def run_net(data, params):
#
# UNPACK DATA
#
x_train_unlabeled, y_train_unlabeled, x_val, y_val, x_test, y_test = data[
'spectral']['train_and_test']
print(params['input_shape'])
inputs_vae = Input(shape=params['input_shape'], name='inputs_vae')
ConvAE = Conv.ConvAE(inputs_vae, params)
try:
ConvAE.vae.load_weights('vae_mnist.h5')
except OSError:
print('No pretrained weights available...')
lh = LearningHandler(lr=params['spec_lr'],
drop=params['spec_drop'],
lr_tensor=ConvAE.learning_rate,
patience=params['spec_patience'])
lh.on_train_begin()
n_epochs = 5000
losses_vae = np.empty((n_epochs, ))
homo_plot = np.empty((n_epochs, ))
nmi_plot = np.empty((n_epochs, ))
ari_plot = np.empty((n_epochs, ))
y_val = np.squeeze(np.asarray(y_val).ravel()) # squeeze into 1D array
start_time = time.time()
for i in range(n_epochs):
# if i==0:
x_recon, _, x_val_y = ConvAE.vae.predict(x_val)
losses_vae[i] = ConvAE.train_vae(x_val, x_val_y, params['batch_size'])
#x_val_y = ConvAE.vae.predict(x_val)[2]
#y_sp = x_val_y.argmax(axis=1)
#print_accuracy(y_sp, y_val, params['n_clusters'])
print("Epoch: {}, loss={:2f}".format(i, losses_vae[i]))
os.makedirs('vae', exist_ok=True)
os.makedirs('vae_umap', exist_ok=True)
fig, axs = plt.subplots(3, 4, figsize=(25, 18))
fig.subplots_adjust(wspace=0.25)
embedding = ConvAE.encoder.predict(x_val)
kmeans = KMeans(n_clusters=params['n_clusters'], n_init=30)
predicted_labels = kmeans.fit_predict(
embedding) # cluster on current embeddings for metric eval
_, confusion_matrix = get_y_preds(predicted_labels, y_val,
params['n_clusters'])
homo_plot[i] = metrics.acc(y_val, predicted_labels)
nmi_plot[i] = metrics.nmi(y_val, predicted_labels)
ari_plot[i] = metrics.ari(y_val, predicted_labels)
tsne = manifold.TSNE(n_components=2, init='pca', random_state=0)
Z_tsne = tsne.fit_transform(embedding)
sc = axs[1][0].scatter(Z_tsne[:, 0],
Z_tsne[:, 1],
s=2,
c=y_train_unlabeled,
cmap=plt.cm.get_cmap("jet", 14))
axs[1][0].set_title('t-SNE Embeddings')
axs[1][0].set_xlabel('t-SNE 1')
axs[1][0].set_ylabel('t-SNE 2')
axs[1][0].set_xticks([])
axs[1][0].set_yticks([])
axs[1][0].spines['right'].set_visible(False)
axs[1][0].spines['top'].set_visible(False)
divider = make_axes_locatable(axs[1][0])
cax = divider.append_axes('right', size='15%', pad=0.05)
cbar = fig.colorbar(sc,
cax=cax,
orientation='vertical',
ticks=range(params['n_clusters']))
cbar.ax.set_yticklabels(
params['cluster_names']) # vertically oriented colorbar
# Create offset transform by 5 points in x direction
dx = 0 / 72.
dy = -5 / 72.
offset = matplotlib.transforms.ScaledTranslation(
dx, dy, fig.dpi_scale_trans)
