[빅데이터 직무연구회] 5회차 모임 예제 소스 (3)

from sklearn.cluster import DBSCAN
X, y = make_blobs(random_state=0, n_samples=12)

dbscan = DBSCAN()
clusters = dbscan.fit_predict(X)
print("클러스터 레이블:\n{}".format(clusters))

클러스터 레이블:
[-1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1]

In [62]:

mglearn.plots.plot_dbscan()

min_samples: 2 eps: 1.000000  cluster: [-1  0  0 -1  0 -1  1  1  0  1 -1 -1]
min_samples: 2 eps: 1.500000  cluster: [0 1 1 1 1 0 2 2 1 2 2 0]
min_samples: 2 eps: 2.000000  cluster: [0 1 1 1 1 0 0 0 1 0 0 0]
min_samples: 2 eps: 3.000000  cluster: [0 0 0 0 0 0 0 0 0 0 0 0]
min_samples: 3 eps: 1.000000  cluster: [-1  0  0 -1  0 -1  1  1  0  1 -1 -1]
min_samples: 3 eps: 1.500000  cluster: [0 1 1 1 1 0 2 2 1 2 2 0]
min_samples: 3 eps: 2.000000  cluster: [0 1 1 1 1 0 0 0 1 0 0 0]
min_samples: 3 eps: 3.000000  cluster: [0 0 0 0 0 0 0 0 0 0 0 0]
min_samples: 5 eps: 1.000000  cluster: [-1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1]
min_samples: 5 eps: 1.500000  cluster: [-1  0  0  0  0 -1 -1 -1  0 -1 -1 -1]
min_samples: 5 eps: 2.000000  cluster: [-1  0  0  0  0 -1 -1 -1  0 -1 -1 -1]
min_samples: 5 eps: 3.000000  cluster: [0 0 0 0 0 0 0 0 0 0 0 0]

In [63]:

X, y = make_moons(n_samples=200, noise=0.05, random_state=1)

scaler = StandardScaler()
scaler.fit(X)
X_scaled = scaler.transform(X)
dbscan = DBSCAN()
clusters = dbscan.fit_predict(X_scaled)
plt.scatter(X_scaled[:, 0], X_scaled[:, 1], c=clusters, cmap=mglearn.cm2, s=60, edgecolors='black')
plt.xlabel("특성 0")
plt.ylabel("특성 1")

Out[63]:

Text(0,0.5,'특성 1')

In [64]:

from sklearn.metrics.cluster import adjusted_rand_score
X, y = make_moons(n_samples=200, noise=0.05, random_state=0)

scaler = StandardScaler()
scaler.fit(X)
X_scaled = scaler.transform(X)

fig, axes = plt.subplots(1, 4, figsize=(15, 3), subplot_kw={'xticks': (), 'yticks': ()})

algorithms = [KMeans(n_clusters=2), AgglomerativeClustering(n_clusters=2), DBSCAN()]

random_state = np.random.RandomState(seed=0)
random_clusters = random_state.randint(low=0, high=2, size=len(X))

axes[0].scatter(X_scaled[:, 0], X_scaled[:, 1], c=random_clusters, cmap=mglearn.cm3, s=60, edgecolors='black')
axes[0].set_title("무작위 할당 - ARI: {:.2f}".format(adjusted_rand_score(y, random_clusters)))

for ax, algorithm in zip(axes[1:], algorithms):
    clusters = algorithm.fit_predict(X_scaled)
    ax.scatter(X_scaled[:, 0], X_scaled[:, 1], c=clusters, cmap=mglearn.cm3, s=60, edgecolors='black')
    ax.set_title("{} - ARI: {:.2f}".format(algorithm.__class__.__name__, adjusted_rand_score(y, clusters)))

In [65]:

from sklearn.metrics import accuracy_score

clusters1 = [0, 0, 1, 1, 0]
clusters2 = [1, 1, 0, 0, 1]
print("정확도: {:.2f}".format(accuracy_score(clusters1, clusters2)))
print("ARI: {:.2f}".format(adjusted_rand_score(clusters1, clusters2)))

