diff options
| -rwxr-xr-x | train.py | 278 |
1 files changed, 150 insertions, 128 deletions
@@ -2,6 +2,8 @@ # Train a model from sample data # Author: Vasil Zlatanov, Nunzio Pucci # EE4 Pattern Recognition coursework +# +# usage: train.py [-h] -i DATA -o MODEL [-m M] import matplotlib.pyplot as plt from mpl_toolkits.mplot3d import Axes3D @@ -14,7 +16,7 @@ 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 confusion_matrix from sklearn.metrics import accuracy_score import argparse @@ -23,16 +25,21 @@ import numpy as np from numpy import genfromtxt from numpy import linalg as LA +from timeit import default_timer as timer + +n_faces = 52 +n_cases = 10 +n_pixels = 2576 + # subtract the normal face from each row of the face matrix def normalise_faces(average_face, faces): 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 = 10 - 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 @@ -40,139 +47,154 @@ def test_split(n_faces, raw_faces, split, seed): 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): + + 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_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 = 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') -parser.add_argument("-s", "--seed", help="Seed to use", type=int, default=0) -parser.add_argument("-t", "--split", help="Fractoin of data to use for testing", type=float, default=0.22) -### best split for lda = 22 -### best plit for pca = 20 -parser.add_argument("-2", "--grapheigen", help="Swow 2D graph of targets versus principal components", action='store_true') -parser.add_argument("-p", "--pca", help="Use PCA", action='store_true') -parser.add_argument("-l", "--lda", help="Use LDA", action='store_true') -parser.add_argument("-r", "--reconstruct", help="Use PCA reconstruction, specify face NR", type=int, default=0) -parser.add_argument("-cm", "--conf_mat", help="Show visual confusion matrix", action='store_true') - -parser.add_argument("-q", "--pca_r", help="Use Reduced PCA", action='store_true') - -args = parser.parse_args() - -M = args.eigen - -raw_faces = genfromtxt(args.data, delimiter=',') -targets = np.repeat(np.arange(52),10) - -n_faces = 52 - -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 -sc = StandardScaler() -#faces_train = sc.fit_transform(faces_train) -#faces_test = sc.transform(faces_test) -raw_faces_train = faces_train - -explained_variances = () - -if args.pca or args.pca_r: - # faces_pca containcts the principial components or the M most variant eigenvectors - average_face = np.mean(faces_train, axis=0) - deviations_tr = np.std(faces_train, axis=0) - deviations_tst = np.std(faces_train, axis=0) - faces_train = normalise_faces(average_face, faces_train) - faces_test = normalise_faces(average_face, faces_test) - if (args.pca_r): - print('Reduced PCA') - e_vals, e_vecs = LA.eigh(np.dot(faces_train, faces_train.T)) - e_vecs = np.dot(faces_train.T, e_vecs) - e_vecs = e_vecs/LA.norm(e_vecs, axis = 0) - else: - print('Standard PCA') - e_vals, e_vecs = LA.eigh(np.cov(faces_train.T)) - # e_vecs = normalise_faces(np.mean(e_vecs,axis=0), e_vecs) - # e_vecs = sc.fit_transform(e_vecs) - - e_vals = np.flip(e_vals)[:M] - e_vecs = np.fliplr(e_vecs).T[:M] - deviations_tr = np.flip(deviations_tr) - deviations_tst = np.flip(deviations_tst) +def draw_conf_mat(target_test, target_pred): + cm = confusion_matrix(target_test, target_pred) + print(cm) + if (args.conf_mat): + plt.matshow(cm, cmap='Blues') + plt.colorbar() + plt.ylabel('Actual') + plt.xlabel('Predicted') + plt.show() + print('Accuracy %fl' % accuracy_score(target_test, target_pred)) + +def test_model(M, faces_train, faces_test, target_train, target_test, args): + raw_faces_train = faces_train + + explained_variances = () + + if args.pca or args.pca_r: + # faces_pca containcts the principial components or the M most variant eigenvectors + average_face = np.mean(faces_train, axis=0) + deviations_tr = np.std(faces_train, axis=0) + deviations_tst = np.std(faces_train, axis=0) + faces_train = normalise_faces(average_face, faces_train) + faces_test = normalise_faces(average_face, faces_test) + if (args.pca_r): + print('Reduced PCA') + e_vals, e_vecs = LA.eigh(np.dot(faces_train, faces_train.T)) + e_vecs = np.dot(faces_train.T, e_vecs) + e_vecs = e_vecs/LA.norm(e_vecs, axis = 0) + else: + print('Standard PCA') + e_vals, e_vecs = LA.eigh(np.cov(faces_train.T)) + # e_vecs = normalise_faces(np.mean(e_vecs,axis=0), e_vecs) + + e_vals = np.flip(e_vals)[:M] + e_vecs = np.fliplr(e_vecs).T[:M] + deviations_tr = np.flip(deviations_tr) + deviations_tst = np.flip(deviations_tst) + + faces_train = np.dot(faces_train, e_vecs.T) + faces_test = np.dot(faces_test, e_vecs.T) + + if (args.reconstruct): + rec_vec = np.add(average_face, np.dot(faces_train[args.reconstruct], e_vecs) * deviations_tr) + rec_faces_test = np.add(average_face, np.dot(faces_test, e_vecs) * deviations_tst) + rec_error = LA.norm(np.subtract(raw_faces_train[args.reconstruct], rec_vec)) + ar = plt.subplot(2, 1, 1) + ar.imshow(rec_vec.reshape([46,56]).T, cmap = 'gist_gray') + ar = plt.subplot(2, 1, 2) + ar.imshow(raw_faces_train[args.reconstruct].reshape([46,56]).T, cmap = 'gist_gray') + plt.show() + + if args.lda or (args.pca and args.lda): + lda = LinearDiscriminantAnalysis(n_components=M, solver='eigen') + faces_train = lda.fit_transform(faces_train, target_train) + faces_test = lda.transform(faces_test) + class_means = lda.means_ + e_vals = lda.explained_variance_ratio_ + + if args.faces: + if args.lda: + for i in range(10): + ax = plt.subplot(2, 5, i + 1) + ax.imshow(class_means[i].reshape([46,56]).T) + else: + for i in range(args.faces): + ax = plt.subplot(2, args.faces/2, i + 1) + ax.imshow(e_vecs[i].reshape([46, 56]).T, cmap = 'gist_gray') + plt.show() - faces_train = np.dot(faces_train, e_vecs.T) - faces_test = np.dot(faces_test, e_vecs.T) + if args.principal: + 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('Number') + plt.show() - if (args.reconstruct): - rec_vec = np.add(average_face, np.dot(faces_train[args.reconstruct], e_vecs) * deviations_tr) - rec_faces_test = np.add(average_face, np.dot(faces_test, e_vecs) * deviations_tst) - rec_error = LA.norm(np.subtract(raw_faces_train[args.reconstruct], rec_vec)) - ar = plt.subplot(2, 1, 1) - ar.imshow(rec_vec.reshape([46,56]).T, cmap = 'gist_gray') - ar = plt.subplot(2, 1, 2) - ar.imshow(raw_faces_train[args.reconstruct].reshape([46,56]).T, cmap = 'gist_gray') + if args.grapheigen: + graph_eigen() + # Colors for distinct individuals + cols = ['#{:06x}'.format(randint(0, 0xffffff)) for i in range(n_faces)] + pltCol = [cols[int(k)] for k in target_train] + fig = plt.figure() + ax = fig.add_subplot(111, projection='3d') + ax.scatter(faces_train[:, 0], faces_train[:, 1], faces_train[:, 2], marker='o', color=pltCol) plt.show() -if args.lda or (args.pca and args.lda): - lda = LinearDiscriminantAnalysis(n_components=M, solver='eigen') - faces_train = lda.fit_transform(faces_train, target_train) - faces_test = lda.transform(faces_test) - class_means = lda.means_ - e_vals = lda.explained_variance_ratio_ - -if args.faces: - if args.lda: - for i in range (10): - ax = plt.subplot(2, 5, i + 1) - ax.imshow(class_means[i].reshape([46,56]).T) + classifier = KNeighborsClassifier(n_neighbors=args.neighbors) + if (args.reconstruct): + classifier.fit(raw_faces_train, target_train) + target_pred = classifier.predict(rec_faces_test) + #Better Passing n_neighbors = 1 + else: + classifier.fit(faces_train, target_train) + target_pred = classifier.predict(faces_test) + #Better n_neighbors = 2 + draw_conf_mat(target_test, target_pred) + +def main(): + 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 = 10 ) + parser.add_argument("-M", "--reigen", help="Number of eigenvalues in model", type=int) + 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') + parser.add_argument("-s", "--seed", help="Seed to use", type=int, default=0) + parser.add_argument("-t", "--split", help="Fractoin of data to use for testing", type=float, default=0.22) + ### best split for lda = 22 + ### best plit for pca = 20 + parser.add_argument("-2", "--grapheigen", help="Swow 2D graph of targets versus principal components", action='store_true') + parser.add_argument("-p", "--pca", help="Use PCA", action='store_true') + parser.add_argument("-l", "--lda", help="Use LDA", action='store_true') + parser.add_argument("-r", "--reconstruct", help="Use PCA reconstruction, specify face NR", type=int, default=0) + parser.add_argument("-cm", "--conf_mat", help="Show visual confusion matrix", action='store_true') + + parser.add_argument("-q", "--pca_r", help="Use Reduced PCA", action='store_true') + + args = parser.parse_args() + + raw_faces = genfromtxt(args.data, delimiter=',') + targets = np.repeat(np.arange(n_faces),n_cases) + + + faces_train, faces_test, target_train, target_test = test_split(n_faces, raw_faces, args.split, args.seed) + + + if args.reigen: + for M in range(args.eigen, args,reigen): + start = time() + test_model(M, faces_train, faces_test, target_train, target_test, args) + end = time() + print("Run with", M, "eigenvalues completed in %.2f" % end-start, "seconds") else: - for i in range(args.faces): - ax = plt.subplot(2, args.faces/2, i + 1) - ax.imshow(e_vecs[i].reshape([46, 56]).T, cmap = 'gist_gray') - plt.show() - -if args.principal: - 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: - # Colors for distinct individuals - cols = ['#{:06x}'.format(randint(0, 0xffffff)) for i in range(52)] - pltCol = [cols[int(k)] for k in target_train] - fig = plt.figure() - ax = fig.add_subplot(111, projection='3d') - ax.scatter(faces_train[:, 0], faces_train[:, 1], faces_train[:, 2], marker='o', color=pltCol) - plt.show() - -classifier = KNeighborsClassifier(n_neighbors=args.neighbors) -if (args.reconstruct): - classifier.fit(raw_faces_train, target_train) - target_pred = classifier.predict(rec_faces_test) - #Better Passing n_neighbors = 1 -else: - classifier.fit(faces_train, target_train) - target_pred = classifier.predict(faces_test) - #Better n_neighbors = 2 - -cm = confusion_matrix(target_test, target_pred) -print(cm) -if (args.conf_mat): - plt.matshow(cm, cmap='Blues') - plt.colorbar() - plt.ylabel('Actual') - plt.xlabel('Predicted') - plt.show() -print('Accuracy %fl' % accuracy_score(target_test, target_pred)) + M = args.eigen + start = time() + test_model(M, faces_train, faces_test, target_train, target_test, args): + end = time() + print("Run with", M, "eigenvalues completed in %.2f" % end-start, "seconds") + + +if __name__ == "__main__": + main() |