mirror of
https://github.com/freedbygrace/SQL.git
synced 2026-07-26 11:28:16 +00:00
Alphaeus Mote
aa803bd3bd
Major expansion from fraud detection to comprehensive business analytics: DATABASE CHANGES: - Renamed database from 'fraud_detection' to 'business_analytics' - Renamed user from 'fraud_analyst' to 'data_analyst' - Expanded from 20 to 39 tables across 4 business models NEW MODELS (19 tables): 1. Customer Analytics (5 tables): - customer_segments, customer_lifetime_value, churn_predictions - customer_satisfaction, engagement_metrics 2. Sales & Revenue Analytics (6 tables): - product_catalog, sales_transactions, sales_targets - sales_performance, revenue_forecasts 3. KPI & Metrics (8 tables): - kpi_definitions, daily_metrics, monthly_summaries - trend_analysis, dashboard_snapshots - report_definitions, report_executions, data_quality_checks DATA GENERATION: - Extended generate_data.sh with 6 new steps (now 15 total) - Added CLV calculations for all customers - Added churn predictions based on transaction recency - Added 30K customer satisfaction surveys - Added 1M sales transactions linked to 24 products - Added 90 days of daily KPI metrics - Added 24 months of business summaries SQL EXERCISES (3 new levels): - Level 2: Customer Analytics (10 exercises + 3 challenges) - Level 3: Sales & Revenue Analysis (12 exercises + 3 challenges) - Level 4: KPI Dashboards & Metrics (12 exercises + 3 challenges) DOCUMENTATION: - Updated README.md with business analytics focus - Updated QUICKSTART.md with new data generation steps - Updated SETUP_COMPLETE.md with 39-table architecture - Added DATA_MODELS.md with complete model specifications - Added WHATS_NEW.md with migration guide SEED DATA: - Added 8 customer segments (VIP, High Value, etc.) - Added 24 products across 5 categories - Added 16 KPI definitions across 4 categories - Added 8 standard report definitions All changes maintain idempotency and backward compatibility with existing fraud detection functionality.
115 lines
4.5 KiB
Bash
115 lines
4.5 KiB
Bash
#!/bin/bash
|
|
|
|
# ============================================================================
|
|
# Database Setup Script - IDEMPOTENT
|
|
# ============================================================================
|
|
# This script sets up the complete business analytics database
|
|
# It can be run multiple times safely - it will recreate everything
|
|
# ============================================================================
|
|
|
|
set -e # Exit on error
|
|
|
|
# Colors for output
|
|
RED='\033[0;31m'
|
|
GREEN='\033[0;32m'
|
|
YELLOW='\033[1;33m'
|
|
BLUE='\033[0;34m'
|
|
NC='\033[0m' # No Color
|
|
|
|
# Configuration from environment or defaults
|
|
DB_HOST="${POSTGRES_HOST:-localhost}"
|
|
DB_PORT="${POSTGRES_PORT:-5432}"
|
|
DB_NAME="${POSTGRES_DB:-business_analytics}"
|
|
DB_USER="${POSTGRES_USER:-data_analyst}"
|
|
DB_PASSWORD="${POSTGRES_PASSWORD:-SecurePass123!}"
|
|
|
|
# Script directory
|
|
SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
|
|
PROJECT_ROOT="$(dirname "$SCRIPT_DIR")"
|
|
|
|
echo -e "${BLUE}============================================================================${NC}"
|
|
echo -e "${BLUE}Business Analytics Database - Setup Script${NC}"
|
|
echo -e "${BLUE}============================================================================${NC}"
|
|
echo -e "Database: ${GREEN}$DB_NAME${NC}"
|
|
echo -e "Host: ${GREEN}$DB_HOST:$DB_PORT${NC}"
|
|
echo -e "User: ${GREEN}$DB_USER${NC}"
|
|
