Отладка DataStore

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

# Enable all debugging
config.enable_debug()        # Verbose logging
config.enable_profiling()    # Performance tracking

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

# View execution plan
result.explain()

# Get profiler report
from chdb.datastore.config import get_profiler
profiler = get_profiler()
profiler.report()

from chdb.datastore.config import config

# Enable debug logging
config.enable_debug()

# Run operations - logs will show:
# - SQL queries generated
# - Execution engine used
# - Cache hits/misses
# - Timing information

DEBUG - DataStore: Creating from file 'data.csv'
DEBUG - Query: SELECT region, SUM(amount) FROM ... WHERE amount > 1000 GROUP BY region
DEBUG - Engine: Using chdb for aggregation
DEBUG - Execution time: 0.089s
DEBUG - Cache: Storing result (key: abc123)

# Step 1: View the execution plan
query = ds.filter(ds['age'] > 25).groupby('city').sum()
query.explain(verbose=True)

# Step 2: Enable logging to see SQL
config.enable_debug()

# Step 3: Run and check logs
result = query.to_df()

# Step 1: Enable profiling
config.enable_profiling()

# Step 2: Run your query
result = process_data()

# Step 3: Check profiler report
profiler = get_profiler()
profiler.report()

# Step 4: Identify slow operations and optimize

# Enable verbose logging
config.enable_debug()

# Run operations
result = ds.filter(ds['x'] > 10).apply(custom_func)

# Logs will show which engine was used for each operation:
# DEBUG - filter: Using chdb engine
# DEBUG - apply: Using pandas engine (custom function)

# Enable debug to see cache operations
config.enable_debug()

# First run
result1 = ds.filter(ds['x'] > 10).to_df()
# LOG: Cache miss, executing query

# Second run (should use cache)
result2 = ds.filter(ds['x'] > 10).to_df()
# LOG: Cache hit, returning cached result

# If not caching when expected, check:
# - Are operations identical?
# - Is cache enabled? config.cache_enabled

# Development
config.enable_debug()
config.enable_profiling()

# Production
config.set_log_level(logging.WARNING)
config.set_profiling_enabled(False)

# Build query
query = ds.filter(...).groupby(...).agg(...)

# Check plan first
query.explain()

# If plan looks good, execute
result = query.to_df()

# Don't guess what's slow - measure it
config.enable_profiling()
result = your_pipeline()
get_profiler().report()

# View generated SQL
print(query.to_sql())

# Compare with expected SQL
# Run SQL directly in ClickHouse to verify