
from sklearn.preprocessing import scale
from sklearn.datasets import load_iris
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
%matplotlib inline

iris = load_iris()
# 보다 편리한 데이터 Handling을 위해 DataFrame으로 변환
irisDF = pd.DataFrame(data=iris.data, columns=['sepal_length','sepal_width','petal_length','petal_width'])
irisDF.head(3)


kmeans = KMeans(n_clusters=3, init='k-means++', max_iter=300,random_state=0) # 초기 중심 설정 방식인 init는 default 값으로
kmeans.fit(irisDF)

KMeans(n_clusters=3, random_state=0)


print(kmeans.labels_)

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


irisDF['target'] = iris.target
irisDF['cluster']=kmeans.labels_
iris_result = irisDF.groupby(['target','cluster'])['sepal_length'].count()
print(iris_result)

target  cluster
0       1          50
1       0          48
        2           2
2       0          14
        2          36
Name: sepal_length, dtype: int64


# PCA를 통해 2개로 속성을 차원 축소한 뒤에 군집화를 시각화
from sklearn.decomposition import PCA

pca = PCA(n_components=2)
pca_transformed = pca.fit_transform(iris.data)

irisDF['pca_x'] = pca_transformed[:,0]
irisDF['pca_y'] = pca_transformed[:,1]
irisDF.head(3)


# cluster 값이 0, 1, 2 인 경우마다 별도의 Index로 추출
marker0_ind = irisDF[irisDF['cluster']==0].index
marker1_ind = irisDF[irisDF['cluster']==1].index
marker2_ind = irisDF[irisDF['cluster']==2].index

# cluster값 0, 1, 2에 해당하는 Index로 각 cluster 레벨의 pca_x, pca_y 값 추출. o, s, ^ 로 marker 표시
plt.scatter(x=irisDF.loc[marker0_ind,'pca_x'], y=irisDF.loc[marker0_ind,'pca_y'], marker='o') 
plt.scatter(x=irisDF.loc[marker1_ind,'pca_x'], y=irisDF.loc[marker1_ind,'pca_y'], marker='s')
plt.scatter(x=irisDF.loc[marker2_ind,'pca_x'], y=irisDF.loc[marker2_ind,'pca_y'], marker='^')

plt.xlabel('PCA 1')
plt.ylabel('PCA 2')
plt.title('3 Clusters Visualization by 2 PCA Components')
plt.show()


import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
from sklearn.datasets import make_blobs
%matplotlib inline

X, y = make_blobs(n_samples=200, n_features=2, centers=3, cluster_std=0.8, random_state=0)
print(X.shape, y.shape)

# y target 값의 분포를 확인
unique, counts = np.unique(y, return_counts=True)
print(unique,counts)

(200, 2) (200,)
[0 1 2] [67 67 66]


import pandas as pd

clusterDF = pd.DataFrame(data=X, columns=['ftr1', 'ftr2'])
clusterDF['target'] = y
clusterDF.head(3)


target_list = np.unique(y)
# 각 target별 scatter plot 의 marker 값들. 
markers=['o', 's', '^', 'P','D','H','x']
# 3개의 cluster 영역으로 구분한 데이터 셋을 생성했으므로 target_list는 [0,1,2]
# target==0, target==1, target==2 로 scatter plot을 marker별로 생성. 
for target in target_list:
    target_cluster = clusterDF[clusterDF['target']==target]
    plt.scatter(x=target_cluster['ftr1'], y=target_cluster['ftr2'], edgecolor='k', marker=markers[target] )
plt.show()


# KMeans 객체를 이용하여 X 데이터를 K-Means 클러스터링 수행 
kmeans = KMeans(n_clusters=3, init='k-means++', max_iter=200, random_state=0)
cluster_labels = kmeans.fit_predict(X)
clusterDF['kmeans_label']  = cluster_labels

#cluster_centers_ 는 개별 클러스터의 중심 위치 좌표 시각화를 위해 추출
centers = kmeans.cluster_centers_
unique_labels = np.unique(cluster_labels)
markers=['o', 's', '^', 'P','D','H','x']

# 군집된 label 유형별로 iteration 하면서 marker 별로 scatter plot 수행. 
for label in unique_labels:
    label_cluster = clusterDF[clusterDF['kmeans_label']==label]
    center_x_y = centers[label]
    plt.scatter(x=label_cluster['ftr1'], y=label_cluster['ftr2'], edgecolor='k', 
                marker=markers[label] )
    
