def plot_one_pr_curve(comps_removed, precision_vectors, recall_vectors, auprc_list, ymax, batch_column, total_comp, filename):
colors_lines = pt.get_style_combos(['lines', 'colors'])
fig = plt.figure(figsize = (7, 7))
ax = fig.add_subplot(1,1,1)
for i, ncomps in enumerate(comps_removed):
# Since sklearn sets the first precision at recall=0 to 1,
# I remove this value and any subsequent values at recall=0
# so that plotting only starts with the precision obtained
# at the threshold of the first true positive observation
# (in case multiple true positives have the same associated
# score).
recall_vec = recall_vectors[i]
precision_vec = precision_vectors[i]
first_nonzero_recall_ind = np.nanmin(np.where(recall_vec > 0)[0])
first_nonzero_recall_val = recall_vec[first_nonzero_recall_ind]
last_first_nonzero_recall_ind = np.nanmax(np.where(recall_vec == first_nonzero_recall_val)[0])
recall_vec = recall_vec[last_first_nonzero_recall_ind:]
precision_vec = precision_vec[last_first_nonzero_recall_ind:]
# On to plotting
style = colors_lines.next()
ax.plot(recall_vec, precision_vec, style, label = '{} (normalized AUPRC = {:.3f})'.format(ncomps, auprc_list[i]))
ax.set_xscale('log')
ax.set_ylim([0, ymax])
ax.set_ylabel('Precision')
ax.set_xlabel('Recall')
plt.title('Precision-recall analysis of\n"{}" batch effects'.format(batch_column))
if total_comp > 1:
plt.title('Precision-recall analysis of\n"{}" batch effects'.format(batch_column))
lgd = ax.legend(bbox_to_anchor = (1.05, 1), loc = 2, title = "Number of components\nremoved")
plt.savefig(filename, bbox_extra_artists = ([lgd]), bbox_inches = 'tight')
else:
plt.title('Precision-recall analysis of "{}"\nbatch effects (normalized AUPRC = {:.3f})'.format(batch_column, auprc_list[i]))
plt.savefig(filename)
def plot_one_pr_curve(comps_removed, precision_vectors, recall_vectors, auc_list, ymax, batch_column, filename):
colors_lines = pt.get_style_combos(['lines', 'colors'])
fig = plt.figure(figsize = (7, 7))
ax = fig.add_subplot(1,1,1)
for i, ncomps in enumerate(comps_removed):
style = colors_lines.next()
ax.plot(recall_vectors[i], precision_vectors[i], style, label = '{} (normalized AUC = {:.3f})'.format(ncomps, auc_list[i]))
ax.set_xscale('log')
ax.set_ylim([0, ymax])
ax.set_ylabel('Precision')
ax.set_xlabel('Recall')
lgd = ax.legend(bbox_to_anchor = (1.05, 1), loc = 2, title = "Number of components\nremoved")
plt.title('Precision-recall analysis of\n"{}" batch effects'.format(batch_column))
plt.savefig(filename, bbox_extra_artists = ([lgd]), bbox_inches = 'tight')
def plot_roc_curves(comps_removed, fpr_vecs, tpr_vecs, auc_list, batch_column, pr_folder):
filename = get_lda_roc_curve_filename(pr_folder)
colors_lines = pt.get_style_combos(['lines', 'colors'])
fig = plt.figure(figsize = (7, 7))
ax = fig.add_subplot(1,1,1)
for i, ncomps in enumerate(comps_removed):
style = colors_lines.next()
ax.plot(fpr_vecs[i], tpr_vecs[i], style, label = '{} (AUC = {:.3f})'.format(ncomps, auc_list[i]))
ax.set_ylim([0, 1])
ax.set_xlabel('False Positive Rate (Specificity)')
ax.set_ylabel('True Positive Rate (Sensitivity)')
lgd = ax.legend(bbox_to_anchor = (1.05, 1), loc = 2, title = "Number of components\nremoved")
plt.title('ROC analysis of\n"{}" batch effects'.format(batch_column))
plt.savefig(filename, bbox_extra_artists = ([lgd]), bbox_inches = 'tight')
