#!/usr/bin/env python3

import os
import re
import json
import argparse
import warnings
from typing import List, Optional, Tuple

import numpy as np
import pandas as pd

from sklearn.model_selection import train_test_split
from sklearn.decomposition import PCA
from sklearn.cluster import KMeans, DBSCAN, AgglomerativeClustering, MiniBatchKMeans
from sklearn.metrics import silhouette_score, calinski_harabasz_score, davies_bouldin_score
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import NearestNeighbors

import matplotlib.pyplot as plt
import seaborn as sns
import joblib

import tensorflow as tf
from keras.applications import MobileNetV2, EfficientNetB0
from keras.applications.mobilenet_v2 import preprocess_input as mobilenet_preprocess
from keras.applications.efficientnet import preprocess_input as efficientnet_preprocess
from keras import backend as K

os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
K.set_image_data_format("channels_last")

# -----------------------------
# Utils
# -----------------------------

def set_seed(seed: int = 42):
    np.random.seed(seed)
    tf.random.set_seed(seed)
    os.environ["PYTHONHASHSEED"] = str(seed)

def ensure_dir(path: str):
    os.makedirs(path, exist_ok=True)

def _read_csv_any(path: str) -> pd.DataFrame:
    for enc in ("utf-8", "utf-8-sig", "latin-1"):
        try:
            return pd.read_csv(path, encoding=enc)
        except UnicodeDecodeError:
            continue
    return pd.read_csv(path, encoding="utf-8", errors="replace")

def _normalize_col_name(name: str) -> str:
    if not isinstance(name, str):
        return ""
    s = name.strip().lower()
    print(f"Normalizing column name: '{name}' -> '{s}'")
    m = re.match(r"^(.*)_(a|b)$", s)
    print(f"  matched: {m}")
    if m:
        s = m.group(1)
    for ch in [" ", "_", "-", ".", "/"]:
        s = s.replace(ch, "")
    return s

def find_matching_cols(df: pd.DataFrame, aliases: List[str]) -> List[str]:
    tgt = {_normalize_col_name(a) for a in aliases}
    out = []
    for c in df.columns:
        if _normalize_col_name(c) in tgt:
            out.append(c)
    return out

def best_filename_from_row(row: pd.Series, img_ext: str = ".jpg") -> Optional[str]:
    for key in ["filename", "file_name", "image", "image_name", "New_Name_With_Date", "New_Name", "Nombre_Nuevo", "Old_Name"]:
        if key in row and pd.notna(row[key]) and str(row[key]).strip() != "":
            fname = str(row[key]).strip()
            if not os.path.splitext(fname)[1]:
                fname = fname + img_ext
            return fname
    for key in ["basename_final", "basename"]:
        if key in row and pd.notna(row[key]) and str(row[key]).strip() != "":
            return f"{row[key]}{img_ext}"
    return None

def attach_paths_single_csv(df: pd.DataFrame, images_dir: str, img_ext: str = ".jpg", search_subdirs: bool = False) -> pd.DataFrame:
    paths = []
    miss = 0
    for _, r in df.iterrows():
        fname = best_filename_from_row(r, img_ext)
        if not fname:
            paths.append((None, None))
            miss += 1
            continue
        p = os.path.join(images_dir, fname)
        if not os.path.exists(p) and search_subdirs:
            # buscar en subcarpetas
            found = None
            for root, _, files in os.walk(images_dir):
                if fname in files:
                    found = os.path.join(root, fname)
                    break
            p = found if found else p
        paths.append((fname, p if p and isinstance(p, str) and os.path.exists(p) else None))
        if paths[-1][1] is None:
            miss += 1
    if miss:
        warnings.warn(f"{miss} archivos listados no existen en disco. Serán ignorados.")
    out = df.copy()
    out["filename"] = [t[0] for t in paths]
    out["path"] = [t[1] for t in paths]
    out = out[pd.notna(out["path"])].reset_index(drop=True)
    return out