    # 군집별 중심 위치 좌표 시각화 
    plt.scatter(x=center_x_y[0], y=center_x_y[1], s=200, color='white',
                alpha=0.9, edgecolor='k', marker=markers[label])
    plt.scatter(x=center_x_y[0], y=center_x_y[1], s=70, color='k', edgecolor='k', 
                marker='$%d$' % label)

plt.show()


print(clusterDF.groupby('target')['kmeans_label'].value_counts())

target  kmeans_label
0       0               66
        1                1
1       2               67
2       1               65
        2                1
Name: kmeans_label, dtype: int64


from sklearn.preprocessing import scale
from sklearn.datasets import load_iris
from sklearn.cluster import KMeans
# 실루엣 분석 metric 값을 구하기 위한 API 추가
from sklearn.metrics import silhouette_samples, silhouette_score
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

%matplotlib inline

iris = load_iris()
feature_names = ['sepal_length','sepal_width','petal_length','petal_width']
irisDF = pd.DataFrame(data=iris.data, columns=feature_names)
kmeans = KMeans(n_clusters=3, init='k-means++', max_iter=300,random_state=0).fit(irisDF)

irisDF['cluster'] = kmeans.labels_

# iris 의 모든 개별 데이터에 실루엣 계수값을 구함. 
score_samples = silhouette_samples(iris.data, irisDF['cluster'])
print('silhouette_samples( ) return 값의 shape' , score_samples.shape)

# irisDF에 실루엣 계수 컬럼 추가
irisDF['silhouette_coeff'] = score_samples

# 모든 데이터의 평균 실루엣 계수값을 구함. 
average_score = silhouette_score(iris.data, irisDF['cluster'])
print('붓꽃 데이터셋 Silhouette Analysis Score:{0:.3f}'.format(average_score))

irisDF.head(3)

silhouette_samples( ) return 값의 shape (150,)
붓꽃 데이터셋 Silhouette Analysis Score:0.553


# 군집별 평균 실루엣 계수 값
irisDF.groupby('cluster')['silhouette_coeff'].mean()

cluster
0    0.417320
1    0.798140
2    0.451105
Name: silhouette_coeff, dtype: float64


irisDF = pd.DataFrame(data=iris.data, columns=['sepal_length','sepal_width','petal_length','petal_width'])


iris_real = irisDF.copy()
# PCA를 통해 2개로 속성을 차원 축소한 뒤에 군집화를 시각화
from sklearn.decomposition import PCA

pca = PCA(n_components=2)
pca_transformed = pca.fit_transform(iris_real)

iris_real['pca_x'] = pca_transformed[:,0]
iris_real['pca_y'] = pca_transformed[:,1]
iris_real = iris_real[['pca_x', 'pca_y']]
iris_real.head(5)


clustering_inertia = []

for n in range(1, 11):
    model = KMeans(n_clusters = n, init = 'k-means++', n_init = 10, 
                  max_iter=300, random_state = 2020)
    model.fit(iris_real.values)
    clustering_inertia.append(model.inertia_)
    
plt.plot(np.arange(1,11), clustering_inertia, 'o')
plt.plot(np.arange(1, 11), clustering_inertia, '-')
plt.xlabel('Number of Clusters')
plt.ylabel('inertia')
plt.show()

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py:881: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1.
  warnings.warn(


from yellowbrick.cluster import KElbowVisualizer
model = KMeans(init='k-means++', n_init = 10, max_iter=300,random_state=2020)
visualizer = KElbowVisualizer(model, k = (1,11))
plt.xlabel('Number of Clusters')
plt.ylabel('inertia')
iris_visual = visualizer.fit(iris_real.values)

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py:881: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1.
  warnings.warn(


# 시각화 결과
model = KMeans(n_clusters = 3, init='k-means++', n_init = 10, max_iter=300,random_state=2020)
model.fit(iris_real.values)
label = model.labels_
centroid = model.cluster_centers_
print(label)
print(centroid)

