特征降维和聚类的使用

coding=utf-8

“”"
author:lei
function:
“”"

from sklearn.cluster import KMeans
import pandas as pd
from sklearn.decomposition import PCA
from sklearn.metrics import silhouette_score

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")

数据基本处理，表格合并

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”])

print(table.shape)
print(table.head())

交叉表合并

data = pd.crosstab(table[“user_id”], table[“aisle”])
print(data.head())
print(data.shape)

数据截取

new_data = data[:1000]
print(new_data.shape)

特征工程

transform = PCA(n_components=0.9)
trans_data = transform.fit_transform(new_data)
print(trans_data.shape)

机器学习

estimator = KMeans(n_clusters=5)
y_pre = estimator.fit_predict(trans_data)

模型评估

print(silhouette_score(trans_data, y_pre))