def test_from_file_error(self):
for test_path in self.fferror_test_paths:
with open(get_data_path(test_path), 'U') as f:
with npt.assert_raises(FileFormatError):
OrdinationResults.from_file(f)
for test_path in self.verror_test_paths:
with open(get_data_path(test_path), 'U') as f:
with npt.assert_raises(ValueError):
OrdinationResults.from_file(f)
def test_from_file_error(self):
for test_path in self.fferror_test_paths:
with open(get_data_path(test_path), 'U') as f:
with npt.assert_raises(FileFormatError):
OrdinationResults.from_file(f)
for test_path in self.verror_test_paths:
with open(get_data_path(test_path), 'U') as f:
with npt.assert_raises(ValueError):
OrdinationResults.from_file(f)
def test_from_file(self):
for exp_scores, test_path in zip(self.scores, self.test_paths):
for file_type in ('file like', 'file name'):
fname = get_data_path(test_path)
if file_type == 'file like':
with open(fname) as fh:
obs = OrdinationResults.from_file(fh)
elif file_type == 'file name':
obs = OrdinationResults.from_file(fname)
yield self.check_OrdinationResults_equal, obs, exp_scores
def test_from_file(self):
for exp_scores, test_path in zip(self.scores, self.test_paths):
for file_type in ('file like', 'file name'):
fname = get_data_path(test_path)
if file_type == 'file like':
with open(fname) as fh:
obs = OrdinationResults.from_file(fh)
elif file_type == 'file name':
obs = OrdinationResults.from_file(fname)
yield self.check_OrdinationResults_equal, obs, exp_scores
def body_site(coords, mapping_file):
"""Generates as many figures as samples in the coordinates file"""
o = OrdinationResults.from_file(coords)
# coordinates
c_df = pd.DataFrame(o.site, o.site_ids)
# mapping file
mf = pd.read_csv(mapping_file, '\t', converters=defaultdict(str),
index_col='#SampleID')
mf = mf.loc[o.site_ids]
color_hmp_fecal = sns.color_palette('Paired', 12)[10] # light brown
color_agp_fecal = sns.color_palette('Paired', 12)[11] # dark brown
color_hmp_oral = sns.color_palette('Paired', 12)[0] # light blue
color_agp_oral = sns.color_palette('Paired', 12)[1] # dark blue
color_hmp_skin = sns.color_palette('Paired', 12)[2] # light green
color_agp_skin = sns.color_palette('Paired', 12)[3] # dark green
grp_colors = {'AGP-FECAL': color_agp_fecal,
'AGP-ORAL': color_agp_oral,
'AGP-SKIN': color_agp_skin,
'HMP-FECAL': color_hmp_fecal,
'GG-FECAL': color_hmp_fecal,
'PGP-FECAL': color_hmp_fecal,
'HMP-ORAL': color_hmp_oral,
'PGP-ORAL': color_hmp_oral,
'HMP-SKIN': color_hmp_skin,
'PGP-SKIN': color_hmp_skin}
for sample in mf.index:
# plot categories as 50 slices with random zorder
for grp, color in grp_colors.iteritems():
sub_coords = c_df[mf.TITLE_BODY_SITE == grp].values
for i in np.array_split(sub_coords, 50):
plt.scatter(i[:, 0], i[:, 1], color=color,
edgecolor=np.asarray(color)*0.6, lw=LINE_WIDTH,
alpha=ALPHA, zorder=np.random.rand())
# plot participant's dot
plt.scatter(c_df.loc[sample][0], c_df.loc[sample][1],
color=grp_colors[mf.loc[sample]['TITLE_BODY_SITE']],
s=270, edgecolor='w', zorder=1)
plt.scatter(c_df.loc[sample][0], c_df.loc[sample][1],
color=grp_colors[mf.loc[sample]['TITLE_BODY_SITE']],
s=250, edgecolor=np.asarray(
grp_colors[mf.loc[sample]['TITLE_BODY_SITE']])*0.6,
zorder=2)
plt.axis('off')
my_dpi = 72
plt.savefig(sample+'.pdf', figsize=(1000/my_dpi, 1000/my_dpi),
dpi=my_dpi)
plt.close()
def gradient(coords, mapping_file, color):
"""Generates as many figures as samples in the coordinates file"""
o = OrdinationResults.from_file(coords)
# coordinates
c_df = pd.DataFrame(o.site, o.site_ids)
# mapping file
mf = pd.read_csv(mapping_file, '\t', converters=defaultdict(str),
index_col='#SampleID')
mf = mf.loc[o.site_ids]
mf[color] = mf[color].convert_objects(convert_numeric=True)
numeric = mf[~pd.isnull(mf[color])]
non_numeric = mf[pd.isnull(mf[color])]
color_array = plt.cm.RdBu(numeric[color]/max(numeric[color]))
for sample in mf.index:
# plot numeric metadata as colored gradient
ids = numeric.index
x, y = c_df.loc[ids][0], c_df.loc[ids][1]
plt.scatter(x, y, c=numeric[color], cmap=plt.get_cmap('RdBu'),
alpha=ALPHA, lw=LINE_WIDTH, edgecolor=color_array*0.6)
# plt.colorbar()
# plot non-numeric metadata as gray
ids = non_numeric.index
x, y = c_df.loc[ids][0], c_df.loc[ids][1]
plt.scatter(x, y, c='0.5', alpha=ALPHA, lw=LINE_WIDTH, edgecolor='0.3')
# plot individual's dot
try:
color_index = numeric.index.tolist().index(sample)
except ValueError:
color_index = None
if color_index is None:
_color = (0.5, 0.5, 0.5)
else:
_color = color_array[color_index]
plt.scatter(c_df.loc[sample][0], c_df.loc[sample][1],
color=_color, s=270, edgecolor='w')
plt.scatter(c_df.loc[sample][0], c_df.loc[sample][1],
color=_color, s=250, edgecolor=np.asarray(_color)*0.6)
plt.axis('off')
my_dpi = 72
plt.savefig(sample+'.pdf', figsize=(1000/my_dpi, 1000/my_dpi),
dpi=my_dpi)
plt.close()
def format_coords(coord_header, coords, eigvals, pct_var, headers=True):
"""formats coords given specified coords matrix etc."""
