python_sql_connector_benchmark/benchmark_config.yaml at main · Phrendo/python_sql_connector_benchmark · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
# Benchmark Configuration
# Define test scenarios for SQL Server data access performance testing

database:
  table_name: ${SQL_BENCHMARK_TABLE}  # Read from environment

test_scenarios:
  - name: "small_dataset"
    row_count: 100000
    runs: 1
    description: "Small dataset test"

  - name: "medium_dataset"
    row_count: 1000000
    runs: 1
    description: "Medium dataset test"

  - name: "large_dataset"
    row_count: 10000000
    runs: 1
    description: "Large dataset test"

  - name: "xlarge_dataset"
    row_count: 50000000
    runs: 0
    description: "Extra large dataset test"

methods:
  - name: "ConnectorX_Pandas"
    function: "test_connectorx_pandas"
    description: "ConnectorX to Pandas DataFrame"

  - name: "Polars_Native"
    function: "test_polars_native"
    description: "Polars native database reader"

  - name: "ConnectorX_Arrow_Polars"
    function: "test_connectorx_arrow_polars"
    description: "ConnectorX to Arrow to Polars"

  - name: "ConnectorX_Polars_Direct"
    function: "test_connectorx_polars_direct"
    description: "ConnectorX direct to Polars"

  - name: "pyodbc_Pandas"
    function: "test_pyodbc_pandas"
    description: "pyodbc to Pandas DataFrame"

  - name: "SQLAlchemy_Pandas"
    function: "test_sqlalchemy_pandas"
    description: "SQLAlchemy to Pandas DataFrame"

output:
  csv_file: "benchmark_results.csv"
  include_system_info: true
  timestamp_format: "%Y-%m-%d %H:%M:%S"