Move kmean to seperate filee and refactor code

 * Other small quality of life improvements and changes
 * to the flags

2 files changed, 96 insertions, 95 deletions

diff --git a/kmean.py b/kmean.py
new file mode 100755
index 0000000..4e9d03e
--- /dev/null
+++ b/kmean.py
@@ -0,0 +1,62 @@
+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
+
+def create_kmean_clusters(feature_vectors, labels, gallery_idx, camId):
+    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)
+
+    for i in range(2):
+        km_train_data[i] =  KMeans(n_clusters=int(np.max(labels)),random_state=0).fit(train[i])
+        km_labels[i] = np.zeros(int(np.max(labels))) # clusters size
+        km_idx[i] = km_train_data[i].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[0] = np.ones(km_labels_1.size)
+    clustercam[1] = np.add(np.ones(km_labels_2.size), 1)
+    for j in range(2):
+        for j in range(km_labels_1.size):
+            cl.append(km_train_data[i].cluster_centers_[j])
+            cllab.append(km_labels[i][j])
+
+    train_data = np.array(cl)
+    train_label = np.array(cllab)
+    train_cam = np.concatenate(clustercam, axis=1)
+    return train_data, train_label, train_cam
+        
diff --git a/part2.py b/part2.py
index 82a8cdd..679a54d 100755
--- a/part2.py
+++ b/part2.py
@@ -44,9 +44,10 @@ parser.add_argument("-n", "--neighbors", help="Number of neighbors", type=int, d
 parser.add_argument("-v", "--verbose", help="Use verbose output", action='store_true')
 parser.add_argument("-s", "--showrank", help="Save ranklist pic id in a txt file", type=int, default = 0)
 parser.add_argument("-2", "--graphspace", help="Graph space", action='store_true', default=0)
-parser.add_argument("-1", "--norm", help="Normalized features", action='store_true', default=0)
+parser.add_argument("-1", "--normalise", help="Normalized features", action='store_true', default=0)
 parser.add_argument("-M", "--multrank", help="Run for different ranklist sizes equal to M", type=int, default=1)
 parser.add_argument("-C", "--comparison", help="Set to 2 to obtain a comparison of baseline and Improved metric", type=int, default=1)
+parser.add_argument("--data", help="Data folder with features data", default='data')
 
 
 args = parser.parse_args()
@@ -68,23 +69,23 @@ def draw_results(test_label, pred_label):
     return acc_sc
 
 def test_model(gallery_data, probe_data, gallery_label, probe_label, gallery_cam, probe_cam, showfiles_train, showfiles_test, args):
-    
+
     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, 
+        distances = re_ranking(probe_data, gallery_data,
+                               args.reranka ,args.rerankb , 0.3,
                                MemorySave = False, Minibatch = 2000)
     else:
         if args.mahalanobis:
             # metric = 'jaccard' is also valid
             distances = cdist(probe_data, gallery_data, 'sqeuclidean')
         else:
-            distances = cdist(probe_data, gallery_data, 'euclidean') 
+            distances = cdist(probe_data, gallery_data, 'euclidean')
 
     ranklist = np.argsort(distances, axis=1)
-    
+
     test_table = np.arange(1, args.multrank+1)
     target_pred = np.zeros((args.multrank, ranklist.shape[0]))
     nsize = args.neighbors
@@ -92,8 +93,8 @@ def test_model(gallery_data, probe_data, gallery_label, probe_label, gallery_cam
         nsize = test_table[args.multrank-1]
     nneighbors = np.zeros((ranklist.shape[0],nsize))
     nnshowrank = (np.zeros((ranklist.shape[0],nsize))).astype(object)
-    
-    
+
+
     for i in range(args.multrank):
         if args.multrank!= 1:
             args.neighbors = test_table[i]
@@ -109,19 +110,19 @@ def test_model(gallery_data, probe_data, gallery_label, probe_label, gallery_cam
                 nnshowrank[probe_idx][q] = showfiles_train[row[n]] #
                 q += 1
                 n += 1
-                
+
             if (args.neighbors) and (probe_label[probe_idx] in nneighbors[probe_idx]):
                 target_pred[i][probe_idx] = probe_label[probe_idx]
             else:
                 target_pred[i][probe_idx] = nneighbors[probe_idx][0]
-        
-        
-        if (args.showrank): 
+
+
+        if (args.showrank):
             with open("ranklist.txt", "w") as text_file:
                 text_file.write(np.array2string(nnshowrank[:args.showrank]))
             with open("query.txt", "w") as text_file:
                 text_file.write(np.array2string(showfiles_test[:args.showrank]))
-                
+
     if args.graphspace:
             # Colors for distinct individuals
             cols = ['#{:06x}'.format(randint(0, 0xffffff)) for i in range(1467)]
@@ -134,14 +135,14 @@ def test_model(gallery_data, probe_data, gallery_label, probe_label, gallery_cam
     return target_pred
 
