降维案例instacart

# 1.获取数据
# 2.合并表
# 3.找到user_id和aisle之间的关系
# 4.pca降维
import pandas as pd
order_products=pd.read_csv('./data/instacart/order_products__prior.csv')
products=pd.read_csv('./data/instacart/products.csv')
aisles=pd.read_csv('./data/instacart/aisles.csv')
orders=pd.read_csv('./data/instacart/orders.csv')

#合并表
#合并aisles和products
tab1=pd.merge(aisles,products,on=['aisle_id'])
tab2=pd.merge(tab1,order_products,on=['product_id'])
tab3=pd.merge(tab2,orders,on=['order_id'])

# 找到user_id和aisle之间的关系
table=pd.crosstab(tab3['user_id'],tab3['aisle'])
data=table[:10000]

#降维
from sklearn.decomposition import PCA

pca=PCA(n_components=0.95)
data_new=pca.fit_transform(data)
data_new.shape#降维到42个特征了还保留了95%的信息