src/data/loaders/safran.py

"""
ERA5 meteorological reanalysis data loader (SAFRAN alternative).
Single Responsibility: Load and parse ERA5 data with spatial interpolation.
"""
import pandas as pd
import xarray as xr
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from pathlib import Path
from typing import Optional, List
from .base import BaseDataLoader


class SAFRANLoader(BaseDataLoader):
    """
    Loads ERA5 reanalysis data (used as SAFRAN alternative).

    Handles actual ERA5 NetCDF structure:
    - Gridded at 0.25° resolution
    - Variables: t2m, tp, pev, ssrd, u10, v10, sf, ro
    - Interpolates to station points
    """

    # Variable mapping
    VAR_MAP = {
        't2m': 'temp_2m_K',
        'tp': 'precip_m',
        'pev': 'evap_m',
        'ssrd': 'solar_Jm2',
        'u10': 'wind_u_ms',
        'v10': 'wind_v_ms',
        'sf': 'snow_m',
        'ro': 'runoff_m'
    }

    def __init__(
        self,
        data_path: Path,
        station_coords: Optional[pd.DataFrame] = None,
        interp_method: str = "nearest"
    ):
        """
        Initialize ERA5 loader.

        Args:
            data_path: Path to datasets/safran directory
            station_coords: DataFrame with [station_code, lat, lon]
            interp_method: "nearest" or "linear"
        """
        super().__init__(data_path)
        self.station_coords = station_coords
        self.interp_method = interp_method

    def load(self) -> pd.DataFrame:
        """
        Load ERA5 data and interpolate to stations.

        Returns:
            DataFrame with [date, station_code, temp_2m_K, precip_m, ...]
        """
        nc_files = sorted(Path(self.data_path).glob("era5_*.nc"))

        if not nc_files:
            raise FileNotFoundError(f"No ERA5 files in {self.data_path}")

        all_dfs = []

        for nc_file in nc_files:
            df = self._load_and_interpolate(nc_file)
            all_dfs.append(df)

        combined = pd.concat(all_dfs, ignore_index=True)
        return combined.sort_values(['date', 'station_code']).reset_index(drop=True)

    def _load_and_interpolate(self, nc_file: Path) -> pd.DataFrame:
        """
        Load single NetCDF and interpolate to ALL stations in one
        vectorized xarray selection, not one .sel() + .to_dataframe()
        call per station.

        The original per-station loop does real work with meaningful
        per-call overhead (an index lookup, then a full DataFrame
        conversion) once per station PER FILE. At 27 stations across
        ~67 year-files (1960-2026) that's ~1,800 calls -- slow but
        tolerable. At the reach graph's ~2,900 nodes it's ~193,000
        individual calls, which is what was actually hanging, not a
        proportionally-worse runtime.

        Fix: xarray's vectorized ("pointwise") indexing -- when the
        latitude/longitude indexers are DataArrays sharing a common
        dimension name ("station" here), a single .sel() call looks up
        every point at once instead of one point per call, producing a
        result with a "station" dimension instead of separate
        latitude/longitude dimensions. This turns ~193,000 calls into
        ~67 (one per file).

        CAVEAT -- I could not actually run this against xarray/netCDF4
        in this environment (no network access to install them here),
        so this is reasoned from documented xarray API behavior, not
        verified execution like the rest of this project's fixes have
        been. Please test carefully, ideally against a small subset of
        the era5_*.nc files first, and confirm the output matches the
        old per-station-loop version's shape/values before trusting it
        for real training data.
        """
        ds = xr.open_dataset(nc_file)
        time_coord = 'valid_time' if 'valid_time' in ds.coords else 'time'

        station_lats = xr.DataArray(self.station_coords['lat'].values, dims='station')
        station_lons = xr.DataArray(self.station_coords['lon'].values, dims='station')
        station_codes = self.station_coords['station_code'].values

        point_ds = ds.sel(latitude=station_lats, longitude=station_lons, method=self.interp_method)
        # point_ds now has a 'station' dimension (length n_stations) instead
        # of separate latitude/longitude dimensions -- attach real station
        # codes as a coordinate so they survive the to_dataframe() below,
        # rather than staying as anonymous integer positions.
        point_ds = point_ds.assign_coords(station=station_codes)

        df = point_ds.to_dataframe().reset_index()
        df = df.rename(columns={time_coord: 'date', 'station': 'station_code', **self.VAR_MAP})

        keep_cols = ['date', 'station_code'] + [v for v in self.VAR_MAP.values() if v in df.columns]
        df = df[keep_cols].copy()
        df['date'] = pd.to_datetime(df['date']).dt.tz_localize(None)

        ds.close()
        return df

    @staticmethod
    def convert_units(df: pd.DataFrame) -> pd.DataFrame:
        """Convert ERA5 units to standard (°C, mm, W/m²)."""
        df = df.copy()

