backend/app/api/exports.py

import io
import json

import pandas as pd
from fastapi import APIRouter, Depends, HTTPException
from fastapi.responses import StreamingResponse
from sqlalchemy.orm import Session

from backend.app.db import get_db
from backend.app.repositories.dataset_repo import get_dataset
from backend.app.repositories.experiment_repo import get_experiment

router = APIRouter(tags=["exports"])


@router.get("/exports/{experiment_id}")
def export_experiment(experiment_id: str, db: Session = Depends(get_db)):
    experiment = get_experiment(db, experiment_id)
    if not experiment:
        raise HTTPException(status_code=404, detail="Experiment not found")

    dataset = get_dataset(db, experiment.dataset_id)
    if not dataset:
        raise HTTPException(status_code=404, detail="Dataset not found")

    if dataset.file_path.endswith(".csv"):
        df = pd.read_csv(dataset.file_path)
    else:
        df = pd.read_excel(dataset.file_path)

    summary = json.loads(experiment.summary_json) if experiment.summary_json else {}
    points = summary.get("points", [])
    export_df = df.copy()
    if points and len(points) == len(df):
        export_df["cluster_label"] = [p["cluster_label"] for p in points]
        export_df["pca_x"] = [p["x"] for p in points]
        export_df["pca_y"] = [p["y"] for p in points]

    metrics = json.loads(experiment.metrics_json) if experiment.metrics_json else {}
    for key, value in metrics.items():
        export_df[f"metric_{key}"] = value

    buffer = io.StringIO()
    export_df.to_csv(buffer, index=False)
    buffer.seek(0)

    return StreamingResponse(
        iter([buffer.getvalue()]),
        media_type="text/csv",
        headers={"Content-Disposition": f"attachment; filename={experiment_id}_export.csv"},
    )