# apply offset transform to all cluster ticklabels.
for label in cbar.ax.yaxis.get_majorticklabels():
label.set_transform(label.get_transform() + offset)
reducer = umap.UMAP(transform_seed=36, random_state=36)
matrix_reduce = reducer.fit_transform(embedding)
sc = axs[1][1].scatter(matrix_reduce[:, 0],
matrix_reduce[:, 1],
s=2,
c=y_train_unlabeled,
cmap=plt.cm.get_cmap("jet", 14))
axs[1][1].set_title('UMAP Embeddings')
axs[1][1].set_xlabel('UMAP 1')
axs[1][1].set_ylabel('UMAP 2')
axs[1][1].set_xticks([])
axs[1][1].set_yticks([])
# Hide the right and top spines
axs[1][1].spines['right'].set_visible(False)
axs[1][1].spines['top'].set_visible(False)
im = axs[1][2].imshow(confusion_matrix, cmap='YlOrRd')
axs[1][2].set_title('Confusion Matrix')
axs[1][2].set_xticks(range(params['n_clusters']))
axs[1][2].set_yticks(range(params['n_clusters']))
axs[1][2].set_xticklabels(params['cluster_names'], fontsize=8)
axs[1][2].set_yticklabels(params['cluster_names'], fontsize=8)
divider = make_axes_locatable(axs[1][2])
cax = divider.append_axes('right', size='10%', pad=0.05)
cbar = fig.colorbar(im, cax=cax, orientation='vertical', ticks=[])
axs[0][0].plot(losses_vae[:i + 1])
axs[0][0].set_title('VAE Loss')
axs[0][0].set_xlabel('epochs')
axs[0][1].plot(homo_plot[:i + 1])
axs[0][1].set_title('Homogeneity')
axs[0][1].set_xlabel('epochs')
axs[0][1].set_ylim(0, 1)
axs[0][2].plot(ari_plot[:i + 1])
axs[0][2].set_title('ARI')
axs[0][2].set_xlabel('epochs')
axs[0][2].set_ylim(0, 1)
axs[0][3].plot(nmi_plot[:i + 1])
axs[0][3].set_title('NMI')
axs[0][3].set_xlabel('epochs')
axs[0][3].set_ylim(0, 1)
#reconstructed_cell = ConvAE.vae.predict(x_val[:1, ...])[0, ..., 0]
cell_tile = x_val[0, ..., 0]
cell_tile = cell_tile[:, :64]
x_recon = x_recon[0, ..., 0]
reconstructed_cell_tile = x_recon[:, :64]
reconstructed_cell_tile = np.flipud(reconstructed_cell_tile)
cell_heatmap = np.vstack((cell_tile, reconstructed_cell_tile))
axs[1][3].imshow(cell_heatmap, cmap='Reds')
axs[1][3].set_xticks([])
axs[1][3].set_yticks([])
axs[1][3].spines['right'].set_visible(False)
axs[1][3].spines['top'].set_visible(False)
axs[1][3].spines['left'].set_visible(False)
axs[1][3].spines['bottom'].set_visible(False)
# get eigenvalues and eigenvectors
scale = get_scale(embedding, params['batch_size'], params['scale_nbr'])
values, vectors = spectral_clustering(embedding, scale,
params['n_nbrs'],
params['affinity'])
# sort, then store the top n_clusters=2
values_idx = np.argsort(values)
x_spectral_clustering = vectors[:, values_idx[:params['n_clusters']]]
# do kmeans clustering in this subspace
y_spectral_clustering = KMeans(
n_clusters=params['n_clusters']).fit_predict(
vectors[:, values_idx[:params['n_clusters']]])
tsne = manifold.TSNE(n_components=2, init='pca', random_state=0)
Z_tsne = tsne.fit_transform(x_spectral_clustering)
sc = axs[2][0].scatter(Z_tsne[:, 0],
Z_tsne[:, 1],
s=2,
c=y_train_unlabeled,
cmap=plt.cm.get_cmap("jet", 14))
axs[2][0].set_title('Spectral Clusters (t-SNE) True Labels')
axs[2][0].set_xlabel('t-SNE 1')
axs[2][0].set_ylabel('t-SNE 2')
axs[2][0].set_xticks([])
axs[2][0].set_yticks([])
axs[2][0].spines['right'].set_visible(False)
axs[2][0].spines['top'].set_visible(False)
reducer = umap.UMAP(transform_seed=36, random_state=36)
matrix_reduce = reducer.fit_transform(x_spectral_clustering)
axs[2][1].scatter(matrix_reduce[:, 0],
matrix_reduce[:, 1],
s=2,
c=y_spectral_clustering,
cmap=plt.cm.get_cmap("jet", 14))
axs[2][1].set_title('Spectral Clusters (UMAP)')
axs[2][1].set_xlabel('UMAP 1')
axs[2][1].set_ylabel('UMAP 2')
axs[2][1].set_xticks([])
axs[2][1].set_yticks([])
