[빅데이터 직무연구회] 5회차 모임 예제 소스 (2)

mglearn.plots.plot_kmeans_algorithm()

In [45]:

mglearn.plots.plot_kmeans_boundaries()

In [46]:

from sklearn.datasets import make_blobs
from sklearn.cluster import KMeans

X, y = make_blobs(random_state=1)

kmeans = KMeans(n_clusters=3)
kmeans.fit(X)

Out[46]:

KMeans(algorithm='auto', copy_x=True, init='k-means++', max_iter=300,
    n_clusters=3, n_init=10, n_jobs=1, precompute_distances='auto',
    random_state=None, tol=0.0001, verbose=0)

In [47]:

print("클러스터 레이블:\n{}".format(kmeans.labels_))

클러스터 레이블:
[1 0 0 0 2 2 2 0 1 1 0 0 2 1 2 2 2 1 0 0 2 0 2 1 0 2 2 1 1 2 1 1 2 1 0 2 0
 0 0 2 2 0 1 0 0 2 1 1 1 1 0 2 2 2 1 2 0 0 1 1 0 2 2 0 0 2 1 2 1 0 0 0 2 1
 1 0 2 2 1 0 1 0 0 2 1 1 1 1 0 1 2 1 1 0 0 2 2 1 2 1]

In [48]:

print(kmeans.predict(X))

[1 0 0 0 2 2 2 0 1 1 0 0 2 1 2 2 2 1 0 0 2 0 2 1 0 2 2 1 1 2 1 1 2 1 0 2 0
 0 0 2 2 0 1 0 0 2 1 1 1 1 0 2 2 2 1 2 0 0 1 1 0 2 2 0 0 2 1 2 1 0 0 0 2 1
 1 0 2 2 1 0 1 0 0 2 1 1 1 1 0 1 2 1 1 0 0 2 2 1 2 1]

In [49]:

mglearn.discrete_scatter(X[:, 0], X[:, 1], kmeans.labels_, markers='o')
mglearn.discrete_scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], [0, 1, 2], markers='^', markeredgewidth=2)

Out[49]:

[<matplotlib.lines.Line2D at 0x10d747c88>,
 <matplotlib.lines.Line2D at 0x10d727128>,
 <matplotlib.lines.Line2D at 0x10d727550>]

In [50]:

fig, axes = plt.subplots(1, 2, figsize=(10, 5))

kmeans = KMeans(n_clusters=2)
kmeans.fit(X)
assignments = kmeans.labels_
mglearn.discrete_scatter(X[:, 0], X[:, 1], assignments, ax=axes[0])

kmeans = KMeans(n_clusters=5)
kmeans.fit(X)
assignments = kmeans.labels_
mglearn.discrete_scatter(X[:, 0], X[:, 1], assignments, ax=axes[1])

Out[50]:

[<matplotlib.lines.Line2D at 0x10ad91160>,
 <matplotlib.lines.Line2D at 0x10ad915c0>,
 <matplotlib.lines.Line2D at 0x10ad91b00>,
 <matplotlib.lines.Line2D at 0x10ad91f60>,
 <matplotlib.lines.Line2D at 0x10ad9e400>]

In [51]:

X_varied, y_varied = make_blobs(n_samples=200, cluster_std=[1.0, 2.5, 0.5], random_state=170)
y_pred = KMeans(n_clusters=3, random_state=0).fit_predict(X_varied)
mglearn.discrete_scatter(X_varied[:, 0], X_varied[:, 1], y_pred)
plt.legend(["클러스터 0", "클러스터 1", "클러스터 2"], loc='best')
plt.xlabel("특성 0")
plt.ylabel("특성 1")

Out[51]:

Text(0,0.5,'특성 1')

In [52]:

X, y = make_blobs(random_state=170, n_samples=600)
rng = np.random.RandomState(74)

transformation = rng.normal(size=(2, 2))
X = np.dot(X, transformation)

kmeans = KMeans(n_clusters=3)
kmeans.fit(X)
y_pred = kmeans.predict(X)

mglearn.discrete_scatter(X[:, 0], X[:, 1], kmeans.labels_, markers='o')
mglearn.discrete_scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], [0, 1, 2], markers='^', markeredgewidth=2)
plt.xlabel("특성 0")
plt.ylabel("특성 1")

Out[52]:

Text(0,0.5,'특성 1')

In [53]:

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

kmeans = KMeans(n_clusters=2)
kmeans.fit(X)
y_pred = kmeans.predict(X)

plt.scatter(X[:, 0], X[:, 1], c=y_pred, cmap=mglearn.cm2, s=60, edgecolors='k')
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], marker='^', c=[mglearn.cm2(0), mglearn.cm2(1)], s=100, linewidth=2, edgecolors='k')
plt.xlabel("Feature 0")
plt.ylabel("Feature 1")

Out[53]:

Text(0,0.5,'Feature 1')

In [54]:

