Elysia Tools
Navigation
Data Formats
Apache Arrow Samples
Apache Arrow in-memory columnar format examples for high-performance data processing and analytics
Samples
Entries inside this sample collection
JSONjsonSimple
Basic Arrow Schema Definition
Essential Arrow schema examples with primitive data types for columnar data storage
Tags
arrow, schema, primitive, data
json
{
"schema": {
"fields": [
{
"name": "id",
"type": "int64",
"nullable": false,
"metadata": {}
},
{
"name": "name",
"type": "string",
"nullable": false,
"metadata": {
"description": "Person name"
}
},
{
"name": "age",
"type": "int32",
"nullable": true,
"metadata": {}
},
{
"name": "email",
"type": "string",
"nullable": true,
"metadata": {}
},
{
"name": "is_active",
"type": "bool",
"nullable": false,
"metadata": {}
},
{
"name": "salary",
"type": "float64",
"nullable": true,
"metadata": {
"unit": "USD"
}
},
{
"name": "created_at",
"type": "timestamp[us]",
"nullable": false,
"metadata": {}
}
],
"metadata": {
"description": "Employee data schema"
}
}
}JSONjsonSimple
Arrow Record Batch Example
Complete Arrow record batch with data showing columnar memory layout
Tags
arrow, batch, columnar, memory
json
{
"schema": {
"fields": [
{
"name": "product_id",
"type": "int64",
"nullable": false
},
{
"name": "product_name",
"type": "string",
"nullable": false
},
{
"name": "price",
"type": "float64",
"nullable": false
},
{
"name": "in_stock",
"type": "bool",
"nullable": false
}
]
},
"batches": [
{
"count": 4,
"columns": [
{
"name": "product_id",
"type": "int64",
"data": [101, 102, 103, 104]
},
{
"name": "product_name",
"type": "string",
"data": ["Laptop", "Mouse", "Keyboard", "Monitor"]
},
{
"name": "price",
"type": "float64",
"data": [1299.99, 29.99, 79.99, 399.99]
},
{
"name": "in_stock",
"type": "bool",
"data": [true, true, false, true]
}
]
}
]
}JSONjsonIntermediate
Complex Arrow Data Types
Advanced Arrow schema with nested, list, and map types for complex data structures
Tags
arrow, complex, nested, struct, list, map
json
{
"schema": {
"fields": [
{
"name": "user_id",
"type": "int64",
"nullable": false
},
{
"name": "profile",
"type": {
"type": "struct",
"fields": [
{
"name": "first_name",
"type": "string",
"nullable": false
},
{
"name": "last_name",
"type": "string",
"nullable": false
},
{
"name": "age",
"type": "int32",
"nullable": true
}
]
},
"nullable": true
},
{
"name": "tags",
"type": {
"type": "list",
"item_type": "string",
"nullable": false
},
"nullable": true
},
{
"name": "metadata",
"type": {
"type": "map",
"key_type": "string",
"value_type": "string",
"value_nullable": true
},
"nullable": true
},
{
"name": "purchase_history",
"type": {
"type": "list",
"item_type": {
"type": "struct",
"fields": [
{
"name": "product_id",
"type": "int64",
"nullable": false
},
{
"name": "timestamp",
"type": "timestamp[us]",
"nullable": false
},
{
"name": "amount",
"type": "decimal(10,2)",
"nullable": false
}
]
},
"nullable": false
},
"nullable": true
}
]
}
}JSONjsonIntermediate
Arrow Dictionary Encoding
Arrow dictionary encoding for efficient string storage and compression
Tags
arrow, dictionary, encoding, compression
json
{
"schema": {
"fields": [
{
"name": "id",
"type": "int64",
"nullable": false
},
{
"name": "category",
"type": {
"type": "dictionary",
"index_type": "int32",
"value_type": "string",
"ordered": false
