def create_splits(self, X):
# get shape of dataset
N, D = X.shape
# thresholds is set of K-Means of each feature
self.thresholds = []
for d in range(D):
# reshape (n,) to (n,1)
feature = X[:, d]
feature = np.reshape(feature, [feature.size, 1])
# Initialize K-Means model
k_means = Kmeans(k=k)
min_err = np.inf
min_err_means = None
for i in range(50):
k_means.fit(feature)
error = k_means.error(feature)
if error < min_err:
min_err = error
min_err_means = k_means.means
self.thresholds.append(min_err_means)
def closure_1_3_1():
k = 4
best_model = None
min_error = np.inf
for i in range(50):
model = Kmeans(k)
model.fit(X)
error = model.error(X)
if error < min_error:
min_error = error
best_model = model
plt.figure()
utils.plot_2dclustering(X, best_model.predict(X))
fname = os.path.join("..", "figs",
"kmeans_outliers_best_model.png")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
def closure_1_3_2():
minErrs = []
for k in range(1, 11):
best_model = None
min_error = np.inf
for i in range(50):
model = Kmeans(k)
model.fit(X)
error = model.error(X)
if error < min_error:
min_error = error
best_model = model
minErrs.append(min_error)
plt.figure()
plt.plot(list(range(1, 11)), minErrs)
plt.xlabel('k')
plt.ylabel('Error')
plt.title('k-means training error as k increases')
fname = os.path.join("..", "figs", "kmeans_err_k_outliers.png")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
fname = os.path.join("..", "figs", "kmeans_basic.png")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
if question == '1.1':
X = utils.load_dataset('clusterData')['X']
# part 1: implement kmeans.error
# part 2: get clustering with lowest error out of 50 random initialization
best_model = None
min_error = np.inf
for i in range(50):
model = Kmeans(k=4)
model.fit(X)
error = model.error(X)
if error < min_error:
min_error = error
best_model = model
utils.plot_2dclustering(X, best_model.predict(X))
fname = os.path.join("..", "figs", "kmeans_50_inits.png")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
if question == '1.2':
# part 3: plot min error across 50 random inits, as k is varied from 1 to 10
X = utils.load_dataset('clusterData')['X']
model.fit(X)
y = model.predict(X)
plt.scatter(X[:, 0], X[:, 1], c=y, cmap="jet")
fname = os.path.join("..", "figs", "kmeans_basic.png")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
elif question == '5.1':
X = load_dataset('clusterData.pkl')['X']
model = Kmeans(k=4)
low = model.error(X)
for i in range(49):
new_model = Kmeans(k=4)
err = new_model.error(X)
if err < low:
model = new_model
low = err
utils.plot_2dclustering(X, model['predict'](model, X))
print("Displaying figure...")
plt.title("K-Means on clusterData")
plt.show()
elif question == '5.2':
X = load_dataset('clusterData.pkl')['X']
elif question == '5.3':
X = load_dataset('clusterData2.pkl')['X']
plt.xlabel("Random clustering k=4")
fname = os.path.join("..", "figs", "1.png")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
if question == '1.1':
X = utils.load_dataset('clusterData')['X']
models = []
errors = np.zeros(50)
for i in range(0, 50):
model = Kmeans(k=4)
model.fit(X)
models.append(model)
errors[i] = model.error(X)
model = models.pop(np.argmin(errors))
utils.plot_2dclustering(X, model.predict(X))
plt.xlabel("Best of 50 clusterings k=4")
fname = os.path.join("..", "figs", "1.1.png")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
if question == '1.2':
X = utils.load_dataset('clusterData')['X']
k = np.arange(0, 12)
min_errors = np.zeros(k.size)
for kk in k:
models = []
plot_2dclustering(X, model.predict(X))
fname = os.path.join("..", "figs", "kmeans_basic.png")
# plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
elif question == '3.1':
X = load_dataset('clusterData.pkl')['X']
error = float('inf')
model = Kmeans(k=4)
model.fit(X)
error = model.error(X)
for i in range(49):
model_2 = Kmeans(k=4)
model_2.fit(X)
if model_2.error(X) < error:
model = model_2
plot_2dclustering(X, model.predict(X))
fname = os.path.join("..", "figs", "kmeans_3_1.png")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
elif question == '3.2':
X = load_dataset('clusterData.pkl')['X']
errors = np.ones([10, ]) * -1
for i in range(50):
kVal = random.randint(1, 10)
model = Kmeans(k=kVal)
model.fit(X)
error = model.error(X)
