def create_sprite(config, df):
images_array = [
Tools.read_np_picture(os.path.join(
config.get('directory')['collections'], "%s.jpg" % picture_id),
target_size=(TARGET_SIZE_HEIGHT,
TARGET_SIZE_WIDTH))
for picture_id in df['pictures_id']
]
sprite = np.zeros((TARGET_SIZE_HEIGHT * SPRITE_NB_LIGNE,
TARGET_SIZE_WIDTH * SPRITE_NB_COLONNE, 3))
index = 0
for i in range(SPRITE_NB_LIGNE):
for j in range(SPRITE_NB_COLONNE):
sprite[(i * TARGET_SIZE_HEIGHT):(i + 1) * TARGET_SIZE_HEIGHT,
(j * TARGET_SIZE_WIDTH):(j + 1) *
TARGET_SIZE_WIDTH, :] = images_array[index]
index += 1
if index >= len(images_array):
break
if index >= len(images_array):
break
img = Tools.display_one_picture(sprite)
return img
def plot_mosaics(config, clustering_type, clustering, output_image_width,
output_image_height, mosaic_nrow, mosaic_ncol_max):
"""
Mosaic of each cluster
"""
clusters_id = np.unique(clustering.final_labels)
clustering_res = clustering.get_results()
for cluster_id in clusters_id:
cluster_image_filenames = [
os.path.join(
config.get('directory')['collections'], "%s.jpg" % one_res[0])
for one_res in clustering_res if one_res[1] == cluster_id
]
images_array = [
Tools.read_np_picture(img_filename,
target_size=(output_image_height,
output_image_width))
for img_filename in cluster_image_filenames
]
img = Tools.display_mosaic(images_array,
nrow=mosaic_nrow,
ncol_max=mosaic_ncol_max)
img.save(
os.path.join(clustering.save_directory,
"cluster_%s.png" % str(cluster_id).zfill(2)), "PNG")
return clusters_id
def create_poster_picture(config, poster_config, poster, pictures_df):
pictures_id_positions = []
for part in poster_config['DECOUPAGE']:
picture_id = None
directory = config.get('directory')['collections']
if 'directory' in part.keys() and part['directory']:
directory = os.path.join(
config.get('directory')['project_dir'], part['directory'])
if part['cluster']:
selection = pictures_df.loc[pictures_df.label.isin(
part['cluster'])].sample(1)
pictures_df = pictures_df.drop(selection.index)
picture_id = selection.pictures_id.values[0]
else:
picture_id = random.choice(part['picture_ids'])
pictures_id_positions.append({
'pictures_id': picture_id,
'position': part['position']
})
if part['size'][0] < O_WIDTH or part['size'][1] < O_HEIGHT:
part_array = Tools.read_np_picture(os.path.join(
directory, "%s.jpg" % picture_id),
target_size=(O_HEIGHT, O_WIDTH))
index_col = np.floor((O_WIDTH - part['size'][0]) / 2).astype(int)
index_row = np.floor((O_HEIGHT - part['size'][1]) / 2).astype(int)
part_array = part_array[index_col:(index_col + part['size'][1]),
index_row:(index_row +
part['size'][0]), :].copy()
else:
part_array = Tools.read_np_picture(
os.path.join(directory, "%s.jpg" % picture_id),
target_size=(part['size'][1], part['size'][0]))
poster[part['origin'][1]:(part['origin'][1] + part['size'][1]),
part['origin'][0]:(part['origin'][0] +
part['size'][0]), :] = part_array
return poster, pictures_id_positions
#%% [markdown]
# ## Visualisation des clusters
#%%
def select_cluster(clustering, id_cluster):
return [os.path.join('data/processed/models/autoencoder/train/k/', res[0] + '.jpg') for res in clustering.get_zip_results() if res[2] == id_cluster]
#%%
from IPython.display import Image
#%%
for cl in range(0,19):
print("Cluster %s" % (cl))
res_tmp = select_cluster(clustering, cl)
print(len(res_tmp))
image_array = [Tools.read_np_picture(f, target_size = (54, 96)) for f in res_tmp[:100]]
# img = Tools.display_mosaic(image_array, nrow = 10)
# fig = plt.figure(1, figsize=(12, 7))
# plt.imshow(img, aspect = 'auto')
# plt.show()
#%% [markdown]
# ## Zoom sur le cluster 0
#%%
res_tmp = select_cluster(clustering, 1)
#%%
print(len(res_tmp))
image_array = [Tools.read_np_picture(f, target_size = (54, 96)) for f in res_tmp]
#%%[markdown]
# # Graphiques
#%%
def select_cluster(clustering, id_cluster):