정확도: 0.00
ARI: 1.00

In [66]:

from sklearn.metrics.cluster import silhouette_score

X, y = make_moons(n_samples=200, noise=0.05, random_state=0)
scaler = StandardScaler()
scaler.fit(X)
X_scaled = scaler.transform(X)

fig, axes = plt.subplots(1, 4, figsize=(15, 3), subplot_kw={'xticks': (), 'yticks': ()})

random_state = np.random.RandomState(seed=0)
random_clusters = random_state.randint(low=0, high=2, size=len(X))

axes[0].scatter(X_scaled[:, 0], X_scaled[:, 1], c=random_clusters, cmap=mglearn.cm3, s=60, edgecolors='black')
axes[0].set_title("무작위 할당: {:.2f}".format(silhouette_score(X_scaled, random_clusters)))

algorithms = [KMeans(n_clusters=2), AgglomerativeClustering(n_clusters=2), DBSCAN()]

for ax, algorithm in zip(axes[1:], algorithms):
    clusters = algorithm.fit_predict(X_scaled)
    ax.scatter(X_scaled[:, 0], X_scaled[:, 1], c=clusters, cmap=mglearn.cm3, s=60, edgecolors='black')
    ax.set_title("{} : {:.2f}".format(algorithm.__class__.__name__, silhouette_score(X_scaled, clusters)))

In [67]:

from sklearn.decomposition import PCA
pca = PCA(n_components=100, whiten=True, random_state=0)
pca.fit_transform(X_people)
X_pca = pca.transform(X_people)

In [68]:

dbscan = DBSCAN()
labels = dbscan.fit_predict(X_pca)
print("고유한 레이블: {}".format(np.unique(labels)))

고유한 레이블: [-1]

In [69]:

dbscan = DBSCAN(min_samples=3)
labels = dbscan.fit_predict(X_pca)
print("고유한 레이블: {}".format(np.unique(labels)))

고유한 레이블: [-1]

In [70]:

dbscan = DBSCAN(min_samples=3, eps=15)
labels = dbscan.fit_predict(X_pca)
print("고유한 레이블: {}".format(np.unique(labels)))

고유한 레이블: [-1  0]

In [71]:

print("클러스터별 포인트 수: {}".format(np.bincount(labels + 1)))

클러스터별 포인트 수: [  32 2031]

In [72]:

noise = X_people[labels==-1]

fig, axes = plt.subplots(3, 9, subplot_kw={'xticks': (), 'yticks': ()}, figsize=(12, 4))
for image, ax in zip(noise, axes.ravel()):
    ax.imshow(image.reshape(image_shape), vmin=0, vmax=1)

In [73]:

for eps in [1, 3, 5, 7, 9, 11, 13]:
    print("\neps={}".format(eps))
    dbscan = DBSCAN(eps=eps, min_samples=3)
    labels = dbscan.fit_predict(X_pca)
    print("클러스터 수: {}".format(len(np.unique(labels))))
    print("클러스터 크기: {}".format(np.bincount(labels + 1)))

eps=1
클러스터 수: 1
클러스터 크기: [2063]

eps=3
클러스터 수: 1
클러스터 크기: [2063]

eps=5
클러스터 수: 1
클러스터 크기: [2063]

eps=7
클러스터 수: 14
클러스터 크기: [2004    3   14    7    4    3    3    4    4    3    3    5    3    3]

eps=9
클러스터 수: 4
클러스터 크기: [1307  750    3    3]

eps=11
클러스터 수: 2
클러스터 크기: [ 413 1650]

eps=13
클러스터 수: 2
클러스터 크기: [ 120 1943]

In [75]:

dbscan = DBSCAN(min_samples=3, eps=7)
labels = dbscan.fit_predict(X_pca)

for cluster in range(max(labels) + 1):
    mask = labels == cluster
    n_images = np.sum(mask)
    fig, axes = plt.subplots(1, n_images, figsize=(n_images * 1.5, 4), subplot_kw={'xticks': (), 'yticks': ()})
    for image, label, ax in zip(X_people[mask], y_people[mask], axes):
        ax.imshow(image.reshape(image_shape), vmin=0, vmax=1)
        ax.set_title(people.target_names[label].split()[-1])

