def get_outliers_per_gene(data, gene, method="mad", cutoff=2):
result = None
if method == "mad":
result = out.mad_outliers(data, gene, cutoff)
elif method == "kmeans":
result = out.cluster_outliers(data, gene, cutoff)
return result
def stream_detect_outliers_in_data(data, method, min_dist, max_samples, mining_id):
# if exists -> get from db
processing_result = None
store_path = APP_CONFIG["application_files_location"] + APP_CONFIG["application_store_name"]
data = dr.get_data_frame_from_hdf(data, store_path)
# For demo purposes (cleaning)
data = data[-(data.sum(1) <= 5)]
if method == "kmeans_outliers":
return om.cluster_outliers(data, data.index, max_samples=max_samples, min_dist=min_dist, mining_id=mining_id)
if method == "mad":
return om.mad_outliers(data, data.index, max_samples)