return [os.path.join('data/processed/models/autoencoder/train/k/', res[0] + '.jpg') for res in clustering.get_zip_results() if res[2] == id_cluster]
#%%
for cl in np.unique(clustering.kmeans_labels):
print("Cluster %s" % (cl))
res_tmp = select_cluster(clustering, cl)
if len(res_tmp) >= 0:
print(len(res_tmp))
image_array = [Tools.read_np_picture(f, target_size = (54, 96)) for f in res_tmp[:100]]
img = Tools.display_mosaic(image_array, nrow = 10)
fig = plt.figure(1, figsize=(12, 7))
plt.imshow(img, aspect = 'auto')
plt.show()
#%% [markdown]
# ## faut essayer de faire des paquets
#%%
from sklearn.manifold import TSNE
output_tnse = TSNE(n_components=2).fit_transform(clustering.pca_reduction)
#%%
def run_plots(config, clustering_type, clustering):
"""
Plots specifics graphs
"""
if clustering_type in ['classical']:
## Graphs of PCA and final clusters
fig, ax = plt.subplots(figsize=(24, 14))
scatter = ax.scatter(clustering.pca_reduction[:, 0],
clustering.pca_reduction[:, 1],
c=clustering.colors)
legend1 = ax.legend(*scatter.legend_elements(),
loc="lower left",
title="Classes")
ax.add_artist(legend1)
plt.savefig(os.path.join(clustering.save_directory,
'pca_clusters.png'))
if clustering_type in ['classical']:
## Graphs of TSNE and final clusters
fig, ax = plt.subplots(figsize=(24, 14))
classes = clustering.final_labels
scatter = ax.scatter(clustering.tsne_embedding[:, 0],
clustering.tsne_embedding[:, 1],
c=clustering.colors)
legend1 = ax.legend(*scatter.legend_elements(),
loc="lower left",
title="Classes")
ax.add_artist(legend1)
plt.savefig(
os.path.join(clustering.save_directory, 'tsne_clusters.png'))
if clustering_type in ['n2d', 'dbscan']:
## Graphs of TSNE and final clusters
fig, ax = plt.subplots(figsize=(24, 14))
classes = clustering.final_labels
scatter = ax.scatter(clustering.umap_embedding[:, 0],
clustering.umap_embedding[:, 1],
c=clustering.colors)
legend1 = ax.legend(*scatter.legend_elements(),
loc="lower left",
title="Classes")
ax.add_artist(legend1)
plt.savefig(
os.path.join(clustering.save_directory, 'umap_clusters.png'))
if clustering_type in ['n2d', 'classical', 'dbscan']:
filenames = [
os.path.join(
config.get('directory')['collections'], "%s.jpg" % one_res[0])
for one_res in clustering.get_results()
]
images_array = [
Tools.read_np_picture(img_filename, target_size=(54, 96))
for img_filename in filenames
]
base64_images = [Tools.base64_image(img) for img in images_array]
if clustering_type in ['n2d', 'dbscan']:
x = clustering.umap_embedding[:, 0]
y = clustering.umap_embedding[:, 1]
html_file = 'umap_bokeh.html'
title = 'UMAP projection of iss clusters'
elif clustering_type == 'classical':
x = clustering.tsne_embedding[:, 0]
y = clustering.tsne_embedding[:, 1]
html_file = 'tsne_bokeh.html'
title = 't-SNE projection of iss clusters'
df = pd.DataFrame({'x': x, 'y': y})
df['image'] = base64_images
df['label'] = clustering.final_labels.astype(str)
df['color'] = df['label'].apply(Tools.get_color_from_label)
datasource = ColumnDataSource(df)
output_file(os.path.join(clustering.save_directory, html_file))
plot_figure = figure(
title=title,
# plot_width=1200,
# plot_height=1200,
tools=('pan, wheel_zoom, reset'))
plot_figure.add_tools(
HoverTool(tooltips="""
<div>
<div>
<img src='@image' style='float: left; margin: 5px 5px 5px 5px'/>
</div>
<div>
<span style='font-size: 16px'>Cluster:</span>
<span style='font-size: 18px'>@label</span>
</div>
</div>
"""))
plot_figure.circle('x',
'y',
source=datasource,
color=dict(field='color'),
line_alpha=0.6,
fill_alpha=0.6,
size=4)
show(plot_figure)
if clustering_type in ['classical']:
## Dendogram
fig, ax = plt.subplots(figsize=(24, 14))
plt.title('Hierarchical Clustering Dendrogram')
Tools.plot_dendrogram(clustering.cah_fit, labels=clustering.cah_labels)
plt.savefig(os.path.join(clustering.save_directory, 'dendograms.png'))
return True