第四节 数据降维案列

Posted 2021-03-03 kogmaw

import pandas as pd
from sklearn.decomposition import PCA

# 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)