def tabulate(output_dir: str,
input: qiime2.Metadata,
page_size: int = 100) -> None:
if page_size < 1:
raise ValueError('Cannot render less than one record per page.')
df = input.to_dataframe()
df_columns = pd.MultiIndex.from_tuples([(n, t.type)
for n, t in input.columns.items()],
names=['column header', 'type'])
df.columns = df_columns
df.reset_index(inplace=True)
table = df.to_json(orient='split')
index = os.path.join(TEMPLATES, 'tabulate', 'index.html')
q2templates.render(index,
output_dir,
context={
'table': table,
'page_size': page_size
})
input.save(os.path.join(output_dir, 'metadata.tsv'))
js = os.path.join(TEMPLATES, 'tabulate', 'datatables.min.js')
os.mkdir(os.path.join(output_dir, 'js'))
shutil.copy(js, os.path.join(output_dir, 'js', 'datatables.min.js'))
css = os.path.join(TEMPLATES, 'tabulate', 'datatables.min.css')
os.mkdir(os.path.join(output_dir, 'css'))
shutil.copy(css, os.path.join(output_dir, 'css', 'datatables.min.css'))
def differentialtest(table: biom.Table, metadata: qiime2.Metadata,
variable: str,
taxonomy: TSVTaxonomyFormat) -> pd.DataFrame:
if table.is_empty():
raise ValueError("The provided table object is empty")
## run the R script on the file
with tempfile.TemporaryDirectory() as temp_dir_name:
## write the biom table to file
input_table = os.path.join(temp_dir_name, 'table.tsv')
input_metadata = os.path.join(temp_dir_name, 'metadata.tsv')
with open(input_table, 'w') as fh:
fh.write(table.to_tsv())
metadata.save(input_metadata)
output = os.path.join(temp_dir_name, 'data.tsv')
cmd = [
'differentialtest.R', input_table, input_metadata,
str(taxonomy),
str(variable),
str(output)
]
run_commands([cmd])
data = pd.read_csv(output, sep='\t')
data.index.name = 'Feature ID'
return data
class TestResourceManagerUpdateMetadata(TempfileTestCase):
def setUp(self):
super().setUp()
self.resources = ResourceManager()
def test_resource_manager_update_metadata_correct(self):
self.metadata_fp = self.create_tempfile(suffix='.txt').name
self.test_metadata = pd.DataFrame({
'age_cat': ['30s', '40s', '50s', '30s'],
'num': [7.15, 9.04, 8.25, 7.24],
}, index=pd.Series(['a', 'b', 'c', 'd'], name='#SampleID')
)
self.q2_metadata = Metadata(self.test_metadata)
self.q2_metadata.save(self.metadata_fp)
self.resources.update({'metadata': self.metadata_fp})
self.assertCountEqual(['metadata'], self.resources.keys())
assert_frame_equal(self.resources['metadata'], self.test_metadata)
def test_resource_manager_update_metadata_does_not_exist(self):
self.metadata_fh2 = self.create_tempfile(suffix='.txt')
self.metadata_fh2.close()
self.metadata_fp_dne = self.metadata_fh2.name
with self.assertRaises(MetadataFileError):
self.resources.update({'metadata': self.metadata_fp_dne})
def test_resource_manager_update_metadata_non_string_dict(self):
with self.assertRaisesRegex(MetadataFileError, r'\{(.*)\}'):
self.resources.update({'metadata': {'put': 'some',
'other': 'type'}})
def adonis(output_dir: str,
distance_matrix: skbio.DistanceMatrix,
metadata: qiime2.Metadata,
formula: str,
permutations: int = 999,
n_jobs: int = 1) -> None:
# Validate sample metadata is superset et cetera
metadata_ids = set(metadata.ids)
dm_ids = distance_matrix.ids
_validate_metadata_is_superset(metadata_ids, set(dm_ids))
# filter ids. ids must be in same order as dm
filtered_md = metadata.to_dataframe().reindex(dm_ids)
filtered_md.index.name = 'sample-id'
metadata = qiime2.Metadata(filtered_md)
# Validate formula
terms = ModelDesc.from_formula(formula)
for t in terms.rhs_termlist:
for i in t.factors:
column = metadata.get_column(i.name())
if column.has_missing_values():
raise ValueError(
'adonis requires metadata columns with no '
'NaN values (missing values in column `%s`.)' %
(column.name, ))
# Run adonis
results_fp = os.path.join(output_dir, 'adonis.tsv')
with tempfile.TemporaryDirectory() as temp_dir_name:
dm_fp = os.path.join(temp_dir_name, 'dm.tsv')
distance_matrix.write(dm_fp)
md_fp = os.path.join(temp_dir_name, 'md.tsv')
metadata.save(md_fp)
cmd = [
'run_adonis.R', dm_fp, md_fp, formula,
str(permutations),
str(n_jobs), results_fp
]
_run_command(cmd)
# Visualize results
results = pd.read_csv(results_fp, sep='\t')
results = q2templates.df_to_html(results)
index = os.path.join(TEMPLATES, 'adonis_assets', 'index.html')
q2templates.render(index, output_dir, context={'results': results})
def tabulate(output_dir: str,
input: qiime2.Metadata,
page_size: int = 100) -> None:
if page_size < 1:
raise ValueError('Cannot render less than one record per page.')
