def spectral(X, sigma, k, centroids):
"""
Ng谱聚类算法
:param X: 数据点
:param sigma: 参数
:param k: 参数
:return: accu聚类精度
"""
(n, d) = X.shape
L_sym, L = get_L(X, k, sigma)
eig, eigvec = np.linalg.eig(L_sym) # eigvec按列
# eig_index = np.argsort(eig)[1:d+1]
eig_index = np.argsort(eig)[:d] # 最小的d个特征值的索引
U = eigvec[:, eig_index]
T = np.zeros(U.shape)
for i in range(n):
for j in range(d):
T[i][j] = U[i][j] / np.linalg.norm(U[i])
Y = T
# visual(Y, k=k, sigma=sigma, save=1)
cluster = KMeans(2, 100, centroids)
cluster.fit(Y)
labels = cluster.labels
if labels[0] == 0:
n1 = 100 - sum(labels[:100])
n2 = sum(labels[100:])
else:
n1 = sum(labels[:100])
n2 = 100 - sum(labels[100:])
accu = (n1 + n2) / n
print('---------------------sigma=%.2f, k=%d, accu=%.4f' %
(sigma, k, accu))
return accu
def test_predict(self):
test_samples = [[-3, -3], [3, 3], [-1, -1], [1, 1]]
expected_predictions = [0, 1, 0, 1]
k_means = KMeans(num_clusters=self.num_clusters, seed=1)
k_means.fit(self.data)
predictions = k_means.predict(test_samples)
self.assertEqual(expected_predictions, predictions)
def cluster_newsgroups():
""" Cluster newsgroup categories. """
from kmeans import KMeans
from similarity import simMatrix
corpus, dictionary = build_dictionary(bigram=True)
tfidf = TFIDF(dictionary)
newsgroups = tfidf.vectorize(corpus)
dictionary = tfidf.dictionary
categories = sorted(corpus.keys())
N = 6
print "\n{}-Most Common Words".format(N)
for index, category in enumerate(categories):
nlargest = np.argpartition(newsgroups[index, :], -N)[-N:]
nlargest = nlargest[np.argsort(newsgroups[index, nlargest])][::-1]
print "{:>24} {}".format(category, dictionary[nlargest])
print
K = 3
km = KMeans(n_clusters=K)
km.fit(newsgroups)
labels = km.labels_
print "\nKMeans Label Assignment, K = {}".format(K)
for category, label, in zip(categories, labels):
print int(label), category
simMatrix(newsgroups).plot().show()
def _initialise_prams(self, X):
# Get initial clusters using Kmeans
kmeans = KMeans(k=self.k, max_iters=500)
kmeans.fit(X)
kmeans_preds = kmeans.predict(X)
N, col_length = X.shape
mixture_labels = np.unique(kmeans_preds)
initial_mean = np.zeros((self.k, col_length))
initial_cov = np.zeros((self.k, col_length, col_length))
initial_pi = np.zeros(self.k)
for index, mixture_label in enumerate(mixture_labels):
mixture_indices = (kmeans_preds == mixture_label)
Nk = X[mixture_indices].shape[0]
# Initial pi
initial_pi[index] = Nk / N
# Intial mean
initial_mean[index, :] = np.mean(X[mixture_indices], axis=0)
# Initial covariance
de_meaned = X[mixture_indices] - initial_mean[index, :]
initial_cov[index] = np.dot(initial_pi[index] * de_meaned.T,
de_meaned) / Nk
assert np.sum(initial_pi) == 1
return initial_pi, initial_mean, initial_cov
def __init__(self,
n_cluster: int,
data: np.ndarray,
use_kmeans: bool = False,
w: float = 0.9,
c1: float = 0.5,
c2: float = 0.3,
flag: int = 1,
weights: list = None):
index = np.random.choice(list(range(len(data))), n_cluster)
self.centroids = data[index].copy()
if use_kmeans:
kmeans = KMeans(n_cluster=n_cluster, init_pp=False)
kmeans.fit(data)
self.centroids = kmeans.centroid.copy()
self.best_position = self.centroids.copy()
self.best_score = quantization_error(self.centroids, self._predict(data), data)
self.flag=flag
if self.flag%2==1:
self.best_sse = calc_sse(self.centroids, self._predict(data), data)
else:
self.best_sse = calc_sse2(self.centroids, self._predict(data), data, weights)
self.velocity = np.zeros_like(self.centroids)
self._w = w
self._c1 = c1
self._c2 = c2
def test_whole(self):
"""
Tests the score method.
