def test_calinski_harabaz_score():
rng = np.random.RandomState(seed=0)
# Assert message when there is only one label
assert_raise_message(ValueError, "Number of labels is",
calinski_harabaz_score,
rng.rand(10, 2), np.zeros(10))
# Assert message when all point are in different clusters
assert_raise_message(ValueError, "Number of labels is",
calinski_harabaz_score,
rng.rand(10, 2), np.arange(10))
# Assert the value is 1. when all samples are equals
assert_equal(1., calinski_harabaz_score(np.ones((10, 2)),
[0] * 5 + [1] * 5))
# Assert the value is 0. when all the mean cluster are equal
assert_equal(0., calinski_harabaz_score([[-1, -1], [1, 1]] * 10,
[0] * 10 + [1] * 10))
# General case (with non numpy arrays)
X = ([[0, 0], [1, 1]] * 5 + [[3, 3], [4, 4]] * 5 +
[[0, 4], [1, 3]] * 5 + [[3, 1], [4, 0]] * 5)
labels = [0] * 10 + [1] * 10 + [2] * 10 + [3] * 10
assert_almost_equal(calinski_harabaz_score(X, labels),
45 * (40 - 4) / (5 * (4 - 1)))
def test_calinski_harabaz_score():
rng = np.random.RandomState(seed=0)
# Assert message when there is only one label
assert_raise_message(ValueError, "Number of labels is",
calinski_harabaz_score, rng.rand(10, 2), np.zeros(10))
# Assert message when all point are in different clusters
assert_raise_message(ValueError,
"Number of labels is", calinski_harabaz_score,
rng.rand(10, 2), np.arange(10))
# Assert the value is 1. when all samples are equals
assert_equal(1., calinski_harabaz_score(np.ones((10, 2)),
[0] * 5 + [1] * 5))
# Assert the value is 0. when all the mean cluster are equal
assert_equal(
0., calinski_harabaz_score([[-1, -1], [1, 1]] * 10,
[0] * 10 + [1] * 10))
# General case (with non numpy arrays)
X = ([[0, 0], [1, 1]] * 5 + [[3, 3], [4, 4]] * 5 + [[0, 4], [1, 3]] * 5 +
[[3, 1], [4, 0]] * 5)
labels = [0] * 10 + [1] * 10 + [2] * 10 + [3] * 10
assert_almost_equal(calinski_harabaz_score(X, labels),
45 * (40 - 4) / (5 * (4 - 1)))
def cluster_number_study(n=50):
""" Check out some basic cluster metrics for different cluster sizes. """
fnamecsv = './AL_pchange_vars.csv'
df = pd.read_csv(fnamecsv)
variables = (df.as_matrix())[:, 1:].astype(float)
for j in range(len(variables[0, :])): #ugly way of looping over columns
variables[:,
j] = (variables[:, j] - np.mean(variables[:, j])) / np.std(
variables[:, j])
scores = []
for i in (2 + np.array(range(n))):
k = KMeans(n_clusters=i, n_init=50, n_jobs=3).fit(variables)
y = silhouette_score(variables, k.labels_)
scores.append((i, y))
with open('cluster_vs_silhouette.txt', 'w') as f:
for s in scores:
f.write(str(s[0]) + "\t" + str(s[1]) + "\n")
print scores
scores = []
for i in (2 + np.array(range(n))):
k = KMeans(n_clusters=i, n_init=50, n_jobs=3).fit(variables)
#y = silhouette_score(variables,k.labels_)
y = calinski_harabaz_score(variables, k.labels_)
scores.append((i, y))
with open('cluster_vs_calharabaz.txt', 'w') as f:
for s in scores:
f.write(str(s[0]) + "\t" + str(s[1]) + "\n")
def no_label_metrics(input_feature,
assigned_label,
print_metric,
metric='euclidean'):
""" https://scikit-learn.org/stable/modules/clustering.html#clustering-evaluation """
no_label_metrics = {}
no_label_metrics['silhouette_score'] = \
cluster_metric.silhouette_score(input_feature,
assigned_label,
metric=metric)
no_label_metrics['calinski_score'] = \
cluster_metric.calinski_harabaz_score(input_feature,