df = input.to_dataframe()
df_columns = pd.MultiIndex.from_tuples([(n, t.type)
for n, t in input.columns.items()],
names=['column header', 'type'])
df.columns = df_columns
df.reset_index(inplace=True)
# `force_ascii` ensures that unicode code points are emitted. `True` is the
# default setting for this parameter, but explicitly setting here in case
# of future pandas API changes.
table = df.to_json(orient='split', force_ascii=True)
# JSON spec doesn't allow single quotes in string values, at all. It does
# however allow unicode values.
table = table.replace("'", r'\u0027')
index = os.path.join(TEMPLATES, 'tabulate', 'index.html')
q2templates.render(index,
output_dir,
context={
'table': table,
'page_size': page_size
})
input.save(os.path.join(output_dir, 'metadata.tsv'))
js = os.path.join(TEMPLATES, 'tabulate', 'datatables.min.js')
os.mkdir(os.path.join(output_dir, 'js'))
shutil.copy(js, os.path.join(output_dir, 'js', 'datatables.min.js'))
css = os.path.join(TEMPLATES, 'tabulate', 'datatables.min.css')
os.mkdir(os.path.join(output_dir, 'css'))
shutil.copy(css, os.path.join(output_dir, 'css', 'datatables.min.css'))
def adonis(output_dir: str,
distance_matrix: skbio.DistanceMatrix,
metadata: qiime2.Metadata,
formula: str,
permutations: int = 999,
n_jobs: str = 1) -> None:
# Validate sample metadata is superset et cetera
metadata_ids = set(metadata.ids)
dm_ids = distance_matrix.ids
_validate_metadata_is_superset(metadata_ids, set(dm_ids))
# filter ids. ids must be in same order as dm
filtered_md = metadata.to_dataframe().reindex(dm_ids)
filtered_md.index.name = 'sample-id'
metadata = qiime2.Metadata(filtered_md)
# Validate formula
terms = ModelDesc.from_formula(formula)
for t in terms.rhs_termlist:
for i in t.factors:
metadata.get_column(i.name())
# Run adonis
results_fp = os.path.join(output_dir, 'adonis.tsv')
with tempfile.TemporaryDirectory() as temp_dir_name:
dm_fp = os.path.join(temp_dir_name, 'dm.tsv')
distance_matrix.write(dm_fp)
md_fp = os.path.join(temp_dir_name, 'md.tsv')
metadata.save(md_fp)
cmd = ['run_adonis.R', dm_fp, md_fp, formula, str(permutations),
str(n_jobs), results_fp]
_run_command(cmd)
# Visualize results
results = pd.read_csv(results_fp, sep='\t')
results = q2templates.df_to_html(results)
index = os.path.join(TEMPLATES, 'adonis_assets', 'index.html')
q2templates.render(index, output_dir, context={'results': results})
def _2(obj: qiime2.Metadata) -> DADA2StatsFormat:
ff = DADA2StatsFormat()
obj.save(str(ff))
return ff
def _2(obj: qiime2.Metadata) -> SongbirdStatsFormat:
ff = SongbirdStatsFormat()
obj.save(str(ff))
return ff
def _14(obj: Metadata) -> ReconSummaryFormat:
ff = ReconSummaryFormat()
obj.save(str(ff))
return ff
index='subject-id')
exmp1_subject_data = exmp1_subject_data.join(get_sheet_as_df(
spreadsheet_id, 'exmp1-weekly-steps', index='subject-id'),
on='subject-id')
exmp1_subject_data = exmp1_subject_data.join(get_sheet_as_df(
spreadsheet_id, 'exmp1-weekly-nmvpa', index='subject-id'),
on='subject-id')
# extend with exmp2 subject data, which has no overlapping subject-ids and
# some of the same columns
exmp2_subject_data = get_sheet_as_df(spreadsheet_id,
'exmp2-subject-data',
index='subject-id')
subject_data = pd.concat([exmp1_subject_data, exmp2_subject_data],
sort=False)
sample_metadata = get_sheet_as_df(spreadsheet_id,
'combined-minimal',
index='sample-id')
subject_data_indexed_by_sample_id = subject_data.loc[
sample_metadata['subject-id']].set_index(sample_metadata.index)
sample_metadata = sample_metadata.join(subject_data_indexed_by_sample_id,
on='sample-id',
lsuffix='',
rsuffix='_drop_me')
sample_metadata = sample_metadata.replace(r'^\s*$', np.nan, regex=True)
sample_metadata = Metadata(sample_metadata)
sample_metadata.save('sample-metadata.tsv')
tabulate(sample_metadata).visualization.save('sample-metadata.qzv')
def _4(obj: qiime2.Metadata) -> MMvecStatsFormat:
ff = MMvecStatsFormat()
obj.save(str(ff))
return ff
def _2(obj: qiime2.Metadata) -> LogRatiosFormat:
ff = LogRatiosFormat()
obj.save(str(ff))
return ff