[1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
 1 1 1 1 1 1 1 1 1 1 1 1 1 2 0 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
 0 0 0 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 0 2 2 2 2 0 2 2 2 2
 2 2 0 0 2 2 2 2 0 2 0 2 0 2 2 0 0 2 2 2 2 2 0 2 2 2 2 0 2 2 2 0 2 2 2 0 2
 2 0]
[[ 0.66567601 -0.3316042 ]
 [-2.64241546  0.19088505]
 [ 2.34652659  0.27393856]]


h = 0.02
x_min, x_max = iris_real['pca_x'].min() - 1, iris_real['pca_x'].max() + 1
y_min, y_max = iris_real['pca_y'].min() - 1, iris_real['pca_y'].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
Z = model.predict(np.c_[xx.ravel(), yy.ravel()])


plt.figure(1, figsize = (15, 7))
plt.clf() # 플롯의 모든 것을 지움

Z = Z.reshape(xx.shape)
# 이미지 출력하기
plt.imshow(Z, interpolation = 'nearest', extent = (xx.min(), xx.max(), yy.min(), yy.max()),
           cmap = 'Pastel1', aspect = 'auto', origin = 'lower' )

plt.scatter ( x = 'pca_x', y = 'pca_y', data = iris_real, c = label, s = 200)
plt.scatter( x = centroid[:, 0], y = centroid[: , 1], s = 300, c = 'red', alpha = 0.5)


plt.show()


# 시각화 결과
model2 = KMeans(n_clusters = 4, init='k-means++', n_init = 10, max_iter=300,random_state=2020)
model2.fit(iris_real.values)
label2 = model2.labels_
centroid2 = model2.cluster_centers_
print(label)
print(centroid)

[1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
 1 1 1 1 1 1 1 1 1 1 1 1 1 2 0 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
 0 0 0 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 0 2 2 2 2 0 2 2 2 2
 2 2 0 0 2 2 2 2 0 2 0 2 0 2 2 0 0 2 2 2 2 2 0 2 2 2 2 0 2 2 2 0 2 2 2 0 2
 2 0]
[[ 0.66567601 -0.3316042 ]
 [-2.64241546  0.19088505]
 [ 2.34652659  0.27393856]]


h = 0.02
x_min, x_max = iris_real['pca_x'].min() - 1, iris_real['pca_x'].max() + 1
y_min, y_max = iris_real['pca_y'].min() - 1, iris_real['pca_y'].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
Z2 = model2.predict(np.c_[xx.ravel(), yy.ravel()])


plt.figure(1, figsize = (15, 7))
plt.clf() # 플롯의 모든 것을 지움

Z2 = Z2.reshape(xx.shape)
# 이미지 출력하기
plt.imshow(Z2, interpolation = 'nearest', extent = (xx.min(), xx.max(), yy.min(), yy.max()),
           cmap = 'Paired', aspect = 'auto', origin = 'lower' )

plt.scatter ( x = 'pca_x', y = 'pca_y', data = iris_real, c = label2, s = 200)
plt.scatter( x = centroid2[:, 0], y = centroid2[: , 1], s = 300, c = 'red', alpha = 0.5)


plt.show()


from sklearn.datasets import make_blobs
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_samples, silhouette_score

import matplotlib.pyplot as plt
import matplotlib.cm as cm
import numpy as np

# Generating the sample data from make_blobs
# This particular setting has one distinct cluster and 3 clusters placed close
# together.
X, y = make_blobs(
    n_samples=500,
    n_features=2,
    centers=4,
    cluster_std=1,
    center_box=(-10.0, 10.0),
    shuffle=True,
    random_state=1,
)  # For reproducibility

range_n_clusters = [2, 3, 4, 5, 6]

for n_clusters in range_n_clusters:
    # Create a subplot with 1 row and 2 columns
    fig, (ax1, ax2) = plt.subplots(1, 2)
    fig.set_size_inches(18, 7)

    # The 1st subplot is the silhouette plot
    # The silhouette coefficient can range from -1, 1 but in this example all
    # lie within [-0.1, 1]
    ax1.set_xlim([-0.1, 1])
    # The (n_clusters+1)*10 is for inserting blank space between silhouette
    # plots of individual clusters, to demarcate them clearly.
    ax1.set_ylim([0, len(X) + (n_clusters + 1) * 10])

    # Initialize the clusterer with n_clusters value and a random generator
    # seed of 10 for reproducibility.
    clusterer = KMeans(n_clusters=n_clusters, random_state=10)
    cluster_labels = clusterer.fit_predict(X)

    # The silhouette_score gives the average value for all the samples.
    # This gives a perspective into the density and separation of the formed
    # clusters
    silhouette_avg = silhouette_score(X, cluster_labels)
    print(
        "For n_clusters =",
        n_clusters,
        "The average silhouette_score is :",
        silhouette_avg,
    )