assigned_label)
# no_label_metrics['davie_bouldin_score'] = \
# cluster_metric.davies_bouldin_score(input_feature,
# assigned_label)
if (print_metric):
print('Metrics without ture labels')
print("silhouette score: % s" %
no_label_metrics['silhouette_score'])
print("calinski score: % s" % no_label_metrics['calinski_score'])
# print("davie bouldin score: % s"
# % no_label_metrics['davie_bouldin_score'])
return no_label_metrics
def _check_silhouette(self, dataset, transformed):
expected = KMeans().fit_predict(dataset)
got = KMeans().fit_predict(transformed)
if type(dataset) is not np.ndarray:
dataset = dataset.toarray()
if type(expected) is not np.ndarray:
expected = expected.toarray()
if type(got) is not np.ndarray:
got = got.toarray()
print("Silhouette Index: expected:",
silhouette_score(dataset, expected), "got:",
silhouette_score(dataset, got))
print("Calinski-Harabaz Index: expected:",
calinski_harabaz_score(dataset, expected), "got:",
calinski_harabaz_score(dataset, got))
def _print_clusteringMetrics(_kMean, _X):
metrics = [['Clustering K-Means', 'Datos obtenidos'],
['Inercia', _kMean.inertia_],
['Entropy', entropy(_kMean.labels_)],
['Silhouette Score', silhouette_score(_X, _kMean.labels_, random_state = 0)],
['Calinski-Harabaz Score', calinski_harabaz_score(_X, _kMean.labels_)], ]
print('\nMinería de Datos - Clustering K-Means - <VORT>', '\n')
print(_kMean, '\n')
print(look(metrics))
def test_calinski_harabaz_score():
assert_raises_on_only_one_label(calinski_harabaz_score)
assert_raises_on_all_points_same_cluster(calinski_harabaz_score)
# Assert the value is 1. when all samples are equals
assert_equal(1., calinski_harabaz_score(np.ones((10, 2)),
[0] * 5 + [1] * 5))
# Assert the value is 0. when all the mean cluster are equal
assert_equal(0., calinski_harabaz_score([[-1, -1], [1, 1]] * 10,
[0] * 10 + [1] * 10))
# General case (with non numpy arrays)
X = ([[0, 0], [1, 1]] * 5 + [[3, 3], [4, 4]] * 5 +
[[0, 4], [1, 3]] * 5 + [[3, 1], [4, 0]] * 5)
labels = [0] * 10 + [1] * 10 + [2] * 10 + [3] * 10
pytest.approx(calinski_harabaz_score(X, labels),
45 * (40 - 4) / (5 * (4 - 1)))
def test_calinski_harabaz_score():
assert_raises_on_only_one_label(calinski_harabaz_score)
assert_raises_on_all_points_same_cluster(calinski_harabaz_score)
# Assert the value is 1. when all samples are equals
assert_equal(1., calinski_harabaz_score(np.ones((10, 2)),
[0] * 5 + [1] * 5))
# Assert the value is 0. when all the mean cluster are equal
assert_equal(
0., calinski_harabaz_score([[-1, -1], [1, 1]] * 10,
[0] * 10 + [1] * 10))
# General case (with non numpy arrays)
X = ([[0, 0], [1, 1]] * 5 + [[3, 3], [4, 4]] * 5 + [[0, 4], [1, 3]] * 5 +
[[3, 1], [4, 0]] * 5)
labels = [0] * 10 + [1] * 10 + [2] * 10 + [3] * 10
pytest.approx(calinski_harabaz_score(X, labels),
45 * (40 - 4) / (5 * (4 - 1)))
def ECBO(dataSet, c):
n, m = dataSet.shape
clusterAssment = np.mat(np.zeros((n, 1)))
#1. init membership and centroids
#initail_U = initial_U(dataSet, c)
initial_centroids = initCentroids(dataSet, c)
print('initial centroids:\n', initial_centroids)
#2. update membership U
lastJ, lastU = upUwithSimplex(dataSet, initial_centroids, c, A1, A2)
last_centroids = calCentroids(dataSet, lastU, c)
#3. update centroids
J, U = upUwithSimplex(dataSet, last_centroids, c, A1, A2)
centroids = calCentroids(dataSet, U, c)