X_train, X_test, y_train, y_test = train_test_split(X_people, y_people, stratify=y_people, random_state=0)
nmf = NMF(n_components=100, random_state=0)
nmf.fit(X_train)
pca = PCA(n_components=100, random_state=0)
pca.fit(X_train)
kmeans = KMeans(n_clusters=100, random_state=0)
kmeans.fit(X_train)

X_reconstructed_pca = pca.inverse_transform(pca.transform(X_test))
X_reconstructed_kmeans = kmeans.cluster_centers_[kmeans.predict(X_test)]
X_reconstructed_nmf = np.dot(nmf.transform(X_test), nmf.components_)

fig, axes = plt.subplots(3, 5, figsize=(8, 8), subplot_kw={'xticks': (), 'yticks': ()})
fig.suptitle("추출한 성분")
for ax, comp_kmeans, comp_pca, comp_nmf in zip(axes.T, kmeans.cluster_centers_, pca.components_, nmf.components_):
    ax[0].imshow(comp_kmeans.reshape(image_shape))
    ax[1].imshow(comp_pca.reshape(image_shape), cmap='viridis')
    ax[2].imshow(comp_nmf.reshape(image_shape))
    
axes[0, 0].set_ylabel("kmeans")
axes[1, 0].set_ylabel("pca")
axes[2, 0].set_ylabel("nmf")

fig, axes = plt.subplots(4, 5, subplot_kw={'xticks': (), 'yticks': ()}, figsize=(8, 8))
fig.suptitle("재구성")
for ax, orig, rec_kmeans, rec_pca, rec_nmf in zip(axes.T, X_test, X_reconstructed_kmeans, X_reconstructed_pca, X_reconstructed_nmf):
    ax[0].imshow(orig.reshape(image_shape))
    ax[1].imshow(rec_kmeans.reshape(image_shape))
    ax[2].imshow(rec_pca.reshape(image_shape))
    ax[3].imshow(rec_nmf.reshape(image_shape))
    
axes[0, 0].set_ylabel("원본")
axes[1, 0].set_ylabel("kmeans")
axes[2, 0].set_ylabel("pca")
axes[3, 0].set_ylabel("nmf")

Out[54]:

Text(0,0.5,'nmf')

In [55]:

X, y = make_moons(n_samples=200, noise=0.05, random_state=0)

kmeans = KMeans(n_clusters=10, random_state=0)
kmeans.fit(X)
y_pred = kmeans.predict(X)

plt.scatter(X[:, 0], X[:, 1], c=y_pred, s=60, cmap='Paired', edgecolors='black')
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s=60, marker='^', c=range(kmeans.n_clusters), linewidth=2, cmap='Paired', edgecolors='black')
plt.xlabel("특성 0")
plt.ylabel("특성 1")
print("클러스터 레이블:\n()".format(y_pred))

클러스터 레이블:
()

In [56]:

distance_features = kmeans.transform(X)
print("클러스터 거리 데이터의 형태: {}".format(distance_features.shape))
print("클러스터 거리:\n{}".format(distance_features))

클러스터 거리 데이터의 형태: (200, 10)
클러스터 거리:
[[0.9220768  1.46553151 1.13956805 ... 1.16559918 1.03852189 0.23340263]
 [1.14159679 2.51721597 0.1199124  ... 0.70700803 2.20414144 0.98271691]
 [0.78786246 0.77354687 1.74914157 ... 1.97061341 0.71561277 0.94399739]
 ...
 [0.44639122 1.10631579 1.48991975 ... 1.79125448 1.03195812 0.81205971]
 [1.38951924 0.79790385 1.98056306 ... 1.97788956 0.23892095 1.05774337]
 [1.14920754 2.4536383  0.04506731 ... 0.57163262 2.11331394 0.88166689]]

In [57]:

mglearn.plots.plot_agglomerative_algorithm()

In [58]:

from sklearn.cluster import AgglomerativeClustering
X, y = make_blobs(random_state=1)

agg = AgglomerativeClustering(n_clusters=3)
assignment = agg.fit_predict(X)

mglearn.discrete_scatter(X[:, 0], X[:, 1], assignment)
plt.legend(["클러스터 0", "클러스터 1", "클러스터 2"], loc="best")
plt.xlabel("특성 0")
plt.ylabel("특성 1")

Out[58]:

Text(0,0.5,'특성 1')

In [59]:

mglearn.plots.plot_agglomerative()

In [60]:

from scipy.cluster.hierarchy import dendrogram, ward

X, y = make_blobs(random_state=0, n_samples=12)
linkage_array = ward(X)
dendrogram(linkage_array)

ax = plt.gca()
bounds = ax.get_xbound()
ax.plot(bounds, [7.25, 7.25], '--', c='k')
ax.plot(bounds, [4, 4], '--', c='k')

ax.text(bounds[1], 7.25, ' 두 개 클러스터', va='center', fontdict={'size': 15})
ax.text(bounds[1], 4, ' 세 개 클라스터', va='center', fontdict={'size': 15})
plt.xlabel("샘플 번호")
plt.ylabel("클러스터 거리")

Out[60]:

Text(0,0.5,'클러스터 거리')