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)
min_error = -1
y = []
# size = X.shape[0]
for i in range(50):
model.fit(X)
cur_error = model.error(X)
y.append(cur_error)
if min_error == -1:
min_error = cur_error
pred = model.predict(X)
elif cur_error < min_error:
min_error = cur_error
pred = model.predict(X)
plt.scatter(X[:, 0], X[:, 1], c=pred, cmap="jet")
plt.show()
plt.plot(np.arange(1, 51), y)
plt.xlabel(r'iterations')
plt.ylabel(r'error')
plt.show()
elif question == '5.2':
elif question == '5':
X = load_dataset('clusterData.pkl')['X']
model = Kmeans(k=4)
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']
plt.scatter(X[:, 0], X[:, 1], c=y, cmap="jet")
fname = os.path.join("..", "figs", "q5_1_best_model.png")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
elif question == '5.2':
X = load_dataset('clusterData.pkl')['X']
errors = np.zeros(10)
k_s = np.array(range(1, 11))
for k in k_s:
errors_k = np.zeros(50)
for z in range(50):
model = Kmeans(k=k)
model.fit(X)
errors_k[z] = model.error(X)
errors[k - 1] = np.min(errors_k)
# save figure
plt.plot(k_s, errors)
filename = "q5_2_min_errors.pdf"
plt.xlabel("k")
plt.ylabel("Minimum error")
fname = os.path.join("..", "figs", filename)
plt.savefig(fname)
print("\nFigure saved as '%s'" % filename)
elif question == '5.3':
X = load_dataset('clusterData2.pkl')['X']
model = Kmeans(k=4)
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)
min_error = 9999999
min_model = None
for i in range(0, 50):
model = Kmeans(4)
model.fit(X)
error = model.error(X)
if error < min_error:
min_model = model
min_error = error
print("Minimum error: " + str(min_error))
plt.scatter(X[:, 0], X[:, 1], c=min_model.predict(X))
fname = os.path.join("..", "figs", "kmeans_good.png")
plt.savefig(fname)
print("Figure saved as ", fname)
elif question == '5.1':
X = load_dataset('clusterData.pkl')['X']
elif question == '5.2':
X = load_dataset('clusterData.pkl')['X']
model = Kmeans(k=4)
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']
# for the first question: print the error of the final clustering model
model = Kmeans(k=4)
model.fit(X)
dist_error_final = model.error(X)
print(dist_error_final)
# for the third question: print the figure with the lowest error
model_best = None
error_minimum = np.inf
for i in range(50):
model = Kmeans(4)
model.fit(X)
error_minimum = np.inf
error = model.error(X)
if error <= error_minimum:
error_minimum = error
model_best = model
y = model_best.predict(X)
plt.scatter(X[:, 0], X[:, 1], c=y, cmap="jet")
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']
min_err = np.inf
for i in range(50):
model = Kmeans(k=4)
model.fit(X)
y = model.predict(X)
err = model.error(X)
if (err < min_err):
min_err = err
plt.scatter(X[:, 0], X[:, 1], c=y, cmap="jet")
fname = os.path.join("..", "figs", "kmeans_basic.png")
plt.savefig(fname)
print("K-means minimum error: %.3f" % min_err)
# used to output error during fitting
# model = Kmeans(k=4)
# model.fit(X)
# y = model.predict(X)
# err = model.error(X)
# print("K-means error: %.3f" % err)
