Add PCA and NORM (no sklearn)

Try to fix LDA

1 files changed, 57 insertions, 49 deletions

diff --git a/train.py b/train.py
index 46f76a4..93139b7 100755
--- a/train.py
+++ b/train.py
@@ -24,12 +24,37 @@ from numpy import linalg as LA
 
 # subtract the normal face from each row of the face matrix
 def normalise_faces(average_face, faces):
-    return np.subtract(faces, np.tile(average_face, (faces.shape[0],1)))
+    faces = np.subtract(faces, np.tile(average_face, (faces.shape[0],1)))
+    return np.divide(faces.T, np.std(faces.T, axis=0)).T
+
+# Split data into training and testing sets
+def test_split(n_faces, raw_faces, split, seed):
+    random.seed(seed)
+    n_cases = 52
+    n_pixels = 2576 
+    
+    raw_faces_split = np.split(raw_faces,n_cases)
+    n_training_faces = int(round(n_cases*(1 - split)))
+    n_test_faces = n_cases - n_training_faces
+    faces_train = np.zeros((n_faces, n_training_faces, n_pixels))
+    faces_test = np.zeros((n_faces, n_test_faces, n_pixels))
+    target_train = np.repeat(np.arange(n_faces), n_training_faces)
+    target_test = np.repeat(np.arange(n_faces), n_test_faces)
+    
+    for x in range (n_faces):
+        samples = random.sample(range(n_cases), n_training_faces)
+        faces_train[x] = [raw_faces[i+n_cases*x] for i in samples]
+        faces_test[x] = [raw_faces[i+n_cases*x] for i in range (n_cases) if i not in samples]
+
+    faces_train = faces_train.reshape(n_faces*n_training_faces, n_pixels)
+    faces_test = faces_test.reshape(n_faces*n_test_faces, n_pixels)
+    return faces_train, faces_test, target_train, target_test
+
 
 # usage: train.py [-h] -i DATA -o MODEL [-m M]
 parser = argparse.ArgumentParser()
 parser.add_argument("-i", "--data", help="Input CSV file", required=True)
-parser.add_argument("-m", "--eigen", help="Number of eigenvalues in model", type=int, default = 140 )
+parser.add_argument("-m", "--eigen", help="Number of eigenvalues in model", type=int, default = 10 )
 parser.add_argument("-n", "--neighbors", help="How many neighbors to use", type=int, default = 3)
 parser.add_argument("-f", "--faces", help="Show faces", type=int, default = 0)
 parser.add_argument("-c", "--principal", help="Show principal components", action='store_true')
@@ -50,33 +75,8 @@ M = args.eigen
 raw_faces = genfromtxt(args.data, delimiter=',')
 targets = np.repeat(np.arange(10),52)
 
-#faces_train, faces_test, target_train, target_test = train_test_split(raw_faces, targets, test_size=args.split, random_state=args.seed)
-
-### Splitter
 n_faces = 10
 
-def test_split(n_faces, raw_faces, split, seed):
-    random.seed(seed)
-    n_cases = 52
-    n_pixels = 2576 
-    
-    raw_faces_split = np.split(raw_faces,n_cases)
-    n_training_faces = int(round(n_cases*(1 - split)))
-    n_test_faces = n_cases - n_training_faces
-    faces_train = np.zeros((n_faces, n_training_faces, n_pixels))
-    faces_test = np.zeros((n_faces, n_test_faces, n_pixels))
-    target_train = np.repeat(np.arange(n_faces), n_training_faces)
-    target_test = np.repeat(np.arange(n_faces), n_test_faces)
-    
-    for x in range (n_faces):
-        samples = random.sample(range(n_cases), n_training_faces)
-        faces_train[x] = [raw_faces[i+n_cases*x] for i in samples]
-        faces_test[x] = [raw_faces[i+n_cases*x] for i in range (n_cases) if i not in samples]
-
-    faces_train = faces_train.reshape(n_faces*n_training_faces, n_pixels)
-    faces_test = faces_test.reshape(n_faces*n_test_faces, n_pixels)
-    return faces_train, faces_test, target_train, target_test
-
 faces_train, faces_test, target_train, target_test = test_split(n_faces, raw_faces, args.split, args.seed)
 
