writing_pattern_classifier/src/pipeline.py

"""
End-to-end pipeline for Sinhala dyslexic writing pattern analysis.

This module orchestrates sentence-level feature extraction,
pattern inference, and essay-level profiling.
"""

import pandas as pd

from .feature_extraction import extract_surface_features
from .pattern_rules import infer_pattern
from .essay_profile import assign_essay_ids, profile_essays


def run_pattern_analysis(
    df: pd.DataFrame,
    essay_size: int = 5
) -> tuple[pd.DataFrame, pd.DataFrame]:
    """
    Run the complete dyslexic writing pattern analysis pipeline.

    Parameters
    ----------
    df : pd.DataFrame
        Input DataFrame containing:
        - 'clean_sentence'
        - 'dyslexic_sentence'
    essay_size : int
        Number of sentences per essay abstraction.

    Returns
    -------
    tuple (sentence_df, essay_df)
        sentence_df : pd.DataFrame
            Sentence-level features and inferred patterns.
        essay_df : pd.DataFrame
            Essay-level dominance profiles.
    """

    df = df.copy()

    # --- Sentence-level feature extraction ---
    surface_features = df.apply(
        lambda row: extract_surface_features(
            row["clean_sentence"],
            row["dyslexic_sentence"]
        ),
        axis=1
    )

    feature_df = pd.concat(
        [df.reset_index(drop=True), surface_features.apply(pd.Series)],
        axis=1
    )

    # --- Sentence-level pattern inference ---
    feature_df["writing_pattern"] = feature_df.apply(
        lambda row: infer_pattern(row),
        axis=1
    )

    # --- Essay-level profiling ---
    feature_df = assign_essay_ids(feature_df, essay_size=essay_size)
    essay_df = profile_essays(feature_df)

    return feature_df, essay_df