# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import datetime
import os
import pickle
from io import BytesIO
from PIL import Image
import cv2
import numpy as np
import sklearn
import paddle
from scipy import interpolate
from sklearn.decomposition import PCA
from sklearn.model_selection import KFold


class LFold:
    def __init__(self, n_splits=2, shuffle=False):
        self.n_splits = n_splits
        if self.n_splits > 1:
            self.k_fold = KFold(n_splits=n_splits, shuffle=shuffle)

    def split(self, indices):
        if self.n_splits > 1:
            return self.k_fold.split(indices)
        else:
            return [(indices, indices)]


def calculate_roc(thresholds,
                  embeddings1,
                  embeddings2,
                  actual_issame,
                  nrof_folds=10,
                  pca=0):
    assert (embeddings1.shape[0] == embeddings2.shape[0])
    assert (embeddings1.shape[1] == embeddings2.shape[1])
    nrof_pairs = min(len(actual_issame), embeddings1.shape[0])
    nrof_thresholds = len(thresholds)
    k_fold = LFold(n_splits=nrof_folds, shuffle=False)

    tprs = np.zeros((nrof_folds, nrof_thresholds))
    fprs = np.zeros((nrof_folds, nrof_thresholds))
    accuracy = np.zeros((nrof_folds))
    indices = np.arange(nrof_pairs)

    if pca == 0:
        diff = np.subtract(embeddings1, embeddings2)
        dist = np.sum(np.square(diff), 1)

    for fold_idx, (train_set, test_set) in enumerate(k_fold.split(indices)):
        if pca > 0:
            print('doing pca on', fold_idx)
            embed1_train = embeddings1[train_set]
            embed2_train = embeddings2[train_set]
            _embed_train = np.concatenate((embed1_train, embed2_train), axis=0)
            pca_model = PCA(n_components=pca)
            pca_model.fit(_embed_train)
            embed1 = pca_model.transform(embeddings1)
            embed2 = pca_model.transform(embeddings2)
            embed1 = sklearn.preprocessing.normalize(embed1)
            embed2 = sklearn.preprocessing.normalize(embed2)
            diff = np.subtract(embed1, embed2)
            dist = np.sum(np.square(diff), 1)

        # Find the best threshold for the fold
        acc_train = np.zeros((nrof_thresholds))
        for threshold_idx, threshold in enumerate(thresholds):
            _, _, acc_train[threshold_idx] = calculate_accuracy(
                threshold, dist[train_set], actual_issame[train_set])
        best_threshold_index = np.argmax(acc_train)
        for threshold_idx, threshold in enumerate(thresholds):
            tprs[fold_idx, threshold_idx], fprs[
                fold_idx, threshold_idx], _ = calculate_accuracy(
                    threshold, dist[test_set], actual_issame[test_set])
        _, _, accuracy[fold_idx] = calculate_accuracy(
            thresholds[best_threshold_index], dist[test_set],
            actual_issame[test_set])

    tpr = np.mean(tprs, 0)
    fpr = np.mean(fprs, 0)
    return tpr, fpr, accuracy


def calculate_accuracy(threshold, dist, actual_issame):
    predict_issame = np.less(dist, threshold)
    tp = np.sum(np.logical_and(predict_issame, actual_issame))
    fp = np.sum(np.logical_and(predict_issame, np.logical_not(actual_issame)))
    tn = np.sum(
        np.logical_and(
            np.logical_not(predict_issame), np.logical_not(actual_issame)))
    fn = np.sum(np.logical_and(np.logical_not(predict_issame), actual_issame))

    tpr = 0 if (tp + fn == 0) else float(tp) / float(tp + fn)
    fpr = 0 if (fp + tn == 0) else float(fp) / float(fp + tn)
    acc = float(tp + tn) / dist.size
    return tpr, fpr, acc


def calculate_val(thresholds,
                  embeddings1,
                  embeddings2,
                  actual_issame,
                  far_target,
                  nrof_folds=10):
    assert (embeddings1.shape[0] == embeddings2.shape[0])
    assert (embeddings1.shape[1] == embeddings2.shape[1])
    nrof_pairs = min(len(actual_issame), embeddings1.shape[0])
    nrof_thresholds = len(thresholds)
    k_fold = LFold(n_splits=nrof_folds, shuffle=False)

    val = np.zeros(nrof_folds)
    far = np.zeros(nrof_folds)

    diff = np.subtract(embeddings1, embeddings2)
    dist = np.sum(np.square(diff), 1)
    indices = np.arange(nrof_pairs)

    for fold_idx, (train_set, test_set) in enumerate(k_fold.split(indices)):