"""
X, y, centers = generate_cluster_samples()
n_samples = X.shape[0]
n_features = X.shape[1]
k = centers.shape[0]
# run N_TRIALS, pick best model
best_model = None
for i in range(N_TRIALS):
kmeans = KMeans(k, N_ITER)
kmeans.fit(X)
if best_model is None:
best_model = kmeans
elif kmeans.score(X) < best_model.score(X):
best_model = kmeans
# check sum squared errors
sum_squared_errors = best_model.score(X)
self.assertLess(sum_squared_errors / n_samples, EPS)
# compare centers to expected centers
smallest_distances = find_smallest_distances(
best_model.cluster_centers, centers)
for distance in smallest_distances:
self.assertLess(distance, EPS)
def test_fit_with_different_initial_centroids(self):
expected_labels = [0, 0, 0, 1, 1, 1]
expected_centroids = [[-1.6666667, -1.6666667], [1.6666667, 1.6666667]]
k_means = KMeans(num_clusters=self.num_clusters, seed=0)
k_means.fit(self.data)
self.assertEqual(expected_labels, k_means.labels_)
np.testing.assert_almost_equal(expected_centroids, k_means.centroids_)
def B1(pca=False):
'''
Plot WC_SSD and SC over K.
'''
K = [2, 4, 6, 8, 16, 32]
fnames = [
'digits-embedding.csv', 'digits-embedding-2467.csv',
'digits-embedding-67.csv'
]
wc_ssd_val = zeros((len(fnames), len(K)))
sc_val = zeros((len(fnames), len(K)))
for i, fname in enumerate(fnames):
X = genfromtxt(fname, delimiter=',')[:, 2:]
for j, k in enumerate(K):
kmeans = KMeans(n_clusters=k)
kmeans.fit(X)
wc_ssd_val[i, j], sc_val[i, j], _ = kmeans.get_evals()
# Plot WC_SSD
figure()
for i, fname in enumerate(fnames):
plot(K, wc_ssd_val[i], label=fname)
legend()
title('WC_SSD v.s. K')
figure()
for i, fname in enumerate(fnames):
plot(K, sc_val[i], label=fname)
legend()
title('SC v.s. K')
show()
def main2():
df = pd.read_csv('credit_card_data.csv')
df = df.fillna(df.median())
original_data = df.iloc[:, 1:].values
data = copy.deepcopy(original_data)
columns = list(df.columns)[1:] # lista naziva kolona
print(columns)
# min_max_data(df, columns)
normalizacija(data) # radimo normalizaciju nad ucitanim podacima
pca = PCA()
pca.fit(data)
# odredjujem na koliiko cu da smanjim dimenzionalnost
plt.plot(range(1, 18), pca.explained_variance_ratio_.cumsum(), marker='x', linestyle='--')
plt.xlabel('Components') # features
plt.ylabel('Variance')
plt.show()
components = 7 # vidimo iz plota
pca = PCA(n_components=components)
pca.fit(data)
scores = pca.transform(data)
# print(scores) # ima onoliko komponenti koliko smo stavili
# pokazujemo da prve dve dimenzije uticu najvise na grafik
plt.bar(range(pca.n_components_), pca.explained_variance_ratio_, color='black')
plt.xlabel('PCA components')
plt.ylabel('Variance %') # procenat koliko uticu na grafik, da tako kazemo
plt.xticks(range(pca.n_components_))
plt.show()
# dobijam optimal k = 5 za 500 prvih ucitanih
# za sve ucitane dobijam 6
# optimal_k_plot(data)
broj_klastera = 6
k_means = MyKMeans(n_clusters=broj_klastera, max_iter=100)
k_means.fit(scores, normalize=False)
klaster_indeksi = k_means.klaster_indeksi
print(klaster_indeksi)
lista_klastera_sa_originalnim_podacima = [] # lista klastera sa originalnim podacima
for i in range(broj_klastera):
lista_klastera_sa_originalnim_podacima.append([])
for i in range(len(original_data)):
lista_klastera_sa_originalnim_podacima[klaster_indeksi[i]].append(original_data[i])
# printujem osobine i stablo odlucivanja
print_descriptions(lista_klastera_sa_originalnim_podacima, columns)
# print_decision_tree(original_data, klaster_indeksi, columns)
print_clusters_description()
# iscrtavamo tacke
plot_2_D(k_means)
def cluster_newsgroups():
""" Cluster newsgroup categories. """
from kmeans import KMeans
from similarity import simMatrix
corpus, dictionary = build_dictionary(bigram=True)
tfidf = TFIDF(dictionary)
newsgroups = tfidf.vectorize(corpus)
