原始数据统计信息

Sheet Ｉ -- Deals Sheet Ⅱ -- Shops

概要：原始数据采集自美团美食搜索结果，搜索关键词为 `奶茶`，搜索城市为全国范围内的直辖市、一线城市、省会城市，每个城市取搜索结果中前 30 页约 1000 条店铺信息。

Sheet Ｉ：各个店铺推荐的热销商品信息

Dataset info

Number of variables	6
Number of observations	105705
Missing cells	0 (0.0%)
Duplicate rows	4024 (3.8%)
Total size	4.8 MB
Average size	48.0 B

Variables types

Numeric	3
Categorical	2
Boolean	0
Date	0
URL	0
Text (Unique)	0
Rejected	1

Variables Description

Name	Description	Std	Mean	Median
`title`	商品标题（字符）	——	——	——
`price`	标价（数值）	73.21	32.51	14.00
`value`	原价（数值）	107.44	46.05	18.00
`sales`	销量（数值）	3.16e+5	1.18e+5	5.40e+3
`shop_id`	与表二对应的商店ID（编号）	——	——	——
`city`	所属城市（字符）	——	——	——

Warnings

Dataset has 4024 (3.8%) duplicate rows	Warning
`price` is highly skewed (γ1 = 34.17525054)	Skewed
`sales` has 3092 (2.9%) zeros	Zeros
`title` has a high cardinality: 20916 distinct values	Warning
`value` is highly correlated with `price` (ρ = 0.9631010987)	Rejected

Sheet Ⅱ：各个城市的店铺信息

Dataset info

Number of variables	14
Number of observations	30145
Missing cells	2039 (0.5%)
Duplicate rows	2218 (7.4%)
Total size	3.0 MB
Average size	105.0 B

Variables types

Numeric	6
Categorical	7
Boolean	1
Date	0
URL	0
Text (Unique)	0
Rejected	0

Variables Description

Name	Description	Std	Mean	Median
`id`	商店ID（编号）	——	——	——
`title`	商店名称（字符）	——	——	——
`address`	地址（字符）	——	——	——
`avgprice`	产品均价（数值）	47.19	18.35	14.00
`latitude`	纬度（数值）	6.80	33.05	31.95
`longitude`	经度（数值）	8.32	112.35	113.64
`avgscore`	评分均值（数值）	1.39	3.79	4.00
`comments`	评论数量（数值）	1675	358	22
`backCateName`	店铺分类（字符）	——	——	——
`areaname`	所在区域（字符）	——	——	——
`phone`	联系电话	——	——	——
`region`	行政区域（字符）	——	——	——
`isMain`	是否主营茶饮（逻辑）	——	69.2%	——
`city`	所在城市（字符）	——	——	——

Warnings

Dataset has 2218 (7.4%) duplicate rows	Warning
`address` has a high cardinality: 27651 distinct values	Warning
`areaname` has a high cardinality: 3280 distinct values	Warning
`avgprice` is highly skewed (γ1 = 94.30320468)	Skewed
`avgprice` has 5963 (19.8%) zeros	Zeros
`avgscore` has 3063 (10.2%) zeros	Zeros
`backCateName` has a high cardinality: 220 distinct values	Warning
`comments` has 9078 (30.1%) zeros	Zeros
`phone` has a high cardinality: 25710 distinct values	Warning
`phone` has 2039 (6.8%) missing values	Missing
`region` has a high cardinality: 2116 distinct values	Warning
`title` has a high cardinality: 9027 distinct values	Warning