def clustering(the_image_autoencoded, the_image_shape, number_of_clusters, extra_parameters=""):
print()
print("*** Mean-Shift clustering ***")
print("---------------------------------")
# https://towardsdatascience.com/the-5-clustering-algorithms-data-scientists-need-to-know-a36d136ef68
# https://scikit-learn.org/stable/modules/generated/sklearn.cluster.MeanShift.html
print("Image shape: ", the_image_shape)
# print("Creating dataframe")
# df = DataFrame(data=the_image_autoencoded)
print("Running fit function for mean-shift clustering")
clust = MeanShift(bandwidth=2).fit(the_image_autoencoded)
print("Creating list for clustered data")
clustered_data = np.zeros((the_image_shape[0], the_image_shape[1]))
print("Clustered data shape: ", np.shape(clustered_data))
x = 0
y = 0
for i in range(the_image_shape[0] * the_image_shape[1]):
clustered_data[y, x] = clust.labels_[i]
x = x + 1
if x == the_image_shape[1]:
x = 0
y = y + 1
# Parameters start
print("Parameters for this estimation: ", clust.get_params())
label_min = 1
label_max = 0
for i in range(np.shape(clustered_data)[0] * np.shape(clustered_data)[1]):
if clust.labels_[i] > label_max:
label_max = clust.labels_[i]
if clust.labels_[i] < label_min:
label_min = clust.labels_[i]
print("Labels from", label_min, " ,to", label_max, ". Number of labels: ", label_max - label_min)
# Parameters stop
return clustered_data
def _mean_shift(table,
input_cols,
prediction_col='prediction',
bandwidth=None,
bin_seeding=False,
min_bin_freq=1,
cluster_all=True):
inputarr = table[input_cols]
ms = MeanShift(bandwidth=bandwidth,
bin_seeding=bin_seeding,
min_bin_freq=min_bin_freq,
cluster_all=cluster_all,
n_jobs=1)
ms.fit(inputarr)
label_name = {
'bandwidth': 'Bandwidth',
'bin_seeding': 'Bin Seeding',
'min_bin_freq': 'Minimum Bin Frequency',
'cluster_all': 'Cluster All'
}
get_param = ms.get_params()
param_table = pd.DataFrame.from_items(
[['Parameter', list(label_name.values())],
['Value', [get_param[x] for x in list(label_name.keys())]]])
cluster_centers = ms.cluster_centers_
n_clusters = len(cluster_centers)
colors = cm.nipy_spectral(np.arange(n_clusters).astype(float) / n_clusters)
labels = ms.labels_
if len(input_cols) > 1:
pca2_model = PCA(n_components=2).fit(inputarr)
pca2 = pca2_model.transform(inputarr)
fig_centers = _mean_shift_centers_plot(input_cols, cluster_centers, colors)
fig_samples = _mean_shift_samples_plot(
table, input_cols, 100, cluster_centers,
colors) if len(table.index) > 100 else _mean_shift_samples_plot(
table, input_cols, None, cluster_centers, colors)
if len(input_cols) > 1:
fig_pca = _mean_shift_pca_plot(labels, cluster_centers, pca2_model,
pca2, colors)
rb = BrtcReprBuilder()
rb.addMD(
strip_margin("""
| ## Mean Shift Result
| - Coordinates of cluster centers
| {fig_cluster_centers}
| - Samples
| {fig_pca}
| {fig_samples}
| ### Parameters
| {params}
""".format(fig_cluster_centers=fig_centers,
fig_pca=fig_pca,
fig_samples=fig_samples,
params=pandasDF2MD(param_table))))
else:
rb = BrtcReprBuilder()
rb.addMD(
strip_margin("""
| ## Mean Shift Result
| - Coordinates of cluster centers
| {fig_cluster_centers}
| - Samples
| {fig_samples}
| ### Parameters
| {params}
""".format(fig_cluster_centers=fig_centers,
fig_samples=fig_samples,
params=pandasDF2MD(param_table))))
model = _model_dict('mean_shift')
model['model'] = ms
model['input_cols'] = input_cols
model['_repr_brtc_'] = rb.get()
out_table = table.copy()
out_table[prediction_col] = labels
return {'out_table': out_table, 'model': model}
print("Clustered data shape: ", np.shape(clustered_data))
x = 0
y = 0
for i in range(np.shape(clustered_data)[0] * np.shape(clustered_data)[1]):
clustered_data[x][y] = clust.labels_[i]
x = x + 1
if x == 100:
x = 0
y = y + 1
plt.imshow(clustered_data)
name = img_dir + 'img_mean_shift_clustering.png'
plt.savefig(name, bbox_inches='tight')
print("Parameters for this estimation: ", clust.get_params())
label_min = 1
label_max = 0
for i in range(np.shape(clustered_data)[0] * np.shape(clustered_data)[1]):
if clust.labels_[i] > label_max:
label_max = clust.labels_[i]
if clust.labels_[i] < label_min:
label_min = clust.labels_[i]
print("Labels from", label_min, " ,to", label_max, ". Number of labels: ",
label_max - label_min)
print()
print(datetime.now().strftime('%Y-%m-%d %H:%M:%S'))
end_time = time.time()
print("End time: ", time.ctime(end_time))
print("Duration: ", int(end_time - start_time), " seconds")