dictionary = tfidf.dictionary
categories = sorted(corpus.keys())
N = 6
print "\n{}-Most Common Words".format(N)
for index, category in enumerate(categories):
nlargest = np.argpartition(newsgroups[index,:], -N)[-N:]
nlargest = nlargest[np.argsort(newsgroups[index,nlargest])][::-1]
print "{:>24} {}".format(category, dictionary[nlargest])
print
K = 3
km = KMeans(n_clusters=K)
km.fit(newsgroups)
labels = km.labels_
print "\nKMeans Label Assignment, K = {}".format(K)
for category, label, in zip(categories, labels):
print int(label), category
simMatrix(newsgroups).plot().show()
def test_select_initial_centroids(self):
expected_initial_centroids = [[2, 1], [-1, -2]]
k_means = KMeans(num_clusters=self.num_clusters, seed=3)
k_means.fit(self.data)
initial_centroids = k_means._select_initial_centroids(self.data)
self.assertEqual(expected_initial_centroids, initial_centroids)
self.assertEqual(self.num_clusters, len(initial_centroids))
def __init_parameters(self):
N = self.X.shape[0]
n_features = self.X.shape[1]
kmeans = KMeans(n_clusters=self.n_components, n_init=5)
kmeans.fit(self.X)
# mu, means for each component
self.means_ = kmeans.cluster_centers_
# sigma, covariances for each component
self.covariances_ = np.zeros(
[self.n_components, n_features, n_features])
# pi, weights for each component
self.weights_ = np.zeros(self.n_components)
for k in range(self.n_components):
logic = (kmeans.labels_ == k)
Nk = logic.sum()
# otherwise error
if Nk > 1:
Xk = self.X[logic]
self.covariances_[k] = np.cov(Xk.T)
self.weights_[k] = Nk / N
# gamma(Znk)
self.gamma = np.zeros([N, self.n_components])
# log_likelihood
self.lower_bound_ = -np.inf
return self
def main():
filepath = "./data/self_test.csv"
#filepath = "./data/self_test_petit.csv"
#filepath = "./data/iris.csv"
# chargement des données
data, labels = load_dataset(filepath)
# initialisation de l'objet KMeans
kmeans = KMeans(n_clusters=3,
max_iter=100,
early_stopping=True,
tol=1e-6,
display=True)
# calcule les clusters
kmeans.fit(data)
# calcule la pureté de nos clusters
score = kmeans.score(data, labels)
print("Pureté : {}".format(score))
input("Press any key to exit...")
def test06_fit_two_clusters(self):
np.random.seed(1)
model = KMeans(k=2, init=init.forgy_initialization)
data = np.array([[-1.0, 0.0], [-1.001, 0.0], [-0.999, 0.0], [0.0, 1.0],
[0.0, 0.999], [0.0, 1.001]])
model.fit(data)
self.assertEquals(model.predict(data), [1, 1, 1, 0, 0, 0])
def plot_elbow(interval, data, random_seed=None):
inertia = []
for n_clusters in interval:
clf = KMeans(k=n_clusters, init='kmeans++', random_seed=random_seed)
clf.fit(data)
inertia.append(clf.inertia)
plot_metrics(interval, inertia, 'Elbow method', 'Number of clusters (K)',
'Sum of Squared Error')
def test_fit():
test_model = KMeans(n_clust=2, random_seed=100)
test_x_train = np.array([[1, 2], [1, 4.1], [1, 0], [10, 2.1], [10, 4.1],
[10, 0]])
test_model.fit(test_x_train)
expected_classes = np.array([0, 0, 0, 1, 1, 1])
expected_centers = np.array([[1., 2.0333333], [10., 2.0666667]])
np.testing.assert_array_equal(test_model.classes, expected_classes)
np.testing.assert_allclose(test_model.centers, expected_centers)
def test_kmeans():
X = np.random.normal(size=(50, 2))
km = KMeans(nr_clusters=2)
km.fit(X)
assert km.centroids.shape[0] == 2
distances = []
for centroid in km.centroids:
distances.append(km.euclidean_distance_2d(centroid, X[-1:]))
assert km.predict(X[-1:])[0] == np.argmin(distances)
def test_fit(self):
expected_labels = [0, 0, 0, 1, 1, 1]
expected_centroids = [[-1.6666667, -1.6666667], [1.6666667, 1.6666667]]
expected_inertia = 2.6666667
k_means = KMeans(num_clusters=self.num_clusters, seed=1)
k_means.fit(self.data)
self.assertEqual(expected_labels, k_means.labels_)
