def output_groups_by_species(min_group_size=2):
all_species = kv.get_species_collections()
groups_list = get_groups()
groups_list.sort(key=len, reverse=True)
groups_df = pd.DataFrame(data={n:0 for n in all_species}, index=[str(x+1) for x in range(0, len(groups_list))])
group_no = 0
for group in groups_list:
if len(group) >= min_group_size:
group_no += 1
species_in_group = [x[0] for x in group]
for species in species_in_group:
groups_df[species][group_no-1] = 1
groups_df.to_csv('groups_by_species.csv')
for pair in list_of_species_pairs:
if pair[0] == pairs[0][0]:
ax = fig.add_axes([1,ypos,1,1])
output_loc_hist(pair[0], pair[1], ax)
plot_url = py.plot_mpl(fig)
print plot_url
# plt.xlabel("Position")
# plt.ylabel("percent identity")
# plt.savefig('/Users/KBLaptop/Desktop/try.pdf')
if __name__ == '__main__':
kv.mongo_init('more_genomes')
os.chdir('/Users/KBLaptop/computation/kvasir/data/output/more_genomes/')
ls = kv.get_species_collections()
print ls
ls.remove('Arthrobacter_arilaitensis_Re117')
pairs = []
for pair in combinations(ls, 2):
pairs.append((pair[0], pair[1]))
plot_many(pairs)
# if os.path.isfile('{}_{}.pdf'.format(pair[0], pair[1])):
# continue
# try:
# output_loc_hist(pair[0], pair[1])
# except RuntimeError:
# print "Couldn't compare {} and {}".format(pair[0], pair[1])
