ax.scatter(Z[:,0], Z[:,1])
plt.ylabel('z2')
plt.xlabel('z1')
plt.title('MDS')
for i in range(n):
ax.annotate(animals[i], (Z[i,0], Z[i,1]))
utils.savefig('MDS_animals.png')
elif question == '4.1':
dataset = load_dataset('animals.pkl')
X = dataset['X'].astype(float)
animals = dataset['animals']
n,d = X.shape
for n_neighbours in [2,3]:
#for n_neighbours in range(n):
model = ISOMAP(n_components=2,
n_neighbours=n_neighbours) # TODO: finish implementing this class
Z = model.compress(X)
fig, ax = plt.subplots()
ax.scatter(Z[:,0], Z[:,1])
plt.ylabel('z2')
plt.xlabel('z1')
plt.title('ISOMAP with NN=%d' % n_neighbours)
for i in range(n):
ax.annotate(animals[i], (Z[i,0], Z[i,1]))
utils.savefig('ISOMAP%d_animals.png' % n_neighbours)
else:
print("Unknown question: %s" % question)
fig, ax = plt.subplots()
ax.scatter(Z[:, 0], Z[:, 1])
plt.ylabel('z2')
plt.xlabel('z1')
plt.title('MDS')
for i in range(n):
ax.annotate(animals[i], (Z[i, 0], Z[i, 1]))
utils.savefig('MDS_animals.png')
elif question == '4.1':
dataset = load_dataset('animals.pkl')
X = dataset['X'].astype(float)
animals = dataset['animals']
n, d = X.shape
for n_neighbours in [2, 3]:
model = ISOMAP(n_components=2, n_neighbours=n_neighbours)
Z = model.compress(X)
fig, ax = plt.subplots()
ax.scatter(Z[:, 0], Z[:, 1])
plt.ylabel('z2')
plt.xlabel('z1')
plt.title('ISOMAP with NN=%d' % n_neighbours)
for i in range(n):
ax.annotate(animals[i], (Z[i, 0], Z[i, 1]))
utils.savefig('ISOMAP%d_animals.png' % n_neighbours)
else:
print("Unknown question: %s" % question)
X = data.values
names = X[:,0]
# get rid of country names
X = X[:,1:]
X = np.array(X).astype(np.float32)
X[X<=0] = 1.
X[np.isnan(X)] = 1.
X[np.isinf(X)] = 1.
X = np.log(X)
#X = X / X.max()
n,d = X.shape
print("n =", n)
print("d =", d)
for n_neighbours in [2,3]:
model = ISOMAP(n_components=2, n_neighbours=n_neighbours)
Z = model.compress(X)
fig, ax = plt.subplots()
ax.scatter(Z[:,0], Z[:,1])
plt.ylabel('z2')
plt.xlabel('z1')
plt.title('ISOMAP with NN=%d' % n_neighbours)
for i in range(n):
ax.annotate(names[i], (Z[i,0], Z[i,1]))
utils.savefig('ISOMAP%d_animals.png' % n_neighbours)
#pca = PCA(n_components = 2)
#pca.fit(X)
#pcaTransform = pca.transform(X)
#f1 = pcaTransform[:, 0]
#f2 = pcaTransform[:, 1] #np.random.choice(d, size=2, replace=False)
#print(pca.singular_values_)