np.testing.assert_almost_equal(expected_centroids, k_means.centroids_)
self.assertAlmostEqual(expected_inertia, k_means.inertia_)
def initialize(self, data):
"""
:param data: data, numpy 2-D array
"""
clf = KMeans(self.K)
clf.fit(data, 10)
self.centers = clf.get_centers()
self.weights = np.ones(self.K) / self.K
self.covariances = np.array(
[1e10 * np.eye(data.shape[1]) for _ in range(self.K)])
def main():
(X_train, y_train), (X_test, y_test) = tf.contrib.keras.datasets.mnist.load_data()
X_train = (X_train).reshape(-1, 28*28)
X_test = (X_test).reshape(-1, 28*28)
Y_train = tf.contrib.keras.utils.to_categorical(y_train)
print("Data Loaded")
model = KMeans(k=25, n_features=28*28, n_classes=10)
model.fit(X_train, Y_train)
print("final testing accuracy: %.4f" % (model.predict(X_test) == y_test).mean())
def test_manhattan_distance(self):
expected_labels = [0, 0, 0, 1, 1, 1]
expected_centroids = [[-2, -2], [2, 2]]
expected_inertia = 4
k_means = KMeans(num_clusters=self.num_clusters,
distance_function='manhattan',
seed=1)
k_means.fit(self.data)
self.assertEqual(expected_labels, k_means.labels_)
np.testing.assert_almost_equal(expected_centroids, k_means.centroids_)
self.assertAlmostEqual(expected_inertia, k_means.inertia_)
def test_gaussian_mixture(self):
pos_list, ground_truth = datasets.make_blobs(n_samples=100,
centers=[[3, 3], [-3, -3], [3, -3], [-3, 3]],
cluster_std=1, random_state=0)
kmeans = KMeans(4)
standard_kmeans = cluster.KMeans(4, random_state=0)
np.random.seed(2020)
kmeans.fit(pos_list)
standard_kmeans.fit(pos_list)
self.assertAlmostEqual(metrics.adjusted_rand_score(kmeans.labels_, ground_truth), 1.0)
self.assertAlmostEqual(kmeans.inertia_, standard_kmeans.inertia_)
def test_implementation(self):
x = np.array([[0, 0], [0, 1], [4, 0], [4, 1]])
kmeans = KMeans(2)
np.random.seed(2020)
kmeans.fit(x)
self.assertAlmostEqual(kmeans.inertia_, 1.0)
self.assertAlmostEqual(metrics.adjusted_rand_score(kmeans.labels_, [0, 0, 1, 1]), 1.0)
if np.abs(kmeans.cluster_centers_[0, 0] - 4) < 1e-5:
assert_array_almost_equal(kmeans.cluster_centers_, np.array([[4, 0.5], [0, 0.5]]))
else:
assert_array_almost_equal(kmeans.cluster_centers_, np.array([[0, 0.5], [4, 0.5]]))
def test_fit_predict(self):
data = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
model = KMeans(2)
model.fit(data)
labels = model.predict(data)
self.assertEqual(len(labels), len(data))
self.assertGreaterEqual(2, len(np.unique(labels)))
for label in labels:
self.assertTrue(
isinstance(label, np.int64) or isinstance(label, np.int32)
or isinstance(label, int))
def test05_fit_one_cluster(self):
model = KMeans(k=1, init=init.forgy_initialization)
data = np.array([[0.0, 0.0]])
model.fit(data)
self.assertEqual(model.predict(data), [0])
np_test.assert_array_equal(model.centroids, np.array([[0.0, 0.0]]))
test_points = np.array([[1.0, 0.0], [0.0, 1.0], [1.0, 1.0]])
self.assertEqual(model.predict(test_points), [0] * 3)
def plot_optimal_k(data):
plt.figure()
sum_squared_errors = []
for n_clusters in range(1, 20):
k_means = KMeans(n_clusters=n_clusters, max_iter=100)
k_means.fit(data)
sse = k_means.sum_squared_error()
sum_squared_errors.append(sse)
print(sum_squared_errors)
plt.plot(range(1, 20), sum_squared_errors)
plt.xlabel('# of clusters')
plt.ylabel('WCSSE')
plt.show()
def initialize(self, data: np.ndarray):
"""
Initializes cluster centers, weights, and covariances
:param data: data, numpy 2-D array
"""
km = KMeans(self.K)
km.fit(data)
_ = km.predict(data)
self.centers = km.get_centers()
self.weights = np.random.uniform(0, 1, (self.K, ))
self.weights = self.weights / np.sum(self.weights)
self.covariances = np.array([np.eye(data.shape[-1])] * self.K) * 10e8
def train(self, x_train):
"""Receive the input training data, then learn the model.
