数据处理的一些基础导包

1. sklearn.manifold

1.1 TSNE降维算法

from sklearn.manifold import TSNE
TSNE(random_state=0).fit_transform(data)

2. sklearn.metrics

2.1 计算轮廓系数 silhouette_score

from sklearn.metrics import silhouette_score
labels = KMeans(n_clusters=2,random_state=0).fit_predict(data)
silhouette_score(data,labels,random_state=0)

2.1.1 绘制轮廓系数图

scores = []
for k in range(2,11):
    labels = KMeans(n_clusters=k,random_state=0).fit_predict(data)
    score = silhouette_score(data,labels,random_state=0)
    scores.append(score)
    
x = range(2,11)
y = scores
plt.plot(x,y,'bx-')
plt.title()
plt.xlabel()
plt.ylabel()
plt.show()

2.2 平衡准确度函数 balanced_accuracy_score

from sklearn.metrics import balanced_accuracy_score
#评估它在测试集上的表现：计算平衡准确度
balanced_accuracy_score(y_test, y_pred)

2.3 混淆矩阵 confusion_matrix

from sklearn.metrics import confusion_matrix
#计算混淆矩阵
cnf_matrix = confusion_matrix(y_test, y_pred)

2.3.1 绘制混淆矩阵图

plt.imshow(cnf_matrix, cmap