# -----------------------------
# Embeddings
# -----------------------------

def make_preprocess(backbone: str):
    return mobilenet_preprocess if backbone == "mobilenet" else efficientnet_preprocess

def make_backbone_model(img_size: int, backbone: str) -> tf.keras.Model:
    tf.keras.backend.clear_session()
    K.set_image_data_format("channels_last")
    input_shape = (img_size, img_size, 3)
    if backbone == "efficientnet":
        try:
            model = EfficientNetB0(include_top=False, weights="imagenet", input_shape=input_shape, pooling="avg")
        except Exception as e:
            warnings.warn(f"No se pudo cargar EfficientNetB0 con pesos ImageNet ({e}). Se usarán pesos aleatorios.")
            model = EfficientNetB0(include_top=False, weights=None, input_shape=input_shape, pooling="avg")
    else:
        model = MobileNetV2(include_top=False, weights="imagenet", input_shape=input_shape, pooling="avg")
    model.trainable = False
    return model

def build_dataset(paths: List[str], img_size: int, preprocess_fn, batch_size: int = 64) -> tf.data.Dataset:
    ds = tf.data.Dataset.from_tensor_slices(paths)
    def _load_tf(p):
        x = tf.io.read_file(p)
        x = tf.image.decode_jpeg(x, channels=3)
        x = tf.image.resize(x, [img_size, img_size], method="bilinear", antialias=True)
        x = tf.cast(x, tf.float32)
        x = preprocess_fn(x)
        return x
    return ds.map(_load_tf, num_parallel_calls=tf.data.AUTOTUNE).batch(batch_size).prefetch(tf.data.AUTOTUNE)

def compute_embeddings(model: tf.keras.Model, ds: tf.data.Dataset) -> np.ndarray:
    return model.predict(ds, verbose=1)

# -----------------------------
# Reduction + clustering
# -----------------------------

def fit_reduction(train_emb: np.ndarray, n_pca: int = 50):
    scaler = StandardScaler()
    Xs = scaler.fit_transform(train_emb)
    pca = PCA(n_components=min(n_pca, Xs.shape[1]))
    Z = pca.fit_transform(Xs)
    return scaler, pca, Z

def transform_reduction(emb: np.ndarray, scaler: StandardScaler, pca: PCA) -> np.ndarray:
    return pca.transform(scaler.transform(emb))

def _centers_from_labels(X: np.ndarray, y: np.ndarray) -> Optional[np.ndarray]:
    cs = []
    for c in sorted(set(y)):
        if c == -1:
            continue
        cs.append(X[y == c].mean(axis=0))
    return np.array(cs) if cs else None

def tune_dbscan(train_feats: np.ndarray,
                metric: str = "euclidean",
                min_samples_grid=(3, 5, 10),
                quantiles=(0.6, 0.7, 0.8, 0.9)) -> Tuple[Optional[DBSCAN], Optional[np.ndarray], Optional[np.ndarray]]:
    best = {"score": -np.inf, "model": None, "labels": None}
    for ms in min_samples_grid:
        k = max(2, min(ms, len(train_feats)-1))
        nbrs = NearestNeighbors(n_neighbors=k, metric=metric).fit(train_feats)
        dists, _ = nbrs.kneighbors(train_feats)
        kth = np.sort(dists[:, -1])
        for q in quantiles:
            eps = float(np.quantile(kth, q))
            m = DBSCAN(eps=eps, min_samples=ms, metric=metric, n_jobs=-1)
            y = m.fit_predict(train_feats)
            valid = y[y != -1]
            if len(np.unique(valid)) < 2:
                continue
            try:
                score = silhouette_score(train_feats[y != -1], y[y != -1])
            except Exception:
                score = -np.inf
            if score > best["score"]:
                best = {"score": score, "model": m, "labels": y}
    if best["model"] is None:
        return None, None, None
    return best["model"], best["labels"], _centers_from_labels(train_feats, best["labels"])

