Merge pull request #58 from lyakhovv/main

UDT Types schema samples

Author: michaelraney

java/datastax-v4/udt-types/LICENSE

@@ -0,0 +1,15 @@
+Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
+the Software, and to permit persons to whom the Software is furnished to do so.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
+IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+

java/datastax-v4/udt-types/README.MD

@@ -0,0 +1,152 @@
+# User-defined types (UDTs) in Amazon Keyspaces
+
+Amazon Keyspaces (for Apache Cassandra) allows the use of user-defined types (UDTs) to optimize data organization and enhance data modeling capabilities.
+
+A user-defined type (UDT) is a grouping of fields and data types that you can use to define a single column in Amazon Keyspaces. 
+Valid data types for UDTs are all supported Cassandra data types, including collections and other UDTs that you've already created in the same keyspace. 
+
+For more information about supported Keyspaces data types, see [Cassandra data type support](https://docs.aws.amazon.com/keyspaces/latest/devguide/cassandra-apis.html#cassandra-data-type) .
+
+
+# Amazon Keyspaces Real Estate Schema Example
+
+This example demonstrates a comprehensive Real Estate data model using Amazon Keyspaces with User Defined Types (UDTs). The schema showcases how to structure complex real estate data including property details, market analytics, and location-based queries.
+
+
+## Schema Overview
+The real estate schema consists of three main tables and seven UDTs that model comprehensive property information:
+
+### User Defined Types (UDTs)
+
+- **address_details**: Complete address information including coordinates and neighborhood data
+- **property_specifications**: Physical property details (size, rooms, construction details)
+- **property_amenities**: Features and amenities (pool, security, smart home features)
+- **financial_details**: Pricing, taxes, HOA fees, and financing information
+- **location_quality**: School districts, walkability scores, and area ratings
+- **market_intelligence**: Market trends, days on market, and pricing analytics
+- **listing_details**: Agent information, listing status, and marketing materials
+
+### Tables
+
+1. **properties**: Main property table with complete property information
+2. **properties_by_location**: Optimized for geographic and price range queries
+3. **market_analytics**: Time-series market data for trend analysis
+
+## Sample Data
+
+The schema includes sample data for the Seattle/Bellevue area:
+
+- **Luxury Properties**: High-end homes and condos ($1M+)
+- **Mid-Range Properties**: Family homes and investment properties ($500K-$1M)
+- **Market Analytics**: Historical market data with trends and statistics
+- **Location Data**: Properties organized by ZIP code and property type
+
+## Quick Start
+
+### Prerequisites
+
+- Amazon Keyspaces access or local Cassandra installation
+- cqlsh or cqlsh-expansion for Amazon Keyspaces
+
+### Setup
+
+1. **Execute the setup script:**
+   ```bash
+   cd real_eastate_schema_sample
+   chmod +x execute_real_estate_schema.sh
+   ./execute_real_estate_schema.sh
+   ```
+
+2. **Manual setup (alternative):**
+   ```bash
+   # Create keyspace
+   cqlsh -e "CREATE KEYSPACE IF NOT EXISTS real_estate WITH REPLICATION = {'class': 'SingleRegionStrategy'};"
+   
+   # Execute files in order
+   cqlsh -f 01_real_estate_udts.cql
+   cqlsh -f 02_properties_table.cql
+   cqlsh -f 03_sample_luxury_properties.cql
+   cqlsh -f 04_sample_midrange_properties.cql
+   cqlsh -f 05_sample_properties_by_location.cql
+   cqlsh -f 06_sample_market_analytics.cql
+   ```
+
+
+## Sample Queries
+
+The schema supports various query patterns:
+
+### Location-Based Queries
+```cql
+-- Properties by ZIP code and type
+SELECT property_id, address.street_name, financial.listing_price
+FROM properties_by_location 
+WHERE zip_code = '98101' 
+AND property_type = 'condo';
+```
+
+### Market Analytics
+```cql
+-- Market trends over time
+SELECT area_code, date, avg_price, median_price, 
+       market_stats.market_temperature
+FROM market_analytics 
+WHERE area_code = '98101' 
+AND property_type = 'condo';
+```
+
+## Schema Features
+
+### Complex Data Modeling
+- **Nested UDTs**: Rich data structures for comprehensive property information
+- **Collections**: Lists and maps for amenities, school ratings, and features
+- **Flexible Schema**: Easy to extend with additional property attributes
+
+### Query Optimization
+- **Partition Keys**: Efficient data distribution by location and property type
+- **Clustering Keys**: Ordered data for range queries and time-series analysis
+
+### Real Estate Use Cases
+- **Property Listings**: Complete MLS-style property information
+- **Market Analysis**: Historical trends and comparative market analysis
+- **Location Intelligence**: School districts, walkability, and neighborhood data
+- **Investment Analysis**: Financial metrics and market performance
+
+## File Structure
+
+```
+real_eastate_schema_sample/
+├── 01_real_estate_udts.cql          # UDT definitions
+├── 02_properties_table.cql          # Table schemas
+├── 03_sample_luxury_properties.cql  # High-end property samples
+├── 04_sample_midrange_properties.cql # Mid-range property samples
+├── 05_sample_properties_by_location.cql # Location-based data
+├── 06_sample_market_analytics.cql   # Market trend data
+├── 07_sample_queries.cql            # Example queries
+└── execute_real_estate_schema.sh    # Setup script
+```
+
+## Data Model Benefits
+
+### Structured Data
+- **Type Safety**: UDTs provide schema validation
+- **Data Integrity**: Consistent structure across all properties
+- **Rich Metadata**: Comprehensive property and market information
+
+### Flexibility
+- **Extensible**: Easy to add new UDT fields
+- **Backward Compatible**: Schema evolution without breaking changes
+- **Multi-Use**: Supports various real estate applications
+
+---
+## Amazon Keyspaces Considerations
+When using with Amazon Keyspaces:
+- Use point-in-time recovery for data protection
+- Consider on-demand billing for variable workloads
+- Implement proper IAM policies for data access
+
+### Next Steps
+
+1. **Extend the Schema**: Add more UDTs for additional property types
+2. **Implement Applications**: Build real estate applications using this schema
+3. **Monitor Performance**: Use CloudWatch metrics to optimize queries