    # Compute the silhouette scores for each sample
    sample_silhouette_values = silhouette_samples(X, cluster_labels)

    y_lower = 10
    for i in range(n_clusters):
        # Aggregate the silhouette scores for samples belonging to
        # cluster i, and sort them
        ith_cluster_silhouette_values = sample_silhouette_values[cluster_labels == i]

        ith_cluster_silhouette_values.sort()

        size_cluster_i = ith_cluster_silhouette_values.shape[0]
        y_upper = y_lower + size_cluster_i

        color = cm.nipy_spectral(float(i) / n_clusters)
        ax1.fill_betweenx(
            np.arange(y_lower, y_upper),
            0,
            ith_cluster_silhouette_values,
            facecolor=color,
            edgecolor=color,
            alpha=0.7,
        )

        # Label the silhouette plots with their cluster numbers at the middle
        ax1.text(-0.05, y_lower + 0.5 * size_cluster_i, str(i))

        # Compute the new y_lower for next plot
        y_lower = y_upper + 10  # 10 for the 0 samples

    ax1.set_title("The silhouette plot for the various clusters.")
    ax1.set_xlabel("The silhouette coefficient values")
    ax1.set_ylabel("Cluster label")

    # The vertical line for average silhouette score of all the values
    ax1.axvline(x=silhouette_avg, color="red", linestyle="--")

    ax1.set_yticks([])  # Clear the yaxis labels / ticks
    ax1.set_xticks([-0.1, 0, 0.2, 0.4, 0.6, 0.8, 1])

    # 2nd Plot showing the actual clusters formed
    colors = cm.nipy_spectral(cluster_labels.astype(float) / n_clusters)
    ax2.scatter(
        X[:, 0], X[:, 1], marker=".", s=30, lw=0, alpha=0.7, c=colors, edgecolor="k"
    )

    # Labeling the clusters
    centers = clusterer.cluster_centers_
    # Draw white circles at cluster centers
    ax2.scatter(
        centers[:, 0],
        centers[:, 1],
        marker="o",
        c="white",
        alpha=1,
        s=200,
        edgecolor="k",
    )

    for i, c in enumerate(centers):
        ax2.scatter(c[0], c[1], marker="$%d$" % i, alpha=1, s=50, edgecolor="k")

    ax2.set_title("The visualization of the clustered data.")
    ax2.set_xlabel("Feature space for the 1st feature")
    ax2.set_ylabel("Feature space for the 2nd feature")

    plt.suptitle(
        "Silhouette analysis for KMeans clustering on sample data with n_clusters = %d"
        % n_clusters,
        fontsize=14,
        fontweight="bold",
    )

plt.show()

For n_clusters = 2 The average silhouette_score is : 0.7049787496083262
For n_clusters = 3 The average silhouette_score is : 0.5882004012129721
For n_clusters = 4 The average silhouette_score is : 0.6505186632729437
For n_clusters = 5 The average silhouette_score is : 0.56376469026194
For n_clusters = 6 The average silhouette_score is : 0.4504666294372765


### 여러개의 클러스터링 갯수를 List로 입력 받아 각각의 실루엣 계수를 면적으로 시각화한 함수 작성
def visualize_silhouette(cluster_lists, X_features): 
    
    from sklearn.datasets import make_blobs
    from sklearn.cluster import KMeans
    from sklearn.metrics import silhouette_samples, silhouette_score

    import matplotlib.pyplot as plt
    import matplotlib.cm as cm
    import math
    
    # 입력값으로 클러스터링 갯수들을 리스트로 받아서, 각 갯수별로 클러스터링을 적용하고 실루엣 개수를 구함
    n_cols = len(cluster_lists)
    
    # plt.subplots()으로 리스트에 기재된 클러스터링 수만큼의 sub figures를 가지는 axs 생성 
    fig, axs = plt.subplots(figsize=(4*n_cols, 4), nrows=1, ncols=n_cols)
    
