tests/conftest.py

"""Shared test fixtures for the Pigeon Pea Pangenome Atlas."""

import os
import sys
import pytest
import numpy as np
import pandas as pd
from pathlib import Path

# Ensure project root is in path
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))

from src.state import AppState


@pytest.fixture
def synthetic_pav():
    """20 genes x 10 lines, random 0/1."""
    np.random.seed(42)
    genes = [f"g{i:05d}" for i in range(20)]
    lines = [f"Line_{i}_India" for i in range(10)]
    data = np.random.randint(0, 2, size=(20, 10))
    return pd.DataFrame(data, index=genes, columns=lines)


@pytest.fixture
def synthetic_gff():
    """20 genes on 3 contigs."""
    records = []
    for i in range(20):
        contig = f"contig_{i % 3}"
        start = i * 1000
        end = start + 500
        records.append({
            "gene_id": f"g{i:05d}",
            "contig_id": contig,
            "start": start,
            "end": end,
            "strand": "+" if i % 2 == 0 else "-",
        })
    return pd.DataFrame(records)


@pytest.fixture
def synthetic_protein():
    """20 genes with random lengths."""
    records = []
    for i in range(20):
        records.append({
            "gene_id": f"g{i:05d}",
            "protein_length": np.random.randint(50, 1000),
            "composition_summary": "L:9.0%, A:8.0%, G:7.0%, S:6.0%, V:5.0%",
        })
    return pd.DataFrame(records)


@pytest.fixture
def synthetic_contig_index():
    """3 contigs."""
    return {"contig_0": 50000, "contig_1": 80000, "contig_2": 30000}


@pytest.fixture
def empty_state():
    """Fresh AppState."""
    return AppState()


@pytest.fixture
def populated_state():
    """AppState with some selections."""
    state = AppState()
    state.selected_line = "Line_0_India"
    state.backpack_genes = ["g00001", "g00002"]
    state.achievements = {"Explorer"}
    return state


@pytest.fixture
def synthetic_data(synthetic_pav, synthetic_gff, synthetic_protein, synthetic_contig_index):
    """Complete synthetic data dict matching app DATA format."""
    from src.precompute import (
        compute_gene_frequency, compute_line_stats,
        compute_line_embedding, compute_similarity_topk,
        compute_hotspot_bins, compute_cluster_markers,
    )

    gene_freq = compute_gene_frequency(synthetic_pav)
    line_stats = compute_line_stats(synthetic_pav)

    # Simple embedding without UMAP (too small for meaningful UMAP)
    line_ids = list(synthetic_pav.columns)
    embedding = pd.DataFrame({
        "line_id": line_ids,
        "umap_x": np.random.randn(len(line_ids)),
        "umap_y": np.random.randn(len(line_ids)),
        "cluster_id": [i % 3 for i in range(len(line_ids))],
    })

    similarity = compute_similarity_topk(synthetic_pav, k=5)

    hotspots = compute_hotspot_bins(synthetic_gff, gene_freq, synthetic_contig_index)
    markers = compute_cluster_markers(synthetic_pav, embedding)

    return {
        "pav": synthetic_pav,
        "gene_freq": gene_freq,
        "line_stats": line_stats,
        "embedding": embedding,
        "similarity": similarity,
        "gff_index": synthetic_gff,
        "protein": synthetic_protein,
        "hotspots": hotspots,
        "markers": markers,
    }


@pytest.fixture
def precomputed_dir():
    """Path to precomputed directory (if exists)."""
    p = Path(__file__).resolve().parent.parent / "precomputed"
    if p.exists():
        return p
    return None