import glob
import pandas as pd
import os

def main():
    path = "./stundenwerte/*.csv"    
    files = glob.glob(path)
    dfs = []
    print("Working", end="", flush=True)
    for file in files:
        df_temp= pd.read_csv(file,low_memory=False)
        df_temp["year"] = os.path.basename(file).split("_")[2].split(".")[0]
        dfs.append(df_temp.astype({"year":int}))
        print(".", end="", flush=True)

    max_df = pd.concat(dfs, ignore_index=True)

    # Mannheim subset
    df_ma = max_df[max_df["domain_name"] == "Stadt Mannheim"]
    df_ma.to_csv("../data/processed/hourly_bikes_mannheim.csv", index=False)
        

if __name__ == "__main__":
    main()