Parameters
----------
x_train: np.array, shape (num_samples, num_features)
Returns
-------
None
"""
self.affinity_matrix_ = self._get_affinity_matrix(x_train)
embedding_features = self._get_embedding()
kmeans = KMeans(n_clusters=self.n_clusters)
kmeans.fit(embedding_features)
self.labels_ = kmeans.labels_
def main(args):
data = load_data(Path(args.data_csv))
plt.clf()
plt.scatter(data[:, 0], data[:, 1], s=3, color='blue')
if args.algorithm == 'gmm':
gmm = GaussianMixtureModel(args.num_clusters)
gmm.fit(data)
y = gmm.predict_cluster(data)
else:
km = KMeans(args.num_clusters)
km.fit(data)
y = km.predict(data)
plt.scatter(data[:, 0], data[:, 1], c=y)
plt.show()
def main():
ds = Dataset(config)
imgs, annots = ds.open_traffic_ds(config)
dp = DataPrepper(x_data=imgs,y_data=annots)
dp.x_data_scaled,dp.y_data_scaled = dp.rescale_data(dp.x_data,dp.y_data)
km = KMeans(k=args.k,dataset=dp.y_data_scaled)
if(args.fit_avg):
km.fit_average(max_iterations=args.kmeans_iters)
if(args.save_anchors):
km.write_anchors(km.centroids)
else:
km.fit()
if(args.save_anchors):
km.write_anchors(km.centroids)
def kmeans_toy():
x, y = toy_dataset(4)
fig = Figure()
fig.ax.scatter(x[:, 0], x[:, 1], c=y)
fig.savefig('plots/toy_dataset_real_labels.png')
fig.ax.scatter(x[:, 0], x[:, 1])
fig.savefig('plots/toy_dataset.png')
n_cluster = 4
k_means = KMeans(n_cluster=n_cluster, max_iter=100, e=1e-8)
centroids, membership, i = k_means.fit(x)
assert centroids.shape == (n_cluster, 2), \
('centroids for toy dataset should be numpy array of size {} X 2'
.format(n_cluster))
assert membership.shape == (50 * n_cluster,), \
'membership for toy dataset should be a vector of size 200'
assert type(i) == int and i > 0, \
'Number of updates for toy datasets should be integer and positive'
print('[success] : kmeans clustering done on toy dataset')
print('Toy dataset K means clustering converged in {} steps'.format(i))
fig = Figure()
fig.ax.scatter(x[:, 0], x[:, 1], c=membership)
fig.ax.scatter(centroids[:, 0], centroids[:, 1], c='red')
fig.savefig('plots/toy_dataset_predicted_labels.png')
np.savez('results/k_means_toy.npz',
centroids=centroids,
step=i,
membership=membership,
y=y)
def main(args):
df = pd.read_csv(args.data_csv)
data = np.array(df[['X', 'Y']])
plt.clf()
plt.scatter(data[:, 0], data[:, 1], s=3, color='blue')
if args.algorithm == 'gmm':
gmm = GaussianMixtureModel(args.num_clusters)
gmm.fit(data)
y = gmm.predict_cluster(data)
else:
km = KMeans(args.num_clusters)
km.fit(data)
y = km.predict(data)
plt.scatter(data[:, 0], data[:, 1], c=y)
plt.show()
def calculate_em(X, n_clusters, diag=False, ridge=1e-10, verbose=False, max_iterations=100):
"""
Returns mu, sigma and tpi
"""
n_samples, n_features = X.shape
# Initialise the data using kmeans
k_means = KMeans(k=n_clusters)
k_means_labels, _ = k_means.fit(X.copy())
k_means_cluster_centers = k_means.centers_
# OK, so we've got the centers and the labels. Let's now compute the EM
# algorithm
tau = np.zeros((n_samples, n_clusters))
mu = np.zeros((n_clusters, n_features))
sigma = np.zeros((n_clusters, n_features, n_features))
p = np.zeros((n_clusters, n_samples))
# FIXME shouldbe able to do the following using pure matric arithmetics
for i, element in enumerate(k_means_labels):
tau[i, element] = 1
for j in range(max_iterations):
old_mu = mu.copy()
for i in range(n_clusters):
mu[i] = (tau[:, i].reshape((tau.shape[0], 1)) * X).sum(axis=0) / (tau[:, i]).sum()
