机器学习算法基础案例1：instacart

import pandas as pd
from sklearn.decomposition import PCA

#读取四张表的数据
prior=pd.read_csv("C:/01-工作相关/0002-钉钉下载/数据集/instacart-market-basket-analysis/instacart-market-basket-analysis/order_products__prior.csv")
prior.head()

	order_id	product_id	add_to_cart_order	reordered
0	2	33120	1	1
1	2	28985	2	1
2	2	9327	3	0
3	2	45918	4	1
4	2	30035	5	0

product=pd.read_csv("C:/01-工作相关/0002-钉钉下载/数据集/instacart-market-basket-analysis/instacart-market-basket-analysis/products.csv")
product.head()

	product_id	product_name	aisle_id	department_id
0	1	Chocolate Sandwich Cookies	61	19
1	2	All-Seasons Salt	104	13
2	3	Robust Golden Unsweetened Oolong Tea	94	7
3	4	Smart Ones Classic Favorites Mini Rigatoni Wit...	38	1
4	5	Green Chile Anytime Sauce	5	13

orders=pd.read_csv("C:/01-工作相关/0002-钉钉下载/数据集/instacart-market-basket-analysis/instacart-market-basket-analysis/orders.csv")
orders.head()

	order_id	user_id	eval_set	order_number	order_dow	order_hour_of_day	days_since_prior_order
0	2539329	1	prior	1	2	8	NaN
1	2398795	1	prior	2	3	7	15.0
2	473747	1	prior	3	3	12	21.0
3	2254736	1	prior	4	4	7	29.0
4	431534	1	prior	5	4	15	28.0

aisles=pd.read_csv("C:/01-工作相关/0002-钉钉下载/数据集/instacart-market-basket-analysis/instacart-market-basket-analysis/aisles.csv")
aisles.head()

	aisle_id	aisle
0	1	prepared soups salads
1	2	specialty cheeses
2	3	energy granola bars
3	4	instant foods
4	5	marinades meat preparation

_mg=pd.merge(prior,product,on=["product_id","product_id"])
_mg.head()

	order_id	product_id	add_to_cart_order	reordered	product_name	aisle_id	department_id
0	2	33120	1	1	Organic Egg Whites	86	16
1	26	33120	5	0	Organic Egg Whites	86	16
2	120	33120	13	0	Organic Egg Whites	86	16
3	327	33120	5	1	Organic Egg Whites	86	16
4	390	33120	28	1	Organic Egg Whites	86	16

_mg2=pd.merge(_mg,orders,on=["order_id","order_id"])
_mg2.head()

	order_id	product_id	add_to_cart_order	reordered	product_name	aisle_id	department_id	user_id	eval_set	order_number	order_dow	order_hour_of_day	days_since_prior_order
0	2	33120	1	1	Organic Egg Whites	86	16	202279	prior	3	5	9	8.0
1	2	28985	2	1	Michigan Organic Kale	83	4	202279	prior	3	5	9	8.0
2	2	9327	3	0	Garlic Powder	104	13	202279	prior	3	5	9	8.0
3	2	45918	4	1	Coconut Butter	19	13	202279	prior	3	5	9	8.0
4	2	30035	5	0	Natural Sweetener	17	13	202279	prior	3	5	9	8.0

mt=pd.merge(_mg2,aisles,on=["aisle_id","aisle_id"])
mt.head(10)

	order_id	product_id	add_to_cart_order	reordered	product_name	aisle_id	department_id	user_id	eval_set	order_number	order_dow	order_hour_of_day	days_since_prior_order	aisle
0	2	33120	1	1	Organic Egg Whites	86	16	202279	prior	3	5	9	8.0	eggs
1	26	33120	5	0	Organic Egg Whites	86	16	153404	prior	2	0	16	7.0	eggs
2	120	33120	13	0	Organic Egg Whites	86	16	23750	prior	11	6	8	10.0	eggs
3	327	33120	5	1	Organic Egg Whites	86	16	58707	prior	21	6	9	8.0	eggs
4	390	33120	28	1	Organic Egg Whites	86	16	166654	prior	48	0	12	9.0	eggs
5	537	33120	2	1	Organic Egg Whites	86	16	180135	prior	15	2	8	3.0	eggs
6	582	33120	7	1	Organic Egg Whites	86	16	193223	prior	6	2	19	10.0	eggs
7	608	33120	5	1	Organic Egg Whites	86	16	91030	prior	11	3	21	12.0	eggs
8	623	33120	1	1	Organic Egg Whites	86	16	37804	prior	63	3	12	3.0	eggs
9	689	33120	4	1	Organic Egg Whites	86	16	108932	prior	16	1	13	3.0	eggs

#交叉表，特殊的分组工具
cross=pd.crosstab(mt["user_id"],mt["aisle"])

cross.head(10)

aisle	air fresheners candles	asian foods	baby accessories	baby bath body care	baby food formula	bakery desserts	baking ingredients	baking supplies decor	beauty	beers coolers	...	spreads	tea	tofu meat alternatives	tortillas flat bread	trail mix snack mix	trash bags liners	vitamins supplements	water seltzer sparkling water	white wines	yogurt
user_id
1	0	0	0	0	0	0	0	0	0	0	...	1	0	0	0	0	0	0	0	0	1
2	0	3	0	0	0	0	2	0	0	0	...	3	1	1	0	0	0	0	2	0	42
3	0	0	0	0	0	0	0	0	0	0	...	4	1	0	0	0	0	0	2	0	0
4	0	0	0	0	0	0	0	0	0	0	...	0	0	0	1	0	0	0	1	0	0
5	0	2	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	3
6	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
7	0	0	0	0	0	0	2	0	0	0	...	0	0	0	0	0	0	0	0	0	5
8	0	1	0	0	0	0	1	0	0	0	...	0	0	0	0	0	0	0	0	0	0
9	0	0	0	0	6	0	2	0	0	0	...	0	0	0	0	0	0	0	2	0	19
10	0	1	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	2

10 rows × 134 columns

#进行主成分分析
pca=PCA(n_components=0.9)

data=pca.fit_transform(cross)
data

array([[-2.42156587e+01,  2.42942720e+00, -2.46636975e+00, ...,
         6.86800336e-01,  1.69439402e+00, -2.34323022e+00],
       [ 6.46320806e+00,  3.67511165e+01,  8.38255336e+00, ...,
         4.12121252e+00,  2.44689740e+00, -4.28348478e+00],
       [-7.99030162e+00,  2.40438257e+00, -1.10300641e+01, ...,
         1.77534453e+00, -4.44194030e-01,  7.86665571e-01],
       ...,
       [ 8.61143331e+00,  7.70129866e+00,  7.95240226e+00, ...,
        -2.74252456e+00,  1.07112531e+00, -6.31925661e-02],
       [ 8.40862199e+01,  2.04187340e+01,  8.05410372e+00, ...,
         7.27554259e-01,  3.51339470e+00, -1.79079914e+01],
       [-1.39534562e+01,  6.64621821e+00, -5.23030367e+00, ...,
         8.25329076e-01,  1.38230701e+00, -2.41942061e+00]])

data.shape

(206209, 27)

cross.shape

(206209, 134)