# Hide the right and top spines
axs[2][1].spines['right'].set_visible(False)
axs[2][1].spines['top'].set_visible(False)
axs[2][2].scatter(matrix_reduce[:, 0],
matrix_reduce[:, 1],
s=2,
c=y_train_unlabeled,
cmap=plt.cm.get_cmap("jet", 14))
axs[2][2].set_title('True Labels (UMAP)')
axs[2][2].set_xlabel('UMAP 1')
axs[2][2].set_ylabel('UMAP 2')
axs[2][2].set_xticks([])
axs[2][2].set_yticks([])
# Hide the right and top spines
axs[2][2].spines['right'].set_visible(False)
axs[2][2].spines['top'].set_visible(False)
axs[2][3].hist(x_spectral_clustering)
axs[2][3].set_title("histogram of true eigenvectors")
train_time = str(
datetime.timedelta(seconds=(int(time.time() - start_time))))
n_matrices = (i + 1) * params['batch_size'] * 100
fig.suptitle('Trained on ' + '{:,}'.format(n_matrices) + ' cells\n' +
train_time)
plt.savefig('vae/%d.png' % i)
plt.close()
plt.close()
if i > 1:
if np.abs(losses_vae[i] - losses_vae[i - 1]) < 0.0001:
print('STOPPING EARLY')
break
print("finished training")
plt.plot(losses_vae)
plt.title('VAE Loss')
plt.show()
x_val_y = ConvAE.vae.predict(x_val)[2]
# x_val_y = ConvAE.classfier.predict(x_val_lp)
y_sp = x_val_y.argmax(axis=1)
print_accuracy(y_sp, y_val, params['n_clusters'])
from sklearn.metrics import normalized_mutual_info_score as nmi
y_val = np.squeeze(np.asarray(y_val).ravel()) # squeeze into 1D array
print(y_sp.shape, y_val.shape)
nmi_score1 = nmi(y_sp, y_val)
print('NMI: ' + str(np.round(nmi_score1, 4)))
embedding = ConvAE.encoder.predict(x_val)
tsne = manifold.TSNE(n_components=2, init='pca', random_state=0)
Z_tsne = tsne.fit_transform(embedding)
fig = plt.figure()
plt.scatter(Z_tsne[:, 0],
Z_tsne[:, 1],
s=2,
c=y_train_unlabeled,
cmap=plt.cm.get_cmap("jet", 14))
plt.colorbar(ticks=range(params['n_clusters']))
plt.show()
def process(x_spectralnet, y_spectralnet, data, params):
# UNPACK DATA
x_train, y_train, x_val, y_val, x_test, y_test = data['spectral'][
'train_and_test']
# concatenate
x = np.concatenate([x_train, x_val, x_test], axis=0)
y = np.concatenate([y_train, y_val, y_test], axis=0)
# PERFORM SPECTRAL CLUSTERING ON DATA
# get eigenvalues and eigenvectors
scale = get_scale(x, params['batch_size'], params['scale_nbr'])
values, vectors = spectral_clustering(x, scale, params['n_nbrs'],
params['affinity'])
# sort, then store the top n_clusters=2
values_idx = np.argsort(values)
x_spectral_clustering = vectors[:, values_idx[:params['n_clusters']]]
# do kmeans clustering in this subspace
y_spectral_clustering = KMeans(
n_clusters=params['n_clusters']).fit_predict(
vectors[:, values_idx[:params['n_clusters']]])
# PLOT RESULTS
# plot spectral net clustering
fig2 = plt.figure()
if x.shape[1] == 2:
ax1 = fig2.add_subplot(311)
ax1.scatter(x[:, 0],
x[:, 1],
alpha=0.5,
s=20,
cmap='rainbow',
c=y_spectralnet,
lw=0)
ax1.set_title("x colored by net prediction")
# plot spectral clustering clusters
if x.shape[1] == 2:
ax2 = fig2.add_subplot(313)
ax2.scatter(x[:, 0],
x[:, 1],
alpha=0.5,
s=20,
cmap='rainbow',
c=y_spectral_clustering,
lw=0)
ax2.set_title("x colored by spectral clustering")
# plot histogram of eigenvectors
fig3 = plt.figure()
ax1 = fig3.add_subplot(212)
ax1.hist(x_spectral_clustering)
ax1.set_title("histogram of true eigenvectors")
ax2 = fig3.add_subplot(211)
ax2.hist(x_spectralnet)
ax2.set_title("histogram of net outputs")
# plot eigenvectors
y_idx = np.argsort(y)
fig4 = plt.figure()
ax1 = fig4.add_subplot(212)
ax1.plot(x_spectral_clustering[y_idx])
ax1.set_title("plot of true eigenvectors")
ax2 = fig4.add_subplot(211)
ax2.plot(x_spectralnet[y_idx])
ax2.set_title("plot of net outputs")
plt.draw()
plt.show()