java/datastax-v4/udt-types/real_eastate_schema_sample/01_real_estate_udts.cql

@@ -0,0 +1,148 @@
+-- Real Estate UDT Definitions
+-- Execute these first before inserting sample data
+
+USE real_estate;
+
+-- Address Information
+CREATE TYPE IF NOT EXISTS address_details (
+    street_number TEXT,
+    street_name TEXT,
+    unit_number TEXT,
+    city TEXT,
+    state TEXT,
+    zip_code TEXT,
+    county TEXT,
+    country TEXT,
+    latitude DECIMAL,
+    longitude DECIMAL,
+    timezone TEXT,
+    neighborhood TEXT,
+    subdivision TEXT
+);
+
+-- Property Specifications
+CREATE TYPE IF NOT EXISTS property_specifications (
+    property_type TEXT,
+    property_subtype TEXT,
+    square_feet INT,
+    lot_size_sqft INT,
+    bedrooms INT,
+    bathrooms DECIMAL,
+    half_baths INT,
+    stories INT,
+    year_built INT,
+    year_renovated INT,
+    garage_spaces INT,
+    parking_spaces INT,
+    basement_type TEXT,
+    foundation_type TEXT,
+    roof_type TEXT,
+    exterior_material TEXT,
+    heating_type TEXT,
+    cooling_type TEXT,
+    flooring_types LIST<TEXT>
+);
+
+-- Property Amenities
+CREATE TYPE IF NOT EXISTS property_amenities (
+    pool BOOLEAN,
+    pool_type TEXT,
+    spa_hot_tub BOOLEAN,
+    fireplace BOOLEAN,
+    fireplace_count INT,
+    deck BOOLEAN,
+    patio BOOLEAN,
+    balcony BOOLEAN,
+    fence BOOLEAN,
+    fence_type TEXT,
+    security_system BOOLEAN,
+    alarm_system BOOLEAN,
+    sprinkler_system BOOLEAN,
+    central_vacuum BOOLEAN,
+    intercom_system BOOLEAN,
+    elevator BOOLEAN,
+    wheelchair_accessible BOOLEAN,
+    solar_panels BOOLEAN,
+    energy_efficient_appliances BOOLEAN,
+    smart_home_features LIST<TEXT>,
+    outdoor_features LIST<TEXT>,
+    interior_features LIST<TEXT>
+);
+
+-- Financial Details
+CREATE TYPE IF NOT EXISTS financial_details (
+    listing_price DECIMAL,
+    original_list_price DECIMAL,
+    price_per_sqft DECIMAL,
+    last_sold_price DECIMAL,
+    last_sold_date DATE,
+    assessed_value DECIMAL,
+    assessment_year INT,
+    annual_property_taxes DECIMAL,
+    monthly_hoa_fees DECIMAL,
+    hoa_name TEXT,
+    special_assessments DECIMAL,
+    homeowners_insurance_estimate DECIMAL,
+    utilities_included LIST<TEXT>,
+    financing_options LIST<TEXT>
+);
+
+-- Location Quality
+CREATE TYPE IF NOT EXISTS location_quality (
+    school_district TEXT,
+    elementary_school TEXT,
+    middle_school TEXT,
+    high_school TEXT,
+    school_ratings MAP<TEXT, INT>,
+    crime_index INT,
+    walkability_score INT,
+    transit_score INT,
+    bike_score INT,
+    noise_level TEXT,
+    air_quality_index INT,
+    flood_zone TEXT,
+    earthquake_zone TEXT,
+    hurricane_zone TEXT,
+    nearby_amenities MAP<TEXT, DECIMAL>,
+    commute_times MAP<TEXT, INT>,
+    walkable_destinations LIST<TEXT>
+);
+
+
+
+-- Market Intelligence
+CREATE TYPE IF NOT EXISTS market_intelligence (
+    days_on_market INT,
+    listing_views INT,
+    showing_count INT,
+    offer_count INT,
+    market_temperature TEXT,
+    price_trend_30_days DECIMAL,
+    price_trend_90_days DECIMAL,
+    price_trend_1_year DECIMAL,
+    comparable_sales_count INT,
+    inventory_level TEXT,
+    absorption_rate DECIMAL,
+    median_dom_area INT,
+    price_per_sqft_area DECIMAL,
+    market_velocity TEXT
+);
+
+-- Listing Details
+CREATE TYPE IF NOT EXISTS listing_details (
+    listing_agent_name TEXT,
+    listing_agent_phone TEXT,
+    listing_agent_email TEXT,
+    listing_brokerage TEXT,
+    listing_date DATE,
+    listing_status TEXT,
+    listing_type TEXT,
+    showing_instructions TEXT,
+    commission_rate DECIMAL,
+    buyer_agent_commission DECIMAL,
+    listing_remarks TEXT,
+    private_remarks TEXT,
+    virtual_tour_url TEXT,
+    video_tour_url TEXT,
+    floor_plan_url TEXT
+);