for i in range(n_clusters):
a = 0
for n in range(n_samples):
b = (X[n, :] - mu[i]).reshape((2, 1))
if diag:
a += tau[n, i] * np.dot(b.T, b)
else:
a += tau[n, i] * np.dot(b, b.T)
if diag:
sigma[i, :] = a.mean() / tau[:, i].sum() * np.identity(mu.shape[1])
else:
sigma[i, :] = a / tau[:, i].sum()
tpi = tau.sum(axis=1) / n_samples
for i in range(n_clusters):
p[i, :] = _calculate_normal(X, mu[i, :], sigma[i, :])
for i in range(n_clusters):
tau.T[i, :] = tpi[i] * p[i, :] / (tpi * p).sum(axis=0)
if ((old_mu - mu) ** 2).sum() < ridge:
if verbose:
print "break at iterations %d" % j
break
return mu, sigma, tpi
iris_data = iris_data.data[:, 1:3] # uzima se druga i treca osobina iz data seta (sirina sepala i duzina petala)
plt.figure()
for i in range(len(iris_data)):
plt.scatter(iris_data[i, 0], iris_data[i, 1])
plt.xlabel('Sepal width')
plt.ylabel('Petal length')
plt.show()
# --- INICIJALIZACIJA I PRIMENA K-MEANS ALGORITMA --- #
# TODO 2: K-means na Iris data setu
kmeans = KMeans(n_clusters=2, max_iter=100)
kmeans.fit(iris_data)
colors = {0: 'red', 1: 'green'}
plt.figure()
for idx, cluster in enumerate(kmeans.clusters):
plt.scatter(cluster.center[0], cluster.center[1], c=colors[idx], marker='x', s=200) # iscrtavanje centara
for datum in cluster.data: # iscrtavanje tacaka
plt.scatter(datum[0], datum[1], c=colors[idx])
plt.xlabel('Sepal width')
plt.ylabel('Petal length')
plt.show()
# --- ODREDJIVANJE OPTIMALNOG K --- #
X = load_data('EMGaussienne.data')
X_test = load_data('EMGaussienne.data')
n_clusters = 4
num_init = 3
##############################################################################
# Plot result
fig = pl.figure()
colors = ['#4EACC5', '#FF9C34', '#4E9A06', '#00465F']
for ini in range(num_init):
km = KMeans(k=n_clusters)
k_means_labels, k_means_inertia = km.fit(X)
k_means_cluster_centers = km.centers_
k_means_labels_test, k_means_inertia_test = km.predict(X_test)
# KMeans
ax = fig.add_subplot(num_init, 2, 2 * ini + 1)
for k, col in zip(range(n_clusters), colors):
my_members = k_means_labels == k
cluster_center = k_means_cluster_centers[k]
ax.plot(X[my_members, 0], X[my_members, 1], 'w',
markerfacecolor=col, marker='.')
ax.plot(cluster_center[0], cluster_center[1], 'o', markerfacecolor=col,
markeredgecolor='k', markersize=6)
ax.set_title('KMeans - inertia %d' % k_means_inertia)
r2, theta2 = np.random.normal(5, 0.25), np.random.uniform(0, 2*np.pi)
x2, y2 = r2 * np.cos(theta2), r2 * np.sin(theta2)
s2[i] = (x2, y2, r2, theta2)
plt.scatter(x1, y1)
plt.scatter(x2, y2)
data.append((x1, y1))
data.append((x2, y2))
plt.show()
# TODO 5: K-means nad ovim podacima
kmeans = KMeans(n_clusters=2, max_iter=100)
kmeans.fit(data)
colors = {0: 'red', 1: 'green'}
plt.figure()
for idx, cluster in enumerate(kmeans.clusters):
plt.scatter(cluster.center[0], cluster.center[1], c=colors[idx], marker='x', s=200) # iscrtavanje centara
for datum in cluster.data: # iscrtavanje tacaka
plt.scatter(datum[0], datum[1], c=colors[idx])
plt.show()
# TODO 7: DBSCAN nad ovim podacima
dbscan = DBScan(epsilon=1.2, min_points=3)
dbscan.fit(data)
colors = {0: 'red', 1: 'pink', 2: 'yellow', 3: 'cyan', 4: 'green', 5: 'blue'}
class ClsfCRTL(object):
def __init__(self, n_clusters, initCent, max_iter):
self.data = np.array([])
self.belongApp = np.array([])
self.n_clusters = n_clusters
self.clf = KMeans(n_clusters, initCent, max_iter)
def genDataset(self, file_name):