        # K → °C
        if 'temp_2m_K' in df.columns:
            df['temp_C'] = df['temp_2m_K'] - 273.15

        # m → mm
        for var in ['precip_m', 'evap_m', 'snow_m', 'runoff_m']:
            if var in df.columns:
                df[var.replace('_m', '_mm')] = df[var] * 1000

        # J/m² → W/m²
        if 'solar_Jm2' in df.columns:
            df['solar_Wm2'] = df['solar_Jm2'] / 86400

        # Wind speed
        if 'wind_u_ms' in df.columns and 'wind_v_ms' in df.columns:
            df['wind_speed_ms'] = np.sqrt(df['wind_u_ms']**2 + df['wind_v_ms']**2)

        return df

    def get_metadata(self) -> dict:
        """Get ERA5 metadata."""
        meta = super().get_metadata()
        meta.update({
            "data_type": "era5_reanalysis",
            "source": "Copernicus CDS",
            "resolution": "0.25 degrees",
            "interp_method": self.interp_method
        })
        return meta

    def plot_temperature(
        self,
        df: Optional[pd.DataFrame] = None,
        stations: Optional[List[str]] = None,
        figsize: tuple = (12, 5),
        save_path: Optional[Path] = None,
    ) -> plt.Axes:
        """
        Plot 2m air temperature time series, one line per station.

        Args:
            df: Optional pre-loaded DataFrame (raw or already converted). If not
                provided, data is loaded and unit-converted from disk.
            stations: Optional list of station codes to plot. Defaults to all.
            figsize: Figure size in inches.
            save_path: If provided, saves the figure to this path.

        Returns:
            The matplotlib Axes object.
        """
        if df is None:
            df = self.convert_units(self.load())
        elif "temp_C" not in df.columns and "temp_2m_K" in df.columns:
            df = self.convert_units(df)

        plot_df = df.dropna(subset=["temp_C"])
        if stations:
            plot_df = plot_df[plot_df["station_code"].isin(stations)]
        if plot_df.empty:
            raise ValueError("No temperature data available to plot")

        fig, ax = plt.subplots(figsize=figsize)
        for station_code, group in plot_df.groupby("station_code"):
            group = group.sort_values("date")
            ax.plot(group["date"], group["temp_C"], linewidth=1, label=station_code)

        ax.set_title("2m Air Temperature")
        ax.set_xlabel("Date")
        ax.set_ylabel("Temperature (°C)")
        ax.xaxis.set_major_locator(mdates.AutoDateLocator())
        ax.xaxis.set_major_formatter(mdates.ConciseDateFormatter(ax.xaxis.get_major_locator()))
        ax.legend(title="Station", fontsize=8)
        ax.grid(True, alpha=0.3)
        plt.tight_layout()

        if save_path:
            plt.savefig(save_path, dpi=150, bbox_inches="tight")
            print(f"Plot saved to {save_path}")

        return ax

    def plot_precipitation(
        self,
        df: Optional[pd.DataFrame] = None,
        stations: Optional[List[str]] = None,
        cumulative: bool = True,
        figsize: tuple = (12, 5),
        save_path: Optional[Path] = None,
    ) -> plt.Axes:
        """
        Plot precipitation, one line per station. Cumulative by default,
        which makes it easy to compare total rainfall received over the
        record and spot where stations diverge.

        Args:
            df: Optional pre-loaded DataFrame (raw or already converted). If not
                provided, data is loaded and unit-converted from disk.
            stations: Optional list of station codes to plot. Defaults to all.
            cumulative: If True, plot the running cumulative total (mm).
                        If False, plot the raw daily/timestep values.
            figsize: Figure size in inches.
            save_path: If provided, saves the figure to this path.

        Returns:
            The matplotlib Axes object.
        """
        if df is None:
            df = self.convert_units(self.load())
        elif "precip_mm" not in df.columns and "precip_m" in df.columns:
            df = self.convert_units(df)

        plot_df = df.dropna(subset=["precip_mm"])
        if stations:
            plot_df = plot_df[plot_df["station_code"].isin(stations)]
        if plot_df.empty:
            raise ValueError("No precipitation data available to plot")

        fig, ax = plt.subplots(figsize=figsize)
        for station_code, group in plot_df.groupby("station_code"):
            group = group.sort_values("date")
            values = group["precip_mm"].cumsum() if cumulative else group["precip_mm"]
            ax.plot(group["date"], values, linewidth=1, label=station_code)

        ax.set_title("Cumulative Precipitation" if cumulative else "Precipitation")
        ax.set_xlabel("Date")
        ax.set_ylabel("Cumulative precipitation (mm)" if cumulative else "Precipitation (mm)")
        ax.xaxis.set_major_locator(mdates.AutoDateLocator())
        ax.xaxis.set_major_formatter(mdates.ConciseDateFormatter(ax.xaxis.get_major_locator()))
        ax.legend(title="Station", fontsize=8)
        ax.grid(True, alpha=0.3)
        plt.tight_layout()

        if save_path:
            plt.savefig(save_path, dpi=150, bbox_inches="tight")
            print(f"Plot saved to {save_path}")

        return ax