X_train_features = np.column_stack((X_train_features_1_ltr_gmm,X_train_features_1_rtl_gmm,X_train_features_1_ttb_gmm,X_train_features_1_btt_gmm,X_train_features_0_ltr_gmm,X_train_features_0_rtl_gmm,X_train_features_0_btt_gmm,X_train_features_0_ttb_gmm))
X_test_features = np.column_stack((X_test_features_1_ltr_gmm,X_test_features_1_rtl_gmm,X_test_features_1_ttb_gmm,X_test_features_1_btt_gmm,X_test_features_0_ltr_gmm,X_test_features_0_rtl_gmm,X_test_features_0_btt_gmm,X_test_features_0_ttb_gmm))
ridge_model = RidgeClassifier().fit(X_train_features, y_train)
gmm_train_accuracy_ridge[t] = ridge_model.score(X_train_features, y_train)
gmm_test_accuracy_ridge[t] = ridge_model.score(X_test_features, y_test)
c = 10
svm_model = SVC(kernel='rbf', C=c).fit(X_train_features, y_train)
gmm_train_accuracy_svm[t] = svm_model.score(X_train_features, y_train)
gmm_test_accuracy_svm[t] = svm_model.score(X_test_features, y_test)
### Persistence images
p = [15,15]
s = 1
X_train_features_0_ltr_imgs, X_test_features_0_ltr_imgs = persistence_image_features(zero_dim_ltr_train, zero_dim_ltr_test, pixels=p, spread=s)
X_train_features_0_rtl_imgs, X_test_features_0_rtl_imgs = persistence_image_features(zero_dim_rtl_train, zero_dim_rtl_test, pixels=p, spread=s)
X_train_features_0_ttb_imgs, X_test_features_0_ttb_imgs = persistence_image_features(zero_dim_ttb_train, zero_dim_ttb_test, pixels=p, spread=s)
X_train_features_0_btt_imgs, X_test_features_0_btt_imgs = persistence_image_features(zero_dim_btt_train, zero_dim_btt_test, pixels=p, spread=s)
X_train_features_1_ltr_imgs, X_test_features_1_ltr_imgs = persistence_image_features(one_dim_ltr_train, one_dim_ltr_test, pixels=p, spread=s)
X_train_features_1_rtl_imgs, X_test_features_1_rtl_imgs = persistence_image_features(one_dim_rtl_train, one_dim_rtl_test, pixels=p, spread=s)
X_train_features_1_ttb_imgs, X_test_features_1_ttb_imgs = persistence_image_features(one_dim_ttb_train, one_dim_ttb_test, pixels=p, spread=s)
X_train_features_1_btt_imgs, X_test_features_1_btt_imgs = persistence_image_features(one_dim_btt_train, one_dim_btt_test, pixels=p, spread=s)
X_train_features = np.column_stack((X_train_features_1_ltr_imgs,X_train_features_1_rtl_imgs,X_train_features_1_ttb_imgs,X_train_features_1_btt_imgs,X_train_features_0_ltr_imgs,X_train_features_0_rtl_imgs,X_train_features_0_btt_imgs,X_train_features_0_ttb_imgs))
X_test_features = np.column_stack((X_test_features_1_ltr_imgs,X_test_features_1_rtl_imgs,X_test_features_1_ttb_imgs,X_test_features_1_btt_imgs,X_test_features_0_ltr_imgs,X_test_features_0_rtl_imgs,X_test_features_0_btt_imgs,X_test_features_0_ttb_imgs))
ridge_model = RidgeClassifier().fit(X_train_features, y_train)
images_train_accuracy_ridge[t] = ridge_model.score(X_train_features, y_train)
images_test_accuracy_ridge[t] = ridge_model.score(X_test_features, y_test)
gmm_train_accuracy_ridge[k] = ridge_model.score(X_train_features, y_train)
gmm_test_accuracy_ridge[k] = ridge_model.score(X_test_features, y_test)
svm_model = SVC(kernel='rbf', C=1).fit(X_train_features, y_train)
gmm_train_accuracy_svm[k] = svm_model.score(X_train_features, y_train)
gmm_test_accuracy_svm[k] = svm_model.score(X_test_features, y_test)
### Persistence Images
pixels = [[15, 15], [20, 20]]
spread = [.5, 1]
i = 1
j = 1
X_train_features_R0_imgs, X_test_features_R0_imgs = persistence_image_features(
R0_train_sample, R0_test_sample, pixels=pixels[i], spread=spread[j])
X_train_features_G0_imgs, X_test_features_G0_imgs = persistence_image_features(
G0_train_sample, G0_test_sample, pixels=pixels[i], spread=spread[j])
X_train_features_B0_imgs, X_test_features_B0_imgs = persistence_image_features(
B0_train_sample, B0_test_sample, pixels=pixels[i], spread=spread[j])
X_train_features_X0_imgs, X_test_features_X0_imgs = persistence_image_features(
X0_train_sample, X0_test_sample, pixels=pixels[i], spread=spread[j])
X_train_features_Y0_imgs, X_test_features_Y0_imgs = persistence_image_features(
Y0_train_sample, Y0_test_sample, pixels=pixels[i], spread=spread[j])
X_train_features_Z0_imgs, X_test_features_Z0_imgs = persistence_image_features(
Z0_train_sample, Z0_test_sample, pixels=pixels[i], spread=spread[j])
X_train_features_H0_imgs, X_test_features_H0_imgs = persistence_image_features(
H0_train_sample, H0_test_sample, pixels=pixels[i], spread=spread[j])
X_train_features_S0_imgs, X_test_features_S0_imgs = persistence_image_features(
S0_train_sample, S0_test_sample, pixels=pixels[i], spread=spread[j])
X_train_features_V0_imgs, X_test_features_V0_imgs = persistence_image_features(
X_test_features = np.column_stack(
(X_test_features_0_gmm, X_test_features_1_gmm))
ridge_model = RidgeClassifier().fit(X_train_features, y_train)
gmm_train_accuracy_ridge[k] = ridge_model.score(X_train_features, y_train)
gmm_test_accuracy_ridge[k] = ridge_model.score(X_test_features, y_test)
c = 1
svm_model = SVC(kernel='rbf', C=c).fit(X_train_features, y_train)
gmm_train_accuracy_svm[k] = svm_model.score(X_train_features, y_train)
gmm_test_accuracy_svm[k] = svm_model.score(X_test_features, y_test)
### Persistence images
pixels = [20, 20]
spread = 1
X_train_features_1_imgs, X_test_features_1_imgs = persistence_image_features(
X_dgm1_train, X_dgm1_test, pixels=pixels, spread=1)
X_train_features_0_imgs, X_test_features_0_imgs = persistence_image_features(
X_dgm0_train, X_dgm0_test, pixels=pixels, spread=1)
X_train_features = np.column_stack(
(X_train_features_1_imgs, X_train_features_0_imgs))
X_test_features = np.column_stack(
(X_test_features_1_imgs, X_test_features_0_imgs))
ridge_model = RidgeClassifier().fit(X_train_features, y_train)
images_train_accuracy_ridge[k] = ridge_model.score(X_train_features,
y_train)
images_test_accuracy_ridge[k] = ridge_model.score(X_test_features, y_test)
c = 1
svm_model = SVC(kernel='rbf', C=c).fit(X_train_features, y_train)
images_train_accuracy_svm[k] = svm_model.score(X_train_features, y_train)