write_profiles_cin.py

import pandas as pd
import string
from pathlib import Path
import re

# Directory containing your files
home_dir = Path("E:/Work/SG_Model")
data_dir = Path("E:/Work/SG_Model/sol")
out_dir = Path("E:/Work/SG_Model/output")
# Match all .txt files
files = list(data_dir.glob("*.sol"))
ns_per_csv = 10

seasons = 12
daytypes = 2
hours = 24
lt = string.ascii_lowercase

techcodes_df = pd.read_csv('techcodes.csv')

n_ts = seasons * daytypes * hours
alpha_ts = []
alpha_ts_dict ={}
for i in range(0, seasons):
    for j in range(0, daytypes):
        for k in range(0, hours):
            t = f"{lt[i]}{lt[j]}{lt[k]}"
            alpha_ts.append(t)
            alpha_ts_dict[t] = {"season":i+1, "daytype":j+1, "hour":k+1}


# List of codes you want to extract
codes = list(techcodes_df['MessageCode'])

token_re = re.compile(r"^([A-Za-z.]+?)\.+([A-Za-z]+)(\d+)$")

rows = []
for fid, filepath in enumerate(files):
    print(f"processing {filepath}")
    with open(filepath, "r") as f:
        for line in f:
            parts = line.split()
            if len(parts) < 5:
                continue  # skip malformed lines

            token = parts[1]          # e.g. "s.ve......fal037"
            value_str = parts[3]      # e.g. "0.2397099" (first numeric column after BS/LL)

            m = token_re.match(token)
            if not m:
                continue  # doesn't match expected pattern

            code, v1, v2_str = m.groups()

            # Filter to codes we care about
            if codes and code not in codes:
                continue

            # Convert v2 to integer (strip leading zeros if any)
            v2 = int(v2_str)

            # Convert value to float
            value = float(value_str)
            #get second element of solution file name as scenario name
            rows.append((filepath.name.split('_')[1], code, v1, v2, alpha_ts_dict[v1]['season'], alpha_ts_dict[v1]['daytype'], alpha_ts_dict[v1]['hour'], value))

    if (fid+1) % ns_per_csv == 0:

        # Build DataFrame
        df = pd.DataFrame(rows, columns=["filename", "code", "v1", "year", "season","daytype","hour", "value"])

        #print(df)
        df.to_csv(f'{out_dir}/profiles_{(fid+1)//ns_per_csv}.csv')
        rows = []



aa =0
if aa == 1:

    cin_out = ("title: Battery\n"
               "unit: , 1.\n"
               "direction: hor\n"
               "@\n")
    for i in range(0, seasons):
        for j in range(0, daytypes):
            for k in range(0, hours):
                t = f"{lt[i]}{lt[j]}{lt[k]}"
                alpha_ts.append(t)
                for index, row in techcodes_df.iterrows():
                    cin_out += f"{str(i)}_{str(j)}_{str(k)}_{row['Technology']} =    {row['MessageCode']}....F.{t}: out\n"

    cin_out += ("@\n"
                "@\n"
                "@\n")

    with open("profile.cin", "w", encoding="utf-8") as file:
        file.write(cin_out)