result = []
if (headers):
result.append('pc vector number\t' +
'\t'.join(map(str, range(1,
len(coords[0]) + 1))))
for name, row in zip(coord_header, coords):
result.append('\t'.join([name] + map(str, row)))
result.append('')
result.append('')
result.append('eigvals\t' + '\t'.join(map(str, eigvals)))
result.append('% variation explained\t' + '\t'.join(map(str, pct_var)))
else:
result = ['\t'.join(map(str, row)) for row in coords]
result.append('')
return '\n'.join(result)
if __name__ == "__main__":
old_file = argv[1]
new_file = argv[2]
with open(old_file, 'U') as infile:
with open(new_file, 'w') as outfile:
res = OrdinationResults.from_file(infile)
lines = format_coords(res.site_ids, res.site, res.eigvals,
res.proportion_explained)
outfile.write(lines)
def country(coords, mapping_file):
"""Generates as many figures as samples in the coordinates file"""
o = OrdinationResults.from_file(coords)
x, y = o.site[:, 0], o.site[:, 1]
# coordinates
c_df = pd.DataFrame(o.site, o.site_ids)
# mapping file
mf = pd.read_csv(mapping_file, '\t', converters=defaultdict(str),
index_col='#SampleID')
mf = mf.loc[o.site_ids]
color_Venezuela = sns.color_palette('Paired', 12)[10]
color_Malawi = sns.color_palette('Paired', 12)[1]
color_Western = sns.color_palette('Paired', 12)[4]
color_Highlight = sns.color_palette('Paired', 12)[5]
color_no_data = (0.5, 0.5, 0.5)
grp_colors = OrderedDict()
grp_colors['no_data'] = color_no_data
grp_colors['Australia'] = color_Western
grp_colors['Belgium'] = color_Western
grp_colors['Canada'] = color_Western
grp_colors['China'] = color_Western
grp_colors['Finland'] = color_Western
grp_colors['France'] = color_Western
grp_colors['Germany'] = color_Western
grp_colors['Great Britain'] = color_Western
grp_colors['Ireland'] = color_Western
grp_colors['Japan'] = color_Western
grp_colors['Netherlands'] = color_Western
grp_colors['New Zealand'] = color_Western
grp_colors['Norway'] = color_Western
grp_colors['Scotland'] = color_Western
grp_colors['Spain'] = color_Western
grp_colors['Switzerland'] = color_Western
grp_colors['Thailand'] = color_Western
grp_colors['United Arab Emirates'] = color_Western
grp_colors['United Kingdom'] = color_Western
grp_colors['United States of America'] = color_Western
grp_colors['Malawi'] = color_Malawi
grp_colors['Venezuela'] = color_Venezuela
for sample in mf.index:
# countour plot superimposed
sns.kdeplot(x, y, cmap='bone')
sns.set_context(rc={"lines.linewidth": 0.75})
# change particapant's country's color to color_Highlight unless
# country is Venezuela or Malawi
if (mf.loc[sample]['COUNTRY'] != 'Malawi') & (
mf.loc[sample]['COUNTRY'] != 'Venezuela'):
grp_colors[mf.loc[sample]['COUNTRY']] = color_Highlight
# plot each country except participant's according to colors above
for grp, color in grp_colors.iteritems():
if grp == mf.loc[sample]['COUNTRY']:
continue
sub_coords = c_df[mf.COUNTRY == grp]
plt.scatter(sub_coords[0], sub_coords[1], color=color,
edgecolor=np.asarray(color)*0.6, lw=LINE_WIDTH,
alpha=ALPHA)
# now plot participant's country
grp = mf.loc[sample]['COUNTRY']
color = grp_colors[grp]
sub_coords = c_df[mf.COUNTRY == grp]
plt.scatter(sub_coords[0], sub_coords[1], color=color,
edgecolor=np.asarray(color)*0.6, lw=LINE_WIDTH,
alpha=ALPHA)
# plot participant's dot
plt.scatter(c_df.loc[sample][0], c_df.loc[sample][1],
color=grp_colors[mf.loc[sample]['COUNTRY']],
s=270, edgecolor='w', zorder=1)
plt.scatter(c_df.loc[sample][0], c_df.loc[sample][1],
color=grp_colors[mf.loc[sample]['COUNTRY']],
s=250, edgecolor=np.asarray(grp_colors[mf.loc[sample]
['COUNTRY']])*0.6, zorder=2)
# reset particapant's country's color to color_Western unless country
# is Venezuela or Malawi
if (mf.loc[sample]['COUNTRY'] != 'Malawi') & (
mf.loc[sample]['COUNTRY'] != 'Venezuela'):
grp_colors[mf.loc[sample]['COUNTRY']] = color_Western
plt.axis('off')
my_dpi = 72
plt.savefig(sample+'.pdf', figsize=(1000/my_dpi, 1000/my_dpi),
dpi=my_dpi)
plt.close()