In [76]:

# k-평균으로 클러스터를 추출
km = KMeans(n_clusters=10, random_state=0)
labels_km = km.fit_predict(X_pca)
print("k-평균의 클러스터 크기: {}".format(np.bincount(labels_km)))

k-평균의 클러스터 크기: [155 175 238  75 358 257  91 219 323 172]

In [77]:

fig, axes = plt.subplots(2, 5, subplot_kw={'xticks': (), 'yticks': ()}, figsize=(12, 4))
for center, ax in zip(km.cluster_centers_, axes.ravel()):
    ax.imshow(pca.inverse_transform(center).reshape(image_shape), vmin=0, vmax=1)

In [78]:

mglearn.plots.plot_kmeans_faces(km, pca, X_pca, X_people, y_people, people.target_names)

In [79]:

# 병합 군집으로 클러스터를 추출
agglomerative = AgglomerativeClustering(n_clusters=10)
labels_agg = agglomerative.fit_predict(X_pca)
print("병합 군집의 클러스터 크기: {}".format(np.bincount(labels_agg)))

병합 군집의 클러스터 크기: [169 660 144 329 217  85  18 261  31 149]

In [80]:

print("ARI: {:.2f}".format(adjusted_rand_score(labels_agg, labels_km)))

ARI: 0.09

In [81]:

linkage_array = ward(X_pca)
# 클러스터 사이의 거리가 담겨있는 linkage_array로 덴드로그램을 그립니다.
plt.figure(figsize=(20, 5))
dendrogram(linkage_array, p=7, truncate_mode='level', no_labels=True)
plt.xlabel("샘플 번호")
plt.ylabel("클러스터 거리")
ax = plt.gca()
bounds = ax.get_xbound()
ax.plot(bounds, [36, 36], '--', c='k')

Out[81]:

[<matplotlib.lines.Line2D at 0x11424c7b8>]

In [82]:

n_clusters = 10
for cluster in range(n_clusters):
    mask = labels_agg == cluster
    fig, axes = plt.subplots(1, 10, subplot_kw={'xticks': (), 'yticks': ()}, figsize=(15, 8))
    axes[0].set_ylabel(np.sum(mask))
    for image, label, asdf, ax in zip(X_people[mask], y_people[mask], labels_agg[mask], axes):
        ax.imshow(image.reshape(image_shape), vmin=0, vmax=1)
        ax.set_title(people.target_names[label].split()[-1], fontdict={'fontsize': 9})

In [88]:

# 병합 군집으로 클러스터를 추출합니다.
agglomerative = AgglomerativeClustering(n_clusters=40)
labels_agg = agglomerative.fit_predict(X_pca)
print("병합 군집의 클러스터 크기: {}".format(np.bincount(labels_agg)))

n_clusters = 40
for cluster in [10, 13, 19, 22, 36]:
    mask = labels_agg == cluster
    fig, axes = plt.subplots(1, 15, subplot_kw={'xticks': (), 'yticks': ()}, figsize=(15,8))
    cluster_size = np.sum(mask)
    axes[0].set_ylabel("#{}: {}".format(cluster, cluster_size))
    for image, label, asdf, ax in zip(X_people[mask], y_people[mask], labels_agg[mask], axes):
        ax.imshow(image.reshape(image_shape), vmin=0, vmax=1)
        ax.set_title(people.target_names[label].split()[-1], fontdict={'fontsize': 9})
    for i in range(cluster_size, 15):
        axes[i].set_visible(False)

병합 군집의 클러스터 크기: [ 43 120 100 194  56  58 127  22   6  37  65  49  84  18 168  44  47  31
  78  30 166  20  57  14  11  29  23   5   8  84  67  30  57  16  22  12
  29   2  26   8]