import pandas as pd

VARIABLES_TO_TRANSLATE = {
    "Gebruikersnaam": "username",
    "Geslacht": "gender",
    "Geboortedatum": "date_of_birth",
}

filenames = snakemake.input["data"]

baseline_dfs = []

for fn in filenames:
    baseline_dfs.append(pd.read_csv(fn,
                                    parse_dates=["Geboortedatum"],
                                    infer_datetime_format=True,
                                    cache_dates=True,
                                    ))

baseline = (
    pd.concat(baseline_dfs, join="inner")
    .reset_index()
    .drop(columns="index")
)

baseline.rename(columns=VARIABLES_TO_TRANSLATE, copy=False, inplace=True)
now = pd.Timestamp("now")
baseline = baseline.assign(
    age=lambda x: (now - x.date_of_birth).dt.days / 365.25245,
)

baseline.to_csv(snakemake.output[0],
                index=False,
                encoding="utf-8",)