def plot(
ranks: str,
table: str,
sample_metadata: str,
feature_metadata: str,
output_dir: str,
extreme_feature_count: int,
assume_gnps_feature_metadata: bool,
debug: bool,
) -> None:
"""Generates a visualization of feature rankings and log-ratios.
The resulting visualization contains two plots. The first plot shows
how features are ranked, and the second plot shows the log-ratio
of "selected" features' abundances within samples.
The visualization is interactive, so which features are "selected" to
construct log-ratios -- as well as various other properties of the
visualization -- can be changed by the user.
"""
# inspired by https://stackoverflow.com/a/14098306/10730311
if debug:
logging.basicConfig(level=logging.DEBUG)
logging.debug("Starting the standalone Qurro script.")
loaded_biom = load_table(table)
logging.debug("Loaded BIOM table.")
df_sample_metadata = escape_columns(read_metadata_file(sample_metadata),
"sample metadata")
feature_ranks = read_rank_file(ranks)
df_feature_metadata = None
if feature_metadata is not None:
if assume_gnps_feature_metadata:
df_feature_metadata = read_gnps_feature_metadata_file(
feature_metadata, feature_ranks)
else:
df_feature_metadata = escape_columns(
read_metadata_file(feature_metadata), "feature metadata")
logging.debug("Read in metadata.")
process_and_generate(
feature_ranks,
df_sample_metadata,
loaded_biom,
output_dir,
df_feature_metadata,
extreme_feature_count,
)
print("Successfully generated a visualization in the folder {}.".format(
output_dir))
def create_q2_visualization(
output_dir,
feature_ranks,
rank_type,
table,
sample_metadata,
feature_metadata,
extreme_feature_count,
debug,
):
# Same thing as in the standalone version of Qurro -- only show debug
# messages if explicitly requested with --(p-)debug. As with there, this is
# inspired by https://stackoverflow.com/a/14098306/10730311.
if debug:
logging.basicConfig(level=logging.DEBUG)
logging.debug("Starting create_q2_visualization().")
df_feature_metadata = None
if feature_metadata is not None:
df_feature_metadata = escape_columns(feature_metadata.to_dataframe(),
"feature metadata")
df_sample_metadata = escape_columns(sample_metadata.to_dataframe(),
"sample metadata")
logging.debug("Converted metadata to DataFrames.")
feature_ranks = escape_columns(feature_ranks, "feature ranks")
index_path = process_and_generate(
feature_ranks,
rank_type,
df_sample_metadata,
table,
output_dir,
df_feature_metadata,
extreme_feature_count,
)
# render the visualization using q2templates.render().
# TODO: do we need to specify plot_name in the context in this way? I'm not
# sure where it is being used in the first place, honestly.
plot_name = output_dir.split("/")[-1]
q2templates.render(index_path,
output_dir,
context={"plot_name": plot_name})
def read_rank_file(file_loc):
"""Converts an input file of ranks to a DataFrame."""
if file_loc.endswith(".tsv"):
rank_df = differentials_to_df(file_loc)
else:
# ordination_to_df() will raise an appropriate error if it can't
# process this file.
rank_df = ordination_to_df(file_loc)
return escape_columns(rank_df, "feature ranks")
def read_rank_file(file_loc):
"""Converts an input file of ranks to a DataFrame.
Also returns a human-readable "rank type" -- either "Differential" or
"Feature Loading".
"""
if file_loc.endswith(".tsv"):
rank_df = differentials_to_df(file_loc)
rank_type = "Differential"
else:
# ordination_to_df() will raise an appropriate error if it can't
# process this file.
rank_df = ordination_to_df(file_loc)
rank_type = "Feature Loading"
return escape_columns(rank_df, "feature ranks"), rank_type