dataSet, belongApp = [], []
f = open(file_name, "r")
lines = f.readlines()
for line in lines:
line_elm = line.split("\t")
dataSet.append([int(line_elm[0]), 0])
belongApp.append(line_elm[1].rstrip("\n"))
self.data = np.array(dataSet)
self.belongApp = np.array(belongApp)
f.close()
def clsf(self):
self.clf.fit(self.data)
def show(self):
cents = self.clf.centroids
labels = self.clf.labels
sse = self.clf.sse
colors = ['b', 'g', 'r', 'k', 'c', 'm', 'y', '#e24fff', '#524C90', '#845868', '#00FF00', '#330000',
'#333300', '#333333', '#CC0099', '#FFFF00', '#FF99CC', '#CCCC66', '#003333', '#66FFFF']
for i in range(self.n_clusters):
index = np.nonzero(labels==i)[0]
x0 = self.data[index, 0]
x1 = self.data[index, 1]
y_i = self.belongApp[index]
for j in range(len(x0)):
plt.scatter(x0[j], x1[j], marker='o', color=colors[i])
# plt.text(x0[j],x1[j],str(y_i[j]),color=colors[i],fontdict={'weight': 'bold', 'size': 9})
plt.scatter(cents[i,0], cents[i,1], marker='x', color=colors[i], linewidths=5)
plt.title("SSE={:.2f}".format(sse))
plt.axis([0, 1600, -2, 2])
plt.show()
def showBar(self):
n = 1600
X = np.arange(n)
Y1 = (1-X/float(n) * np.random.uniform(0.5, 1.0, n))
rect = plt.bar(X, +Y1, facecolor='#524C90', edgecolor='white')
for x,y in zip(X, Y1):
plt.text(x+0.4, y+0.05, '%.2f' % y, ha='center', va='bottom')
plt.xlim(-0.5, 12.5)
plt.ylim(-0.1, +1.25)
plt.xlabel("xlabel")
plt.ylabel("ylabel")
plt.title("title")
plt.legend((rect,), ("example",))
plt.show()
def genResFile(self, i):
cents = self.clf.centroids
sse = self.clf.sse
f = open("Res" + "-" + str(i), "w")
f.write(str(cents.shape[0]) + '\n')
for cent in cents:
f.write(str(cent[0]) + '\t' + str(cent[1]) + '\n')
f.write(str(sse) + '\n')
# test
f.write("\n")
for clu in self.clf.clusterAssment:
f.write(str(clu[0]) + '\t' + str(clu[1]) + '\n')
# test
f.close()
iris_data = iris_data.data[:, 1:3] # uzima se druga i treca osobina iz data seta (sirina sepala i duzina petala)
plt.figure()
for i in range(len(iris_data)):
plt.scatter(iris_data[i, 0], iris_data[i, 1])
plt.xlabel('Sepal width')
plt.ylabel('Petal length')
plt.show()
# --- INICIJALIZACIJA I PRIMENA K-MEANS ALGORITMA --- #
# TODO 2: K-means na Iris data setu
kmeans = KMeans(n_clusters=2, max_iter=100)
kmeans.fit(iris_data, normalize=True)
colors = {0: 'red', 1: 'green'}
plt.figure()
for idx, cluster in enumerate(kmeans.clusters):
plt.scatter(cluster.center[0], cluster.center[1], c=colors[idx], marker='x', s=200) # iscrtavanje centara
for datum in cluster.data: # iscrtavanje tacaka
plt.scatter(datum[0], datum[1], c=colors[idx])
plt.xlabel('Sepal width')
plt.ylabel('Petal length')
plt.show()
# --- ODREDJIVANJE OPTIMALNOG K --- #
from em import calculate_log_likelihood
from kmeans import KMeans
n_clusters = 4
X = utils.load_data('EMGaussienne.data')
Xtest = utils.load_data('EMGaussienne.test')
max_iterations = 150
ridge = 1e-6
verbose = True
n_samples, n_features = X.shape
# Initialise the data using kmeans
k_means = KMeans(k=n_clusters)
k_means_labels, _ = k_means.fit(X.copy())
k_means_cluster_centers = k_means.centers_
mu, sigma, tpi = calculate_em(X, n_clusters)
print 'Log likelihood %d' % calculate_log_likelihood(X, mu, sigma, tpi)
print 'Log likelihood %d' % calculate_log_likelihood(Xtest, mu, sigma, tpi)
p = np.zeros((n_clusters, n_samples))
for i in range(n_clusters):
p[i, :] = _calculate_normal(X, mu[i, :], sigma[i, :])
