def run_k_means_elbow(params, x_data):
model = KMeans()
visualizer = KElbowVisualizer(model, k=(2, 40), metric='distortion')
plt.figure()
visualizer.fit(x_data)
visualizer.set_title(params['elbow_graph'])
try:
path = params['path'] + params['elbow_graph'] + '.png'
except:
path = params['elbow_graph'] + '.png'
visualizer.show(outpath=path)
def perform_elbow_method(x_scaled):
"""
Perform the elbow method to help us decide the number of clusters
:param x_scaled: Values of our data after normalization
:return: A plot of the elbow method
"""
# Instantiate the clustering model and visualizer
mpl.rcParams['xtick.labelsize'] = 12
mpl.rcParams['ytick.labelsize'] = 12
mpl.rcParams['axes.titlesize'] = 18
mpl.rcParams['axes.labelsize'] = 14
model = KMeans()
visualizer = KElbowVisualizer(model, k=(1, 12))
# Fit the data to the visualizer
visualizer.fit(x_scaled)
visualizer.set_title("The Elbow Method")
visualizer.show()
def perform_elbow_method(points, method):
"""
Perform and visualize elbow method.
:param points: the data's points
:param method: clustering method - K means or Hierarchical
:return: None
"""
if method == 'K means':
model = KMeans()
elif method == 'Hierarchical':
model = AgglomerativeClustering()
else:
raise Exception(
'This elbow method designed only for K means and Hierarchical')
visualizer = KElbowVisualizer(model, k=(1, 12))
# Fit the data to the visualizer
visualizer.fit(points)
visualizer.set_title("The Elbow Method")
visualizer.show()
def elbow_kmeans(datasetDir, flag):
all_data = datasets.load_files(datasetDir,
description=None, load_content=True, encoding='utf-8', shuffle=False)
#--------------------------------------------------------------
count_vectorizer = TfidfVectorizer(stop_words='english')
X = count_vectorizer.fit_transform(raw_documents=all_data.data)
svd = TruncatedSVD(n_components=200)
normalizer = Normalizer(copy=False)
lsa = make_pipeline(svd, normalizer)
X = lsa.fit_transform(X)
# Instantiate the clustering model and visualizer
title = "Elbow calinski_harabasz Score of Kmeans clustering"
kwargs = {'title': title}
plot_Dir = os.path.join(os.getcwd(), "elbow for kmeans")
if not (os.path.exists(plot_Dir)):
os.makedirs(plot_Dir)
filename = plot_Dir + "\\"
model = KMeans(random_state=42)
if flag == 0:
suffix = "_full.png"
if flag == 1:
suffix = "_stemming.png"
if flag == 2:
suffix = "_lemmatizing.png"
visualizer = KElbowVisualizer(
model, k=(4,30), metric='calinski_harabasz', **kwargs
)
visualizer.fit(X) # Fit the data to the visualizer
visualizer.set_title(title=title)
plt.savefig(filename + title + suffix)
plt.close()
# visualizer.show() # Finalize and render the figure
# plt.savefig(filename + title + suffix)
title = "Elbow silhouette Score of Kmeans clustering"
kwargs = {'title': title}
visualizer = KElbowVisualizer(
model, k=(4,30), metric='silhouette', **kwargs
)
visualizer.fit(X) # Fit the data to the visualizer
visualizer.set_title(title=title)
plt.savefig(filename + title + suffix)
plt.close()
# visualizer.show() # Finalize and render the figure
# plt.savefig(filename + title + suffix)
title = "Elbow distortion of Kmeans clustering"
kwargs = {'title': title}
visualizer = KElbowVisualizer(
model, k=(4,20), metric='distortion', **kwargs
)
visualizer.fit(X) # Fit the data to the visualizer
visualizer.set_title(title=title)
plt.savefig(filename + title + suffix)
plt.close()
# visualizer.show() # Finalize and render the figure
# plt.savefig(filename + title + suffix)
sil = []
for n_cluster in range(4, 30):
model = KMeans(random_state=42, n_clusters=n_cluster).fit(X)
labels = model.labels_
sil.append(silhouette_score(X, labels, metric = 'euclidean'))
# model = KMeans(random_state=42, n_clusters=n_cluster)
# Svisualizer = SilhouetteVisualizer(model)
# Svisualizer.fit(X) # Fit the data to the visualizer
# Svisualizer.poof() # Draw/show/poof the data
# plt.
plt.plot(list(range(4, 30)), sil)
plt.grid(True)
plt.savefig(filename + "sihouette" + suffix)
plt.close()
