PCA降维小项目

话不多说，直接上代码

'''
1、获取数据
2、合并表
3、找出user_id和aisle之间的关系
4、PCA降维
'''
import pandas as pd
from sklearn.decomposition import PCA

order_products = pd.read_csv("./instacart/order_products__prior.csv")
products = pd.read_csv("./instacart/products.csv")
orders = pd.read_csv("./instacart/orders.csv")
aisles = pd.read_csv("./instacart/aisles.csv")

table1 = pd.merge(aisles, products, on=["aisle_id", "aisle_id"])
table2 = pd.merge(table1, order_products, on=["product_id", "product_id"])
table3 = pd.merge(table2, orders, on=["order_id", "order_id"])

table = pd.crosstab(table3["user_id"], table3["aisle"])

data = table[:10000]  # 数据太大，简单起见
# PCA降维
transfer = PCA(n_components=0.95)
data_new = transfer.fit_transform(data)
print("data_new: \n", data_new)
print("data_new shape: \n", data_new.shape)  # data.shape为特征量