames"]]
colors = [cfg["group_1_color"], cfg["group_2_color"]]
labels = [cfg["group_1_label"], cfg["group_2_label"]]
# ns = []
data_example = dataio.load_pickle(
fnc.get_ind_fname(fname_group_list[0][0], cfg,
settings.link_distance_tag))
densities = data_example[settings.config_tag][settings.densities_tag]
# for individual plots:
# figs = [plt.figure() for p in densities]
# axs = [fig.add_subplot(111) for fig in figs]
group_distances = []
for i, fname in enumerate(fname_group_list):
# ns.append(len(fname))
distances = [np.array([]) for p in densities]
for fname in fname:
print fname
data = dataio.load_pickle(
fnc.get_ind_fname(fname, cfg, settings.link_distance_tag))
p_f_dists = data[settings.link_distance_tag]
for j, p in enumerate(densities):
# print p
distances[j] = np.hstack((distances[j], p_f_dists[j]))
# for individual plots:
# for j in range(len(densities)):
# genplots.plot_inv_cdf(
# axs[j], distances[j], yscale='log',
# label=labels[i], color=colors[i])
group_distances.append(distances)
indices = range(len(densities)) # [6,7,10] #density indices
print densities
for k, j in enumerate(indices):
fig = plt.figure(figsize=(4, 3))
p = densities[j]
ax = fig.add_subplot(1, 1, 1)
ax.set_xlabel(settings.get_prop_tex_name(settings.link_distance_tag))
ax.set_ylabel(r"1-CDF(d)")
print p, j
ax.text(.5,
0.10,
r"$\rho$ = " + str(p * 100) + "\%",
ha='center',
va='center',
transform=ax.transAxes)
for i in range(len(fname_group_list)):
genplots.plot_inv_cdf(ax,
group_distances[i][j],
label=labels[i],
color=colors[i],
yscale='log')
plt.tight_layout()
fig.savefig(cfg['outdata_dir'] + "linkDistProbs_" + str(p) + ".pdf",
format="pdf",
bbox_inches="tight")
plt.close(fig)
return None