def make_PR_data(gs, confidences):
data = utils.melt_and_reindex_dataframe(
confidences, value_name=CONFIDENCE_COLUMN).reset_index()
data = data.join(utils.melt_and_reindex_dataframe(
gs, value_name=GOLD_STANDARD_COLUMN),
on=[TARGET_COLUMN, REGULATOR_COLUMN],
how='outer')
return data
def process_network(metric, priors, confidence_threshold=0, beta_threshold=None, extra_columns=None):
"""
Process rank-summed results into a network data frame
:param metric: RankSummingMetric
The rank-sum object with the math in it
:param priors: pd.DataFrame [G x K]
Prior data
:param confidence_threshold: numeric
The minimum confidence score needed to write a network edge
:param beta_threshold: pd.DataFrame [G x K]
The thresholded betas to include in the network. If None, include everything.
:param extra_columns: dict(col_name: pd.DataFrame [G x K])
Any additional data to include, keyed by column name and indexable with row and column names
:return network_data: pd.DataFrame [(G*K) x 7+]
Network edge dataframe
"""
assert check.argument_type(metric, RankSummingMetric)
assert check.argument_type(priors, pd.DataFrame, allow_none=True)
assert check.argument_type(beta_threshold, pd.DataFrame, allow_none=True)
assert check.argument_numeric(confidence_threshold, 0, 1)
# Get the combined confidences and subset for confidence threshold
network_data = metric.confidence_dataframe()
network_data = network_data.loc[network_data[CONFIDENCE_COLUMN] > confidence_threshold, :]
# If beta_threshold has been provided, melt and join it to the network data
# Then discard anything which isn't meeting the threshold
if beta_threshold is not None and False:
beta_data = utils.melt_and_reindex_dataframe(beta_threshold, BETA_THRESHOLD_COLUMN)
network_data = network_data.join(beta_data, on=[TARGET_COLUMN, REGULATOR_COLUMN])
network_data = network_data.loc[network_data[BETA_THRESHOLD_COLUMN] == 1, :]
del network_data[BETA_THRESHOLD_COLUMN]
if priors is not None:
prior_data = utils.melt_and_reindex_dataframe(priors, PRIOR_COLUMN)
network_data = network_data.join(prior_data, on=[TARGET_COLUMN, REGULATOR_COLUMN])
# Add any extra columns as needed
if extra_columns is not None:
for k in sorted(extra_columns.keys()):
extra_data = utils.melt_and_reindex_dataframe(extra_columns[k], k)
network_data = network_data.join(extra_data, on=[TARGET_COLUMN, REGULATOR_COLUMN])
# Make sure all missing values are NaN
network_data[pd.isnull(network_data)] = np.nan
return network_data
def __init__(self,
rankable_data,
gold_standard,
filter_method='keep_all_gold_standard'):
"""
Take rankable data and process it into confidence scores which are stored in this object
:param rankable_data: list(pd.DataFrame) [B x [G x K]]
A list of numeric dataframes (with identical axes)
:param gold_standard: pd.DataFrame [G x K]
A dataframe which corresponds to known, gold-standard data
:param filter_method: str
The method of aligning the
"""
# Get the filtering method
assert check.argument_enum(filter_method,
self.filter_method_lookup.keys())
self.filter_method = getattr(self,
self.filter_method_lookup[filter_method])
# Explicitly cast the gold standard data to a boolean array [0,1]
gold_standard = (gold_standard != 0).astype(int)
self.gold_standard = gold_standard
# Calculate confidences based on the ranked data
self.all_confidences = self.compute_combined_confidences(rankable_data)
# Convert the confidence data to long format
confidence_data = utils.melt_and_reindex_dataframe(
self.all_confidences,
CONFIDENCE_COLUMN,
idx_name=TARGET_COLUMN,
col_name=REGULATOR_COLUMN)
# Attach the gold standard
confidence_data = self.attach_gs_to_confidences(
confidence_data, gold_standard)
# Sort by confidence (descending) and reset the index
self.confidence_data = confidence_data.sort_values(
by=CONFIDENCE_COLUMN, ascending=False, na_position='last')
self.confidence_data.reset_index(inplace=True)
# Filter the gold standard and confidences down to a format that can be directly compared
utils.Debug.vprint("GS: {gs} edges, Confidences: {conf} edges".format(
gs=gold_standard.shape[0], conf=self.confidence_data.shape[0]),
level=0)
self.filtered_data = self.filter_method(GOLD_STANDARD_COLUMN,
CONFIDENCE_COLUMN,
self.confidence_data)
utils.Debug.vprint("Filtered data to {e} edges".format(
e=self.filtered_data.shape[0], level=0))
def attach_gs_to_confidences(confidence_data, gold_standard):
"""
Outer join the gold standard into the confidence data
:param confidence_data: pd.DataFrame [G*K x n]
:param gold_standard: pd.DataFrame [G x K]
:return:
"""
gold_standard = utils.melt_and_reindex_dataframe(
gold_standard,
GOLD_STANDARD_COLUMN,
idx_name=TARGET_COLUMN,
col_name=REGULATOR_COLUMN)
return confidence_data.join(gold_standard,
how='outer',
on=[TARGET_COLUMN, REGULATOR_COLUMN])
