def do_clustering(reduced_data, pca_samples):
range_n_clusters = [2, 3, 4, 5, 6]
best_score = 0
best_cluster_size = 0
for num_clusters in range_n_clusters:
# Apply your unsupervised algorithm of choice to the reduced data
clusterer = KMeans(n_clusters=num_clusters)
clusterer.fit(reduced_data)
# Predict the cluster for each data point
preds = clusterer.predict(reduced_data)
# Find the cluster centers (or means for GMM)
centers = clusterer.cluster_centers_
# Predict the cluster for each transformed sample data point
sample_preds = clusterer.predict(pca_samples)
# Calculate the mean silhouette coefficient for the number of clusters chosen
score = silhouette_score(reduced_data, preds)
if score > best_score:
best_score = score
best_cluster_size = num_clusters
print "Silhouette score for", num_clusters, "clusters =", score
print "Best cluster size = ", best_cluster_size
# re-run the unsupervised with a specific number of clusters
clusterer = KMeans(n_clusters=best_cluster_size)
clusterer.fit(reduced_data)
preds = clusterer.predict(reduced_data)
centers = clusterer.cluster_centers_
sample_preds = clusterer.predict(pca_samples)
# Display the results of the unsupervised from implementation
rs.cluster_results(reduced_data, preds, centers, pca_samples)
# Display the predictions
for i, pred in enumerate(sample_preds):
print "Sample point", i, "predicted to be in Cluster", pred
return centers
def do_clustering(reduced_data, pca_samples): range_n_clusters = [2, 3, 4, 5, 6] best_score = 0 best_cluster_size = 0 for num_clusters in range_n_clusters: # Apply your unsupervised algorithm of choice to the reduced data clusterer = KMeans(n_clusters=num_clusters) clusterer.fit(reduced_data) # Predict the cluster for each data point preds = clusterer.predict(reduced_data) # Find the cluster centers (or means for GMM) centers = clusterer.cluster_centers_ # Predict the cluster for each transformed sample data point sample_preds = clusterer.predict(pca_samples) # Calculate the mean silhouette coefficient for the number of clusters chosen score = silhouette_score(reduced_data, preds) if score > best_score: best_score= score best_cluster_size = num_clusters print "Silhouette score for" , num_clusters, "clusters =", score print "Best cluster size = ", best_cluster_size # re-run the unsupervised with a specific number of clusters clusterer = KMeans(n_clusters=best_cluster_size) clusterer.fit(reduced_data) preds = clusterer.predict(reduced_data) centers = clusterer.cluster_centers_ sample_preds = clusterer.predict(pca_samples) # Display the results of the unsupervised from implementation rs.cluster_results(reduced_data, preds, centers, pca_samples) # Display the predictions for i, pred in enumerate(sample_preds): print "Sample point", i, "predicted to be in Cluster", pred return centers
# TODO: Calculate the mean silhouette coefficient for the number of clusters chosen
scores_K_n += [metrics.silhouette_score(kp,preds_K)]
scores_G_n += [metrics.silhouette_score(kp,preds_G)]
#print n, scores_K_n
scores_K += [np.average(scores_K_n)]
scores_G += [np.average(scores_G_n)]
print pd.DataFrame(data={'Kmeans':scores_K,'GMM':scores_G},index=n_range)
plt.plot(n_range,scores_K)
plt.plot(n_range,scores_G)
plt.legend(['KMeans','GMM'])
plt.show()
#clusterer = GMM(n_components=12)
clusterer = KMeans(n_clusters=n_range[np.argmax(scores_K)])
preds = clusterer.fit_predict(kp)
#centers = clusterer.means_
centers = clusterer.cluster_centers_
#print clusterer.weights_
rs.cluster_results(kp,preds,centers,np.asarray([(0,0)]))
cv2.imwrite('sift_keypoints.jpg',image)
#cv2.imshow('keypoints',image)
plt.show()
for j in range(n_cl):
ix = preds==j
pl.scatter(reduced_data.ix[ix,0], reduced_data.ix[ix,1], color=clr[j])
pl.plot(centers[0,0], centers[0,1], 'yo', markersize=20)
pl.plot(centers[1,0], centers[1,1], 'go', markersize=20)
pl.xlabel('PC1');
pl.ylabel('PC2');
pl.axhline(0, color='k', linestyle='--');
pl.axvline(0, color='k', linestyle='--');
# TODO: Calculate the mean silhouette coefficient for the number of clusters chosen
score_opt = silhouette_score(reduced_data, clf.labels_)
print "Score (# clusters = %i) = %1.2f" % (n_cl, score_opt)
# Display the results of the clustering from implementation
rs.cluster_results(reduced_data, preds, centers, pca_samples)
# --------------------------------
# GMM
# --------------------------------
from sklearn import mixture
clfGMM = mixture.GMM(n_components=2,covariance_type='full')
aicGMM = np.zeros_like(score)
bicGMM = np.zeros_like(score)
scoreGMM = np.zeros_like(score)
for i, n_cl in enumerate(n_clusters):
print "Fitting with # clusters = %i" % n_cl
clfGMM = mixture.GMM(n_components=n_cl, covariance_type='full')
clfGMM.fit(reduced_data)
scores = []
for x in range(2, 4):
gmm = GMM(n_components=x)
clusterer = gmm.fit(reduced_data)
preds = clusterer.predict(reduced_data)
centers = clusterer.means_
score = silhouette_score(reduced_data, preds)
scores.append(score)
print scores
# Display the results of the clustering from implementation
rs.cluster_results(reduced_data, preds, centers)
plt.show()
# Inverse transform the centers
log_centers = pca.inverse_transform(centers)
# Exponentiate the centers
true_centers = np.exp(log_centers)
# Display the true centers
segments = ['Segment {}'.format(i) for i in range(0, len(centers))]
true_centers = pd.DataFrame(np.round(true_centers), columns=data.keys())
true_centers.index = segments
true_centers = true_centers.append(data.describe().loc['50%'])
true_centers = true_centers.append(data.describe().loc['mean'])