#while last_centroids.all() != centroids.all():
#count = 0
#while (count < 2):
lastcentroids = centroids
J, U = upUwithSimplex(dataSet, lastcentroids, c, A1, A2)
centroids = calCentroids(dataSet, U, c)
#count += 1
#assgin data to clusters
for k in range(n):
for i in range(c):
if (U[k, i] == 1):
clusterAssment[k] = i
"""for i in range(n):
minDist = 10000.0
minIdex = 0
for j in range(c):
distance = euclDistance(dataSet[i], centroids[j])
if distance < minDist:
minDist = distance #update min distance
minIdex = j #update assignment of data to cluster
if clusterAssment[i, 0] != minIdex:
clusterAssment[i, :] = minIdex"""
label_pred = clusterAssment
#print(label_pred)
CHI = calinski_harabaz_score(dataSet, label_pred)
print('final U:\n', np.mat(U))
print('final centroids:\n', centroids)
print('objective function:', value(J.objective))
print('cluster assignment:', clusterAssment)
print('Calinski-Harabaz Index:', CHI)
for i in range(c):
print(np.sum(U[:, i]))
return U, centroids, J, clusterAssment
def ECBO(dataSet, c):
n, m = dataSet.shape
clusterAssment = np.mat(np.zeros((n, 1)))
#1. init membership and centroids
#initail_U = initial_U(dataSet, c)
initial_centroids = initCentroids(dataSet, c)
print('initial centroids:\n', initial_centroids)
#2. update membership U
lastJ, lastU = upUwithSimplex(dataSet, initial_centroids, c, k)
last_centroids = calCentroids(dataSet, lastU, c)
#3. update centroids
J, U = upUwithSimplex(dataSet, last_centroids, c, k)
centroids = calCentroids(dataSet, U, c)
#while last_centroids.all() != centroids.all():
count = 0
while (count < 10):
lastcentroids = centroids
J, U = upUwithSimplex(dataSet, lastcentroids, c, k)
centroids = calCentroids(dataSet, U, c)
count += 1
for p in range(n):
for i in range(c):
if (U[p, i] == 1):
clusterAssment[p] = i
label_pred = clusterAssment
# print(label_pred)
CHI = calinski_harabaz_score(dataSet, label_pred)
print('final U:\n', np.mat(U))
print('final centroids:\n', centroids)
print('objective function:', value(J.objective))
print('cluster assignment:', clusterAssment)
print('Calinski-Harabaz Index:', CHI)
for i in range(c):
print(np.sum(U[:, i]))
return U, centroids, J, clusterAssment
def main():
min_pts = 69
epsilon = 0.0031894736842105263
with open('train.dat', 'r') as fh:
data = fh.read().splitlines()
data_csr = build_csr(data)
# tf-idf + TruncatedSVD = LSA (latent semantic analysis)
X = TfidfTransformer(norm='l2',
use_idf=True,
smooth_idf=True,
sublinear_tf=False).fit_transform(data_csr)
selector = TruncatedSVD(n_components=5, algorithm="arpack", random_state=8)
X = selector.fit_transform(X)
X = sparse.csr_matrix(X)
X = csr_l2normalize(X, copy=True)
print('Running DBSCAN clustering algorithm now....')
print("For eps: {}, minPts: {}".format(epsilon, min_pts))
labels, core_pts, border_pts = DBSCAN(X, eps=epsilon, minPts=min_pts)
labels = assign_noise_to_centroid(X, labels, recompute_centroid=True)
n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
print(' Estimated number of clusters: %d' % n_clusters_)
sil_score = silhouette_score(X, labels, metric='cosine', random_state=8)
print(" Silhouette Coefficient: %0.5f" % sil_score)
X_dense = X.toarray()
ch_score = calinski_harabaz_score(X_dense, labels)
print(" Calinski Harabaz Score: %0.5f" % ch_score)
print('Writing out predictions now....')
