import json
import pathlib

TASK_CATEGORIES: dict[str, list[str]] = {
    "histone_marks": [
        "h2afz", "h3k27ac", "h3k27me3", "h3k36me3",
        "h3k4me1", "h3k4me2", "h3k4me3", "h3k9ac", "h3k9me3", "h4k20me1",
    ],
    "promoter": ["promoter_all", "promoter_tata", "promoter_no_tata"],
    "enhancer": ["enhancers", "enhancers_types"],
    "splice_site": ["splice_sites_all", "splice_sites_donors", "splice_sites_acceptors"],
    "variant_effect": [
        "variant_effect_pathogenic_clinvar", "variant_effect_pathogenic_omim", "variant_effect_causal_eqtl",
    ],
    "rna_expression": ["bulk_rna_expression"],
}

# Inverse map: task_name -> category label
TASK_TO_CATEGORY: dict[str, str] = {
    task: cat for cat, tasks in TASK_CATEGORIES.items() for task in tasks
}

# Mean sequence lengths in bp per task, populated by tools/compute_seq_lengths.py
_SEQ_LEN_PATH = pathlib.Path(__file__).parent.parent / "tools" / "task_seq_lengths.json"
TASK_SEQ_LENGTHS: dict[str, int] = (
    json.loads(_SEQ_LEN_PATH.read_text()) if _SEQ_LEN_PATH.exists() else {}
)

CLASSIFICATION_METRICS: dict[str, str] = {
    "mcc_test": "MCC",
    "accuracy_test": "Accuracy",
    "weighted_f1_test": "Weighted F1",
    "macro_f1_test": "Macro F1",
    "auprc_test": "AUPRC",
}

CATEGORY_DISPLAY_NAMES: dict[str, str] = {
    "histone_marks": "Histone Marks",
    "promoter": "Promoter",
    "enhancer": "Enhancer",
    "splice_site": "Splice Site",
    "variant_effect": "Variant Effect",
    "rna_expression": "RNA Expression",
    "other": "Other",
}

# One color per task category — pastel, full-opacity friendly, distinct from _MODEL_PALETTE
CATEGORY_COLORS: dict[str, str] = {
    "histone_marks":  "#8EB4E8",
    "promoter":       "#F5956C",
    "enhancer":       "#60C4A8",
    "splice_site":    "#5AC8D8",
    "variant_effect": "#C49AE0",
    "rna_expression": "#F075A0",
    "other":          "#BCC4CC",
}