#!/usr/bin/env python
# Author: Vasil Zlatanov, Nunzio Pucci
# EE4 Pattern Recognition coursework
#
# usage: part2.py [-h] [-t] [-cm] [-km] [-ma] [-e] [-r] [-ka RERANKA]
#                [-kb RERANKB] [-v]

import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import sys
import random
import os
import json
import scipy.io
from random import randint
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neighbors import DistanceMetric
from sklearn.cluster import KMeans
from sklearn.decomposition import PCA
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
import argparse
import numpy as np
from numpy import genfromtxt
from numpy import linalg as LA
from timeit import default_timer as timer
from scipy.spatial.distance import cdist
from rerank import re_ranking

parser = argparse.ArgumentParser()
parser.add_argument("-t", "--test", help="Use test data instead of query", action='store_true')
parser.add_argument("-cm", "--conf_mat", help="Show visual confusion matrix", action='store_true')
parser.add_argument("-km", "--kmean", help="Perform Kmeans", action='store_true', default=0)
parser.add_argument("-ma", "--mahalanobis", help="Perform Mahalanobis Distance metric", action='store_true', default=0)
parser.add_argument("-e", "--euclidean", help="Standard euclidean", action='store_true', default=0)
parser.add_argument("-r", "--rerank", help="Use k-reciprocal rernaking", action='store_true')
parser.add_argument("-ka", "--reranka", help="Parameter 1 for Rerank", type=int, default = 20)
parser.add_argument("-kb", "--rerankb", help="Parameter 2 for rerank", type=int, default = 6)
parser.add_argument("-v", "--verbose", help="Use verbose output", action='store_true')
args = parser.parse_args()

def verbose(*text):
    if args.verbose:
        print(text)

#prob query, gal train
def draw_results(test_label, pred_label):
    acc_sc = accuracy_score(test_label, pred_label)
    cm = confusion_matrix(test_label, pred_label)
    print('Accuracy: ', acc_sc)
    if (args.conf_mat):
        plt.matshow(cm, cmap='Blues')
        plt.colorbar()
        plt.ylabel('Actual')
        plt.xlabel('Predicted')
        plt.show()
    return

def test_model(gallery_data, probe_data, gallery_label, probe_label, gallery_cam, probe_cam):
    # metric = 'jaccard' is also valid
    if args.mahalanobis:
        metric = 'sqeuclidean'
    else:
        metric = 'euclidean'

    verbose("probe shape:", probe_data.shape)
    verbose("gallery shape:", gallery_data.shape)

    if args.rerank:
        distances = re_ranking(probe_data, gallery_data, 
                               args.reranka ,args.rerankb , 0.3, 
                               MemorySave = False, Minibatch = 2000)
    else:
        distances = cdist(probe_data, gallery_data, metric) 

    ranklist = np.argsort(distances, axis=1)

    target_pred = np.zeros(ranklist.shape[0])
    for probe_idx in range(probe_data.shape[0]):
        row = ranklist[probe_idx]
        n = 0 
        while (probe_cam[probe_idx] == gallery_cam[row[n]] and
          probe_label[probe_idx] == gallery_label[row[n]]):
            n += 1
        target_pred[probe_idx] = gallery_label[row[n]]

    return target_pred

def main():
    mat = scipy.io.loadmat('data/cuhk03_new_protocol_config_labeled.mat')
    camId = mat['camId']
    filelist = mat['filelist']
    labels = mat['labels']
    gallery_idx = mat['gallery_idx'] - 1
    query_idx = mat['query_idx'] - 1 
    train_idx = mat['train_idx'] - 1
    with open("data/feature_data.json", "r") as read_file:
        feature_vectors = np.array(json.load(read_file))

    gallery_idx = gallery_idx.reshape(gallery_idx.shape[0])
    if args.test:
        query_idx = train_idx.reshape(train_idx.shape[0])
    else:
        query_idx = query_idx.reshape(query_idx.shape[0])
    camId = camId.reshape(camId.shape[0])

    train_data = feature_vectors[gallery_idx]
    test_data = feature_vectors[query_idx]
    train_label = labels[gallery_idx]
    test_label = labels[query_idx]
    train_cam = camId[gallery_idx]
    test_cam = camId[query_idx]
    
    if(args.kmean):
        km_labels_1 = np.arange(1,np.max(labels)+1)
        km_labels_2 = np.arange(1,np.max(labels)+1)
        km_train_data_1 = np.zeros(((km_labels_1.size),(feature_vectors.shape[1])))
        km_train_data_2 = np.zeros(((km_labels_2.size),(feature_vectors.shape[1])))
        km_train_data_1 = KMeans(n_clusters=int(np.max(labels)),random_state=0).fit(train_data_1)
        km_train_data_2 = KMeans(n_clusters=int(np.max(labels)),random_state=0).fit(train_data_2)

        km_idx_1 = km_train_data_1.labels_ 
        for i in range(np.max(labels)):
            class_vote = np.zeros(np.max(labels))
            for q in range(km_idx_1.size):
                if km_idx_1[q]==i:
                    class_vote[int(train_label_1[q])-1] = class_vote[int(train_label_1[q])-1] + 1
            km_labels_1[i] = np.argmax(class_vote) + 1
            
        target_pred = test_model(km_train_data_1.cluster_centers_, test_data_2, km_labels_1, test_label_2)    
        draw_results(test_label_2, target_pred)
        
        km_idx_2 = km_train_data_2.labels_ 
        for i in range(np.max(labels)):
            class_vote = np.zeros(np.max(labels))
            for q in range(km_idx_2.size):
                if km_idx_2[q]==i:
                    class_vote[int(train_label_2[q])-1] = class_vote[int(train_label_2[q])-1] + 1
            km_labels_2[i] = np.argmax(class_vote) + 1
            
        target_pred = test_model(km_train_data_2.cluster_centers_, test_data_1, km_labels_2, test_label_1)    
        draw_results(test_label_1, target_pred)
    
    else:    
        target_pred = test_model(train_data, test_data, train_label, test_label, train_cam, test_cam)
        draw_results(test_label, target_pred)

if __name__ == "__main__":
    main()