    # 리스트에 기재된 클러스터링 갯수들을 차례로 iteration 수행하면서 실루엣 개수 시각화
    for ind, n_cluster in enumerate(cluster_lists):
        
        # KMeans 클러스터링 수행하고, 실루엣 스코어와 개별 데이터의 실루엣 값 계산. 
        clusterer = KMeans(n_clusters = n_cluster, max_iter=500, random_state=0)
        cluster_labels = clusterer.fit_predict(X_features)
        
        sil_avg = silhouette_score(X_features, cluster_labels)
        sil_values = silhouette_samples(X_features, cluster_labels)
        
        y_lower = 10
        axs[ind].set_title('Number of Cluster : '+ str(n_cluster)+'\n' \
                          'Silhouette Score :' + str(round(sil_avg,3)) )
        axs[ind].set_xlabel("The silhouette coefficient values")
        axs[ind].set_ylabel("Cluster label")
        axs[ind].set_xlim([-0.1, 1])
        axs[ind].set_ylim([0, len(X_features) + (n_cluster + 1) * 10])
        axs[ind].set_yticks([])  # Clear the yaxis labels / ticks
        axs[ind].set_xticks([0, 0.2, 0.4, 0.6, 0.8, 1])
        
        # 클러스터링 갯수별로 fill_betweenx( )형태의 막대 그래프 표현. 
        for i in range(n_cluster):
            ith_cluster_sil_values = sil_values[cluster_labels==i]
            ith_cluster_sil_values.sort()
            
            size_cluster_i = ith_cluster_sil_values.shape[0]
            y_upper = y_lower + size_cluster_i
            
            color = cm.nipy_spectral(float(i) / n_cluster)
            axs[ind].fill_betweenx(np.arange(y_lower, y_upper), 0, ith_cluster_sil_values, \
                                facecolor=color, edgecolor=color, alpha=0.7)
            axs[ind].text(-0.05, y_lower + 0.5 * size_cluster_i, str(i))
            y_lower = y_upper + 10
            
        axs[ind].axvline(x=sil_avg, color="red", linestyle="--")


# make_blobs 을 통해 clustering 을 위한 4개의 클러스터 중심의 500개 2차원 데이터 셋 생성  
from sklearn.datasets import make_blobs
X, y = make_blobs(n_samples=500, n_features=2, centers=4, cluster_std=1, \
                  center_box=(-10.0, 10.0), shuffle=True, random_state=1)  

# cluster 개수를 2개, 3개, 4개, 5개 일때의 클러스터별 실루엣 계수 평균값을 시각화 
visualize_silhouette([ 2, 3, 4, 5 ], X)


# 붓꽃 데이터
from sklearn.datasets import load_iris

iris=load_iris()
visualize_silhouette([ 2, 3, 4, 5 ], iris.data)


import numpy as np
from sklearn.datasets import make_blobs
from sklearn.cluster import MeanShift

X, y = make_blobs(n_samples=200, n_features=2, centers=3, 
                  cluster_std=0.7, random_state=0) # 3개의 군집 데이터

meanshift= MeanShift(bandwidth=0.8)
cluster_labels = meanshift.fit_predict(X)
print('cluster labels 유형:', np.unique(cluster_labels))

cluster labels 유형: [0 1 2 3 4 5]


meanshift= MeanShift(bandwidth=1) # bandwidth를 살짝 높였다.
cluster_labels = meanshift.fit_predict(X)
print('cluster labels 유형:', np.unique(cluster_labels))

cluster labels 유형: [0 1 2]


# bandwidth를 최적화 값으로 설정하기 위해 값을 찾음

from sklearn.cluster import estimate_bandwidth

bandwidth = estimate_bandwidth(X)
print('bandwidth 값:', round(bandwidth,3))

bandwidth 값: 1.816


import pandas as pd


clusterDF = pd.DataFrame(data=X, columns=['ftr1', 'ftr2'])
clusterDF['target'] = y

# estimate_bandwidth()로 최적의 bandwidth 계산
best_bandwidth = estimate_bandwidth(X)

meanshift= MeanShift(bandwidth=best_bandwidth)
cluster_labels = meanshift.fit_predict(X)
print('cluster labels 유형:',np.unique(cluster_labels))

cluster labels 유형: [0 1 2]


import matplotlib.pyplot as plt
%matplotlib inline

clusterDF['meanshift_label']  = cluster_labels
centers = meanshift.cluster_centers_    # 군집 중심 좌표 표시 
unique_labels = np.unique(cluster_labels)
markers=['o', 's', '^', 'x', '*']

for label in unique_labels:
    label_cluster = clusterDF[clusterDF['meanshift_label']==label]
    center_x_y = centers[label]
    # 군집별로 다른 마커로 산점도 적용
    plt.scatter(x=label_cluster['ftr1'], y=label_cluster['ftr2'], edgecolor='k', marker=markers[label] )
    
