def generate_dict(samples_dict, number_of_folds = 15000):
taxonomic_levels = ['genus', 'family', 'order', 'class', 'phylum']
samples = helper_functions.sorted_copy(samples_dict.keys())
rarefaction_dict = {}
for sample in samples:
print "sample name: ", sample
rarefaction_dict[sample] = {}
for taxonomic_level in taxonomic_levels:
species_in_the_sample = []
OTUs = samples_dict[sample][taxonomic_level].keys()
for i in range(0, len(OTUs)):
species_in_the_sample += [i] * samples_dict[sample][taxonomic_level][OTUs[i]]
print "level: ", taxonomic_level, "sequences: ", len(species_in_the_sample), "folds: ", number_of_folds
rarefaction_values_lists = []
for i in range(0, number_of_folds):
random.shuffle(species_in_the_sample)
rarefaction_values_lists.append(get_rarefaction_values(species_in_the_sample))
means_and_stdev_tmp = []
for i in range(0, len(rarefaction_values_lists[0])):
means_and_stdev_tmp.append((scipy.mean([x[i] for x in rarefaction_values_lists]), scipy.std([x[i] for x in rarefaction_values_lists])),)
rarefaction_dict[sample][taxonomic_level] = means_and_stdev_tmp
return rarefaction_dict
def generate(samples_dict, img_save_path = None, data_save_path = None, type = None, method='simpsons'):
taxonomic_level = const.ranks[type][-1]
samples = helper_functions.sorted_copy(samples_dict.keys())
samples_diversity_index_list = []
if method == 'simpsons':
samples_diversity_index_list = [get_simpsons_diversity_index(samples_dict[sample][taxonomic_level]) for sample in samples]
lbl = "Simpson's Sample Diversity Index"
c = color='#ADADEF'
elif method == 'shannons':
samples_diversity_index_list = [get_shannons_diversity_index(samples_dict[sample][taxonomic_level]) for sample in samples]
lbl = "Shannon Diversity Index"
c = color='#66AA66'
else:
return None
# store diveristy indices in a text file as well
if data_save_path:
f = open(data_save_path, 'w')
for i in range(0, len(samples)):
f.write("%s\t%f\n" % (samples[i], samples_diversity_index_list[i]))
f.close()
width = len(samples) / 5
if width < 5:
width = 5
if width > 15:
width = 15
fig = pylab.figure(figsize=(width, 4))
pylab.rcParams.update({'axes.linewidth' : 0, 'axes.axisbelow': False})
pylab.rc('grid', color='0.80', linestyle='-', linewidth=0.1)
pylab.grid(True)
pos = pylab.arange(len(samples))+.5
pylab.bar(pos, samples_diversity_index_list, align='center', color=c, linewidth=0.1)
pylab.plot([0], [1], '^', visible = False)
pylab.xticks(pos, samples, rotation=90, size='xx-small')
pylab.xlim(xmax=len(samples))
pylab.yticks(size='xx-small')
pylab.ylabel(lbl, fontsize = 12)
if img_save_path:
pylab.savefig(img_save_path)
else:
pylab.show()
def generate(samples_dict, otu_t_p_tuples_dict, sample_map_file_path, rank = "genus", save_dir = None, is_transparent = False, real_abundance = False):
sample_groups, group_colors = helper_functions.get_groups_colors_from_sample_map_file(sample_map_file_path)
if real_abundance:
"""if we're gonna work with real abundance, we need to find out about the
ymax of the y axis. to do that, first, we learn the max abundance, then,
find out the smallest power of 10 that is larger than max_abundance.."""
max_abundance = helper_functions.get_largest_abundance_number_in_all_samples(samples_dict)
max_y = 1
while 1:
if max_y > max_abundance:
break
max_y *= 10
for otu in [t[0] for t in otu_t_p_tuples_dict[rank]]:
txt_output = ''
plot_dict = {}
for group in sample_groups.keys():
plot_dict[group] = []
for sample in sample_groups[group]:
if samples_dict[sample][rank].has_key(otu):
if real_abundance:
plot_dict[group].append([samples_dict[sample][rank][otu], sample],)
txt_output += '%s\t%s\t%f\n' % (group, sample, samples_dict[sample][rank][otu])
else:
if samples_dict[sample]['tr'] == 0:
otu_vectors[group].append(0.0)
else:
plot_dict[group].append([samples_dict[sample][rank][otu] * 100.0 / samples_dict[sample]['tr'], sample],)
txt_output += '%s\t%s\t%f\n' % (group, sample, samples_dict[sample][rank][otu] * 100.0 / samples_dict[sample]['tr'])
else:
plot_dict[group].append([0.0, sample],)
txt_output += '%s\t%s\t0.0\n' % (group, sample)
fig = pylab.figure(figsize=(3, 6))
if real_abundance:
ax = pylab.axes()
pylab.rcParams['axes.titlesize'] = 12.0
pylab.rcParams['font.size'] = 8.0
pylab.rcParams.update({'axes.linewidth' : 0, 'axes.axisbelow': False})
pylab.rc('grid', color='0.50', linestyle='-', linewidth=0.1)
pylab.grid(True)
keys = helper_functions.sorted_copy(plot_dict.keys())
presence = []
for key in keys:
i = keys.index(key)
if real_abundance:
"""if abundance is 0.0, make it 1 so it would look better on log scale"""
for j in range(0, len(plot_dict[key])):
if plot_dict[key][j][0] < 1:
plot_dict[key][j][0] = 1.0
pylab.title(otu)
presence.append('%.3f' % (len([t[0] for t in plot_dict[key] if t[0] > 0.01]) * 100.0 / len(plot_dict[key])) )
