import marimo

__generated_with = "0.18.3"
app = marimo.App(width="medium")


@app.cell
def _():
    import marimo as mo
    import pandas as pd
    from pathlib import Path

    INPUT_DIR = Path("./data/processing/03_sentiment_analysis")
    WORKING_DIR = Path('./data/processing/04_sentiment_aggregation')

    if not WORKING_DIR.exists():
        WORKING_DIR.mkdir(parents=True)
    return INPUT_DIR, mo, pd


@app.cell(hide_code=True)
def _(mo):
    mo.md(r"""
    # Voices
    """)
    return


@app.cell
def _(INPUT_DIR, mo):
    voice_csv_files = list(INPUT_DIR.glob("*voice*.csv"))
    file_options = {f.stem: str(f) for f in voice_csv_files}

    voice_multiselect = mo.ui.multiselect(options=file_options, label="Select Voice CSV Files for Aggregation")
    voice_multiselect
    return (voice_multiselect,)


@app.cell
def _(mo, voice_multiselect):
    mo.hstack([voice_multiselect, mo.md(f"Has value: {voice_multiselect.value}")])
    return


@app.cell
def _(pd, voice_multiselect):
    # Load all voice CSV files and aggregate them so that each row-column pair is summed
    KEY_COL = "_context"

    def _read_voice_csv(path: str) -> pd.DataFrame:
        df = pd.read_csv(path).set_index(KEY_COL)
        df = df.apply(pd.to_numeric, errors="coerce")
        return df

    def aggregate_voice_data(files: list[str]) -> pd.DataFrame:
        if not files:
            return pd.DataFrame()

        master = _read_voice_csv(files[0])
        for path in files[1:]:
            master = master.add(_read_voice_csv(path), fill_value=0)

        return master.reset_index()

    master_df = aggregate_voice_data(voice_multiselect.value)
    master_df
    return


@app.cell(hide_code=True)
def _(mo):
    mo.md(r"""
    # Characters
    """)
    return


@app.cell
def _(INPUT_DIR):
    char_csv_files = list(INPUT_DIR.glob("*character*.csv"))
    char_csv_files
    return


if __name__ == "__main__":
    app.run()