执行引擎配置

from chdb.datastore.config import config

# Option 1: Using set method
config.set_execution_engine('auto')    # Default
config.set_execution_engine('chdb')    # Force ClickHouse
config.set_execution_engine('pandas')  # Force pandas

# Option 2: Using shortcuts
config.use_auto()     # Auto-select
config.use_chdb()     # Force ClickHouse
config.use_pandas()   # Force pandas

print(config.execution_engine)  # 'auto', 'chdb', or 'pandas'

from chdb import datastore as pd
from chdb.datastore.config import config

config.use_auto()  # Default

ds = pd.read_csv("data.csv")

# This uses chDB (SQL)
result = (ds
    .filter(ds['amount'] > 100)   # SQL: WHERE
    .groupby('region')            # SQL: GROUP BY
    .agg({'amount': 'sum'})       # SQL: SUM()
)

# This uses pandas (custom function)
result = ds.apply(lambda row: complex_calculation(row), axis=1)

config.use_chdb()

config.use_pandas()

# Set cross-DataStore engine
config.set_cross_datastore_engine('auto')
config.set_cross_datastore_engine('chdb')
config.set_cross_datastore_engine('pandas')

ds1 = pd.read_csv("sales.csv")
ds2 = pd.read_csv("inventory.csv")

# This operation involves two DataStores
result = ds1.join(ds2, on='product_id')
# Uses cross_datastore_engine setting

Operation requested
    │
    ├─ Can be expressed in SQL?
    │      │
    │      ├─ Yes → Use chDB
    │      │
    │      └─ No → Use pandas
    │
    └─ Cross-DataStore operation?
           │
           └─ Use cross_datastore_engine setting

from chdb.datastore.config import function_config

# Force specific functions to use specific engine
function_config.use_chdb('length', 'substring')
function_config.use_pandas('upper', 'lower')

config.use_auto()  # Let DataStore decide

config.enable_profiling()
# Run your workload
# Check profiler report to see where time is spent

# For heavy aggregation workloads
config.use_chdb()

# For pandas compatibility testing
config.use_pandas()

ds = pd.read_csv("data.csv")
query = ds.filter(ds['age'] > 25).groupby('city').agg({'salary': 'sum'})

# See what SQL will be generated
query.explain()

# Check current engine
print(config.execution_engine)

# Enable debug to see what's happening
config.enable_debug()

# Try forcing specific engine
config.use_chdb()  # or config.use_pandas()

# Some pandas operations aren't supported in SQL
# Solution: use auto mode
config.use_auto()

# Or explicitly convert to pandas first
df = ds.to_df()
result = df.some_pandas_specific_operation()

# Use chdb engine to avoid loading all data into memory
config.use_chdb()

# Filter early to reduce data size
result = ds.filter(ds['date'] >= '2024-01-01').to_df()

# For maximum throughput on large datasets, use performance mode
# which enables parallel Parquet reading and single-SQL aggregation
config.use_performance_mode()