# scattering the samples in X axis, so it would be easier to see them when there are a bunch of them
# at the same spot. instead of this, i * len(plot_dict[key]) could be used to plot them.
y_positions = [((1 - (r.gauss(100, 3) /100)) + i) for x in range(0, len(plot_dict[key]))]
pylab.plot(y_positions, [t[0] for t in plot_dict[key]], 'o', color = group_colors[key], ms = 10, mew = 0.6, alpha = .5)
b = pylab.boxplot([t[0] for t in plot_dict[key]], positions=[i + 0.35], sym=',', widths=0.2)
pylab.setp(b['medians'], color=group_colors[key])
pylab.setp(b['whiskers'], color='black', alpha=0.3)
pylab.setp(b['boxes'], color='black', alpha=0.3)
pylab.setp(b['fliers'], color='black', alpha=0.3)
pylab.setp(b['caps'], color='black', alpha=0.3)
if real_abundance:
ax.set_yscale('log')
formatter = pylab.FuncFormatter(log_10_fix)
ax.yaxis.set_major_formatter(formatter)
pylab.xlim(xmin=-0.75, xmax=len(plot_dict) - 0.15)
pylab.xticks(pylab.arange(len(plot_dict)), keys, rotation=90)
pylab.ylim(ymin=1e-1, ymax=max_y)
else:
pylab.ylim(ymin=-5, ymax=105)
pylab.xlim(xmin=-0.75, xmax=len(plot_dict) - 0.15)
pylab.xticks(pylab.arange(len(plot_dict)), keys, rotation=90)
pylab.yticks(pylab.arange(0, 101, 10))
print '%s,%s' % (otu, ','.join(presence))
if not save_dir:
pylab.show()
else:
if real_abundance:
pylab.savefig(os.path.join(save_dir, rank + "_" + helper_functions.get_fs_compatible_name(otu) + '_real_abundance' + '.png'), transparent = is_transparent)
open(os.path.join(save_dir, rank + "_" + helper_functions.get_fs_compatible_name(otu) + '_real_abundance.txt'), 'w').write(txt_output)
else:
pylab.savefig(os.path.join(save_dir, rank + "_" + helper_functions.get_fs_compatible_name(otu) + '.png'), transparent = is_transparent)
open(os.path.join(save_dir, rank + "_" + helper_functions.get_fs_compatible_name(otu) + '.txt'), 'w').write(txt_output)
# clean memory
try:
fig.clf()
except:
pass
pylab.close('all')
def generate_for_sample_map(samples_dict, sample_map_file_path, save_dir = None, type = None, method='simpsons'):
taxonomic_level = const.ranks[type][-1]
sample_groups, group_colors = helper_functions.get_groups_colors_from_sample_map_file(sample_map_file_path)
plot_dict = {}
for group in sample_groups:
plot_dict[group] = []
for sample in sample_groups[group]:
if method == 'simpsons':
plot_dict[group].append(get_simpsons_diversity_index(samples_dict[sample][taxonomic_level]))
__title = "Simpson's Diversity Index"
if method == 'shannons':
plot_dict[group].append(get_shannons_diversity_index(samples_dict[sample][taxonomic_level]))
__title = "Shannon Diversity Index"
max_val = max([max(l) for l in plot_dict.values()])
max_val = max_val + max_val * 10 / 100
fig = pylab.figure(figsize=(3.5, 6.5))
pylab.rcParams['axes.titlesize'] = 12.0
pylab.rcParams['font.size'] = 8.0
pylab.rcParams.update({'axes.linewidth' : 0, 'axes.axisbelow': False})
pylab.rc('grid', color='0.50', linestyle='-', linewidth=0.1)
pylab.grid(True)
pylab.title(__title)
keys = helper_functions.sorted_copy(plot_dict.keys())
for key in keys:
i = keys.index(key)
# scattering the samples in X axis, so it would be easier to see them when there are a bunch of them
# at the same spot. instead of this, [i] * len(plot_dict[key]) could be used to plot them.
y_positions = [((1 - (r.gauss(100, 3) /100)) + i) for x in range(0, len(plot_dict[key]))]
pylab.plot(y_positions, plot_dict[key], 'o', color = group_colors[key], ms = 10, mew = 0.6, alpha = .5)
b = pylab.boxplot(plot_dict[key], positions=[i + 0.35], sym=',', widths=0.2)
pylab.setp(b['medians'], color=group_colors[key])
pylab.setp(b['whiskers'], color='black', alpha=0.3)
pylab.setp(b['boxes'], color='black', alpha=0.3)
pylab.setp(b['fliers'], color='black', alpha=0.3)
pylab.setp(b['caps'], color='black', alpha=0.3)
pylab.ylim(ymin=-max_val * 10 / 100, ymax=max_val)
pylab.xlim(xmin=-0.75, xmax=len(plot_dict) - 0.15)
pylab.xticks(pylab.arange(len(plot_dict)), keys, rotation=90)
if not save_dir:
pylab.show()
else:
pylab.savefig(os.path.join(save_dir, method + ".png"))
# clean memory
try:
fig.clf()
except:
pass
pylab.close('all')