em_labels = p.argmax(axis=0)
p = np.zeros((n_clusters, n_samples))
for i in range(n_clusters):
p[i, :] = _calculate_normal(Xtest, mu[i, :], sigma[i, :])
def fit(self, X):
self.X = X
self.N = X.shape[0]
self.ndim = X.shape[1]
np.random.seed(self.random_seed)
matX = np.asmatrix(X)
# initialization schemes
if self.init_method == 'random':
if self.init_means is not None:
mu = self.init_means
else:
mu = X[np.random.choice(range(0, len(X)), self.num_gaussians), :] # sample from the data
if self.init_cov is not None:
sigma = self.init_cov
else:
sigma = list()
for k in range(self.num_gaussians):
sigma.append(np.identity(self.ndim, dtype=np.float64))
sigma[k] += np.random.rand(self.ndim, self.ndim) # purely synthetic
sigma[k] = np.dot(sigma[k], sigma[k].T) # making it positive semi-definite and symmetric
sigma[k] /= sigma[k].sum()
# lowerbound = k * self.N / self.num_gaussians # sample from data
# upperbound = lowerbound + 20
# sigma[k] = np.cov(X[lowerbound:upperbound, :].T)
if self.init_weights is not None:
lmbda = self.init_weights
else:
lmbda = np.random.rand(self.num_gaussians)
lmbda /= lmbda.sum()
elif self.init_method == 'kmeans': # use means of kmeans as initial means, and calculate cov from the clusters
model = KMeans(K=self.num_gaussians, max_iter=5)
model.fit(X)
labels = model.pred(X)
mu = np.zeros((self.num_gaussians, self.ndim))
sigma = [np.zeros((self.ndim, self.ndim))] * self.num_gaussians
for k in range(self.num_gaussians):
cluster = X[labels == k]
mu[k] = cluster.mean(axis=0)
sigma[k] = np.cov(cluster.T)
if self.init_weights is not None:
lmbda = self.init_weights
else:
lmbda = np.random.rand(self.num_gaussians)
lmbda /= lmbda.sum()
######## BEGIN ACTUAL ALGORITHM ###################
for iter in range(self.max_iter):
phat = np.zeros((self.N, self.num_gaussians))
N = np.zeros(self.num_gaussians)
# E step
for k in range(0, self.num_gaussians):
normal_var = normal(mean=mu[k], cov=sigma[k])
phat[:, k] = lmbda[k] * normal_var.pdf(X)
phat /= phat.sum(axis=1)[:, None]
# faster to do it all with numpy than use loops
# for n in range(0, self.N): # loop over each data point
# for k in range(0, self.num_gaussians):
# normalx = normal(mean=mu[k], cov=sigma[k]).pdf(X[n, :])
# phat[n, k] = lmbda[k] * normalx
# phat[n, :] /= phat[n, :].sum()
# M step
for k in range(self.num_gaussians):
N[k] = phat[:, k].sum()
mu[k] = np.dot(phat[:, k], X) / N[k]
intermed = np.multiply(phat[:, k], (matX - mu[k]).T).T
sigma[k] = np.dot(intermed.T, (matX - mu[k])) / N[k]
lmbda[k] = N[k] / self.N
pass # end of this iteration
self.mu = mu
self.sigma = sigma
self.lmbda = lmbda
import matplotlib.pyplot as plt
import numpy as np
from kmeans import KMeans,biKMeans
if __name__ == "__main__":
#加载数据
X,y = cPickle.load(open('data.pkl','r'))
#依次画出迭代1次、2次、3次...的图
for max_iter in range(6):
#设置参数
n_clusters = 10
initCent = X[50:60] #将初始质心初始化为X[50:60]
#训练模型
clf = KMeans(n_clusters,initCent,max_iter)
clf.fit(X)
cents = clf.centroids
labels = clf.labels
sse = clf.sse
#画出聚类结果，每一类用一种颜色
colors = ['b','g','r','k','c','m','y','#e24fff','#524C90','#845868']
for i in range(n_clusters):
index = np.nonzero(labels==i)[0]
x0 = X[index,0]
x1 = X[index,1]
y_i = y[index]
for j in range(len(x0)):
plt.text(x0[j],x1[j],str(int(y_i[j])),color=colors[i],\
fontdict={'weight': 'bold', 'size': 9})
plt.scatter(cents[i,0],cents[i,1],marker='x',color=colors[i],linewidths=12)
plt.title("SSE={:.2f}".format(sse))