 # This remove the mean and scales to unit variance
@@ -86,42 +86,50 @@ faces_train, faces_test, target_train, target_test = test_split(n_faces, raw_fac
 
 explained_variances = ()
 if args.lda:
-    lda = LinearDiscriminantAnalysis(n_components=M)
-    faces_train = lda.fit_transform(faces_train, target_train)
-    faces_test = lda.transform(faces_test)
-    explained_variances = lda.explained_variance_ratio_
+    average_face = np.mean(faces_train, axis=0) 
+    n_cases = 52
+
+#    lda = LinearDiscriminantAnalysis(n_components=M)
+#    faces_train = lda.fit_transform(faces_train, target_train)
+#    faces_test = lda.transform(faces_test)
+#    explained_variances = lda.explained_variance_ratio_
+### FIND MEAN OF EACH CLASS
+    n_training_faces = int(round(n_cases*(1 - args.split)))
+    n_test_faces = n_cases - n_training_faces
+    mean_vector = np.zeros(10) 
+    for n in range (10):
+        mean_acc = 0
+        for x in range (int(np.divide(n_training_faces,10))):
+            mean_acc = np.add(mean_acc, np.mean(faces_train[x + n*10], axis=0))
+        mean_vector [n] = np.divide(mean_acc, np.divide(n_training_faces,10))
+    print (mean_vector)
+### SCATTER MATRIX
+    for n in range (10)
+        faces_train = normalise_faces(mean_vector[n], faces_train[ 
 else:
     # faces_pca containcts the principial components or the M most variant eigenvectors
-###  FROM SKLEARN
-#    pca = PCA(svd_solver='full', n_components=M)
-#    faces_train = pca.fit_transform(faces_train)
-#    faces_test = pca.transform(faces_test)
-#    explained_variances = pca.explained_variance_ratio_
-
-###  FROM OLD CODE
     average_face = np.mean(faces_train, axis=0) 
-    plt.imshow(average_face.reshape(46,56))
-    plt.show()
     faces_train = normalise_faces(average_face, faces_train)
     faces_test = normalise_faces(average_face, faces_test)
-    e_vals, e_vecs = LA.eigh(np.dot(faces_train.T, faces_train))
-    print(e_vecs.shape)
-    explained_variances = e_vals[:M]
-    e_vecs =np.divide(e_vecs, LA.norm(e_vecs))
-    faces_train = np.dot(faces_train, e_vecs[:M])
-    faces_test = np.dot(faces_test, e_vecs[:M])
+    e_vals, e_vecs = LA.eigh(np.cov(faces_train.T))
+    e_vals = np.flip(e_vals)
+    e_vecs = np.fliplr(e_vecs).T
+    faces_train = np.dot(faces_train, e_vecs[:M].T)
+    faces_test = np.dot(faces_test, e_vecs[:M].T)
+    
 # Plot the variances (eigenvalues) from the pca object
 if args.faces:
     if args.lda:
         sys.exit("Can not plot eigenfaces when using LDA")
     for i in range(args.faces):
         ax = plt.subplot(2, args.faces/2, i + 1)
-        ax.imshow(e_vecs[i].reshape([46, 56]), cmap = 'gist_gray')
+        ax.imshow(e_vecs[i].reshape([46, 56]).T, cmap = 'gist_gray')
     plt.show()
 
 if args.principal:
-    plt.bar(np.arange(explained_variances.size), explained_variances)
-    plt.ylabel('Varaiance ratio');plt.xlabel('Face Number')
+    e_vals = np.multiply(np.divide(e_vals, np.sum(e_vals)), 100)
+    plt.bar(np.arange(M), e_vals[:M])
+    plt.ylabel('Varaiance ratio (%)');plt.xlabel('Eigenface Number')
     plt.show()
 
 if args.grapheigen: