Модель выполнения DataStore

from pathlib import Path
Path("sales.csv").write_text("""\
region,product,category,amount,quantity,price,date,order_id
East,Widget,Electronics,5200,10,120,2024-01-15,1001
West,Gadget,Electronics,800,5,160,2024-02-20,1002
East,Gizmo,Home,6500,3,100,2024-03-10,1003
North,Widget,Electronics,4500,6,150,2024-06-18,1004
West,Gadget,Electronics,2000,8,250,2024-09-14,1005
""")

from chdb import datastore as pd

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

# These operations are NOT executed yet
result = (ds
    .filter(ds['amount'] > 1000)    # Recorded, not executed
    .select('region', 'amount')      # Recorded, not executed
    .groupby('region')               # Recorded, not executed
    .agg({'amount': 'sum'})          # Recorded, not executed
    .sort('sum', ascending=False)    # Recorded, not executed
)

# Still no execution - just building the query plan
print(result.to_sql())
# SELECT region, SUM(amount) AS sum
# FROM file('sales.csv', 'CSVWithNames')
# WHERE amount > 1000
# GROUP BY region
# ORDER BY sum DESC

# NOW execution happens
df = result.to_df()  # <-- Triggers execution

# All these trigger execution
print(ds)              # Display
len(ds)                # 1000
ds.columns             # Index(['name', 'age', 'city'])
ds.shape               # (1000, 3)
list(ds)               # List of values
ds.to_df()             # pandas DataFrame

# These do NOT trigger execution - they stay lazy
result = ds.filter(ds['age'] > 25)      # Returns DataStore
result = ds.select('name', 'age')        # Returns DataStore
result = ds['name']                      # Returns ColumnExpr
result = ds.groupby('city')              # Returns LazyGroupBy

result = (ds
    .filter(ds['status'] == 'active')   # WHERE
    .select('user_id', 'amount')         # SELECT
    .groupby('user_id')                  # GROUP BY
    .agg({'amount': 'sum'})              # SUM()
    .sort('sum', ascending=False)        # ORDER BY
    .limit(10)                           # LIMIT
)
# All compiled into one SQL query

# Execution triggered here
df = result.to_df()  
# The single optimized SQL query runs now

# Mixed operations
result = (ds
    .filter(ds['amount'] > 100)          # Phase 1: SQL
    .to_df()                             # Phase 2: Execute
    .pivot_table(...)                    # Phase 3: pandas
)

query.explain(verbose=True)

from pathlib import Path
Path("data.csv").write_text("""\
name,age,city,salary,department
Alice,25,NYC,55000,Engineering
Bob,30,LA,65000,Product
Charlie,35,NYC,80000,Engineering
Diana,28,SF,70000,Design
Eve,42,NYC,95000,Product
""")

ds = pd.read_csv("data.csv")
result = ds.filter(ds['age'] > 25)

# First access - executes query
print(result.shape)  # Executes and caches

# Second access - uses cache
print(result.columns)  # Uses cached result

# Third access - uses cache
df = result.to_df()  # Uses cached result

result = ds.filter(ds['age'] > 25)
print(result.shape)  # Executes, caches

# New operation invalidates cache
result2 = result.filter(result['city'] == 'NYC')
print(result2.shape)  # Re-executes (different query)

# Clear cache
ds.clear_cache()

# Disable caching
from chdb.datastore.config import config
config.set_cache_enabled(False)

# SQL phase
result = (ds
    .filter(ds['amount'] > 100)      # SQL
    .groupby('category')              # SQL
    .agg({'amount': 'sum'})           # SQL
)

# Execution + pandas phase
result = (result
    .to_df()                          # Execute SQL
    .pivot_table(...)                 # pandas operation
)

from chdb.datastore.config import config

config.set_execution_engine('auto')  # Default
# Automatically selects best engine per operation

config.set_execution_engine('chdb')
# All operations use ClickHouse SQL

config.set_execution_engine('pandas')
# All operations use pandas

# Good: Filter in SQL, then aggregate
result = (ds
    .filter(ds['date'] >= '2024-01-01')  # Reduces data early
    .groupby('category')
    .agg({'amount': 'sum'})
)

# Bad: Aggregate all, then filter
result = (ds
    .groupby('category')
    .agg({'amount': 'sum'})
    .to_df()
    .query('sum > 1000')  # Pandas filter after aggregation
)

# Good: Select columns in SQL
result = (ds
    .select('user_id', 'amount', 'date')
    .filter(ds['date'] >= '2024-01-01')
    .groupby('user_id')
    .agg({'amount': 'sum'})
)

# Good: Complex aggregation in SQL
result = (ds
    .groupby('category')
    .agg({
        'amount': ['sum', 'mean', 'count'],
        'quantity': 'sum'
    })
    .sort('sum', ascending=False)
    .limit(10)
)
# One SQL query does everything

# Bad: Multiple separate queries
sums = ds.groupby('category')['amount'].sum().to_df()
means = ds.groupby('category')['amount'].mean().to_df()
# Two queries instead of one