概要
Confluent が提供する kafka-connect-datagen を使用して生成可能なサンプルデータを整理しました。本記事のデータは実際にツールを用いて生成したものではなく、下記リンク先の定義に基づき生成AIを使用して作成したため、一部に誤りが含まれる可能性があります。ご了承のうえご参照ください。
引用元：kafka-connect-datagen/src/main/resources at master · confluentinc/kafka-connect-datagen
本記事は、以下のシリーズの一部です。
引用元：Data in Motion 実現へ：Data Streaming Platform である Confluent の全貌 #Kafka - Qiita
サンプルデータ
campaign_finance
{
"time": 1619273364600,
"candidate_id": "A12345678",
"party_affiliation": "DEM",
"contribution": 3500
}
clickstream_codes
{
"code": 200,
"definition": "Successful"
}
clickstream
{
"ip": "111.152.45.45",
"userid": 1,
"remote_user": "-",
"time": "379521",
"_time": 1609459200010,
"request": "GET /index.html HTTP/1.1",
"status": "200",
"bytes": "278",
"referrer": "-",
"agent": "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"
}
clickstream_users
{
"user_id": 1,
"username": "akatz1022",
"registered_at": 1407645330000,
"first_name": "Elwyn",
"last_name": "Vanyard",
"city": "Palo Alto",
"level": "Gold"
}
credit_cards
{
"card_id": 1,
"card_number": 6011601160116611,
"cvv": 832,
"expiration_date": "12/27"
}
device_information
{
"device_ip": "204.149.41.63",
"mac_address": "20-FC-45-56-D4-11",
"owner": "Frieda Baldi"
}
fleet_mgmt_description
{
"vehicle_id": 1234,
"driver_name": "Frieda Baldi",
"license_plate": "AB123456C"
}
fleet_mgmt_location
{
"vehicle_id": 1234,
"location": {
"latitude": 37.416834,
"longitude": -121.975002
},
"ts": 1609459200000
}
fleet_mgmt_sensors
{
"vehicle_id": 1234,
"engine_temperature": 200,
"average_rpm": 3000
}
gaming_games
{
"id": 1000,
"room_name": "Arcade -- Rookie",
"created_date": 1609459200000
}
gaming_player_activity
{
"player_id": 1001,
"game_room_id": 1000,
"points": 250,
"coordinates": "[12,34]"
}
gaming_players
{
"player_id": 1001,
"player_name": "Frieda Baldi",
"ip": "117.119.34.13"
}
insurance_customer_activity
{
"activity_id": 1,
"customer_id": 415,
"activity_type": "web_open",
"propensity_to_churn": 0.25,
"ip_address": "223.135.0.204"
}
insurance_customers
{
"customer_id": 415,
"first_name": "Herold",
"last_name": "Agdahl",
"email": "hagdahlbi@last.fm",
"gender": "Male",
"income": 444152,
"fico": 423,
"years_active": 1
}
insurance_offers
{
"offer_id": 1,
"offer_name": "new_home_policy",
"offer_url": "http://privacy.gov.au/in/faucibus/orci/luctus.js"
}
inventory
{
"id": 0,
"quantity": 0,
"productid": 0
}
orders
{
"ordertime": 1519273364600,
"orderid": 1,
"itemid": "Item_1",
"orderunits": 1.0,
"address": {
"city": "City_1",
"state": "State_1",
"zipcode": 10001
}
}
pageviews
{
"viewtime": 1694763296000,
"userid": "User_1",
"pageid": "Page_10"
}
payroll_bonus
{
"employee_id": 1000,
"bonus": 10,
"ts": 1609459200000
}
payroll_employee
{
"employee_id": 1000,
"first_name": "Carleton",
"last_name": "Beagan",
"age": 32,
"ssn": "723-37-6885",
"hourly_rate": 20,
"gender": "female",
"email": "xcqn@mycompany.com"
}
payroll_employee_location
{
"employee_id": 1000,
"lab": "lab-1",
"department_id": 5,
"arrival_date": 18001
}
pizza_orders
{
"store_id": 1,
"store_order_id": 1000,
"coupon_code": 1001,
"date": 18000,
"status": "accepted",
"order_lines": [
{
"product_id": 66,
"category": "calzone",
"quantity": 4,
"unit_price": 18.78,
"net_price": 75.12
