mm/citybert
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

drop pena

Browse Source
This commit is contained in:
Michael Pilosov 2026-05-25 22:09:57 +00:00
parent 8af279771a
commit 40967a303c
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
prepare_training_data.py
View File

@ -3,6 +3,7 @@ import argparse
import pandas as pd import pandas as pd
INPUT_COLUMNS = ["intersection", "text_on_sign_exact", "latitude", "longitude"] INPUT_COLUMNS = ["intersection", "text_on_sign_exact", "latitude", "longitude"]
EXCLUDED_INTERSECTIONS = {"56th-pena"}
def parse_args(): def parse_args():
@ -57,6 +58,7 @@ def load_raw_data(path):
data = data.dropna(subset=INPUT_COLUMNS) data = data.dropna(subset=INPUT_COLUMNS)
data["text_on_sign_exact"] = data["text_on_sign_exact"].astype(str).str.strip() data["text_on_sign_exact"] = data["text_on_sign_exact"].astype(str).str.strip()
data = data[data["text_on_sign_exact"] != ""] data = data[data["text_on_sign_exact"] != ""]
data = data[~data["intersection"].isin(EXCLUDED_INTERSECTIONS)]
return data return data