submission_df = pd.read_csv("format.dat", sep="\t", header=None)
submission_df[0] = labels
submission_df.to_csv('submission.txt', sep='\n', index=False, header=False)
def L1_ECBO(dataSet, c):
n, m = dataSet.shape
clusterAssment = np.mat(np.zeros((n, 1)))
initial_centroids = initCentroids(dataSet, c)
print('initial centroids:\n', initial_centroids)
lastJ, lastU = upUwithSimplex(dataSet, initial_centroids, c, A1, A2)
last_centroids = calCentroids(dataSet, lastU, c)
# 3. update centroids
J, U = upUwithSimplex(dataSet, last_centroids, c, A1, A2)
centroids = calCentroids(dataSet, U, c)
count = 0
while count < 9:
lastcentroids = centroids
J, U = upUwithSimplex(dataSet, lastcentroids, c, A1, A2)
centroids = calCentroids(dataSet, U, c)
count += 1
for p in range(n):
for i in range(c):
if (U[p, i] == 1):
clusterAssment[p] = i
label_pred = clusterAssment
# print(label_pred)
CHI = calinski_harabaz_score(dataSet, label_pred)
print('final membership:', U)
print('objetive function:', J)
print('final centroids:', centroids, type(centroids))
#print('cluster assignment:', clusterAssment)
print('Calinski-Harabaz Index:', CHI)
for i in range(c):
print(np.sum(U[:, i]))
return U, J, centroids, clusterAssment
def L1_kMeans(dataSet, c):
n, m = dataSet.shape
clusterAssment = np.mat(np.zeros((n, 1)))
initial_centroids = initCentroids(dataSet, c)
print('initial centroids:\n', initial_centroids)
lastJ, lastU = updateU(dataSet, initial_centroids, c)
centroids = calCentroids(dataSet, lastU, c)
J, U = updateU(dataSet, centroids, c)
centroids = np.array(centroids)
count = 0
while count < 10:
lastJ = J
centroids = calCentroids(dataSet, U, c)
J, U = updateU(dataSet, centroids, c)
count += 1
print('count:', count)
for k in range(n):
for i in range(c):
if (U[k, i] == 1):
clusterAssment[k] = i
label_pred = clusterAssment
# print(label_pred)
CHI = calinski_harabaz_score(dataSet, label_pred)
print('final membership:', U)
print('objetive function:', J)
print('final centroids:', centroids)
#print('cluster assignment:', clusterAssment)
print('Calinski-Harabaz Index:', CHI)
for i in range(c):
print(np.sum(U[:, i]))
return U, J, centroids, clusterAssment
def fuzzyCMeans(dataSet, c, m):
#n, p = dataSet.shape
# 1. init centroids randomly
initial_centroids = initCentroids(dataSet, c)
# 2. update membership U with fixing centroids
last_U = calUwithCent(dataSet, initial_centroids, c, m)
last_J = objFuncJ(dataSet, last_U, initial_centroids, c, m)
# 3. update centroids with fixing U
centroids = calCentwithU(dataSet, last_U, c, m)
U = calUwithCent(dataSet, centroids, c, m)
J = objFuncJ(dataSet, U, centroids, c, m)
count = 0
while count < 10:
centroids = calCentwithU(dataSet, U, c, m)
U = calUwithCent(dataSet, centroids, c, m)
J = objFuncJ(dataSet, U, centroids, c, m)
count += 1
clusterAssment = getCluster(dataSet, U, c)
#label_pred = clusterAssment
CHI = calinski_harabaz_score(dataSet, clusterAssment)
print('final membership:', U)
print('objetive function:', J)
print('final centroids:', centroids)
print('cluster assignment:', clusterAssment)
print('Calinski-Harabaz Index:', CHI)
for i in range(c):
print("cluster size:", np.sum(U[:, i]))
