書記が数学やるだけ#576 k-平均法

#必要なライブラリ
from sklearn import datasets
from sklearn.decomposition import PCA
import numpy as np
import pandas as pd
from pandas import DataFrame
import matplotlib.pyplot as plt
import seaborn as sns

#irisデータセット
dataset = datasets.load_iris()
target_names = dataset.target_names
targets = dataset.target
feature_names = dataset.feature_names
features = dataset.data
df = DataFrame(features, columns = feature_names)
df['target'] = target_names[targets]

#"petal length (cm)", “sepal length (cm)”の2変数
df1 = df[["petal length (cm)", "petal width (cm)", "target"]]

#実際のデータセット
sns.scatterplot(x='petal length (cm)', y='petal width (cm)', hue='target', data=df1)

df2 = df[["petal length (cm)", "petal width (cm)"]]
#標準化
from sklearn.preprocessing import StandardScaler
dfSS = DataFrame(StandardScaler().fit_transform(df2))
#可視化
sns.scatterplot(x=0, y=1, data=dfSS)

#k-平均法の実行
from sklearn.cluster import KMeans
model = KMeans(n_clusters=3, random_state=0)
model.fit(dfSS)
clusters = model.predict(dfSS)
clusters

#クラスター重心の座標
df_cluster_centers = pd.DataFrame(model.cluster_centers_)
df_cluster_centers.columns = ['x1', 'x2']
df_cluster_centers

df = pd.DataFrame(dfSS)
df['class'] = clusters
# クラスタリングデータ
sns.scatterplot(data=df, x=0, y=1, hue='class', palette='bright')
# クラスター重心
sns.scatterplot(data=df_cluster_centers, x='x1', y='x2', s=400, marker='*', color='black')
plt.show()

# エルボー法を実行
sum_of_squared_errors = []
for i in range(1, 11):
   model = KMeans(n_clusters=i, random_state=0, init='random')
   model.fit(dfSS)
   sum_of_squared_errors.append(model.inertia_)  # 損失関数の値を保存
plt.plot(range(1, 11), sum_of_squared_errors, marker='o')
plt.xlabel('number of clusters')
plt.ylabel('sum of squared errors')
plt.show()

#シルエット分析
import matplotlib.cm as cm
from sklearn.metrics import silhouette_samples
def show_silhouette(fitted_model):
   cluster_labels = np.unique(fitted_model.labels_)
   num_clusters = cluster_labels.shape[0]
   silhouette_vals = silhouette_samples(dfSS, fitted_model.labels_)  # シルエット係数の計算
   # 可視化
   y_ax_lower, y_ax_upper = 0, 0
   y_ticks = []
   for idx, cls in enumerate(cluster_labels):
       cls_silhouette_vals = silhouette_vals[fitted_model.labels_==cls]
       cls_silhouette_vals.sort()
       y_ax_upper += len(cls_silhouette_vals)
       cmap = cm.get_cmap("Spectral")
       rgba = list(cmap(idx/num_clusters))  # rgbaの配列
       rgba[-1] = 0.7  # alpha値を0.7にする
       plt.barh(
           y=range(y_ax_lower, y_ax_upper), 
           width=cls_silhouette_vals,
           height=1.0,
           edgecolor='none',
           color=rgba)
       y_ticks.append((y_ax_lower + y_ax_upper) / 2.0)
       y_ax_lower += len(cls_silhouette_vals)
   silhouette_avg = np.mean(silhouette_vals)
   plt.axvline(silhouette_avg, color='orangered', linestyle='--')
   plt.xlabel('silhouette coefficient')
   plt.ylabel('cluster')
   plt.yticks(y_ticks, cluster_labels + 1)
   plt.show()

for i in range(2, 5):
   model = KMeans(n_clusters=i, random_state=0, init='random')
   model.fit(dfSS)
   show_silhouette(model)