def fit_cluster_algo(kind: str,
                     n_clusters: int,
                     train_feats: np.ndarray,
                     fast_kmeans: bool = True,
                     dbscan_eps: float = 0.8,
                     dbscan_min_samples: int = 5,
                     dbscan_metric: str = "euclidean",
                     dbscan_auto: bool = False):
    if kind == "kmeans":
        m = MiniBatchKMeans(n_clusters=n_clusters, batch_size=2048, n_init=10, random_state=42) if fast_kmeans \
            else KMeans(n_clusters=n_clusters, n_init=10, random_state=42)
        y = m.fit_predict(train_feats)
        return m, y, getattr(m, "cluster_centers_", None)

    if kind == "dbscan":
        if dbscan_auto:
            m, y, centers = tune_dbscan(train_feats, metric=dbscan_metric)
            if m is None:
                warnings.warn("DBSCAN(auto) no encontró ≥2 clusters. Fallback a KMeans.")
                km = MiniBatchKMeans(n_clusters=max(n_clusters, 2), batch_size=2048, n_init=10, random_state=42)
                y = km.fit_predict(train_feats)
                return km, y, km.cluster_centers_
            print(f"DBSCAN(auto) seleccionado (metric={dbscan_metric}).")
            return m, y, centers
        m = DBSCAN(eps=dbscan_eps, min_samples=dbscan_min_samples, metric=dbscan_metric, n_jobs=-1)
        y = m.fit_predict(train_feats)
        uniq = set(y) - {-1}
        if len(uniq) < 2:
            warnings.warn(f"DBSCAN devolvió {len(uniq)} cluster(s) válido(s). Considera ajustar eps/min_samples/metric o usar --dbscan_auto.")
        return m, y, _centers_from_labels(train_feats, y)

    ag = AgglomerativeClustering(n_clusters=n_clusters)
    y = ag.fit_predict(train_feats)
    centers = _centers_from_labels(train_feats, y)
    return ag, y, centers

def assign_to_nearest_centroid(feats: np.ndarray, centers: Optional[np.ndarray]) -> np.ndarray:
    if centers is None or len(centers) == 0:
        return np.full((feats.shape[0],), -1, dtype=int)
    d = ((feats[:, None, :] - centers[None, :, :]) ** 2).sum(axis=2)
    return np.argmin(d, axis=1)

def internal_metrics(X: np.ndarray, y: np.ndarray) -> dict:
    m = y != -1
    if m.sum() > 1 and len(np.unique(y[m])) > 1:
        return {
            "silhouette": float(silhouette_score(X[m], y[m])),
            "calinski_harabasz": float(calinski_harabasz_score(X[m], y[m])),
            "davies_bouldin": float(davies_bouldin_score(X[m], y[m])),
        }
    return {"silhouette": None, "calinski_harabasz": None, "davies_bouldin": None}

# -----------------------------
# Plot
# -----------------------------

def plot_scatter_2d(X2d: np.ndarray, labels: np.ndarray, title: str, out_path: str):
    plt.figure(figsize=(8, 6))
    uniq = np.unique(labels)
    if len(uniq) <= 1:
        sns.scatterplot(x=X2d[:, 0], y=X2d[:, 1], s=12, linewidth=0, color="#1f77b4", legend=False)
    else:
        palette = sns.color_palette("tab20", n_colors=len(uniq))
        sns.scatterplot(x=X2d[:, 0], y=X2d[:, 1], hue=labels, palette=palette, s=12, linewidth=0, legend=False)
    plt.title(title)
    plt.tight_layout()
    plt.savefig(out_path, dpi=180)
    plt.close()

