import pandas as pd
from sklearn.decomposition import PCA
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score
# 1.获取数据
order_product = pd.read_csv("./data/instacart/order_products__prior.csv")
products = pd.read_csv("./data/instacart/products.csv")
orders = pd.read_csv("./data/instacart/orders.csv")
aisles = pd.read_csv("./data/instacart/aisles.csv")
# 2.数据基本处理
# 2.1 合并表格
table1 = pd.merge(order_product, products, on=["product_id", "product_id"])
table2 = pd.merge(table1, orders, on=["order_id", "order_id"])
table = pd.merge(table2, aisles, on=["aisle_id", "aisle_id"])
# 2.2 交叉表合并 主要取用户和物品来进行分析
table = pd.crosstab(table["user_id"], table["aisle"])
# 2.3 数据截取
table = table[:1000]
# 3.特征⼯程 — PCA
transfer = PCA(n_components=0.9)
data = transfer.fit_transform(table)
# 4.机器学习（k-means）
estimator = KMeans(n_clusters=8, random_state=22)
y_predict = estimator.fit_predict(data)
# 5.模型评估
score = silhouette_score(data, y_predict)
print(score)
