def knn_bootstrap(emb_df, num_bootstrap=2, seed=SEED, percent_norm=False,
factor_analys=False):
"""Generate bootstrap statistics.
Args:
emb_df (pandas dataframe): dataframe to use (includes controls)
num_bootstrap (int): number of bootstrap reps
seed (int): which seed value to use for bootstrapping
percent_norm (bool): whether to apply percentile normalization
factor_analys (bool): whether to apply factor analysis
Returns:
stats_dict (dict): dictionary containing mean and
standard deviation information for each overlapping
category and value of k.
"""
boot_knns = []
boot_clustering_scores = []
np.random.seed(seed=seed)
for _ in range(num_bootstrap):
boot_emb = transform.get_bootstrap_sample(emb_df)
boot_post_proc = apply_post_processing(boot_emb,
percent_norm=percent_norm,
factor_analys=factor_analys)
boot_means = transform.drop_unevaluated_comp(boot_post_proc).groupby(level=[
metadata.MOA, metadata.COMPOUND,
metadata.CONCENTRATION, metadata.BATCH,
metadata.TREATMENT_GROUP]).mean()
scores = get_scores_from_means(boot_means, report_confusion_matrix=False)
boot_knns.append(scores["knn"])
boot_clustering_scores.append(scores["clustering_score"])
knn_return = {"knn_scores": elementwise_stats(boot_knns),
"clustering_scores": boot_clustering_scores}
return knn_return
def cross_val_knn_bootstrap(emb_df, contents, steps, list_of_comp_set,
num_bootstrap=2, seed=SEED,
percent_norm=False,
factor_analys=False):
"""Generate bootstrap statistics.
Args:
emb_df (pandas dataframe): dataframe to use
contents (dict): Contents from Wasserstein training routine
steps (int): List of timesteps at which timestep to evaluate
list_of_comp_set (list): each element is a dict for cross-validation.
num_bootstrap (int): number of bootstrap reps
seed (int): which seed value to use for bootstrapping
percent_norm (bool): whether to apply percentile normalization
factor_analys (bool): whether to apply factor analysis
Returns:
cross_validated_scores (list): list of cross-validated knn scores for each
bootstrap sample.
"""
cross_validated_scores = []
n_comp = len(list_of_comp_set)
np.random.seed(seed=seed)
for _ in range(num_bootstrap):
boot_emb = transform.get_bootstrap_sample(emb_df)
cross_val = cross_val_train(boot_emb, contents, steps,
list_of_comp_set, n_comp,
report_confusion_matrix=False,
percent_norm=percent_norm,
factor_analys=factor_analys)
cross_validated_scores.append(cross_val)
return cross_validated_scores
def testGetBootstrapSampleRun(self):
bootstrap_data = transform.get_bootstrap_sample(self.data)
self.assertTupleEqual(self.data.shape, bootstrap_data.shape)