    # 군집별 중심 표현
    plt.scatter(x=center_x_y[0], y=center_x_y[1], s=200, color='gray', alpha=0.9, marker=markers[label])
    plt.scatter(x=center_x_y[0], y=center_x_y[1], s=70, color='k', edgecolor='k', marker='$%d$' % label)
    
plt.show()


# target값과 군집 label 값을 비교
print(clusterDF.groupby('target')['meanshift_label'].value_counts())

target  meanshift_label
0       0                  67
1       1                  67
2       2                  66
Name: meanshift_label, dtype: int64


from sklearn.datasets import load_iris
from sklearn.cluster import KMeans

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
%matplotlib inline

iris = load_iris()
feature_names = ['sepal_length','sepal_width','petal_length','petal_width']

# 보다 편리한 데이타 Handling을 위해 DataFrame으로 변환
irisDF = pd.DataFrame(data=iris.data, columns=feature_names)
irisDF['target'] = iris.target


from sklearn.mixture import GaussianMixture

gmm = GaussianMixture(n_components=3, random_state=0).fit(iris.data)
gmm_cluster_labels = gmm.predict(iris.data)

# 클러스터링 결과를 irisDF 의 'gmm_cluster' 컬럼명으로 저장
irisDF['gmm_cluster'] = gmm_cluster_labels
irisDF['target'] = iris.target

# target 값에 따라서 gmm_cluster 값이 어떻게 매핑되었는지 확인. 
iris_result = irisDF.groupby(['target'])['gmm_cluster'].value_counts()
print(iris_result)

target  gmm_cluster
0       0              50
1       2              45
        1               5
2       1              50
Name: gmm_cluster, dtype: int64


kmeans = KMeans(n_clusters=3, init='k-means++', max_iter=300,random_state=0).fit(iris.data)
kmeans_cluster_labels = kmeans.predict(iris.data)
irisDF['kmeans_cluster'] = kmeans_cluster_labels
iris_result = irisDF.groupby(['target'])['kmeans_cluster'].value_counts()
print(iris_result)

target  kmeans_cluster
0       1                 50
1       0                 48
        2                  2
2       2                 36
        0                 14
Name: kmeans_cluster, dtype: int64


### 클러스터 결과를 담은 DataFrame과 사이킷런의 Cluster 객체등을 인자로 받아 클러스터링 결과를 시각화하는 함수  
def visualize_cluster_plot(clusterobj, dataframe, label_name, iscenter=True):
    if iscenter :
        centers = clusterobj.cluster_centers_
        
    unique_labels = np.unique(dataframe[label_name].values)
    markers=['o', 's', '^', 'x', '*']
    isNoise=False

    for label in unique_labels:
        label_cluster = dataframe[dataframe[label_name]==label]
        if label == -1:
            cluster_legend = 'Noise'
            isNoise=True
        else :
            cluster_legend = 'Cluster '+str(label)
        
        plt.scatter(x=label_cluster['ftr1'], y=label_cluster['ftr2'], s=70,\
                    edgecolor='k', marker=markers[label], label=cluster_legend)
        
        if iscenter:
            center_x_y = centers[label]
            plt.scatter(x=center_x_y[0], y=center_x_y[1], s=250, color='white',
                        alpha=0.9, edgecolor='k', marker=markers[label])
            plt.scatter(x=center_x_y[0], y=center_x_y[1], s=70, color='k',\
                        edgecolor='k', marker='$%d$' % label)
    if isNoise:
        legend_loc='upper center'
    else: legend_loc='upper right'
    
    plt.legend(loc=legend_loc)
    plt.show()


from sklearn.datasets import make_blobs

# make_blobs() 로 300개의 데이터 셋, 3개의 cluster 셋, cluster_std=0.5 을 만듬. 
X, y = make_blobs(n_samples=300, n_features=2, centers=3, cluster_std=0.5, random_state=0)

# 길게 늘어난 타원형의 데이터 셋을 생성하기 위해 변환함. 
transformation = [[0.60834549, -0.63667341], [-0.40887718, 0.85253229]]
X_aniso = np.dot(X, transformation)
# feature 데이터 셋과 make_blobs( ) 의 y 결과 값을 DataFrame으로 저장
clusterDF = pd.DataFrame(data=X_aniso, columns=['ftr1', 'ftr2'])
clusterDF['target'] = y
# 생성된 데이터 셋을 target 별로 다른 marker 로 표시하여 시각화 함. 
visualize_cluster_plot(None, clusterDF, 'target', iscenter=False)


