python库实现简单的聚类和展示

features = quantitative + qual_encoded
# t-SNE：可视化效果最好的降维算法,做这个处理是为了展示
model = TSNE(n_components=2, random_state=0, perplexity=50)
X = train[features].fillna(0.).values
tsne = model.fit_transform(X)

std = StandardScaler()
s = std.fit_transform(X)
pca = PCA(n_components=30)
pca.fit(s)
pc = pca.transform(s)
kmeans = KMeans(n_clusters=5)
# 类别信息在 kmeans.labels_
kmeans.fit(pc)

fr = pd.DataFrame({'tsne1': tsne[:,0], 'tsne2': tsne[:, 1], 'cluster': kmeans.labels_})
sns.lmplot(data=fr, x='tsne1', y='tsne2', hue='cluster', fit_reg=False)
print(np.sum(pca.explained_variance_ratio_))