def compare_components_and_plot(images, labels, scoring, force_match=False, out_dir=None):
"""
For any given pair of ica component images, compute score matrix and plot the matrix.
Returns score matrix and sign matrix.
"""
# Compare components
# The sign_mat contains signs that gave the best score for the comparison
score_mat, sign_mat = compare_components(images, labels, scoring)
# Plot comparison matrix
for normalize in [False, True]:
plot_comparison_matrix(
score_mat, labels, scoring, normalize=normalize, out_dir=out_dir)
return score_mat, sign_mat
def load_or_generate_summary(images, term_scores, n_components, scoring, dataset,
force=False, sparsityThreshold=0.000005,
memory=Memory(cachedir='nilearn_cache')):
"""
For a given n_components, load summary csvs if they already exist, or
run main.py to get and save necessary summary data required for plotting.
Returns (wb_summary, R_sparsity, L_sparsity), each of which are DataFrame.
"""
# Directory to find or save the summary csvs
out_dir = op.join('ica_imgs', dataset, 'analyses', str(n_components))
summary_csvs = ["wb_summary.csv", "R_sparsity.csv", "L_sparsity.csv"]
# If summary data are already saved as csv files, simply load them
if not force and all([op.exists(op.join(out_dir, csv)) for csv in summary_csvs]):
print("Loading summary data from %s" % out_dir)
(wb_summary, R_sparsity, L_sparsity) = (pd.read_csv(op.join(out_dir, csv))
for csv in summary_csvs)
# Otherwise run main.py and save them as csv files
else:
# Initialize summary DFs
(wb_summary, R_sparsity, L_sparsity) = (pd.DataFrame(
{"n_comp": [n_components] * n_components}) for i in range(3))
if not op.exists(out_dir):
os.makedirs(out_dir)
# Use wb matching in main analysis to get component images and
# matching scores
match_method = 'wb'
img_d, score_mats_d, sign_mats_d = do_main_analysis(
dataset=dataset, images=images, term_scores=term_scores,
key=match_method, force=force, plot=False,
n_components=n_components, scoring=scoring)
# 1) Get sparsity for each hemisphere for "wb", "R" and "L" imgs
hemis = ("R", "L")
sparsitySigns = ("pos", "neg", "abs")
# Dict of DF and labels used to get and store Sparsity results
label_dict = {"wb": (wb_summary, hemis),
"R": (R_sparsity, ["R"]),
"L": (L_sparsity, ["L"])}
for key in label_dict:
(df, labels) = label_dict[key]
sparsityResults = {label: getHemiSparsity(img_d[key], label,
threshold=sparsityThreshold, memory=memory)
for label in labels} # {label: (pos_arr, neg_arr, abs_arr)}
for i, sign in enumerate(sparsitySigns):
for label in labels:
df["%s_%s" % (sign, label)] = sparsityResults[label][i]
# For wb only, also compute Total sparsity and HPI
if key == "wb":
df["%sTotal" % sign] = df["%s_R" % sign] + df["%s_L" % sign]
df["%sHPI" % sign] = ((df["%s_R" % sign] - df["%s_L" % sign]) /
df["%sTotal" % sign].astype(float))
# Save R/L_sparsity DFs
R_sparsity.to_csv(op.join(out_dir, "R_sparsity.csv"))
L_sparsity.to_csv(op.join(out_dir, "L_sparsity.csv"))
# 2) Get SAS of wb component images as well as matched RL images by passing
# 2 x wb or RL images and hemi labels to the compare_components (make sure
# not to flip when comparing R and L)
name_img_pairs = [("wb_SAS", img_d["wb"]),
("matchedRL_SAS", img_d["RL"])]
for (name, img) in name_img_pairs:
sas_imgs = [img] * 2
score_mat, sign_mat = compare_components(sas_imgs, hemis, scoring,
flip=False)
# we only care about the diagonal in score_mat
wb_summary[name] = score_mat.diagonal()
# 3) Finally store indices of matched R, L, and RL components, and the
# respective match scores against wb
comparisons = [('wb', 'R'), ('wb', 'L'), ('wb', 'RL')]
for comparison in comparisons:
score_mat, sign_mat = score_mats_d[comparison], sign_mats_d[comparison]
matched, unmatched = get_match_idx_pair(score_mat, sign_mat)
# Component indices for matched R, L , RL are in matched[1].
# Multiply it by matched[2], which stores sign flipping info.
matched_indices = matched[1] * matched[2]
wb_summary["matched%s" % comparison[1]] = matched_indices
matched_scores = score_mat[matched[0], matched[1]]
wb_summary["match%s_score" % comparison[1]] = matched_scores
# Save wb_summary
wb_summary.to_csv(op.join(out_dir, "wb_summary.csv"))
return (wb_summary, R_sparsity, L_sparsity)