# -----------------------------
# Main
# -----------------------------

def parse_args():
    p = argparse.ArgumentParser(description="Unsupervised clustering for Carciofo (single CSV)")
    p.add_argument("--images_dir", default=r"C:\Users\sof12\Desktop\ML\Datasets\Carciofo\GBIF", help="Carpeta que contiene las imágenes")
    p.add_argument("--csv_path",   default=r"C:\Users\sof12\Desktop\ML\Datasets\Carciofo\GBIF\joined_metadata.csv")
    p.add_argument("--out_dir",    default=r"C:\Users\sof12\Desktop\ML\Datasets\Carciofo\GBIF\TrainingTEST_PCA_V1_C")

    p.add_argument("--img_ext", default=".jpg")
    p.add_argument("--img_size", type=int, default=224)
    p.add_argument("--batch_size", type=int, default=64)
    p.add_argument("--seed", type=int, default=42)
    p.add_argument("--sample", type=int, default=None)
    p.add_argument("--search_subdirs", action="store_true", help="Buscar archivos faltantes en subcarpetas")
    p.add_argument("--backbone", choices=["mobilenet", "efficientnet"], default="mobilenet")
    p.add_argument("--cluster", choices=["kmeans", "dbscan", "agglomerative"], default="kmeans")
    p.add_argument("--n_clusters", type=int, default=5)
    p.add_argument("--fast_kmeans", action="store_true")
    # DBSCAN
    p.add_argument("--dbscan_eps", type=float, default=0.8)
    p.add_argument("--dbscan_min_samples", type=int, default=5)
    p.add_argument("--dbscan_metric", choices=["euclidean", "cosine", "manhattan"], default="euclidean")
    p.add_argument("--dbscan_auto", action="store_true")
    return p.parse_args()

# ...existing code...
def main():
    args = parse_args()
    set_seed(args.seed)
    ensure_dir(args.out_dir)

    print("Loading CSV...")
    df = _read_csv_any(args.csv_path)

    print("Resolving filenames and verifying files on disk...")
    df = attach_paths_single_csv(df, args.images_dir, img_ext=args.img_ext, search_subdirs=args.search_subdirs)
    if len(df) == 0:
        print("No images found. Check images_dir and csv_path.")
        return

    # --- Solo 'fase' (Carciofo no usa 'fase V' / 'fase R') ---
    phase_cols = find_matching_cols(df, ["fase"])
    if phase_cols:
        ser_phase = None
        for c in phase_cols:
            ser_phase = df[c] if ser_phase is None else ser_phase.combine_first(df[c])
        df["fase"] = ser_phase
        print(f"Using column(s) for 'fase': {phase_cols}")
    else:
        warnings.warn("No se encontró columna 'fase' en el CSV. No se incluirá en el output.")
    # --- fin fase ---

    # Optional sampling
    if args.sample is not None and args.sample < len(df):
        df = df.sample(n=args.sample, random_state=args.seed).reset_index(drop=True)

    # Split indices
    print("Splitting train/val/test...")
    idx_all = np.arange(len(df))
    idx_train, idx_tmp = train_test_split(idx_all, test_size=0.30, random_state=args.seed, shuffle=True)
    idx_val, idx_test = train_test_split(idx_tmp, test_size=0.50, random_state=args.seed, shuffle=True)

    df_train = df.iloc[idx_train].reset_index(drop=True)
    df_val   = df.iloc[idx_val].reset_index(drop=True)
    df_test  = df.iloc[idx_test].reset_index(drop=True)

    # Embeddings in one pass
    print("Building embedding model...")
    preprocess_fn = make_preprocess(args.backbone)
    model = make_backbone_model(args.img_size, args.backbone)

    print("Computing embeddings (one pass)...")
    ds_all = build_dataset(df["path"].tolist(), args.img_size, preprocess_fn, args.batch_size)
    emb_all = compute_embeddings(model, ds_all)

    emb_train = emb_all[idx_train]
    emb_val   = emb_all[idx_val]
    emb_test  = emb_all[idx_test]

    # PCA reduction
    print("Fitting PCA reduction (50D for clustering, 2D for plots)...")
    scaler, pca50, train_50 = fit_reduction(emb_train, n_pca=50)
    val_50  = transform_reduction(emb_val, scaler, pca50)
    test_50 = transform_reduction(emb_test, scaler, pca50)

    pca2 = PCA(n_components=2).fit(scaler.transform(emb_train))
    train_2d = pca2.transform(scaler.transform(emb_train))
    val_2d   = pca2.transform(scaler.transform(emb_val))
    test_2d  = pca2.transform(scaler.transform(emb_test))

