def __init__(
self,
index_file: Path = None,
lineage_column: str = 'mlst',
verbose: bool = True
):
PoreLogger.__init__(
self, level=logging.INFO if verbose else logging.ERROR
)
if index_file:
self.index = pandas.read_csv(
index_file, sep='\t', header=0
)
if 'idx' not in self.index.columns:
self.logger.info('Adding Mash index column "idx" to genotype index')
self.index.index = [i for i in range(
len(self.index)
)]
self.index.index.name = 'idx'
else:
self.logger.info('Using column "idx" as Mash index column in genotype index')
self.index.index = self.index.set_index('idx')
else:
self.index = None
self.lineage_column = lineage_column
def __init__(
self,
fastx: Path,
sketch: Path,
prefix: str = 'sketchy',
outdir: Path = Path('sketchy_out'),
verbose: bool = False,
):
PoreLogger.__init__(
self,
level=logging.INFO if verbose else logging.ERROR,
name='Compute'
)
self.fastx = fastx
self.sketch = sketch
self.prefix = prefix
self.outdir = outdir
self.verbose = verbose
self.logger.info(f'Sketchy wrapper v{__version__}')
self.logger.info(f'Prefix: {prefix}')
self.logger.info(f'Fastq file: {fastx.absolute()}')
self.logger.info(f'Output directory: {outdir.absolute()}')
self.outdir.mkdir(exist_ok=True, parents=True)
def __init__(self, survey_directory: Path):
PoreLogger.__init__(self)
self.survey_data = SurveyData()
self.logger.info(f'Parse survey directory: {survey_directory}')
self.missing = '-'
self.survey_data.read(survey_directory)
def __init__(self):
PoreLogger.__init__(self)
self.inter = pandas.DataFrame() # MASH outputs, updated
self.interim = pandas.DataFrame() # MASH outputs, updated, with data
self.lineage = Counter() # Prime lineage counter
self.genotype = dict() # Genotype counters by lineage
self.susceptibility = dict() # Susceptibility counters by lineage
self.continuous = list()
self.start_time_regex = r'start_time=(.*)Z'
def __init__(
self,
sssh: Path,
index: Path,
key: Path,
stable: int = None,
ssh: Path = None,
verbose: bool = False
):
PoreLogger.__init__(self, name="Evaluate")
if verbose:
self.logger.setLevel(level=logging.INFO)
self.top_feature_values = 5
self.read_limit = 1000
self.preference_threshold = 0.6
self.na_color = 'darkgray'
self.stable = stable
self.logger.info(f"Loading data for evaluations from Sketchy Rust")
self.logger.info(f"Ranked sum of shared hashes: {sssh}")
self.logger.info(f"Sum of shared hashes: {ssh}")
self.logger.info(f"Genotype feature index: {index}")
self.logger.info(f"Genotype feature key: {key}")
self.feature_key = self.read_feature_key(file=key) # key to headers and categories
self.feature_index, self.feature_data = self.read_feature_index(file=index)
self.ssh = self.read_ssh(file=ssh)
self.sssh = self.read_sssh(file=sssh)
self.features = self.feature_index.columns.tolist()
if self.ssh is not None:
# Merge ssh and feature index for heatmap
self.ssh_features = self.ssh \
.join(self.feature_data, how='inner') \
.sort_values(['read', 'rank'])
self.reads = len(
self.ssh_features['read'].unique()
)
self.ranks = len(
self.ssh_features['rank'].unique()
)
def __init__(self):
PoreLogger.__init__(self)
self.data: pandas.DataFrame = pandas.DataFrame(None)
def __init__(self):
PoreLogger.__init__(self)
self.watcher = None # active watcher