第十七节 K-means

sklearn PAI：from sklearn.cluster import KMeans

聚类的原理

评价指标：轮廓系数，一般[-1,1]之间，一般超过0-0.1聚类效果已经十分不错

from sklearn.cluster import KMeans  # K-means PAI
import pandas as pd
from sklearn.decomposition import PCA
import matplotlib.pyplot as plt
from sklearn.metrics import silhouette_score  # 轮廓系数API

# 数据地址：https://www.kaggle.com/c/instacart-market-basket-analysis/data
# 读取表
prior = pd.read_csv(r"E:360DownloadsSoftware降维案列数据order_products__prior.csv")
products = pd.read_csv(r"E:360DownloadsSoftware降维案列数据products.csv")
order = pd.read_csv(r"E:360DownloadsSoftware降维案列数据order.csv")
aisles = pd.read_csv(r"E:360DownloadsSoftware降维案列数据aisles.csv")

# 合并表，prodyct_id按该列合并
_mg = pd.merge(prior, products, on=['prodyct_id', 'product_id'])
_mg = pd.merge(_mg, order, on=['order_id', 'order_id'])
mt = pd.merge(_mg, aisles, on=['aisle_id', 'aisle_id'])

# 使用交叉表，构造用户-购买商品类别表
cross = pd.crosstab(mt['user_id'], mt['aisle'])

# 进行主成分分析，将冗余的商品类别过滤掉，即将少量或者几乎没有人购买的商品类别过滤掉
pca = PCA(n_components=0.9)
data = pca.fit_transform(cross)

data = data[0:500,:]

# n_clusters 开始聚类中心的数量，init初始化方法，默认k-means++
km = KMeans(n_clusters=4)
km.fit(data)
predict = km.predict(data)

plt.figure(figsize=(10, 10))
colored = ['orange', 'green', 'blue', 'purple']
colr = [colored[i] for i in predict]
plt.scatter(data[:,1], data[:,20], color = colr)
plt.xlabel("1")
plt.ylabel('20')
plt.show()

# 聚类的评价：轮廓系数在[-1,1]之间，一般超过0-0.1聚类效果已经十分不错

# 第一个参数特征值，第二个参数被聚类标记的目标值
print(silhouette_score(data, predict))