From 40967a303c9af21a8f50e61ffe0e673ed92f8c0c Mon Sep 17 00:00:00 2001 From: Michael Pilosov Date: Mon, 25 May 2026 22:09:57 +0000 Subject: [PATCH] drop pena --- prepare_training_data.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/prepare_training_data.py b/prepare_training_data.py index 6cbea77..cdabc8c 100644 --- a/prepare_training_data.py +++ b/prepare_training_data.py @@ -3,6 +3,7 @@ import argparse import pandas as pd INPUT_COLUMNS = ["intersection", "text_on_sign_exact", "latitude", "longitude"] +EXCLUDED_INTERSECTIONS = {"56th-pena"} def parse_args(): @@ -57,6 +58,7 @@ def load_raw_data(path): data = data.dropna(subset=INPUT_COLUMNS) data["text_on_sign_exact"] = data["text_on_sign_exact"].astype(str).str.strip() data = data[data["text_on_sign_exact"] != ""] + data = data[~data["intersection"].isin(EXCLUDED_INTERSECTIONS)] return data