# 3개의 Cluster 기반 Kmeans 를 X_aniso 데이터 셋에 적용 
kmeans = KMeans(3, random_state=0)
kmeans_label = kmeans.fit_predict(X_aniso)
clusterDF['kmeans_label'] = kmeans_label

visualize_cluster_plot(kmeans, clusterDF, 'kmeans_label',iscenter=True)


# 3개의 n_components기반 GMM을 X_aniso 데이터 셋에 적용 
gmm = GaussianMixture(n_components=3, random_state=0)
gmm_label = gmm.fit(X_aniso).predict(X_aniso)
clusterDF['gmm_label'] = gmm_label

# GaussianMixture는 cluster_centers_ 속성이 없으므로 iscenter를 False로 설정. 
visualize_cluster_plot(gmm, clusterDF, 'gmm_label',iscenter=False)


print('### KMeans Clustering ###')
print(clusterDF.groupby('target')['kmeans_label'].value_counts())
print('\n### Gaussian Mixture Clustering ###')
print(clusterDF.groupby('target')['gmm_label'].value_counts())

### KMeans Clustering ###
target  kmeans_label
0       2                73
        0                27
1       1               100
2       0                86
        2                14
Name: kmeans_label, dtype: int64

### Gaussian Mixture Clustering ###
target  gmm_label
0       2            100
1       1            100
2       0            100
Name: gmm_label, dtype: int64


from sklearn.datasets import load_iris

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
%matplotlib inline

iris = load_iris()
feature_names = ['sepal_length','sepal_width','petal_length','petal_width']

# 보다 편리한 데이타 Handling을 위해 DataFrame으로 변환
irisDF = pd.DataFrame(data=iris.data, columns=feature_names)
irisDF['target'] = iris.target


from sklearn.cluster import DBSCAN

dbscan = DBSCAN(eps=0.6, min_samples=8, metric='euclidean')
dbscan_labels = dbscan.fit_predict(iris.data)

irisDF['dbscan_cluster'] = dbscan_labels
irisDF['target'] = iris.target

iris_result = irisDF.groupby(['target'])['dbscan_cluster'].value_counts()
print(iris_result)

target  dbscan_cluster
0        0                49
        -1                 1
1        1                46
        -1                 4
2        1                42
        -1                 8
Name: dbscan_cluster, dtype: int64


from sklearn.decomposition import PCA
# 2차원으로 시각화하기 위해 PCA n_componets=2로 피처 데이터 세트 변환
pca = PCA(n_components=2, random_state=0)
pca_transformed = pca.fit_transform(iris.data)
# visualize_cluster_2d( ) 함수는 ftr1, ftr2 컬럼을 좌표에 표현하므로 PCA 변환값을 해당 컬럼으로 생성
irisDF['ftr1'] = pca_transformed[:,0]
irisDF['ftr2'] = pca_transformed[:,1]

visualize_cluster_plot(dbscan, irisDF, 'dbscan_cluster', iscenter=False)


# eps를 증가시켜 노이즈 데이터의 개수를 줄인 모습

from sklearn.cluster import DBSCAN

dbscan = DBSCAN(eps=0.8, min_samples=8, metric='euclidean')
dbscan_labels = dbscan.fit_predict(iris.data)

irisDF['dbscan_cluster'] = dbscan_labels
irisDF['target'] = iris.target

iris_result = irisDF.groupby(['target'])['dbscan_cluster'].value_counts()
print(iris_result)

visualize_cluster_plot(dbscan, irisDF, 'dbscan_cluster', iscenter=False)

target  dbscan_cluster
0        0                50
1        1                50
2        1                47
        -1                 3
Name: dbscan_cluster, dtype: int64


