#!/usr/bin/env python
# Author: Vasil Zlatanov, Nunzio Pucci
# EE4 Pattern Recognition coursework
#
# usage: kmean.py 

from logging import debug
import numpy as np
from sklearn.cluster import KMeans

def create_kmean_clusters(feature_vectors, labels, gallery_idx, camId):
    gallery = ([],[])
    gallerylab = ([],[])
    for i in range(gallery_idx.size):
        cam = camId[gallery_idx[i]] - 1
        gallery[cam].append(feature_vectors[gallery_idx[i]])
        gallerylab[cam].append(labels[gallery_idx[i]])
            
    
    train = np.array(gallery)
    tlabel = np.array(gallerylab)

    km_train_data = []
    km_idx = []
    km_labels = []

    for i in range(2):
        km_train_data.append(KMeans(n_clusters=int(np.max(labels)),random_state=0).fit(train[i]))
        km_idx.append(km_train_data[i].labels_)
        km_labels.append(list(range(np.max(labels))))
        for j in range(np.max(labels)):
            class_vote = np.zeros(np.max(labels))
            for q in range(km_idx[i].size):
                if km_idx[i][q]==j:
                    class_vote[int(tlabel[i][q])-1] += 1
            km_labels[i][j] = np.argmax(class_vote) + 1
        
    #MERGE CLUSTERS
    cl = []
    cllab = []
    clustercam = []
    for i in range(2):
        clustercam.append(np.add(np.ones(len(km_labels[i])), i))
        for j in range(len(km_labels[i])):
            cl.append(km_train_data[i].cluster_centers_[j])
            cllab.append(km_labels[i][j])

    train_data = np.array(cl)
    debug("Kmean data has shape", train_data.shape)
    train_label = np.array(cllab)
    train_cam = np.array([clustercam[i] for i in range(2)]).reshape(train_label.shape[0])
    return train_data, train_label, train_cam