"""
Essay-level dyslexic writing pattern profiling.

This module aggregates sentence-level dyslexic writing patterns
into dominance-based essay profiles.
"""

import pandas as pd


def assign_essay_ids(df: pd.DataFrame, essay_size: int = 5) -> pd.DataFrame:
    """
    Assign essay IDs to sentence-level data using fixed-size grouping.

    Parameters
    ----------
    df : pd.DataFrame
        DataFrame containing sentence-level patterns.
    essay_size : int
        Number of sentences per essay abstraction.

    Returns
    -------
    pd.DataFrame
        DataFrame with an added 'essay_id' column.
    """
    df = df.copy()
    df["essay_id"] = df.index // essay_size
    return df


def profile_essays(df: pd.DataFrame) -> pd.DataFrame:
    """
    Aggregate sentence-level patterns into essay-level dominance profiles.

    Parameters
    ----------
    df : pd.DataFrame
        DataFrame containing 'essay_id' and 'writing_pattern'.

    Returns
    -------
    pd.DataFrame
        Essay-level pattern profiles with dominance and confidence.
    """

    # Count patterns per essay
    pattern_counts = (
        df
        .groupby("essay_id")["writing_pattern"]
        .value_counts()
        .unstack(fill_value=0)
    )

    essay_summary = pattern_counts.copy()

    # Dominant pattern
    essay_summary["dominant_pattern"] = essay_summary.idxmax(axis=1)

    # Compute dominance metrics
    pattern_columns = pattern_counts.columns
    essay_summary["max_count"] = essay_summary[pattern_columns].max(axis=1)
    essay_summary["total_sentences"] = essay_summary[pattern_columns].sum(axis=1)

    essay_summary["confidence"] = (
        essay_summary["max_count"] / essay_summary["total_sentences"]
    )

    # Dominance strength categorization
    essay_summary["dominance_strength"] = essay_summary["confidence"].apply(
        dominance_strength
    )

    return essay_summary.reset_index()


def dominance_strength(confidence: float) -> str:
    """
    Categorize dominance strength based on confidence score.
    """
    if confidence >= 0.6:
        return "Strong"
    elif confidence >= 0.4:
        return "Moderate"
    else:
        return "Weak / Mixed"