    # Clustering
    print(f"Clustering with {args.cluster}...")
    model_c, y_train, centers = fit_cluster_algo(
        args.cluster, args.n_clusters, train_50,
        fast_kmeans=args.fast_kmeans,
        dbscan_eps=args.dbscan_eps,
        dbscan_min_samples=args.dbscan_min_samples,
        dbscan_metric=args.dbscan_metric,
        dbscan_auto=args.dbscan_auto,
    )

    if args.cluster == "kmeans":
        y_val  = model_c.predict(val_50)
        y_test = model_c.predict(test_50)
    else:
        y_val  = assign_to_nearest_centroid(val_50, centers)
        y_test = assign_to_nearest_centroid(test_50, centers)

    # Metrics
    print("Computing internal metrics...")
    train_m = internal_metrics(train_50, y_train)
    val_m   = internal_metrics(val_50, y_val)
    test_m  = internal_metrics(test_50, y_test)

    # Save outputs (filename, fase, cluster, split)
    print("Saving outputs...")
    ensure_dir(args.out_dir)

    def pick_min(df_split: pd.DataFrame, y: np.ndarray, split: str) -> pd.DataFrame:
        cols = ["filename", "fase"]
        keep = [c for c in cols if c in df_split.columns]
        out = df_split[keep].copy()
        out["cluster"] = y
        out["split"] = split
        return out

    train_out = pick_min(df_train, y_train, "train")
    val_out   = pick_min(df_val,   y_val,   "val")
    test_out  = pick_min(df_test,  y_test,  "test")

    assignments = pd.concat([train_out, val_out, test_out], ignore_index=True)
    assignments.to_csv(os.path.join(args.out_dir, "assignments.csv"), index=False, encoding="utf-8")
    train_out.to_csv(os.path.join(args.out_dir, "train_assignments.csv"), index=False, encoding="utf-8")
    val_out.to_csv(os.path.join(args.out_dir, "val_assignments.csv"), index=False, encoding="utf-8")
    test_out.to_csv(os.path.join(args.out_dir, "test_assignments.csv"), index=False, encoding="utf-8")

    # Save models
    joblib.dump(scaler,  os.path.join(args.out_dir, "scaler.joblib"))
    joblib.dump(pca50,   os.path.join(args.out_dir, "pca50.joblib"))
    joblib.dump(pca2,    os.path.join(args.out_dir, "pca2.joblib"))
    joblib.dump(model_c, os.path.join(args.out_dir, f"{args.cluster}.joblib"))

    # Plots
    plot_scatter_2d(train_2d, y_train, f"Train clusters ({args.cluster})", os.path.join(args.out_dir, "train_clusters_2d.png"))
    plot_scatter_2d(val_2d,   y_val,   f"Val clusters ({args.cluster})",   os.path.join(args.out_dir, "val_clusters_2d.png"))
    plot_scatter_2d(test_2d,  y_test,  f"Test clusters ({args.cluster})",  os.path.join(args.out_dir, "test_clusters_2d.png"))

    # Summary
    summary = {
        "counts": {"train": len(df_train), "val": len(df_val), "test": len(df_test)},
        "cluster": args.cluster, "n_clusters": args.n_clusters,
        "backbone": args.backbone, "img_size": args.img_size,
        "internal_metrics": {"train": train_m, "val": val_m, "test": test_m},
        "csv": os.path.join(args.out_dir, "assignments.csv"),
    }
    with open(os.path.join(args.out_dir, "summary.json"), "w", encoding="utf-8") as f:
        json.dump(summary, f, indent=2, ensure_ascii=False)

    # Optional: save features
    np.save(os.path.join(args.out_dir, "features.npy"), emb_all)
    np.save(os.path.join(args.out_dir, "feature_paths.npy"), df["path"].to_numpy())

    print("Done. Results saved to:", args.out_dir)

if __name__ == "__main__":
    main()