Commit e0d62130 authored by Paulo Medeiros's avatar Paulo Medeiros
Browse files

More strict GLOSH outlier removal score threshold

parent b205df5b
Pipeline #10389 failed with stages
in 0 seconds
......@@ -254,7 +254,7 @@ def filter_outliers_glosh(df, outlier_scores):
"""
df["GLOSH"] = outlier_scores
threshold = min(0.25, df[df["cluster_label"] > -1]["GLOSH"].quantile(0.75))
threshold = min(0.05, df[df["cluster_label"] > -1]["GLOSH"].quantile(0.75))
outliers_index = (df["cluster_label"] > -1) & (df["GLOSH"] > threshold)
# Use "-2" as a "removed by refining methods" flag
df.at[outliers_index, "cluster_label"] = -2
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment