From c102ac482e1727e4da8695d735bbf2f2629e75aa Mon Sep 17 00:00:00 2001 From: Daniel Rosel Date: Wed, 21 Jan 2026 11:11:49 +0100 Subject: [PATCH] chore: extra commenting --- experiments/procesing/contaminator.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/experiments/procesing/contaminator.py b/experiments/procesing/contaminator.py index 0a3651d..da44c3d 100644 --- a/experiments/procesing/contaminator.py +++ b/experiments/procesing/contaminator.py @@ -1,9 +1,9 @@ import pandas as pd import random -from sim.rl.behavior_loader import AgentBehaviorModel +from sim.rl.behavior_loader import AgentBehaviorModel # TODO: proper import this base_dir = "/home/velocitatem/Documents/Projects/PHANTOM/experiments" -human_dir, agent_dir = f"{base_dir}/collected_data/", f"{base_dir}/agents/collected_data/" +agent_dir = f"{base_dir}/agents/collected_data/" @@ -21,6 +21,7 @@ def contaminate_dataset(df : pd.DataFrame, on : str = "event_type", 'view': 'view_page' # TODO: define properly for the given dataset } + # think about replacing with freqdist method from library OG_event_distribution = df[on].value_counts(normalize=True).to_dict() # normalize to weights OG_event_distribution = {k: v / sum(OG_event_distribution.values()) for k, v in OG_event_distribution.items()}