def time_align_visualize(alignments, time, y, namespace='time_align'):
plt.figure()
heat = np.flip(alignments + alignments.T + np.eye(alignments.shape[0]),
axis=0)
sns.heatmap(heat, cmap="YlGnBu")
plt.savefig(namespace + '_heatmap.svg')
G = nx.from_numpy_matrix(alignments)
G = nx.maximum_spanning_tree(G)
pos = {}
for i in range(len(G.nodes)):
pos[i] = np.array([time[i], y[i]])
mst_edges = set(nx.maximum_spanning_tree(G).edges())
weights = [
G[u][v]['weight'] if (not (u, v) in mst_edges) else 8
for u, v in G.edges()
]
plt.figure()
nx.draw(G, pos, edges=G.edges(), width=10)
plt.ylim([-1, 1])
plt.savefig(namespace + '.svg')
scanorama = np.array(scanorama)
uncorrected = np.array(uncorrected)
below = sum(scanorama > uncorrected + 50)
above = sum(scanorama < uncorrected - 50)
print('{}% above line'.format(float(above) / float(above + below) * 100))
name = sys.argv[1].split('.')[0]
line = max(min(max(scanorama), max(uncorrected)), 2100)
from scipy.stats import pearsonr
print(pearsonr(scanorama, uncorrected))
plt.figure()
plt.scatter(scanorama, uncorrected, s=10)
plt.plot([0, line], [0, line], 'r--')
plt.xlim([0, 2100])
plt.tight_layout()
plt.savefig('oneway_scanorama.png')
# scran MNN.
scranmnn, uncorrected = [], []
for gene in set(mnn.keys()) & set(uncor.keys()):
scranmnn.append(mnn[gene])
uncorrected.append(uncor[gene])
scranmnn = np.array(scranmnn)
uncorrected = np.array(uncorrected)
def plot_stats(stat,
samp_fns=None,
fname=None,
dtype=float,
only_fns=None,
only_replace=None,
max_N=None):
if samp_fns is None:
assert (fname is not None)
samp_fns = parse_stats(fname)
colors = [
#'#377eb8', '#ff7f00', '#f781bf',
#'#4daf4a', '#ff0000', '#a65628', '#984ea3',
#'#999999', '#e41a1c', '#dede00',
#'#ffe119', '#e6194b', '#ffbea3',
#'#911eb4', '#46f0f0', '#f032e6',
#'#d2f53c', '#008080', '#e6beff',
#'#aa6e28', '#800000', '#aaffc3',
#'#808000', '#ffd8b1', '#000080',
#'#808080', '#fabebe', '#a3f4ff'
'#377eb8',
'#ff7f00',
'#4daf4a',
'#984ea3',
#'#f781bf', '#a65628', '#984ea3',
'#999999',
'#e41a1c',
'#dede00',
'#ffe119',
'#e6194b',
'#ffbea3',
'#911eb4',
'#46f0f0',
'#f032e6',
'#d2f53c',
'#008080',
'#e6beff',
'#aa6e28',
'#800000',
'#aaffc3',
'#808000',
'#ffd8b1',
'#000080',
'#808080',
'#fabebe',
'#a3f4ff'
]
plt.figure()
c_idx = 0
for s_idx, (samp_fn, replace) in enumerate(
sorted(samp_fns, key=lambda x: '{}_{}'.format(*x))):
if samp_fn.startswith('_'):
continue
if only_fns is not None and samp_fn not in only_fns:
continue
if only_replace is not None and replace != only_replace:
continue
Ns = []
means = []
sems = []
for N in samp_fns[(samp_fn, replace)]:
if max_N is not None and N > max_N:
continue
stat_vals = [
dtype(stat_dict[stat])
for stat_dict in samp_fns[(samp_fn, replace)][N]
if stat in stat_dict
]
if len(stat_vals) == 0:
continue
Ns.append(N)
means.append(np.mean(stat_vals))
sems.append(ss.sem(stat_vals))
sort_idx = np.argsort(Ns)
Ns = np.array(Ns)[sort_idx]
means = np.array(means)[sort_idx]
sems = np.array(sems)[sort_idx]
label = '{}_{}'.format(samp_fn, replace)
plt.plot(Ns, means, color=colors[c_idx], label=label)
plt.scatter(Ns, means, color=colors[c_idx])
plt.fill_between(Ns,
means - sems,
means + sems,
alpha=0.3,
color=colors[c_idx])
c_idx = (c_idx + 1) % len(colors)
namespace = samp_fns[('_namespace', None)]
title = '{}_{}'.format(namespace, stat)
if only_replace is not None:
title += '_replace{}'.format(only_replace)
plt.title(title)
plt.xlabel('Sample size')
plt.ylabel(stat)
plt.legend()
mkdir_p('target/stats_plots')
plt.savefig('target/stats_plots/{}.svg'.format(title))