java/datastax-v4/udt-types/real_eastate_schema_sample/02_properties_table.cql

@@ -0,0 +1,51 @@
+-- Main Properties Table
+USE real_estate;
+
+CREATE TABLE IF NOT EXISTS properties (
+    property_id UUID PRIMARY KEY,
+    mls_number TEXT,
+    address frozen<address_details>,
+    specifications frozen<property_specifications>,
+    amenities frozen<property_amenities>,
+    financial frozen<financial_details>,
+    location frozen<location_quality>,
+    market frozen<market_intelligence>,
+    listing frozen<listing_details>,
+    created_at TIMESTAMP,
+    updated_at TIMESTAMP,
+    data_source TEXT,
+    data_quality_score INT
+);
+
+-- Properties by Location Table
+CREATE TABLE IF NOT EXISTS properties_by_location (
+    zip_code TEXT,
+    property_type TEXT,
+    price_range TEXT,
+    property_id UUID,
+    address frozen<address_details>,
+    specifications frozen<property_specifications>,
+    financial frozen<financial_details>,
+    location frozen<location_quality>,
+    listing frozen<listing_details>,
+    market frozen<market_intelligence>,
+    PRIMARY KEY ((zip_code, property_type), price_range, property_id)
+) WITH CLUSTERING ORDER BY (price_range ASC, property_id ASC);
+
+-- Market Analytics Table
+CREATE TABLE IF NOT EXISTS market_analytics (
+    area_code TEXT,
+    date DATE,
+    property_type TEXT,
+    avg_price DECIMAL,
+    median_price DECIMAL,
+    avg_price_per_sqft DECIMAL,
+    total_listings INT,
+    new_listings INT,
+    closed_sales INT,
+    pending_sales INT,
+    avg_days_on_market INT,
+    inventory_months DECIMAL,
+    market_stats frozen<market_intelligence>,
+    PRIMARY KEY ((area_code, property_type), date)
+) WITH CLUSTERING ORDER BY (date DESC);