        # Find the threshold that gives FAR = far_target
        far_train = np.zeros(nrof_thresholds)
        for threshold_idx, threshold in enumerate(thresholds):
            _, far_train[threshold_idx] = calculate_val_far(
                threshold, dist[train_set], actual_issame[train_set])
        if np.max(far_train) >= far_target:
            f = interpolate.interp1d(far_train, thresholds, kind='slinear')
            threshold = f(far_target)
        else:
            threshold = 0.0

        val[fold_idx], far[fold_idx] = calculate_val_far(
            threshold, dist[test_set], actual_issame[test_set])

    val_mean = np.mean(val)
    far_mean = np.mean(far)
    val_std = np.std(val)
    return val_mean, val_std, far_mean


def calculate_val_far(threshold, dist, actual_issame):
    predict_issame = np.less(dist, threshold)
    true_accept = np.sum(np.logical_and(predict_issame, actual_issame))
    false_accept = np.sum(
        np.logical_and(predict_issame, np.logical_not(actual_issame)))
    n_same = np.sum(actual_issame)
    n_diff = np.sum(np.logical_not(actual_issame))
    # print(true_accept, false_accept)
    # print(n_same, n_diff)
    val = float(true_accept) / float(n_same)
    far = float(false_accept) / float(n_diff)
    return val, far


def evaluate(embeddings, actual_issame, nrof_folds=10, pca=0):
    # Calculate evaluation metrics
    thresholds = np.arange(0, 4, 0.01)
    embeddings1 = embeddings[0::2]
    embeddings2 = embeddings[1::2]
    tpr, fpr, accuracy = calculate_roc(
        thresholds,
        embeddings1,
        embeddings2,
        np.asarray(actual_issame),
        nrof_folds=nrof_folds,
        pca=pca)
    thresholds = np.arange(0, 4, 0.001)
    val, val_std, far = calculate_val(
        thresholds,
        embeddings1,
        embeddings2,
        np.asarray(actual_issame),
        1e-3,
        nrof_folds=nrof_folds)
    return tpr, fpr, accuracy, val, val_std, far


# 返回为numpy
@paddle.no_grad()
def load_bin(path, image_size):
    try:
        with open(path, 'rb') as f:
            bins, issame_list = pickle.load(f)  # py2
    except UnicodeDecodeError as e:
        with open(path, 'rb') as f:
            bins, issame_list = pickle.load(f, encoding='bytes')  # py3
    data_list = []
    for flip in [0, 1]:
        data = np.empty(
            shape=[len(issame_list) * 2, 3, image_size[0], image_size[1]],
            dtype=np.float32)
        data_list.append(data)
    for idx in range(len(issame_list) * 2):
        _bin = bins[idx]
        img = np.array(Image.open(BytesIO(_bin)), dtype=np.float32)
        if img.shape[1] != image_size[0]:
            img = cv2.resize(img, (image_size[0], image_size[0]))
        img = img.transpose(2, 0, 1)
        for flip in [0, 1]:
            if flip == 1:
                img = np.flip(img, 2)
            data_list[flip][idx][:] = img
        if idx % 1000 == 0:
            print('loading bin', idx)
    print(data_list[0].shape)
    return data_list, issame_list


@paddle.no_grad()
def test(data_set, backbone, batch_size, nfolds=10):
    print('testing verification..')
    data_list = data_set[0]
    issame_list = data_set[1]
    embeddings_list = []
    time_consumed = 0.0
    for i in range(len(data_list)):
        data = data_list[i]
        embeddings = None
        ba = 0
        while ba < data.shape[0]:
            bb = min(ba + batch_size, data.shape[0])
            count = bb - ba
            _data = data[bb - batch_size:bb]
            time0 = datetime.datetime.now()
            img = ((_data / 255) - 0.5) / 0.5
            # 将numpy转Tensor
            img = paddle.to_tensor(img)
            net_out: paddle.Tensor = backbone(img)
            _embeddings = net_out.detach().cpu().numpy()
            time_now = datetime.datetime.now()
            diff = time_now - time0
            time_consumed += diff.total_seconds()
            if embeddings is None:
                embeddings = np.zeros((data.shape[0], _embeddings.shape[1]))
            embeddings[ba:bb, :] = _embeddings[(batch_size - count):, :]
            ba = bb
        embeddings_list.append(embeddings)

    _xnorm = 0.0
    _xnorm_cnt = 0
    for embed in embeddings_list:
        for i in range(embed.shape[0]):
            _em = embed[i]
            _norm = np.linalg.norm(_em)
            _xnorm += _norm
            _xnorm_cnt += 1
    _xnorm /= _xnorm_cnt

    embeddings = embeddings_list[0].copy()
    try:
        embeddings = sklearn.preprocessing.normalize(embeddings)
    except:
        print(embeddings)
    acc1 = 0.0
    std1 = 0.0
    embeddings = embeddings_list[0] + embeddings_list[1]
    embeddings = sklearn.preprocessing.normalize(embeddings)
    print(embeddings.shape)
    print('infer time', time_consumed)
    _, _, accuracy, val, val_std, far = evaluate(
        embeddings, issame_list, nrof_folds=nfolds)
    acc2, std2 = np.mean(accuracy), np.std(accuracy)
    return acc1, std1, acc2, std2, _xnorm, embeddings_list