def test_calculatePrecision_OneReportWithThreeRowsTwoPartiallyCorrectOneBelowThreshold(
self):
columns = [
"sample", "query_probe_header", "ref_probe_header",
"classification"
]
df = pd.DataFrame(
data=[
create_precision_report_row(0.4, gt_conf=100),
create_precision_report_row(0.8, gt_conf=20),
create_precision_report_row(0.3, gt_conf=100),
],
columns=columns,
)
report = PrecisionReport([df])
calculator = PrecisionCalculator(report)
confidence_threshold = 80
actual = calculator._calculate_precision_for_a_given_confidence(
confidence_threshold)
assert actual.precision == 0.7 / 2.0
assert actual.true_positives == 0.7
assert actual.total == 2.0
def test_calculatePrecision_NoReportsRaisesEmptyReportError(self):
columns = [
"sample", "query_probe_header", "ref_probe_header",
"classification"
]
df = pd.DataFrame(columns=columns)
report = PrecisionReport([df])
calculator = PrecisionCalculator(report)
with pytest.raises(EmptyReportError):
calculator._calculate_precision_for_a_given_confidence()
def test_calculatePrecision_OneReportWithOneRowCompletelyCorrectBelowConfThreasholdRaisesEmptyReportError(
self):
columns = [
"sample", "query_probe_header", "ref_probe_header",
"classification"
]
df = pd.DataFrame(data=[create_precision_report_row(1.0, gt_conf=10)],
columns=columns)
report = PrecisionReport([df])
calculator = PrecisionCalculator(report)
confidence_threshold = 60
with pytest.raises(EmptyReportError):
calculator._calculate_precision_for_a_given_confidence(
confidence_threshold)
def test_calculatePrecision_OneReportWithOneRowCompletelyIncorrectReturnsZero(
self):
columns = [
"sample", "query_probe_header", "ref_probe_header",
"classification"
]
df = pd.DataFrame(data=[create_precision_report_row(0.0, gt_conf=100)],
columns=columns)
report = PrecisionReport([df])
calculator = PrecisionCalculator(report)
actual = calculator._calculate_precision_for_a_given_confidence()
assert actual.precision == 0.0
assert actual.true_positives == 0.0
assert actual.total == 1.0
def test_calculatePrecision_OneReportWithOneRowCompletelyCorrectEqualConfThreasholdReturnsOne(
self):
columns = [
"sample", "query_probe_header", "ref_probe_header",
"classification"
]
df = pd.DataFrame(data=[create_precision_report_row(1.0, gt_conf=60)],
columns=columns)
report = PrecisionReport([df])
calculator = PrecisionCalculator(report)
confidence_threshold = 60
actual = calculator._calculate_precision_for_a_given_confidence(
confidence_threshold)
assert actual.precision == 1.0
assert actual.true_positives == 1.0
assert actual.total == 1.0
def test_calculatePrecision_OneReportWithTwoRowsPartiallyCorrect(self):
columns = [
"sample", "query_probe_header", "ref_probe_header",
"classification"
]
df = pd.DataFrame(
data=[
create_precision_report_row(0.5, gt_conf=100),
create_precision_report_row(0.7, gt_conf=100),
],
columns=columns,
)
report = PrecisionReport([df])
calculator = PrecisionCalculator(report)
actual = calculator._calculate_precision_for_a_given_confidence()
assert actual.precision == 1.2 / 2
assert actual.true_positives == 1.2
assert actual.total == 2.0
snakemake.input.precision_report_files_for_all_samples)
output = Path(snakemake.output.precision_file_for_all_samples)
gt_conf_percentiles = snakemake.params.gt_conf_percentiles
tool = snakemake.wildcards.tool
coverage = snakemake.wildcards.coverage
coverage_threshold = snakemake.wildcards.coverage_threshold
strand_bias_threshold = snakemake.wildcards.strand_bias_threshold
gaps_threshold = snakemake.wildcards.gaps_threshold
# API usage
logging.info(f"Loading report")
precision_report = PrecisionReport.from_files(
precision_report_files_for_all_samples)
logging.info(f"Creating calculator")
precision_calculator = PrecisionCalculator(precision_report)
logging.info(f"Calculating precision")
precision_df = precision_calculator.get_precision_report(gt_conf_percentiles)
metadata_df = pd.DataFrame(
data={
"tool": [tool] * len(precision_df),
"coverage": [coverage] * len(precision_df),
"coverage_threshold": [coverage_threshold] * len(precision_df),
"strand_bias_threshold": [strand_bias_threshold] * len(precision_df),
"gaps_threshold": [gaps_threshold] * len(precision_df),
})
output_df = pd.concat([precision_df, metadata_df], axis=1)
# output