 def main():
-    mat = scipy.io.loadmat('data/cuhk03_new_protocol_config_labeled.mat')
+    mat = scipy.io.loadmat(os.path.join(args.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 
+    query_idx = mat['query_idx'] - 1
     train_idx = mat['train_idx'] - 1
-    with open("data/feature_data.json", "r") as read_file:
+    with open(os.path.join(args.data,'feature_data.json'), 'r') as read_file:
         feature_vectors = np.array(json.load(read_file))
     if args.train:
         query_idx = train_idx.reshape(train_idx.shape[0])
@@ -150,7 +151,7 @@ def main():
         query_idx = query_idx.reshape(query_idx.shape[0])
         gallery_idx = gallery_idx.reshape(gallery_idx.shape[0])
     camId = camId.reshape(camId.shape[0])
-    
+
     showfiles_train = filelist[gallery_idx]
     showfiles_test = filelist[query_idx]
     train_data = feature_vectors[gallery_idx]
@@ -159,98 +160,36 @@ def main():
     test_label = labels[query_idx]
     train_cam = camId[gallery_idx]
     test_cam = camId[query_idx]
-    
+
     accuracy = np.zeros((2, args.multrank))
     test_table = np.arange(1, args.multrank+1)
 
-    if (args.norm):
+    if (args.normalise):
         train_data = np.divide(train_data,LA.norm(train_data, axis=0))
         test_data = np.divide(test_data, LA.norm(test_data, axis=0))
     if(args.kmean):
-        gallery1 = []
-        gallery2 = []
-        gallery1lab = []
-        gallery2lab = []
-        for i in range(gallery_idx.size):
-            if camId[gallery_idx[i]] == 1:
-                gallery1.append(feature_vectors[gallery_idx[i]])
-                gallery1lab.append(labels[gallery_idx[i]])
-            else:
-                gallery2.append(feature_vectors[gallery_idx[i]])
-                gallery2lab.append(labels[gallery_idx[i]])
-                
-        train1 = np.array(gallery1)
-        train2 = np.array(gallery2)
-        tlabel1 = np.array(gallery1lab)
-        tlabel2 = np.array(gallery2lab)
+        train_data, train_label, train_cam = create_kmean_clusters(feature_vectors,
+                                                                   labels,
+                                                                   gallery_idx,
+                                                                   camId)
+    for q in range(args.comparison):
+        target_pred = test_model(train_data, test_data, train_label, test_label, train_cam, test_cam, showfiles_train, showfiles_test, args)
+        for i in range(args.multrank):
+            accuracy[q][i] = draw_results(test_label, target_pred[i])
+        args.rerank = True
+        args.neighbors = 1
 
-        km_train_data_1 = KMeans(n_clusters=int(np.max(labels)),random_state=0).fit(train1)
-        km_train_data_2 = KMeans(n_clusters=int(np.max(labels)),random_state=0).fit(train2)
-        
-        ###REMAP LABELS
-        km_labels_1 = np.zeros(int(np.max(labels))) # clusters size
-        km_labels_2 = np.zeros(int(np.max(labels)))
-        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(tlabel1[q])-1] += 1
-            km_labels_1[i] = np.argmax(class_vote) + 1
-            
-        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(tlabel2[q])-1] += 1
-            km_labels_2[i] = np.argmax(class_vote) + 1
-            
-        #MERGE CLUSTERS
-        cl = []
-        cllab = []
-        clcam = []
-        clustercam1 = np.ones(km_labels_1.size)
-        clustercam2 = np.add(np.ones(km_labels_2.size), 1)
-        for i in range(km_labels_1.size):
-            cl.append(km_train_data_1.cluster_centers_[i])
-            cllab.append(km_labels_1[i])
-            clcam.append(clustercam1[i])
-        for i in range(km_labels_2.size):
-            cl.append(km_train_data_2.cluster_centers_[i])
-            cllab.append(km_labels_2[i])
-            clcam.append(clustercam2[i])
-
-        cluster = np.array(cl)
-        clusterlabel = np.array(cllab)
-        clustercam = np.array(clcam)
-        
-        for q in range(args.comparison):
-            target_pred = test_model(cluster, test_data, clusterlabel, test_label, clustercam, test_cam, showfiles_train, showfiles_test, args)
-            for i in range(args.multrank):
-                accuracy[q][i] = draw_results(test_label, target_pred[i])   
-            args.rerank = True
-            args.neighbors = 1
-        
-    else:
-        for q in range(args.comparison):
-            target_pred = test_model(train_data, test_data, train_label, test_label, train_cam, test_cam, showfiles_train, showfiles_test, args)
-            for i in range(args.multrank):
-                accuracy[q][i] = draw_results(test_label, target_pred[i])   
-            args.rerank = True
-            args.neighbors = 1
-            
     if(args.multrank != 1):
         plt.plot(test_table[:(args.multrank)], 100*accuracy[0])
         if(args.comparison!=1):
             plt.plot(test_table[:(args.multrank)], 100*accuracy[1])
-            plt.legend(['Baseline kNN', 'Improved metric'], loc='upper left')    
+            plt.legend(['Baseline kNN', 'Improved metric'], loc='upper left')
         plt.xlabel('k rank')
         plt.ylabel('Recognition Accuracy (%)')
         plt.grid(True)
         plt.show()
-            
+
 
 if __name__ == "__main__":
     main()
-    
+