},
{
"product_id": 71,
"category": "salad",
"quantity": 4,
"unit_price": 4.90,
"net_price": 19.60
}
]
}
pizza_orders_cancelled
{
"store_id": 1,
"store_order_id": 1001,
"date": 18000,
"status": "cancelled"
}
pizza_orders_completed
{
"store_id": 1,
"store_order_id": 1000,
"date": 18000,
"status": "completed",
"rack_time_secs": 150,
"order_delivery_time_secs": 1200
}
product
{
"id": 0,
"name": "Sample Product",
"description": "This is a sample product description.",
"price": 19.99
}
purchase
{
"id": 0,
"item_type": "boots",
"quantity": 1,
"price_per_unit": 10.00
}
ratings
{
"rating_id": 1,
"user_id": 10,
"stars": 4,
"route_id": 123,
"rating_time": 1694763296000,
"channel": "mobile"
}
shoe_clickstream
{
"stream_id": "abc123",
"product_id": "shoe_001",
"user_id": "user_456",
"view_time": 120,
"page_url": "http://example.com/shoe_001",
"ip": "192.168.1.1",
"ts": 1694763296000
}
shoe_customers
{
"id": "01a429f8-f576-4d9b-8d0e-4d5e8ef37e09",
"first_name": "Cyrill",
"last_name": "Haeslier",
"email": "vbiaggelli0@prweb.com",
"phone": "615-978-0286",
"street_address": "7 Hooker Court",
"state": "Massachusetts",
"zip_code": "2119",
"country": "United States",
"country_code": "US"
}
shoe_orders
{
"order_id": "1000",
"product_id": "828044c8-832b-48b4-b1f0-89a500496335",
"customer_id": "01a429f8-f576-4d9b-8d0e-4d5e8ef37e09",
"ts": "1609459200000"
}
shoes
{
"sale_price": 7495,
"id": "828044c8-832b-48b4-b1f0-89a500496335",
"brand": "Jones-Stokes",
"name": "TrailRunner Impreza 239",
"rating": 0.0
}
siem_logs
{
"log_id": "log_001",
"timestamp": 1694763296000,
"source_ip": "192.168.1.1",
"destination_ip": "192.168.1.2",
"event_type": "login_attempt",
"status": "success",
"user": "jdoe"
}
siem_logs
{
"hostname": "204.149.41.63",
"action": "allow",
"l4": "tcp",
"access_group": "group-1",
"source": {
"ip": "54.222.176.193",
"port": 10123
},
"destination": {
"ip": "122.120.109.66",
"port": 10567
}
}
siem_logs
{
"hostname": "204.149.41.63",
"action": "allow",
"l4": "tcp",
"access_group": "group-1",
"source": {
"ip": "54.222.176.193",
"port": 10123
},
"destination": {
"ip": "122.120.109.66",
"port": 10567
}
}
StockTrade
{
"side": "SELL",
"quantity": 3200,
"symbol": "ZXZZT",
"price": 450,
"account": "LMN456",
"userid": "User_7"
}
stores
{
"store_id": 1,
"city": "Raleigh",
"state": "NC"
}
syslog_logs
{
"name": "LogName",
"type": "RFC5424",
"message": "system update",
"host": "121.46.66.201",
"version": "3.25.1",
"tag": ".source.s_src",
"level": 123,
"facility": "syslog",
"severity": 5,
"appName": "APPLOG",
"remoteAddress": "91.253.222.9",
"rawMessage": "update complete",
"processId": "1234567",
"messageId": "123",
"deviceVendor": "loggy",
"deviceProduct": "syspr",
"deviceVersion": "1.0",
"ts": 1609459200100
}
transactions
{
"transaction_id": 1,
"card_id": 12,
"user_id": "User_3",
"purchase_id": 0,
"store_id": 5
}
users_array_map
{
"registertime": 1500000000000,
"userid": "User_3",
"regionid": "Region_4",
"gender": "FEMALE",
"interests": ["News", "Travel"],
"contactinfo": {
"phone": "6503349999",
"city": "San Mateo",
"state": "CA",
"zipcode": "94403"
}
}
users
{
"registertime": 1510000000000,
"userid": "User_5",
"regionid": "Region_3",
"gender": "MALE"
}