# min_samples를 늘림 -> 노이즈 데이터가 기존보다 많이 증가함

dbscan = DBSCAN(eps=0.6, min_samples=16, metric='euclidean')
dbscan_labels = dbscan.fit_predict(iris.data)

irisDF['dbscan_cluster'] = dbscan_labels
irisDF['target'] = iris.target

iris_result = irisDF.groupby(['target'])['dbscan_cluster'].value_counts()
print(iris_result)
visualize_cluster_plot(dbscan, irisDF, 'dbscan_cluster', iscenter=False)

target  dbscan_cluster
0        0                48
        -1                 2
1        1                44
        -1                 6
2        1                36
        -1                14
Name: dbscan_cluster, dtype: int64


from sklearn.datasets import make_circles # 내부 원과 외부 원으로 구분되는 데이터 세트를 생성한다. 
# noise는 노이즈 데이터 세트의 비율, factor는 외부 원과 내부 원의 scale 비율
X, y = make_circles(n_samples=1000, shuffle=True, noise=0.05, random_state=0, factor=0.5)
clusterDF = pd.DataFrame(data=X, columns=['ftr1', 'ftr2'])
clusterDF['target'] = y

visualize_cluster_plot(None, clusterDF, 'target', iscenter=False)


# KMeans로 make_circles( ) 데이터 셋을 클러스터링 수행. 
from sklearn.cluster import KMeans

kmeans = KMeans(n_clusters=2, max_iter=1000, random_state=0)
kmeans_labels = kmeans.fit_predict(X)
clusterDF['kmeans_cluster'] = kmeans_labels

visualize_cluster_plot(kmeans, clusterDF, 'kmeans_cluster', iscenter=True)


# GMM으로 make_circles( ) 데이터 셋을 클러스터링 수행. 
from sklearn.mixture import GaussianMixture

gmm = GaussianMixture(n_components=2, random_state=0)
gmm_label = gmm.fit(X).predict(X)
clusterDF['gmm_cluster'] = gmm_label

visualize_cluster_plot(gmm, clusterDF, 'gmm_cluster', iscenter=False)


# DBSCAN으로 make_circles( ) 데이터 셋을 클러스터링 수행. 
from sklearn.cluster import DBSCAN

dbscan = DBSCAN(eps=0.2, min_samples=10, metric='euclidean')
dbscan_labels = dbscan.fit_predict(X)
clusterDF['dbscan_cluster'] = dbscan_labels

visualize_cluster_plot(dbscan, clusterDF, 'dbscan_cluster', iscenter=False)

	sepal_length	sepal_width	petal_length	petal_width
0	5.1	3.5	1.4	0.2
1	4.9	3.0	1.4	0.2
2	4.7	3.2	1.3	0.2

	sepal_length	sepal_width	petal_length	petal_width	cluster	pca_x	pca_y
0	5.1	3.5	1.4	0.2	1	-2.684126	0.319397
1	4.9	3.0	1.4	0.2	1	-2.714142	-0.177001
2	4.7	3.2	1.3	0.2	1	-2.888991	-0.144949

	ftr1	ftr2	target
0	-1.692427	3.622025	2
1	0.697940	4.428867	0
2	1.100228	4.606317	0

	sepal_length	sepal_width	petal_length	petal_width	cluster	silhouette_coeff
0	5.1	3.5	1.4	0.2	1	0.852955
1	4.9	3.0	1.4	0.2	1	0.815495
2	4.7	3.2	1.3	0.2	1	0.829315

	pca_x	pca_y
0	-2.684126	0.319397
1	-2.714142	-0.177001
2	-2.888991	-0.144949
3	-2.745343	-0.318299
4	-2.728717	0.326755

티스토리

[파이썬 머신러닝 완벽 가이드] 7장. 군집화

[파이썬 머신러닝 완벽 가이드] 7장. 군집화

<파이썬 머신러닝 완벽 가이드>¶

군집화 ( p409 ~ p465 )¶

01. K - 평균 알고리즘¶

K-평균을 이용한 붓꽃 데이터 세트 군집화¶

군집화 알고리즘 테스트를 위한 데이터 생성¶

02. 군집 평가 ( Cluster Evaluation )¶

붓꽃 데이터 세트를 이용한 군집 평가¶

군집별 평균 실루엣 계수의 시각화를 통한 군집 개수 최적화 방법¶

03. 평균 이동¶

04. GMM(Gaussian Mixture Model)¶

GMM을 이용한 붓꽃 데이터 세트 군집화¶

GMM과 K-means 비교¶

05. DBSCAN ( Density Based Spatial Clustering of Applications with Noise )¶

DBSCAN 적용하기 - 붓꽃 데이터 세트¶

DBSCAN 적용하기 - make_circles() 데이터 세트¶