import randomimport datetime
# 设置参数num_records = 1000output_file = 'dw_sales_data.txt'
# 定义可能的值channel_ids = ['C001', 'C002', 'C003', 'C004']product_ids = ['P001', 'P002', 'P003', 'P004']region_ids = ['R001', 'R002', 'R003', 'R004']base_date = datetime.date(2024, 1, 1)
# 生成数据with open(output_file, 'w') as f:    for i in range(num_records):        record_id = f"{i+1:04d}"        date1 = (base_date + datetime.timedelta(days=random.randint(0, 365))).strftime('%Y-%m-%d')        channel_id = random.choice(channel_ids)        product_id = random.choice(product_ids)        region_id = random.choice(region_ids)        amount = random.randint(1, 100)        price = round(random.uniform(10.0, 500.0), 2)                line = f"{record_id},{date1},{channel_id},{product_id},{region_id},{amount},{price}\n"        f.write(line)
print(f"{num_records} records have been written to {output_file}")

# 设置参数output_file = 'dim_channel_data.txt'
# 定义渠道ID和渠道名称channels = [    ('C001', 'Online Sales'),    ('C002', 'Retail Store'),    ('C003', 'Wholesale'),    ('C004', 'Direct Sales')]
# 生成数据with open(output_file, 'w') as f:    for channel_id, channel_name in channels:        line = f"{channel_id},{channel_name}\n"        f.write(line)
print(f"Channel data has been written to {output_file}")

# 设置参数output_file = 'dim_product_data.txt'
# 定义产品ID和产品名称products = [    ('P001', 'Smartphone'),    ('P002', 'Laptop'),    ('P003', 'Tablet'),    ('P004', 'Smartwatch'),    ('P005', 'Camera'),    ('P006', 'Headphones'),    ('P007', 'Monitor'),    ('P008', 'Keyboard'),    ('P009', 'Mouse'),    ('P010', 'Printer')]
# 生成数据with open(output_file, 'w') as f:    for product_id, product_name in products:        line = f"{product_id},{product_name}\n"        f.write(line)
print(f"Product data has been written to {output_file}")

# 设置参数output_file = 'dim_region_data.txt'
# 定义区域ID和区域名称regions = [    ('R001', 'North America'),    ('R002', 'Europe'),    ('R003', 'Asia'),    ('R004', 'South America'),    ('R005', 'Africa'),    ('R006', 'Australia'),    ('R007', 'Antarctica')]
# 生成数据with open(output_file, 'w') as f:    for region_id, region_name in regions:        line = f"{region_id},{region_name}\n"        f.write(line)
print(f"Region data has been written to {output_file}")

-- 创建订单数据库、表结构create database if not exists `wzk_kylin`;-- 1、销售表：dw_sales-- id 唯一标识-- date1 日期-- channelId 渠道ID-- productId 产品ID-- regionId 区域ID-- amount 数量-- price 金额create table wzk_kylin.dw_sales(  id string,  date1 string,  channelId string,  productId string,  regionId string,  amount int,  price double)ROW FORMAT DELIMITED FIELDS TERMINATED BY ',';-- 2、渠道表：dim_channel-- channelId 渠道ID-- channelName 渠道名称create table wzk_kylin.dim_channel(  channelId string,  channelName string)ROW FORMAT DELIMITED FIELDS TERMINATED BY ',';-- 3、产品表：dim_productcreate table wzk_kylin.dim_product(  productId string,  productName string)ROW FORMAT DELIMITED FIELDS TERMINATED BY ',';--4、区域表：dim_regioncreate table wzk_kylin.dim_region(  regionId string,  regionName string)ROW FORMAT DELIMITED FIELDS TERMINATED BY ',';
-- 导入数据LOAD DATA LOCAL INPATH '/opt/wzk/kylin_test/dw_sales_data.txt'OVERWRITE INTO TABLE wzk_kylin.dw_sales;LOAD DATA LOCAL INPATH '/opt/wzk/kylin_test/dim_channel_data.txt'OVERWRITE INTO TABLE wzk_kylin.dim_channel;LOAD DATA LOCAL INPATH '/opt/wzk/kylin_test/dim_product_data.txt'OVERWRITE INTO TABLE wzk_kylin.dim_product;LOAD DATA LOCAL INPATH '/opt/wzk/kylin_test/dim_region_data.txt'OVERWRITE INTO TABLE wzk_kylin.dim_region;

cd /opt/wzk/kylin_test

hive -f kylin_examples.sql

hive

use wzk_kylin;select date1, sum(price) as total_money, sum(amount) astotal_amountfrom dw_salesgroup by date1;