在 Amazon SageMaker 上连接 Amazon Redshift 和 RStudio

CREATE SCHEMA IF NOT EXISTS synthetic;
DROP TABLE IF EXISTS synthetic.transactions;

CREATE TABLE synthetic.transactions(
    user_id INT,
    card_id INT,
    year INT,
    month INT,
    day INT,
    time_stamp TIME,
    amount VARCHAR(100),
    use_chip VARCHAR(100),
    merchant_name VARCHAR(100),
    merchant_city VARCHAR(100),
    merchant_state VARCHAR(100),
    merchant_zip_code VARCHAR(100),
    merchant_category_code INT,
    is_error VARCHAR(100),
    is_fraud VARCHAR(100)
);

COPY synthetic.transactions
FROM 's3://sagemaker-sample-files/datasets/tabular/synthetic_credit_card_transactions/credit_card_transactions-ibm_v2.csv'
IAM_ROLE default
REGION 'us-east-1' 
IGNOREHEADER 1 
CSV;

DROP TABLE IF EXISTS synthetic.cards;

CREATE TABLE synthetic.cards(
    user_id INT,
    card_id INT,
    card_brand VARCHAR(100),
    card_type VARCHAR(100),
    card_number VARCHAR(100),
    expire_date VARCHAR(100),
    cvv INT,
    has_chip VARCHAR(100),
    number_cards_issued INT,
    credit_limit VARCHAR(100),
    account_open_date VARCHAR(100),
    year_pin_last_changed VARCHAR(100),
    is_card_on_dark_web VARCHAR(100)
);

COPY synthetic.cards
FROM 's3://sagemaker-sample-files/datasets/tabular/synthetic_credit_card_transactions/sd254_cards.csv'
IAM_ROLE default
REGION 'us-east-1' 
IGNOREHEADER 1 
CSV;

DROP TABLE IF EXISTS synthetic.users;

CREATE TABLE synthetic.users(
    name VARCHAR(100),
    current_age INT,
    retirement_age INT,
    birth_year INT,
    birth_month INT,
    gender VARCHAR(100),
    address VARCHAR(100),
    apartment VARCHAR(100),
    city VARCHAR(100),
    state VARCHAR(100),
    zip_code INT,
    lattitude VARCHAR(100),
    longitude VARCHAR(100),
    per_capita_income_zip_code VARCHAR(100),
    yearly_income VARCHAR(100),
    total_debt VARCHAR(100),
    fico_score INT,
    number_credit_cards INT
);

COPY synthetic.users
FROM 's3://sagemaker-sample-files/datasets/tabular/synthetic_credit_card_transactions/sd254_users.csv'
IAM_ROLE default
REGION 'us-east-1' 
IGNOREHEADER 1 
CSV;

library(DBI)
library(reticulate)
boto3 <- import('boto3')
client <- boto3$client('redshift-serverless')
workgroup <- unlist(client$list_workgroups())
namespace <- unlist(client$get_namespace(namespaceName=workgroup$workgroups.namespaceName))
creds <- client$get_credentials(dbName=namespace$namespace.dbName,
                                durationSeconds=3600L,
                                workgroupName=workgroup$workgroups.workgroupName)
con <- dbConnect(odbc::odbc(),
                 Driver='redshift',
                 Server=workgroup$workgroups.endpoint.address,
                 Port='5439',
                 Database=namespace$namespace.dbName,
                 UID=creds$dbUser,
                 PWD=creds$dbPassword)

GRANT ALL ON SCHEMA synthetic to "IAMR:SageMakerUserExecutionRole";
GRANT ALL ON ALL TABLES IN SCHEMA synthetic to "IAMR:SageMakerUserExecutionRole";

dbListTables(con)

dbGetQuery(con, "select * from synthetic.users limit 100")
dbGetQuery(con, "select * from synthetic.cards limit 100")
dbGetQuery(con, "select * from synthetic.transactions limit 100")

install.packages(c("dplyr", "dbplyr", "crayon"))

library(dplyr)
library(dbplyr)

users_tbl <- tbl(con, in_schema("synthetic", "users"))
cards_tbl <- tbl(con, in_schema("synthetic", "cards"))
transactions_tbl <- tbl(con, in_schema("synthetic", "transactions"))

count(users_tbl)
count(cards_tbl)
count(transactions_tbl)

show_query(transactions_tbl)

transactions_by_year %
  count(year) %>%
  arrange(year) %>%
  collect()

transactions_by_year
install.packages(c('ggplot2', 'vctrs'))
library(ggplot2)
ggplot(transactions_by_year) +
  geom_col(aes(year, as.integer(n))) +
  ylab('transactions') 

transactions_tbl %>%
  group_by(is_fraud) %>%
  count()
transactions_tbl %>%
  group_by(merchant_category_code, is_fraud) %>%
  count() %>% 
  arrange(merchant_category_code)

cards_tbl %>%
  left_join(transactions_tbl, by = c("user_id", "card_id")) %>%
  group_by(card_brand, card_type, is_fraud) %>%
  count() %>% 
  arrange(card_brand)

discover_tbl %
  filter(card_brand == 'Discover', card_type == 'Credit') %>%
  left_join(transactions_tbl, by = c("user_id", "card_id")) %>%
  select(user_id, is_fraud, merchant_category_code, use_chip, year, month, day, time_stamp, amount)

discover_tbl %
  mutate(is_fraud = ifelse(is_fraud == 'Yes', 1, 0),
         type = str_remove(use_chip, 'Transaction'),
         type = str_trim(type),
         type = tolower(type),
         date = paste(year, month, day, sep = '-'),
         date = as.Date(date),
         amount = str_remove(amount, '[$]'),
         amount = as.numeric(amount)) %>%
  select(-use_chip, -year, -month, -day)

discover <- collect(discover_tbl)
summary(discover)