def persistLocal(self, dfName: str, df: DataFrame, persistType: str):
''' Persist the input Datafrmae locally (memory/disk/none) and runs `df.take(1)` to force persist.
'''
df.persist(
self.getSparkPersistType(persistTypStr=persistType.toUpperCase()))
if (self.__printcount == None):
row = df.take(1)
return df
def _truth_space_table_old(
df_labels_with_splink_scores: DataFrame,
spark: SparkSession,
threshold_actual: float = 0.5,
score_colname: str = None,
):
"""Create a table of the ROC space i.e. truth table statistics
for each discrimination threshold
Args:
df_labels_with_splink_scores (DataFrame): A dataframe of labels and associated splink scores
usually the output of the truth.labels_with_splink_scores function
threshold_actual (float, optional): Threshold to use in categorising clerical match
scores into match or no match. Defaults to 0.5.
score_colname (float, optional): Allows user to explicitly state the column name
in the Splink dataset containing the Splink score. If none will be inferred
Returns:
DataFrame: Table of 'truth space' i.e. truth categories for each threshold level
"""
# This is used repeatedly to generate the roc curve
df_labels_with_splink_scores.persist()
# We want percentiles of score to compute
score_colname = _get_score_colname(df_labels_with_splink_scores,
score_colname)
percentiles = [x / 100 for x in range(0, 101)]
values_distinct = df_labels_with_splink_scores.select(
score_colname).distinct()
thresholds = values_distinct.stat.approxQuantile(score_colname,
percentiles, 0.0)
thresholds.append(1.01)
thresholds = sorted(set(thresholds))
roc_dfs = []
for thres in thresholds:
df_e_t = df_e_with_truth_categories(df_labels_with_splink_scores,
thres, spark, threshold_actual,
score_colname)
df_roc_row = _summarise_truth_cats(df_e_t, spark)
roc_dfs.append(df_roc_row)
all_roc_df = reduce(DataFrame.unionAll, roc_dfs)
return all_roc_df
