import csv
from pathlib import Path

# infile = Path(r"c:\copilot codes\dataclean\Flow_Timedata2025_new_format.csv")
# outfile = Path(r"c:\copilot codes\dataclean\szh_flow_scada.csv")

infile = Path(r"c:\copilot codes\dataclean\Pressure_Timedata2025_new_format.csv")
outfile = Path(r"c:\copilot codes\dataclean\szh_pressure_scada.csv")

with infile.open("r", newline="", encoding="utf-8") as f_in:
    reader = csv.reader(f_in)
    rows = list(reader)

if not rows:
    print("input file is empty")
    raise SystemExit(1)

headers = rows[0]
# keep columns whose header does NOT contain 'SB_'
keep_indices = [i for i,h in enumerate(headers) if 'SB_' not in h]
removed = [h for i,h in enumerate(headers) if 'SB_' in h]

with outfile.open("w", newline="", encoding="utf-8") as f_out:
    writer = csv.writer(f_out)
    for row in rows:
        # ensure row has same length as headers
        if len(row) < len(headers):
            row = row + [''] * (len(headers) - len(row))
        newrow = [row[i] for i in keep_indices]
        writer.writerow(newrow)

print(f"Wrote {outfile} — removed {len(removed)} columns containing 'SB_'.")