},
"nullable": false,
"dictionary": {
"type": "string",
"values": ["Electronics", "Clothing", "Books", "Home", "Sports"]
}
},
{
"name": "status",
"type": {
"type": "dictionary",
"index_type": "int8",
"value_type": "string",
"ordered": true
},
"nullable": false,
"dictionary": {
"type": "string",
"values": ["Active", "Inactive", "Pending", "Deleted"]
}
}
]
},
"batches": [
{
"count": 5,
"columns": [
{
"name": "id",
"type": "int64",
"data": [1, 2, 3, 4, 5]
},
{
"name": "category",
"type": "dictionary[int32]",
"data": [0, 1, 0, 3, 2]
},
{
"name": "status",
"type": "dictionary[int8]",
"data": [0, 0, 2, 0, 1]
}
]
}
]
}JSONjsonComplex
Time Series Data with Arrow
Optimized Arrow schema for time series data with temporal types and windowing functions
Tags
arrow, time-series, temporal, metrics
json
{
"schema": {
"fields": [
{
"name": "timestamp",
"type": "timestamp[ns]",
"nullable": false,
"metadata": {
"timezone": "UTC",
"unit": "nanoseconds"
}
},
{
"name": "metric_name",
"type": "string",
"nullable": false
},
{
"name": "value",
"type": "float64",
"nullable": true,
"metadata": {
"precision": "double"
}
},
{
"name": "tags",
"type": {
"type": "map",
"key_type": "string",
"value_type": "string",
"value_nullable": true
},
"nullable": true
},
{
"name": "window_start",
"type": "timestamp[us]",
"nullable": true
},
{
"name": "window_end",
"type": "timestamp[us]",
"nullable": true
},
{
"name": "aggregation_type",
"type": {
"type": "dictionary",
"index_type": "int8",
"value_type": "string",
"ordered": false
},
"nullable": true,
"dictionary": {
"type": "string",
"values": ["sum", "avg", "min", "max", "count"]
}
}
],
"metadata": {
"description": "Time series metrics schema",
"compression": "lz4",
"partitioning": "by_hour"
}
},
"metadata": {
"name": "timeseries_metrics",
"created_at": "2025-11-30T12:00:00Z",
"version": "1.0",
"creator": "Arrow Time Series Pipeline"
}
}JSONjsonComplex
Arrow Performance Optimization
Advanced Arrow optimization techniques for high-performance analytics and memory efficiency
Tags
arrow, performance, optimization, memory, simd
json
{
"schema": {
"fields": [
{
"name": "partition_key",
"type": "int64",
"nullable": false,
"metadata": {
"partition_key": true
}
},
{
"name": "compressed_strings",
"type": {
"type": "dictionary",
"index_type": "int32",
"value_type": "string",
"ordered": false
},
"nullable": false,
"metadata": {
"compression": "dictionary"
}
},
{
"name": "dense_numeric",
"type": "float32",
"nullable": false,
"metadata": {
"precision": "single",
"compression": "bitshuffle"
}
},
{
"name": "sparse_boolean",
"type": "bool",
"nullable": true,
"metadata": {
"encoding": "run_length"
}
},
{
"name": "large_array",
"type": {
"type": "list",
"item_type": "int64",
"nullable": false
},
"nullable": true,
"metadata": {
"large_list": true,
"offset_size": "64bit"
}
},
{
"name": "union_field",
"type": {
"type": "union",
"mode": "dense",
"types": [
{
"type": "int64",
"id": 0
},
{
"type": "string",
"id": 1
},
{
"type": "float64",
"id": 2
}
]
},
"nullable": true
}
],
"metadata": {
"optimization": "performance",
"memory_layout": "columnar",
"alignment": 64
}
},
"performance_hints": {
"batch_size": 65536,
"memory_pool": "default",
"thread_safety": true,
"zero_copy": true,
"simd_optimized": true
}
}Tools
Tools frequently paired with this sample
Related