echo -e "${BLUE}============================================================================${NC}"
|
|
echo ""
|
|
|
|
# Function to execute SQL command
|
|
execute_sql() {
|
|
PGPASSWORD=$DB_PASSWORD psql -h $DB_HOST -p $DB_PORT -U $DB_USER -d $DB_NAME -c "$1" 2>&1
|
|
}
|
|
|
|
# Function to execute SQL file
|
|
execute_sql_file() {
|
|
local file=$1
|
|
local description=$2
|
|
echo -e "${YELLOW}Executing: $description${NC}"
|
|
PGPASSWORD=$DB_PASSWORD psql -h $DB_HOST -p $DB_PORT -U $DB_USER -d $DB_NAME -f "$file" 2>&1
|
|
if [ $? -eq 0 ]; then
|
|
echo -e "${GREEN}✓ Success: $description${NC}"
|
|
else
|
|
echo -e "${RED}✗ Failed: $description${NC}"
|
|
exit 1
|
|
fi
|
|
echo ""
|
|
}
|
|
|
|
# Wait for PostgreSQL to be ready
|
|
echo -e "${YELLOW}Waiting for PostgreSQL to be ready...${NC}"
|
|
max_attempts=30
|
|
attempt=0
|
|
until PGPASSWORD=$DB_PASSWORD psql -h $DB_HOST -p $DB_PORT -U $DB_USER -d $DB_NAME -c '\q' 2>/dev/null; do
|
|
attempt=$((attempt + 1))
|
|
if [ $attempt -ge $max_attempts ]; then
|
|
echo -e "${RED}✗ PostgreSQL is not available after $max_attempts attempts${NC}"
|
|
exit 1
|
|
fi
|
|
echo -e "${YELLOW}Waiting for PostgreSQL... (attempt $attempt/$max_attempts)${NC}"
|
|
sleep 2
|
|
done
|
|
echo -e "${GREEN}✓ PostgreSQL is ready${NC}"
|
|
echo ""
|
|
|
|
# Step 1: Create schema (drops and recreates all tables)
|
|
echo -e "${BLUE}[Step 1/3] Creating database schema...${NC}"
|
|
execute_sql_file "$PROJECT_ROOT/schema/01-create-tables.sql" "Creating tables, indexes, and constraints"
|
|
|
|
# Step 2: Load seed data (reference tables)
|
|
echo -e "${BLUE}[Step 2/3] Loading reference data...${NC}"
|
|
execute_sql_file "$PROJECT_ROOT/schema/02-seed-data.sql" "Loading countries, merchant categories, transaction types, and fraud types"
|
|
|
|
# Step 3: Verify setup
|
|
echo -e "${BLUE}[Step 3/3] Verifying database setup...${NC}"
|
|
echo -e "${YELLOW}Checking table counts...${NC}"
|
|
|
|
# Get table counts
|
|
table_count=$(execute_sql "SELECT COUNT(*) FROM information_schema.tables WHERE table_schema = 'public' AND table_type = 'BASE TABLE';" | grep -E '^\s*[0-9]+' | tr -d ' ')
|
|
echo -e "Tables created: ${GREEN}$table_count${NC}"
|
|
|
|
# Get reference data counts
|
|
country_count=$(execute_sql "SELECT COUNT(*) FROM countries;" | grep -E '^\s*[0-9]+' | tr -d ' ')
|
|
echo -e "Countries: ${GREEN}$country_count${NC}"
|
|
|
|
category_count=$(execute_sql "SELECT COUNT(*) FROM merchant_categories;" | grep -E '^\s*[0-9]+' | tr -d ' ')
|
|
echo -e "Merchant categories: ${GREEN}$category_count${NC}"
|
|
|
|
transaction_type_count=$(execute_sql "SELECT COUNT(*) FROM transaction_types;" | grep -E '^\s*[0-9]+' | tr -d ' ')
|
|
echo -e "Transaction types: ${GREEN}$transaction_type_count${NC}"
|
|
|
|
fraud_type_count=$(execute_sql "SELECT COUNT(*) FROM fraud_types;" | grep -E '^\s*[0-9]+' | tr -d ' ')
|
|
echo -e "Fraud types: ${GREEN}$fraud_type_count${NC}"
|
|
|
|
echo ""
|
|
echo -e "${GREEN}============================================================================${NC}"
|
|
echo -e "${GREEN}✓ Database setup completed successfully!${NC}"
|
|
echo -e "${GREEN}============================================================================${NC}"
|
|
echo ""
|
|
echo -e "${YELLOW}Next steps:${NC}"
|
|
echo -e "1. Generate test data: ${BLUE}./scripts/generate-data.sh${NC}"
|
|
echo -e "2. Access DB-UI at: ${BLUE}http://localhost:3000${NC}"
|
|
echo -e "3. Start learning SQL with exercises in: ${BLUE}./exercises/${NC}"
|
|
echo ""
|
|
|