return U, centroids, J, clusterAssment
#x = glass.values
#data = x[:, [3, 5]]
#wine = datasets.load_wine()
#x = wine.data
#data = x[:, [0, 11]]
#iris = datasets.load_iris()
#original_x = iris.data
#data = original_x[:, :2] + original_x[:, 2:]
#data = pd.read_csv('D:/Tsukuba/My Research/Program/dataset/4_three_ciecles_with_diffR/three_ciecles_with_diffR.csv')
#x = data.values[1:, :2]
#y = data.values[1:, -1]
#print(x, y)
data = pd.read_csv('D:/Tsukuba/My Research/Program/dataset/diff_var.csv')
x = data.values[:, 1:3]
y = data.values[:, 0]
pso = PSO(n_cluster=3, n_particle=10, data=x) # max_iter, print_debug
pso.run()
pred_cluster = pso.cluster
ari = adjusted_rand_score(y, pred_cluster)
ch = calinski_harabaz_score(x, pred_cluster)
print('ARI:', ari)
print('CH:', ch)
pso.show_cluter()
from sklearn.cluster import KMeans
from sklearn.metrics.cluster import calinski_harabaz_score, silhouette_score
# 加载数据
data = pd.read_csv('data.csv')
# print(data.head())
x_train = data[["2019年国际排名", "2018世界杯", "2015亚洲杯"]]
# 特征工程 - 标准化
min_max_scaler = preprocessing.StandardScaler()
x_train = min_max_scaler.fit_transform(x_train)
# 创建KMeans聚类评估器
estimator = KMeans(n_clusters=3)
# 模型训练
estimator.fit(x_train)
y_predict = estimator.predict(x_train)
# 模型评估
# CH系数
# 值越大聚类效果越好
print('CH系数:', calinski_harabaz_score(x_train, y_predict))
# 平均轮廓系数的取值范围为[-1,1]，系数越大，聚类效果越好
print('平均轮廓系数:', silhouette_score(x_train, y_predict))
# 合并聚类结果，插入到原数据中
result = pd.concat((data, pd.DataFrame(y_predict)), axis=1)
result.rename({0: u'聚类'}, axis=1, inplace=True)
print(result)
'''
for K in range(4, 5):
print('\n\n\nK = ', K)
kmeans = KMeans(n_clusters=K).fit(numpy_selected_data)
labels = kmeans.labels_
save_name = 'Set1_KMeans_K=' + str(K) + '.csv'
np.savetxt(save_name, labels, delimiter=',')
label_counter = collections.Counter(labels)
print(label_counter)
unique_clusters, centroids = getAveragePlayerFromCluster(
non_normalized_data, labels)
print("Start calculating centroids")
i = 0
column_names = []
for _cent in centroids:
if i == 0:
new_file = pd.DataFrame(_cent.values).T
column_names = _cent.index
else:
new_file = new_file.append(pd.DataFrame(_cent.values).T)
i = i + 1
new_file.columns = column_names
new_file.to_csv('KMeans_K=' + str(K) + '.csv', index=False)
unique_clusters = set(labels)
palette = sns.color_palette('hls', len(unique_clusters))
cluster_colors = [palette[col] for col in labels]
print("K-Means Calinski-Harabaz: " +
str(smc.calinski_harabaz_score(selected_data, labels)))
from sklearn.datasets.samples_generator import make_blobs
from sklearn.cluster import KMeans
from sklearn.metrics.cluster import calinski_harabaz_score
# 1. 生成数据
X, y = make_blobs(n_samples=1000,
n_features=2,
centers=[(-1, -1), (0, 0), (1, 1), (2, 2)],
cluster_std=[0.4, 0.2, 0.2, 0.2])
print(X)
# 2. 使用KMeans进行聚类
estimator = KMeans(n_clusters=4)
y_pred = estimator.fit_predict(X)
# 3. 数据可视化(绘制分类结果图)
plt.figure(figsize=(5, 4), dpi=80)
# 绘制散点图, 查看数据的分布情况
plt.scatter(X[:, 0], X[:, 1], c=y_pred)
# 显示
plt.show()
# 分类评估
# 2 3096.7473856516135
# 3 2940.6149446783725
# 4 5866.614435267102
# CH系数: 值越大聚类效果越好.
print('CH系数', calinski_harabaz_score(X, y_pred))